Search

The use of bi-temporal remote sensing images for detecting changes in land cover is an important means of obtaining surface change information, thus contributing to urban governance and ecological environment monitoring. In this article, we propose a deep learning model named Siam-UNet3+ for high-resolution remote sensing image change detection. This model integrates the full-scale skip connections and full-scale deep supervision of the network UNet3+, which can achieve the multi-scale feature fusion of remote sensing images, effectively avoiding the locality disadvantage of convolution operations. Different from UNet3+, Siam-UNet3+ has made major improvements, including the following: (1) incorporating a Siamese network in the encoder, which can process bi-temporal remote sensing images in parallel; (2) leveraging the residual module as the backbone, which can avoid gradient vanishing (or exploding) and model degradation problems; (3) adding a Triplet Attention module to the decoder, which can avoid information redundancy that may occur in full-scale skip connections and increase the ability to focus on changing patterns; and (4) designing a hybrid loss function consisting of focal loss and dice loss, which is more suitable for remote sensing image change detection tasks. In this study, we conducted change detection experiments using the publicly available LEVIR-CD dataset, as well as two local datasets in Beijing. Through comparative experiments with five other models and ablation experiments, the proposed model Siam-UNet3+ in this article demonstrated significant advantages and improvements in four evaluation metrics, namely, precision, recall, F1-score, and overall accuracy (OA), proving to have great potential in the application to highresolution remote sensing image change detection tasks. [ABSTRACT FROM AUTHOR]

• Amplitude and synchrony of 40-Hz ASSR was decreased by sound pressure change. • Decrease of amplitude and synchrony depended on magnitude of sound pressure change. • Transient 40-Hz ASSR desynchronization might be an index of change detection. A periodic sound with a fixed inter-stimulus interval elicits an auditory steady-state response (ASSR). An abrupt change in a continuous sound is known to affect the brain's ongoing neural oscillatory activity, but the underlying mechanism has not been fully clarified. We investigated whether and how an abrupt change in sound intensity affects the ASSR. The control stimulus was a train of 1-ms clicks with a sound pressure level (SPL) of 70 dB at 40 Hz for 1000 ms. In addition to the control stimulus, we applied six stimuli with changes consisting of a 500-ms train at 70 dB followed by a 500-ms similar train with louder clicks of 75, 80, or 85 dB or weaker clicks of 55, 60, or 65 dB. We obtained the magnetoencephalographic responses from 15 healthy subjects while presenting the seven stimuli randomly. The two-dipole model obtained for the 40-Hz ASSR in the control condition was applied to all of the stimulus conditions for each subject, and then the time–frequency analysis was conducted. We observed that both the amplitude and the inter-trial phase coherence of the 40-Hz ASSR transiently decreased and returned to the steady state after the change onset, i.e., the desynchronization of 40-Hz ASSR. The degree of desynchronization depended on the magnitude of the change regardless of whether the sound intensity increased or decreased, which might be a novel neurophysiological index of cerebral response driven by a change in the sensory environment. [ABSTRACT FROM AUTHOR]

Remote sensing image change detection has significant applications across various fields. In recent years, the powerful feature extraction capability of deep learning technology has introduced innovative approaches to change detection methodologies. However, the accuracy of convolutional neural network algorithms hinges heavily on labelled data, necessitating substantial manpower and resources to generate labelled samples. Therefore, this paper proposes an unsupervised change detection model called CIUCD. This model operates on the fundamental premise of unsupervised change detection, employing a generator and a segmenter for iterative training. During each iteration, the generator and segmenter update and optimize their parameters, with the segmenter leveraging the generated change images as labels for training purposes. This iterative labelling process circumvents the need for manually labelled data, thereby mitigating the difficulty of obtaining change detection labels for actual remote sensing images. To validate the efficacy of the proposed model, we conducted experiments using actual remotely sensed images from the 2023 Turkey earthquake and the 2022 Afghanistan earthquake events. The results show that our method enhances the F1, Pr, Re and OA by 5.98%, 2.05%, 11.82% and 8.50% (Turkey earthquake), and by 9.54%, 5.87%, 4.52% and 11.34% (Afghanistan earthquake), respectively, when compared to the unsupervised change detection algorithm KPCA-Mnet. Experiments on real remote sensing images of 1000 × 1000 pixels showed that the CIUCD algorithm not only accurately detect larger change areas but is also capable of identifying changes in subtle objects such as solar panels. Additionally, the CIUCD algorithm is resilient to natural environmental factors like the angle of illumination, enabling precise predictions of changes in the actual remote sensing images and yielding clearer detection results. The performance of the CIUCD algorithm remains outstanding even when applied to larger images with a resolution of 3000 × 3000 pixels. [ABSTRACT FROM AUTHOR]

The regional ecological environment has become a significant subject of study due to the dynamics of the ecosystem, which is represented by vegetation, under the influence of human activities. The objective of this research is to demonstrate the implementation and effectiveness of the forest canopy density (FCD) model in generating a map that illustrates changes in forest canopy density using multitemporal remote sensing data in Tabunio watershed. The methodology relies on vegetation index, including the normalized difference vegetation index (NDVI), shadow index (SI), and bare soil index (BI), to generate a composite vegetation index (CVI). FCD uses multitemporal remote sensing data from Landsat TM images from 2005 to 2020, which have been utilized to accomplish multisource categorization. The findings indicated that the vegetation coverage of the Tabunio watershed presented a predominant pattern of high coverage in the northeastern and eastern regions, whereas most areas of the western region had low coverage; (2) vegetation cover from 2005 to 2020 is dominated by sparse to very dense vegetation cover classes; (3) changes in vegetation cover over two decades are very significant. The expansion of plantation land in 2005 caused a lot of non-vegetated land, which gradually changed in the following year period along with plant growth. At the end of 2020, the percentage of very dense vegetation became increasingly dominant, which was around 42 percent. The results of the study indicate the three biophysical index (NDVI, SI, and BI) used in this model approach were appropriate for precisely discriminating across all canopy density classes, as seen by the overall producer's accuracy of 81.3%. FCD model in multitemporal data can helps in the early identification of deforestation or forest degradation activities. Furthermore, the FCD model may have certain constraints, as it requires an understanding of ground conditions to establish threshold values for each class. [ABSTRACT FROM AUTHOR]

Efficient monitoring of crop water requirements is crucial for assessing the impacts of major irrigation projects, such as the Kaleshwaram lift irrigation project, both before and after their implementation. These projects can significantly change agricultural practices and water usage patterns, necessitating thorough evaluations to ensure sustainable water management and agricultural resilience. The main aim of this study is to evaluate and compare crop water needs during the winter (rabi) seasons of 2018-2019 and 2022-2023 across the command area of the project. This is achieved by mapping major crops and their respective length of growing periods across the study area using sentinel-2 satellite data and ground data, and quantifying crop water requirements using reference evapotranspiration and FAO crop coefficients. Results reveal a significant shift towards rice cultivation, with an over 80% increase in the winter season of 2022-2023 compared to 2018-2019, indicating substantial escalations in crop water requirements. These findings provide valuable insights into agricultural transformations induced by largescale irrigation interventions, emphasizing the need for sustainable water management practices to ensure agricultural resilience and resource conservation in similar contexts. [ABSTRACT FROM AUTHOR]

With the development and popularization of unmanned aerial vehicle (UAV) equipment, UAV-based remote sensing technology has developed rapidly. With UAV aerial photography platforms, the obtained low altitude remote sensing images of surfaces have high temporal and spatial resolution and can be used for monitoring and change analyses of surface geographic information. As it is impractical to carry complex and large load equipment on a UAV, it is desirable to develop embedded systems for relevant real-time processing with UAV remote sensing technology. This study combines the advantages of UAV remote sensing image processing and embedded development technology to develop a near real-time UAV remote sensing image change detection system, which realizes the fast, accurate, and automatic detection of variations in the target area. Finally, the feasibility, correctness, and practicability of the prototype system are demonstrated with experiments. [ABSTRACT FROM AUTHOR]

Remote sensing images provide a valuable way to observe the Earth's surface and identify objects from a satellite or airborne perspective. Researchers can gain a more comprehensive understanding of the Earth's surface by using a variety of heterogeneous data sources, including multispectral, hyperspectral, radar, and multitemporal imagery. This abundance of different information over a specified area offers an opportunity to significantly improve change detection tasks by merging or fusing these sources. This review explores the application of deep learning for change detection in remote sensing imagery, encompassing both homogeneous and heterogeneous scenes. It delves into publicly available datasets specifically designed for this task, analyzes selected deep learning models employed for change detection, and explores current challenges and trends in the field, concluding with a look towards potential future developments. [ABSTRACT FROM AUTHOR]

Remote sensing image change detection is an important research in the field of remote sensing, which aims to use remote sensing technology and image processing methods to identify the patterns and trends of surface cover changes. In order to gain a deeper understanding of the current development of this area and the technical methods used, a large amount of information and literatures are summarized and analyzed to provide a more comprehensive review of remote sensing image change detection methods. Firstly, the concept and processing flow of change detection are introduced. Then the classification system of change detection methods is summarized from six angles, followed by a review of their development history. Subsequently, the principles and characteristics of various types of change detection methods are outlined, their advantages and disadvantages are briefly analyzed, and the real-world application value of change detection on remotely sensed images is discussed from six aspects. Some problems and shortcomings in the area are briefly analyzed, and some possible ways to improve these problems are proposed, while the obstacles that may be encountered in the practical application of these methods are also predicted. Finally, the change detection methods are summarized, and the future development direction is prospected, in order to better understand the research status and development trend of remote sensing image change detection methods, and provide reference for further research. [ABSTRACT FROM AUTHOR]

This study provides a comprehensive overview of Phase I of the deforestation dryland alert system. It focuses on its operation and outcomes from 2020 to 2022 in the Caatinga biome, a unique Brazilian dryland ecosystem. The primary objectives were to analyze deforestation dynamics, identify areas with highest deforestation rates, and determine regions that require prioritization for anti-deforestation efforts and conservation actions. The research methodology involved utilizing remote sensing data, including Landsat imagery, processed through the Google Earth Engine platform. The data were analyzed using spectral unmixing, adjusted Normalized Difference Fraction Index, and harmonic time series models to generate monthly deforestation alerts. The findings reveal a significant increase in deforestation alerts and deforested areas over the study period, with a 148% rise in alerts from 2020 to 2022. The Caatinga biome was identified as the second highest in detected deforestation alerts in Brazil in 2022, accounting for 18.4% of total alerts. Hexagonal assessments illustrate diverse vegetation cover and alert distribution, enabling targeted conservation efforts. The Bivariate Choropleth Map demonstrates the nuanced relationship between alert and vegetation cover, guiding prioritization for deforestation control and native vegetation restoration. The analysis also highlighted the spatial heterogeneity of deforestation, with most deforestation events occurring in small patches, averaging 10.9 ha. The study concludes that while the dryland alert system (SAD-Caatinga—Phase I) has effectively detected deforestation, ongoing challenges such as cloud cover, seasonality, and more frequent and precise monitoring persist. The implementation of DDAS plays a critical role in sustainable forestry by enabling the prompt detection of deforestation, which supports targeted interventions, helps contain the process, and provides decision makers with early insights to distinguish between legal and illegal practices. These capabilities inform decision-making processes and promote sustainable forest management in dryland ecosystems. Future improvements, including using higher-resolution imagery and artificial intelligence for validation, are essential to detect smaller deforestation alerts, reduce manual efforts, and support sustainable dryland management in the Caatinga biome. [ABSTRACT FROM AUTHOR]

This study critically examines the spatial dynamics of urban sprawl and land use changes in Bhilwara, Rajasthan, over the past three decades, utilizing advanced remote sensing and GIS methodologies. The primary objective is to elucidate the patterns of urban expansion and its consequential impacts on green infrastructure. The findings reveal a pronounced increase in built-up areas, with the most significant growth observed towards the north-northwest (NNW) and west-southwest (WSW) directions, driven by the presence of major transportation corridors and proximate urban centers. The LULC classification achieved high accuracy, with Producer's accuracy ranging from 81 to 94.4%, User's accuracy from 73.7 to 100%, and Overall accuracy between 84.5 and 93.8%, accompanied by a Kappa coefficient of 0.78 to 0.83. These results underscore the robust methodology employed and highlight the critical need for integrated urban planning approaches that prioritize sustainable development and green infrastructure preservation. The study's conclusions offer substantial contributions to the academic discourse on urbanization, providing actionable insights for policymakers and urban planners to manage urban growth effectively and sustainably. [ABSTRACT FROM AUTHOR]

To navigate changes within a highly dynamic and complex environment, it is crucial to compare current visual representations of a scene to previously formed representations stored in memory. This process of mental comparison requires integrating information from multiple sources to inform decisions about changes within the environment. In the present article, we combine a novel systems factorial technology change detection task (Blunden et al., 2022) with a set size manipulation. Participants were required to detect 0, 1, or 2 changes of low and high detectability between a memory and probe array of 1–4 spatially separated luminance discs. Analyses using systems factorial technology indicated that the processing architecture was consistent across set sizes but that capacity was always limited and decreased as the number of distractors increased. We developed a novel model of change detection based on the statistical principles of basic sampling theory (Palmer, 1990; Sewell et al., 2014). The sample size model, instantiated parametrically, predicts the architecture and capacity results a priori and quantitatively accounted for several key results observed in the data: (a) increasing set size acted to decrease sensitivity (d′) in proportion to the square root of the number of items in the display; (b) the effect of redundancy benefited performance by a factor of the square root of the number of changes; and (c) the effect of change detectability was separable and independent of the sample size costs and redundancy benefits. [ABSTRACT FROM AUTHOR]

To improve the accuracy of detecting changes in remote sensing time series, an improved algorithm based on the combination of the antileakage least-squares spectral analysis (ALLSSA) algorithm and detecting breakpoints and estimating segments in trends (DBEST) algorithm is proposed and applied. The method uses the ALLSSA algorithm to decompose the time series and identify the trend components in the time series. Then, the trend segmentation mechanism of the DBEST algorithm is used to detect the changes in the trend component. In this paper, the improved algorithm is evaluated using a simulated time series data set, a time series data set with multiple change points, and data set based on the moderate resolution imaging spectroradiometer (MODIS) normalized difference vegetation index (NDVI) remote sensing time series. The results demonstrate that the average detection accuracies of the improved algorithm and DBEST algorithm are 98.4% and 85.2%, respectively, for the simulated time series data set. For the time series data set with multiple change points, the average root mean square errors (RMSEs) of the trend data for the improved and DBEST algorithms are 0.0386 and 0.0331, respectively. The mean normalized residual norms (MNRNs) of the improved and DBEST algorithms are 0.0252 and 0.0351, respectively. Finally, the improved algorithm, DBEST algorithm, and breaks for additive season and trend (BFAST) algorithm are applied to MODIS NDVI data, and their performance with remote sensing data is compared. The improved algorithm has higher detection accuracy and a smaller MNRN, indicating that more information is included in the trend and seasonal components. Therefore, the proposed method is useful for analysing trends in remote sensing time series data. [ABSTRACT FROM AUTHOR]

Misusing image tampering software makes it easier to manipulate satellite images, leading to a crisis of trust and security concerns in society. This study compares the inconsistencies between heterogeneous images to locate tampered areas and proposes a high-precision heterogeneous satellite image manipulation localization (HSIML) framework to distinguish tampered from real landcover changes, such as artificial constructions, and pseudo-changes, such as seasonal variations. The model operates at the patch level and comprises three modules: The heterogeneous image preprocessing module aligns heterogeneous images and filters noisy data. The feature point constraint module mitigates the effects of lighting and seasonal variations in the images by performing feature point matching, applying filtering rules to conduct an initial screening to identify candidate tampered patches. The semantic similarity measurement module designs a classification network to assess RS image feature saliency. It determines image consistency based on the similarity of semantic features and implements IML using predefined classification rules. Additionally, a dataset for IML is constructed based on satellite images. Extensive experiments compared with existing SOTA models demonstrate that our method achieved the highest F1 score in both localization accuracy and robustness tests and demonstrates the capability for handling large-scale areas. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar tomography (TomoSAR) has gained significant attention for three-dimensional (3D) imaging in urban environments. A notable limitation of traditional TomoSAR approaches is their primary focus on persistent scatterers (PSs), disregarding targets with temporal decorrelated characteristics. Temporal variations in coherence, especially in urban areas due to the dense population of buildings and artificial structures, can lead to a reduction in detectable PSs and suboptimal 3D reconstruction performance. The concept of partially coherent scatterers (PCSs) has been proven effective by capturing the partial temporal coherence of targets across the entire time baseline. In this study, an novel approach based on an iterative sub-network generation method is introduced to leverage PCSs for enhanced 3D reconstruction in dynamic environments. We propose a coherence constraint iterative variance analysis approach to determine the optimal temporal baseline range that accurately reflects the interferometric coherence of PCSs. Utilizing the selected PCSs, a 3D imaging technique that incorporates the iterative generation of sub-networks into the SAR tomography process is developed. By employing the PS reference network as a foundation, we accurately invert PCSs through the iterative generation of local star-shaped networks, ensuring a comprehensive coverage of PCSs in study areas. The effectiveness of this method for the height estimation of PCSs is validated using the TerraSAR-X dataset. Compared with traditional PS-based TomoSAR, the proposed approach demonstrates that PCS-based elevation results complement those from PSs, significantly improving 3D reconstruction in evolving urban settings. [ABSTRACT FROM AUTHOR]

In the field of remote sensing (RS), change detection (CD) methods are critical for analyzing the quality of images shot over various geographical areas, particularly for high-resolution images. However, there are some shortcomings of the widely used Convolutional Neural Networks (CNNs) and Transformers-based CD methods. The former is limited by its insufficient long-range modeling capabilities, while the latter is hampered by its computational complexity. Additionally, the commonly used information-fusion methods for pre- and post-change images often lead to information loss or redundancy, resulting in inaccurate edge detection. To address these issues, we propose an Iterative Mamba Diffusion Change Detection (IMDCD) approach to iteratively integrate various pieces of information and efficiently produce fine-grained CD maps. Specifically, the Swin-Mamba-Encoder (SME) within Mamba-CD (MCD) is employed as a semantic feature extractor, capable of modeling long-range relationships with linear computability. Moreover, we introduce the Variable State Space CD (VSS-CD) module, which extracts abundant CD features by training the matrix parameters within the designed State Space Change Detection (SS-CD). The computed high-dimensional CD feature is integrated into the noise predictor using a novel Global Hybrid Attention Transformer (GHAT) while low-dimensional CD features are utilized to calibrate prior CD results at each iterative step, progressively refining the generated outcomes. IMDCD exhibits a high performance across multiple datasets such as the CDD, WHU, LEVIR, and OSCD, marking a significant advancement in the methodologies within the CD field of RS. The code for this work is available on GitHub. [ABSTRACT FROM AUTHOR]

For some time, CNN was the de facto state-of-the-art method in remote sensing image change detection. Although transformer-based models have surpassed CNN-based models due to their larger receptive fields, CNNs still retain their value for their efficiency and ability to extract precise local features. To overcome the limitations of the restricted receptive fields in standard CNNs, deformable convolution allows for dynamic adjustment of sampling locations in convolutional kernels, improving the network's ability to model global contexts. InternImage is an architecture built upon deformable convolution as its foundational operation. Motivated by InternImage, in this paper, a CNN-based change detection vision foundation model is proposed. By introducing deformable convolution into Siamese InternImage architecture, the proposed CNN-based change detection vision foundation model is capable of capturing long-range dependencies and global information. A refinement block is utilized to merge local detail, where channel attention is incorporated. The proposed approach achieved excellent performance on the LEVIR-CD and WHU-CD datasets. [ABSTRACT FROM AUTHOR]

Multimodal change detection (MCD) harnesses multi-source remote sensing data to identify surface changes, thereby presenting prospects for applications within disaster management and environmental surveillance. Nonetheless, disparities in imaging mechanisms across various modalities impede the direct comparison of multimodal images. In response, numerous methodologies employing deep learning features have emerged to derive comparable features from such images. Nevertheless, several of these approaches depend on manually labeled samples, which are resource-intensive, and their accuracy in distinguishing changed and unchanged regions is not satisfactory. In addressing these challenges, a new MCD method based on iterative optimization-enhanced contrastive learning is proposed in this paper. With the participation of positive and negative samples in contrastive learning, the deep feature extraction network focuses on extracting the initial deep features of multimodal images. The common projection layer unifies the deep features of two images into the same feature space. Then, the iterative optimization module expands the differences between changed and unchanged areas, enhancing the quality of the deep features. The final change map is derived from the similarity measurements of these optimized features. Experiments conducted across four real-world multimodal datasets, benchmarked against eight well-established methodologies, incontrovertibly illustrate the superiority of our proposed approach. [ABSTRACT FROM AUTHOR]

Remote sensing image change detection is crucial for urban planning, environmental monitoring, and disaster assessment, as it identifies temporal variations of specific targets, such as surface buildings, by analyzing differences between images from different time periods. Current research faces challenges, including the accurate extraction of change features and the handling of complex and varied image contexts. To address these issues, this study proposes an innovative model named the Segment Anything Model-UNet Change Detection Model (SCDM), which incorporates the proposed center expansion and reduction method (CERM), Segment Anything Model (SAM), UNet, and fine-grained loss function. The global feature map of the environment is extracted, the difference measurement features are extracted, and then the global feature map and the difference measurement features are fused. Finally, a global decoder is constructed to predict the changes of the same region in different periods. Detailed ablation experiments and comparative experiments are conducted on the WHU-CD and LEVIR-CD public datasets to evaluate the performance of the proposed method. At the same time, validation on more complex DTX datasets for scenarios is supplemented. The experimental results demonstrate that compared to traditional fixed-size partitioning methods, the CERM proposed in this study significantly improves the accuracy of SOTA models, including ChangeFormer, ChangerEx, Tiny-CD, BIT, DTCDSCN, and STANet. Additionally, compared with other methods, the SCDM demonstrates superior performance and generalization, showcasing its effectiveness in overcoming the limitations of existing methods. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar (SAR) imaging is essential for monitoring geomorphic changes, urban transformations, and natural disasters. However, the inherent complexities of SAR, particularly pronounced speckle noise, often lead to numerous false detections. To address these challenges, we propose the Multidirectional Attention Fusion Network (MDAF-Net), an advanced framework that significantly enhances image quality and detection accuracy. Firstly, we introduce the Multidirectional Filter (MF), which employs side-window filtering techniques and eight directional filters. This approach supports multidirectional image processing, effectively suppressing speckle noise and precisely preserving edge details. By utilizing deep neural network components, such as average pooling, the MF dynamically adapts to different noise patterns and textures, thereby enhancing image clarity and contrast. Building on this innovation, MDAF-Net integrates multidirectional feature learning with a multiscale self-attention mechanism. This design utilizes local edge information for robust noise suppression and combines global and local contextual data, enhancing the model's contextual understanding and adaptability across various scenarios. Rigorous testing on six SAR datasets demonstrated that MDAF-Net achieves superior detection accuracy compared with other methods. On average, the Kappa coefficient improved by approximately 1.14%, substantially reducing errors and enhancing change detection precision. [ABSTRACT FROM AUTHOR]

Change detection based on optical image processing plays a crucial role in the field of damage assessment. Although existing damage scene change detection methods have achieved some good results, they are faced with challenges, such as low accuracy and slow speed in optical image change detection. To solve these problems, an image change detection approach that combines infrared polarization imaging with a fast principal component analysis network (Fast-PCANet) is proposed. Firstly, the acquired infrared polarization images are analyzed, and pixel image blocks are extracted and filtered to obtain the candidate change points. Then, the Fast-PCANet network framework is established, and the candidate pixel image blocks are sent to the network to detect the change pixel points. Finally, the false-detection points predicted by the Fast-PCANet are further corrected by region filling and filtering to obtain the final binary change map of the damage scene. Comparisons with typical PCANet-based change detection algorithms are made on a dataset of infrared-polarized images. The experimental results show that the proposed Fast-PCANet method improves the PCC and the Kappa coefficient of infrared polarization images over infrared intensity images by 6.77% and 13.67%, respectively. Meanwhile, the inference speed can be more than seven times faster. The results verify that the proposed approach is effective and efficient for the change detection task with infrared polarization imaging. The study can be applied to the damage assessment field and has great potential for object recognition, material classification, and polarization remote sensing. [ABSTRACT FROM AUTHOR]

During visual processing, input that is continuous in space and time is segmented, resulting in the representation of discrete tokens—objects or events. And there has been a great deal of research about how object representations are generalized into types—as when we see an object as an instance of a broader category (e.g., an animal or plant). There has been much less attention, however, to the possibility that vision represents dynamic information in terms of a small number of primitive event types (such as twisting or bouncing). (In models that posit a "language of vision," these would be the foundational visual verbs.) Here we ask whether such event types are extracted spontaneously during visual perception, even when entirely task irrelevant during passive viewing. We exploited the phenomenon of categorical perception—wherein differences are more readily noticed when they are represented in terms of different underlying categories. Observers were better at detecting changes to images or short videos when the changes involved switches in the underlying event type—even when the changes that maintained the same event type were objectively larger (in terms of both brute image metrics and higher level feature change). We observed this categorical "cross-event-type" advantage for visual working memory for twisting versus rotating, scooping versus pouring, and rolling versus bouncing. Moreover, additional control experiments confirmed that such effects could not be explained by appeal to lower-level non-categorical stimulus differences. This spontaneous perception of "visual verbs" might promote both generalization and prediction about how events are likely to unfold. Public Significance Statement: Suppose that you see two photographs or short movies—each presented for only a moment, one after the other—and then you must indicate whether they were identical or not. How would you do this? What sorts of differences would your mind automatically latch onto? Your ability to notice changes might be controlled by the low-level properties of the stimuli—the precise placements of colored pixels and objects here and there. In contrast, this project shows that your ability to notice changes also depends on how your mind automatically and spontaneously categorizes them into distinct "event types"—such as bouncing, rolling, pouring, or scooping—with differences that involve changes in perceived event types being easier to notice (controlling for lower level image properties). This shows how perception involves representations of the world in terms of a foundational set of "visual verbs," which might be a core part of scene understanding. [ABSTRACT FROM AUTHOR]

This work presents AstrobeeCD, a system for 3D scene change detection toward near-real-time environmental awareness of space outposts using the Astrobee free-flying robot in microgravity. Assistive free-flyer robots autonomously caring for future crewed space habitats must be able to detect day-to-day interior changes to track inventory, detect and diagnose faults, and monitor the outpost status. A set of image and depth data from one time step is used to reconstruct a 3D model of the environment. The 3D model is used as the basis for comparison for free-flyer environment surveys at future time steps, where an image-based change detection algorithm identifies inconsistencies against the 3D model. Change detection is demonstrated using real image and pose data collected by an Astrobee robot in a test environment on Earth at NASA Ames Research Center and from microgravity aboard the International Space Station. Change detection computation time and performance are quantitatively evaluated on the test data captured on Earth, and it identifies scene changes more quickly than a point cloud clustering-based algorithm applied to data from the same surveys. [Display omitted] • Free-flying robotic assistants in space need to efficiently detect scene changes. • AstrobeeCD demonstrates near-real-time 3D scene change detection for space habitats. • AstrobeeCD processes Astrobee's images and poses for image-based change detection. • AstrobeeCD is validated on Astrobee data collected on Earth and in space on the ISS. • Data and code are publicly released to promote further development. [ABSTRACT FROM AUTHOR]

Coastal tidal wetlands are crucial for environmental and economic health, but facing threats from various environmental changes. Detecting changes of tidal wetlands is essential for promoting sustainable development in coastal areas. Despite extensive researches on tidal wetland changes, persistent challenges still exist. Firstly, the high similarity among tidal wetland types hinders the effectiveness of existing common indices. Secondly, many current methods, relying on hand-crafted features, are time-consuming and subject to personal biases. Thirdly, few studies effectively integrate multi-temporal and semantic information, leading to misinterpretations from environmental noise and tidal variations. In view of the abovementioned issues, we proposed a novel temporal-spectral-semantic-aware convolutional transformer network (TSSA-CTNet) for multi-class tidal wetland change detection. Firstly, to address spectral similarity among different tidal wetlands, we proposed a sparse second order feature construction (SSFC) module to construct more separable spectral representations. Secondly, to get more separable features automatically, we constructed temporal-spatial feature extractor (TSFE) and siamese semantic sharing (SiamSS) blocks to extract temporal-spatial-semantic features. Thirdly, to fully utilize semantic information, we proposed a center comparative label smoothing (CCLS) module to generate semantic-aware labels. Experiments in the Greater Bay Area, using Landsat data from 2000 to 2019, demonstrated that TSSA-CTNet achieved 89.20% overall accuracy, outperforming other methods by 3.75%–16.39%. The study revealed significant area losses in tidal flats, mangroves, and tidal marshes, decreased by 3148 hectares, 35 hectares, and 240 hectares, respectively. Among the cities in GBA, Zhuhai shows the most significant area loss with a total of 1626 hectares. TSSA-CTNet proves effective for multi-class tidal wetland change detection, offering valuable insights for tidal wetland protection. [ABSTRACT FROM AUTHOR]

Dynamic networks are ubiquitous in many domains for modelling evolving graph-structured data and detecting changes allows us to understand the dynamic of the domain represented. A category of computational solutions is represented by the pattern-based change detectors (PBCDs), which are non-parametric unsupervised change detection methods based on observed changes in sets of frequent patterns over time. Patterns have the ability to depict the structural information of the sub-graphs, becoming a useful tool in the interpretation of the changes. Existing PBCDs often rely on exhaustive mining, which corresponds to the worst-case exponential time complexity, making this category of algorithms inefficient in practice. In fact, in such a case, the pattern mining process is even more time-consuming and inefficient due to the combinatorial explosion of the sub-graph pattern space caused by the inherent complexity of the graph structure. Non-exhaustive search strategies can represent a possible approach to this problem, also because not all the possible frequent patterns contribute to changes in the time-evolving data. In this paper, we investigate the viability of different heuristic approaches which prevent the complete exploration of the search space, by returning a concise set of sub-graph patterns (compared to the exhaustive case). The heuristics differ on the criterion used to select representative patterns. The results obtained on real-world and synthetic dynamic networks show that these solutions are effective, when mining patterns, and even more accurate when detecting changes. [ABSTRACT FROM AUTHOR]

Satellite data are increasingly used to provide information to support forest monitoring and reporting at varying levels of detail and for a range of attributes and spatial extents. Forests are dynamic environments and benefit from regular assessments to capture status and changes both locally and over large areas. Satellite data can provide products relevant to forest science and management on a regular basis (e.g. annually) for land cover, disturbance (i.e. date, extent, severity, and type), forest recovery (e.g. quantification of return of trees following disturbance), and forest structure (e.g. volume, biomass, canopy cover, stand height), with products generated over large areas in a systematic, transparent, and repeatable fashion. While pixel-based outcomes are typical based upon satellite data inputs, many end users continue to require polygon-based forest inventory information. To meet this information need and have a spatial context for forest inventory attributes such as tree species assemblages, we present a new work-flow to produce a novel spatially explicit, stand-level satellite-based forest inventory (SBFI) in Canada applying image segmentation approaches to generate spatially unique forest stands (polygons), which are the fundamental spatial unit of management-level inventories. Thus, SBFI offers spatial context to aggregate and generalize other pixel-based forest data sets. Canada has developed a National Terrestrial Ecosystem Monitoring System (NTEMS) that utilizes medium spatial resolution imagery, chiefly from Landsat, to annually characterize Canada's forests at a pixel level from 1984 until present. These NTEMS datasets are used to populate SBFI polygons with information regarding status (e.g. current land cover type, dominant tree species, or total biomass) as well as information on dynamics (e.g. has this polygon been subject to change, when, by what, and if so, how is the forest recovering). Here, we outline the information drivers for forest monitoring, present a set of products aimed at meeting these information needs, and follow to demonstrate the SBFI concept over the 650-Mha extent of Canada's forest-dominated ecosystems. In so doing, the entirety of Canada's forest ecosystems (managed and unmanaged) were mapped using the same data, attributes, and temporal representation. Moreover, the use of polygons allows for the generation of attributes such as tree species composition, and total biomass and wood volume in a stand-scale format familiar to landscape managers and suitable for strategic planning. The data, methods, and outcomes presented here are portable to other regions and input data sources, and the national SBFI outcomes for Canada are available via open access. [ABSTRACT FROM AUTHOR]

Since the 1970s oil boom, nations surrounding the Arabian Gulf have witnessed rapid coastal urbanization, which accelerated in the early 2000s with the emergence of large-scale coastal 'mega-projects' designed to accommodate growing populations, attract international investments, and promote tourism. This development surge has had profound environmental impacts, including significant habitat modification, land use and land cover (LULC) change, and increased environmental pressure. Remote sensing (RS) technologies have become indispensable tools for monitoring these changes, offering costeffective and non-intrusive methods to map and assess coastal zones. However, RS applications across the Arabian Gulf have been spatially limited, often focusing narrowly on specific cities or habitats while neglecting the broader geographical and coastal dimensions of urbanization. This study addresses this gap by conducting a systematic review of peer-reviewed RS literature from 1971 to 2022, covering the coastal regions of the eight nations bordering the Arabian Gulf. A total of 186 publications were categorized into three focal areas: 1) coastal urbanization and LULC, 2) coastal and marine habitats, and 3) environmental pressures and state changes. The results reveal a significant increase in RS studies in recent years, with around two-thirds of the publications (64.3%) appearing between 2016 and 2022. Studies predominantly focused on environmental pressures and state changes (35%), followed by habitat modification (27%), and coastal urbanization (20%). Geographically, RS research primarily concentrated on the coasts of the southern Gulf (UAE and Qatar) and western Gulf (Bahrain and Saudi Arabia), where major urban centers are located, while the northern Gulf (Kuwait and Iraq) and Iranian coast have been less studied. The systematic review highlights the need for integrated RS and GIS-based monitoring systems that combine different sources of RS data and in situ measurements to evaluate the Gulf as a unified system. Expanding spatial coverage, enhancing temporal analysis, and fostering regional collaboration are necessary to improve the understanding and management of coastal urbanization and environmental changes in the Arabian Gulf. This approach will more effectively inform decision-makers, and support more sustainable coastal management and long-term environmental resilience in the region. [ABSTRACT FROM AUTHOR]

To address the challenges of change detection tasks, including the scarcity and dispersion of labeled samples, the difficulty in efficiently extracting features from unstructured image objects, and the underutilization of high-order correlation information, we propose a novel architecture based on hypergraph convolutional neural networks. By characterizing superpixel vertices and their high-order correlations, the method implicitly expands the number of labels while assigning adaptive weight parameters to adjacent objects. It not only describes changes in vertex features but also uncovers local and consistent changes within hyperedges. Specifically, a vertex aggregation mechanism based on superpixel segmentation is established, which segments the difference map into superpixels of diverse shapes and boundaries, and extracts their significant statistical features. Subsequently, a dynamic hypergraph structure is constructed, with each superpixel serving as a vertex. Based on the multi-head self-attention mechanism, the connection probability between vertices and hyperedges is calculated through learnable parameters, and the hyperedges are generated through threshold filtering. Moreover, a framework based on hypergraph convolutional neural networks is customized, which models the high-order correlations within the data through the learning optimization of the hypergraph, achieving change detection in remote sensing images. The experimental results demonstrate that the method obtains impressive qualitative and quantitative analysis results on the three remote sensing datasets, thereby verifying its effectiveness in enhancing the robustness and accuracy of change detection. [ABSTRACT FROM AUTHOR]

Accurate understanding of urban land use change information is of great significance for urban planning, urban monitoring, and disaster assessment. The use of Very-High-Resolution (VHR) remote sensing images for change detection on urban land features has gradually become mainstream. However, most existing transfer learning-based change detection models compute multiple deep image features, leading to feature redundancy. Therefore, we propose a Transfer Learning Change Detection Model Based on Change Feature Selection (TL-FS). The proposed method involves using a pretrained transfer learning model framework to compute deep features from multitemporal remote sensing images. A change feature selection algorithm is then designed to filter relevant change information. Subsequently, these change features are combined into a vector. The Change Vector Analysis (CVA) is employed to calculate the magnitude of change in the vector. Finally, the Fuzzy C-Means (FCM) classification is utilized to obtain binary change detection results. In this study, we selected four VHR optical image datasets from Beijing-2 for the experiment. Compared with the Change Vector Analysis and Spectral Gradient Difference, the TL-FS method had maximum increases of 26.41% in the F1-score, 38.04% in precision, 29.88% in recall, and 26.15% in the overall accuracy. The results of the ablation experiments also indicate that TL-FS could provide clearer texture and shape detections for dual-temporal VHR image changes. It can effectively detect complex features in urban scenes. [ABSTRACT FROM AUTHOR]

Growing season freeze events pose a threat to quaking aspen (Populus tremuloides Michx.), leading to canopy defoliation, reduced vigor, and increased mortality, especially for declining montane populations western North America. Detecting the spatial distribution and progression of this damage is challenging due to limited in situ observations in this region. This study represents the first attempt to comprehensively resolve the spatial extent of freeze-induced aspen canopy damage in southern Utah using multispectral remote sensing data. We developed an approach to detect the spatial and temporal dynamics of freeze-damaged aspen stands, focusing on a freeze event from 8–9 June 2020 in southern Utah. By integrating medium- (~250 to 500 m) and high-resolution (~10 m) satellite data, we employed the Normalized Difference Vegetation Index (NDVI) to compare post-freeze conditions with historical norms and pre-freeze conditions. Our analysis revealed NDVI reductions of 0.10 to 0.40 from pre-freeze values and a second flush recovery. We introduced a pixel-based method to evaluate freeze vulnerability, establishing a strong correlation (R values 0.78 to 0.82) between the onset of the first flush (NDVI > 0.50) and the accumulation of 100 growing degree days (GDD). These methods support the potential for retrospective assessments, proactive forest monitoring, and forecasting future risks. [ABSTRACT FROM AUTHOR]

Building change detection (BCD) from remote sensing images is an essential field for urban studies. In this well-developed field, Convolutional Neural Networks (CNNs) and Transformer have been leveraged to empower BCD models in handling multi-scale information. However, it is still challenging to accurately detect subtle changes using current models, which has been the main bottleneck to improving detection accuracy. In this paper, a multi-scale differential feature self-attention network (MDFA-Net) is proposed to effectively integrate CNN and Transformer by balancing the global receptive field from the self-attention mechanism and the local receptive field from convolutions. In MDFA-Net, two innovative modules were designed. Particularly, a hierarchical multi-scale dilated convolution (HMDConv) module was proposed to extract local features with hybrid dilation convolutions, which can ameliorate the effect of CNN's local bias. In addition, a differential feature self-attention (DFA) module was developed to implement the self-attention mechanism at multi-scale difference feature maps to overcome the problem that local details may be lost in the global receptive field in Transformer. The proposed MDFA-Net achieves state-of-the-art accuracy performance in comparison with related works, e.g., USSFC-Net, in three open datasets: WHU-CD, CDD-CD, and LEVIR-CD. Based on the experimental results, MDFA-Net significantly exceeds other models in F1 score, IoU, and overall accuracy; the F1 score is 93.81%, 95.52%, and 91.21% in WHU-CD, CDD-CD, and LEVIR-CD datasets, respectively. Furthermore, MDFA-Net achieved first or second place in precision and recall in the test in all three datasets, which indicates its better balance in precision and recall than other models. We also found that subtle changes, i.e., small-sized building changes and irregular boundary changes, are better detected thanks to the introduction of HMDConv and DFA. To this end, with its better ability to leverage multi-scale differential information than traditional methods, MDFA-Net provides a novel and effective avenue to integrate CNN and Transformer in BCD. Further studies could focus on improving the model's insensitivity to hyper-parameters and the model's generalizability in practical applications. [ABSTRACT FROM AUTHOR]

Urban public safety management relies heavily on video surveillance systems, which provide crucial visual data for resolving a wide range of incidents and controlling unlawful activities. Traditional methods for target detection predominantly employ a two-stage approach, focusing on precision in identifying objects such as pedestrians and vehicles. These objects, typically sparse in large-scale, lower-quality surveillance footage, induce considerable redundant computation during the initial processing stage. This redundancy constrains real-time detection capabilities and escalates processing costs. Furthermore, transmitting raw images and videos laden with superfluous information to centralized back-end systems significantly burdens network communications and fails to capitalize on the computational resources available at diverse surveillance nodes. This study introduces DiffRank, a novel preprocessing method for fixed-angle video imagery in urban surveillance. The method strategically generates candidate regions during preprocessing, thereby reducing redundant object detection and improving the efficiency of the detection algorithm. Drawing upon change detection principles, a background feature learning approach utilizing shallow features has been developed. This approach prioritizes learning the characteristics of fixed-area backgrounds over direct background identification. As a result, alterations in ROI are efficiently discerned using computationally efficient shallow features, markedly accelerating the generation of proposed Regions of Interest (ROIs) and diminishing the computational demands for subsequent object detection and classification. Comparative analysis on various public and private datasets illustrates that DiffRank, while maintaining high accuracy, substantially outperforms existing baselines in terms of speed, particularly with larger image sizes (e.g., an improvement exceeding 300 % at 1920×1080 resolution). Moreover, the method demonstrates enhanced robustness compared to baseline methods, efficiently disregarding static targets like mannequins in display windows. The advancements in candidate area preprocessing enable a balanced approach between detection accuracy and overall detection speed, making the algorithm highly applicable for real-time on-site analysis in edge computing scenarios and cloud-edge collaborative computing environments. [ABSTRACT FROM AUTHOR]

Advances in numerical algorithms, improvement of computational power and progress in remote sensing have led to the development of global flood models (GFMs), which promise to be a useful tool for large-scale flood risk management. However, performance and reliability of GFMs, especially in data-scarce regions, is still uncertain, as they are difficult to validate. Here we aim at contributing to develop alternative, more flexible, and consistent methods for GFM validation by applying a change detection analysis on synthetic aperture radar (CD-SAR) imagery obtained from the Sentinel-1 imagery, on a cloud-based geospatial analysis platform. The study addresses two main objectives. First, to validate four widely adopted GFMs with flood maps generated through the proposed CD-SAR approach. This exercise was conducted for eight different large river basins on four continents, to account for a diverse range of hydro-climatic environments. Second, to compare CD-SAR-derived flood maps with those obtained from alternative remote sensing sources. These comparative results offer valuable insights into the reliability of CD-SAR data as a validation tool, more specifically how it stacks up against flood maps generated by other remote sensing techniques. [ABSTRACT FROM AUTHOR]

The denser the Lidar data, the more faithfully it models the terrain. This property of dense Lidar data allows a detection of changes but also their quantification at a level of precision that can highlight even displacements of objects in all three spatial directions. The point cloud has different densities and accuracies depending on the platform on which the scanning system is installed (manned aircraft, drones or ground stations). Density and precision parameters drive different approaches in change detection algorithms. For completing these tasks, two independent applications were developed to highlight both major landscape changes and smaller changes such as displacement of objects, construction settlements, landslides. [ABSTRACT FROM AUTHOR]

Objectives: The state space model Mamba, which combines global sensing field and dynamic weighting, can better capture the trend and periodic information in the time series prediction task, and has become an important direction in the current deep learning technologies for remote sensing image analysis and interpretation. However, the current research of Mamba in the dense prediction of remote sensing images is insufficient, and there are problems such as high computational complexity and low detection efficiency for the change detection of high-resolution remote sensing images. Methods: We conduct an in-depth analysis of the key factors affecting the number of parameters of the Mamba layer, and propose a dual-stream parallel omnidirectional scan Mamba (DSPOSM) model architecture to construct an in-channel data parallelization processing method. The proposed DSPOSM model can effectively reduce the number of channels of the data in single Mamba block while the total number of channels remains unchanged, in order to achieve highly efficient feature extraction based on the decrease of the overall number of parameters of the model. Results: Comparative experimental results on the LEVIR-CD and WHU-CD datasets show that the proposed method outperforms the non-Mamba architecture method in all metrics and significantly reduces the number of parameters and computational complexity of the network by 35.8% and 22.4%, and improves the training efficiency by 19.45% and 8.26%, compared with the benchmark method, respectively. Conclusions: The proposed DSPOSM method can significantly reduce the number of parameters and computational complexity of Mamba-based networks and improve training efficiency. [ABSTRACT FROM AUTHOR]

Cultural property includes immovable assets that are part of a nation's cultural heritage and reflect the cultural identity of a people. Hence, information about armed conflict's impact on historical buildings' structures and heritage sites is extremely important. The study aims to demonstrate the application of Earth observation (EO) synthetic aperture radar (SAR) technology, and in particular Sentinel-1 SAR coherence time-series analysis, to monitor spatial and temporal changes related to the recent Russian–Ukrainian war in the urban areas of Mariupol and Kharkiv, Ukraine. The study considers key events during the siege of Mariupol and the battle of Kharkiv from February to May 2022. Built-up areas and cultural property were identified using freely available OpenStreetMap (OSM) data. Semi-automated coherent change-detection technique (CCD) that utilize difference analysis of pre- and co-conflict coherences were capable of highlighting areas of major impact on the urban structures. The study applied a logistic regression model (LRM) for the discrimination of damaged and undamaged buildings based on an estimated likelihood of damage occurrence. A good agreement was observed with the reference data provided by the United Nations Satellite Centre (UNOSAT) in terms of the overall extent of damage. Damage maps enable the localization of buildings and cultural assets in areas with a high probability of damage and can serve as the basis for a high-resolution follow-up investigation. The study reveals the benefits of Sentinel-1 SAR CCD in the sense of unsupervised delineation of areas affected by armed conflict. However, limitations arise in the detection of local and single-building damage compared to regions with large-scale destruction. The proposed semi-automated multi-temporal Sentinel-1 data analysis using CCD methodology shows its applicability for the timely investigation of damage to buildings and cultural heritage, which can support the response to crises. [ABSTRACT FROM AUTHOR]

The detection of change in remote-sensing images is broadly applicable to many fields. In recent years, both supervised and unsupervised methods have demonstrated excellent capacity to detect changes in high-resolution images. However, most of these methods are sensitive to noise, and their performance significantly deteriorates when dealing with remote-sensing images that have been contaminated by mixed random noises. Moreover, supervised methods require that samples are manually labeled for training, which is time-consuming and labor-intensive. This study proposes a new unsupervised change-detection (CD) framework that is resilient to mixed random noise called self-supervised denoising network-based unsupervised change-detection coupling FCM_SICM and EMD (SSDNet-FSE). It consists of two components, namely a denoising module and a CD module. The proposed method first utilizes a self-supervised denoising network with real 3D weight attention mechanisms to reconstruct noisy images. Then, a noise-resistant fuzzy C-means clustering algorithm (FCM_SICM) is used to decompose the mixed pixels of reconstructed images into multiple signal classes by exploiting local spatial information, spectral information, and membership linkage. Next, the noise-resistant Earth mover's distance (EMD) is used to calculate the distance between signal-class centers and the corresponding fuzzy memberships of bitemporal pixels and generate a map of the magnitude of change. Finally, automatic thresholding is undertaken to binarize the change-magnitude map into the final CD map. The results of experiments conducted on five public datasets prove the superior noise-resistant performance of the proposed method over six state-of-the-art CD competitors and confirm its effectiveness and potential for practical application. [ABSTRACT FROM AUTHOR]

Change detection in high-resolution Earth observation is a fundamental Earth vision task to understand the subtle temporal dynamics of Earth's surface, significantly promoted by generic vision technologies in recent years. Vision Transformer is a powerful component to learning spatiotemporal representation but with enormous computation complexity, especially for high-resolution images. Besides, there is still lacking principles in designing macro architectures integrating these advanced vision components for various change detection tasks. In this paper, we present a deep probabilistic change model (DPCM) to provide a unified, interpretable, modular probabilistic change process modeling to address multiple change detection tasks, including binary change detection, one-to-many semantic change detection, and many-to-many semantic change detection. DPCM describes any complex change process as a probabilistic graphical model to provide theoretical evidence for macro architecture design and generic change detection task modeling. We refer to this probabilistic graphical model as the probabilistic change model (PCM), where DPCM is the PCM parameterized by deep neural networks. For parameterization, the PCM is factorized into many easy-to-solve distributions based on task-specific assumptions, and then we can use deep neural modules to parameterize these distributions to solve the change detection problem uniformly. In this way, DPCM has both theoretical macro architecture from PCM and strong representation capability of deep networks. We also present the sparse change Transformer for better parameterization. Inspired by domain knowledge, i.e., the sparsity of change and the local correlation of change, the sparse change Transformer computes self-attention within change regions to model spatiotemporal correlations, which has a quadratic computational complexity of the change region size but independent of image size, significantly reducing computation overhead for high-resolution image change detection. We refer to this instance of DPCM with sparse change Transformer as ChangeSparse to demonstrate their effectiveness. The experiments confirm ChangeSparse's superiority in speed and accuracy for multiple real-world application scenarios, such as disaster response and urban development monitoring. The code is available at https://github.com/Z-Zheng/pytorch-change-models. More resources can be found in http://rsidea.whu.edu.cn/resource_sharing.htm. [ABSTRACT FROM AUTHOR]

In remote sensing (RS) image change detection (CD) task, many existing CD methods focus more on how to improve accuracy, but they usually have more parameters, higher computational costs, and heavier memory usage. Designing lightweight and performance-sustainable CD model that is more compatible with real-world applications is an urgent problem to be solved. Therefore, we propose a lightweight change detection network, called as robust feature aggregation network (RFANet). To improve representative capability of weaker features extracted from lightweight backbone, a feature reinforcement module (FRM) is proposed. FRM allows current level feature to densely interact and fuse with other level features, thus accomplishing the complementarity of fine-grained details and semantic information. Considering massive objects with rich correlations in RS images, we design semantic split-aggregation module (SSAM) to better capture global semantic information of changed objects. Besides, we present a lightweight decoder containing channel interaction module (CIM), which allows multi-level refined difference features to emphasize changed areas and suppress background and pseudo-changes. Extensive experiments carried out on four challenging RS image CD datasets illustrate that RFANet achieves competitive performance with fewer parameters and lower computational costs. The source code is available at https://github.com/Youzhihui/RFANet. [ABSTRACT FROM AUTHOR]

In remote sensing, change detection based on deep learning shows promising performance. However, collecting multi-temporal paired images for training a change detection model is costly. To solve this problem, unsupervised change detection methodologies have been proposed, but their performance is still low. In this article, we introduce the Unsupervised Change Detection Based on Image Reconstruction Loss (CDRL) and CDRL with Segment Anything (CDRL-SA). Requiring only single-temporal unlabelled images for training, CDRL uses the original and a photometrically transformed image as an unchanged pair, input to a bi-temporal transformer-based network for reconstructing the original image. During inference, changed pairs result in significant reconstruction loss, highlighting change areas. To capture finer details, we change the structure of CDRL to a transformer-based model and introduce the CutSwap method for effective training. Furthermore, this output is fused with the results of a recently proposed Segment Anything (SA) model to improve the final output. We assessed the performance of CDRL and CDRL-SA using the LEVIR change detection dataset and CLCD dataset, and the method achieved competitive results of 88.9 and 91.6 ACC for the respective datasets, demonstrating its effectiveness in unsupervised change detection tasks. [ABSTRACT FROM AUTHOR]

The creation of information transparency solutions to enable humans to understand robot perception is a challenging requirement for autonomous and artificially intelligent robots to impact a multitude of domains. By taking advantage of comprehensive and high-volume data from robot teammates' advanced perception and reasoning capabilities, humans will be able to make better decisions, with significant impacts from safety to functionality. We present a solution to this challenge by coupling augmented reality (AR) with an intelligent mobile robot that is autonomously detecting novel changes in an environment. We show that the human teammate can understand and make decisions based on information shared via AR by the robot. Sharing of robot-perceived information is enabled by the robot's online calculation of the human's relative position, making the system robust to environments without external instrumentation such as global positioning system. Our robotic system performs change detection by comparing current metric sensor readings against a previous reading to identify differences. We experimentally explore the design of change detection visualizations and the aggregation of information, the impact of instruction on communication understanding, the effects of visualization and alignment error, and the relationship between situated 3D visualization in AR and human movement in the operational environment on shared situational awareness in human-robot teams. We demonstrate this novel capability and assess the effectiveness of human-robot teaming in crowdsourced data-driven studies, as well as an in-person study where participants are equipped with a commercial off-the-shelf AR headset and teamed with a small ground robot that maneuvers through the environment. The mobile robot scans for changes, which are visualized via AR to the participant. The effectiveness of this communication is evaluated through accuracy and subjective assessment metrics to provide insight into interpretation and experience. [ABSTRACT FROM AUTHOR]

Forest inspection is a crucial component of forest monitoring in China. The current methods for detecting changes in forest patches primarily rely on remote sensing imagery and manual visual interpretation, which are time-consuming and labor-intensive approaches. This study aims to automate the extraction of changed forest patches using UAVs and artificial intelligence technologies, thereby saving time while ensuring detection accuracy. The research first utilizes position and orientation system (POS) data to perform geometric correction on the acquired UAV imagery. Then, a convolutional neural network (CNN) is used to extract forest boundaries and compare them with the previous vector data of forest boundaries to initially detect patches of forest reduction. The average boundary distance algorithm (ABDA) is applied to eliminate misclassified patches, ultimately generating precise maps of reduced forest patches. The results indicate that using POS data with RTK positioning for correcting UAV imagery results in a central area correction error of approximately 4 m and an edge area error of approximately 12 m. The TernausNet model achieved a maximum accuracy of 0.98 in identifying forest areas, effectively eliminating the influence of shrubs and grasslands. When the UAV flying height is 380 m and the distance threshold is set to 8 m, the ABDA successfully filters out misclassified patches, achieving an identification accuracy of 0.95 for reduced forest patches, a precision of 0.91, and a kappa coefficient of 0.89, fully meeting the needs of forest inspection work in China. Select urban forests with complex scenarios in the research area can be used to better promote them to other regions. This study ultimately developed a fully automated forest change detection system. [ABSTRACT FROM AUTHOR]

In this paper, a feature interactive bi-temporal change detection network (FIBTNet) is designed to solve the problem of pseudo change in remote sensing image building change detection. The network improves the accuracy of change detection through bi-temporal feature interaction. FIBTNet designs a bi-temporal feature exchange architecture (EXA) and a bi-temporal difference extraction architecture (DFA). EXA improves the feature exchange ability of the model encoding process through multiple space, channel or hybrid feature exchange methods, while DFA uses the change residual (CR) module to improve the ability of the model decoding process to extract different features at multiple scales. Additionally, at the junction of encoder and decoder, channel exchange is combined with the CR module to achieve an adaptive channel exchange, which further improves the decision-making performance of model feature fusion. Experimental results on the LEVIR-CD and S2Looking datasets demonstrate that iCDNet achieves superior F1 scores, Intersection over Union (IoU), and Recall compared to mainstream building change detection models, confirming its effectiveness and superiority in the field of remote sensing image change detection. [ABSTRACT FROM AUTHOR]

Forest ecosystems are critical components of Earth's biodiversity and play vital roles in climate regulation and carbon sequestration. They face increasing threats from deforestation, wildfires, and other anthropogenic activities. Timely detection and monitoring of changes in forest landscapes pose significant challenges for government agencies. To address these challenges, we propose a novel pipeline by refining the U-Net design, including employing two different schemata of early fusion networks and a Siam network architecture capable of processing RGB images specifically designed to identify high-risk areas in forest ecosystems through change detection across different time frames in the same location. It annotates ground truth change maps in such time frames using an encoder–decoder approach with the help of an enhanced feature learning and attention mechanism. Our proposed pipeline, integrated with ResNeSt blocks and SE attention techniques, achieved impressive results in our newly created forest cover change dataset. The evaluation metrics reveal a Dice score of 39.03%, a kappa score of 35.13%, an F1-score of 42.84%, and an overall accuracy of 94.37%. Notably, our approach significantly outperformed multitasking model approaches in the ONERA dataset, boasting a precision of 53.32%, a Dice score of 59.97%, and an overall accuracy of 97.82%. Furthermore, it surpassed multitasking models in the HRSCD dataset, even without utilizing land cover maps, achieving a Dice score of 44.62%, a kappa score of 11.97%, and an overall accuracy of 98.44%. Although the proposed model had a lower F1-score than other methods, other performance metrics highlight its effectiveness in timely detection and forest landscape monitoring, advancing deep learning techniques in this field. [ABSTRACT FROM AUTHOR]

Developing sustainable forest management strategies requires careful understanding of changes in forest cover and its driving forces. Therefore, this study was conducted to detect the spatial extent and trends of forest cover change, identify driving forces, and its implication for livelihoods in the Bure district of Illubabor zone, southwest Ethiopia. Landsat images of 1986, 2000, and 2023 were used to detect the forest cover changes. Focus group discussions, survey questionnaire, key informant interviews and field observation were used to identify the drivers for forest cover change. Results identified four different land use and land cover classes, namely forestland, cultivated land, grassland and wetland. The results of the change detection showed that there has been a notable spatiotemporal change in the forest cover in the study district from 1986 to 2023. The forest's initial extent was 52,800 ha in 1986; between 1986 and 2000, it reduced by 3,300 ha, between 2000 and 2023, it shrunk by 30,200 ha, and between 1986 and 2023, it minimized by 33,500 ha. There were several factors that contributed to the observed changes in forest cover, including the expansion of farmland, rapid population growth, demand for fuelwood and construction materials, charcoal making and timber production, and overgrazing. Reduced agricultural productivity, soil erosion, climate change, and biodiversity loss were all caused by changes in the forest cover. Based on the study findings, it is recommended that afforestation and reforestation programs be put in place in order to increase forest cover in the study area.

The regional ecological environment has become a significant subject of study due to the dynamics of the ecosystem, which is represented by vegetation, under the influence of human activities. The objective of this research is to demonstrate the implementation and effectiveness of the Forest Canopy Density (FCD) model in generating a map that illustrates changes in forest canopy density using multitemporal remote sensing data in Tabunio watershed. The methodology relies on vegetation index, including the Normalized Difference Vegetation Index (NDVI), shadow index (SI), and bare soil index (BI), to generate a composite vegetation index (CVI). FCD uses multitemporal remote sensing data from Landsat TM images from 2005 to 2020, which have been utilized to accomplish multi-source categorization. The findings indicated that the vegetation coverage of the Tabunio watershed presented a predominant pattern of high coverage in the northeastern and eastern regions, whereas most areas of the western region had low coverage; (2) vegetation cover from 2005 to 2020 is dominated by sparse to very dense vegetation cover classes; (3) changes in vegetation cover over two decades are very significant. The expansion of plantation land in 2005 caused a lot of non-vegetated land, which gradually changed in the following year period along with plant growth. At the end of 2020, the percentage of very dense vegetation became increasingly dominant, which was around 42 percent. The results of the study indicate the three biophysical index (NDVI, SI, and BI) used in this model approach were appropriate for precisely discriminating across all canopy density classes, as seen by the overall producer's accuracy of 81.3%. FCD model in multitemporal data can help in the early identification of deforestation or forest degradation activities. Furthermore, the FCD model may have certain constraints, as it requires an understanding of ground conditions to establish threshold values for each class.

Urban public safety management relies heavily on video surveillance systems, which provide crucial visual data for resolving a wide range of incidents and controlling unlawful activities. Traditional methods for target detection predominantly employ a two-stage approach, focusing on precision in identifying objects such as pedestrians and vehicles. These objects, typically sparse in large-scale, lower-quality surveillance footage, induce considerable redundant computation during the initial processing stage. This redundancy constrains real-time detection capabilities and escalates processing costs. Furthermore, transmitting raw images and videos laden with superfluous information to centralized back-end systems significantly burdens network communications and fails to capitalize on the computational resources available at diverse surveillance nodes. This study introduces DiffRank, a novel preprocessing method for fixed-angle video imagery in urban surveillance. The method strategically generates candidate regions during preprocessing, thereby reducing redundant object detection and improving the efficiency of the detection algorithm. Drawing upon change detection principles, a background feature learning approach utilizing shallow features has been developed. This approach prioritizes learning the characteristics of fixed-area backgrounds over direct background identification. As a result, alterations in ROI are efficiently discerned using computationally efficient shallow features, markedly accelerating the generation of proposed Regions of Interest (ROIs) and diminishing the computational demands for subsequent object detection and classification. Comparative analysis on various public and private datasets illustrates that DiffRank, while maintaining high accuracy, substantially outperforms existing baselines in terms of speed, particularly with larger image sizes (e.g., an improvement exceeding 300 % at 1920×1080 resolution). Moreover, the method demonstrates enhanced robustness compared to baseline methods, efficiently disregarding static targets like mannequins in display windows. The advancements in candidate area preprocessing enable a balanced approach between detection accuracy and overall detection speed, making the algorithm highly applicable for real-time on-site analysis in edge computing scenarios and cloud-edge collaborative computing environments.

Abstract Growing intracranial aneurysms pose a high risk of rupture, making the detection and quantification of the growth crucial for timely treatment strategy adoption. In this paper we propose a computer-assisted approach based on the extraction of IA shapes from associated baseline and follow-up angiographic scans and non-rigid morphing of the two shapes. From the obtained shape deformations we computed four novel features, including differential volume (dV), surface area (dSA), aneurysm-size normalized median deformation path length (dMPL), and integral of cumulative deformation distances (dICDD). An experienced neuroradiologist manually extracted the IA shape models from the baseline and follow-up MRAs and, by utilizing size change and visual assessments, classified each aneurysm into stable with morphology changes, stable or growing. We investigated the classification performance and found that three of the novel and one cross-sectional feature exhibited significantly different mean values (p-value $$< 0.05$$ < 0.05 ; Tukey’s HSD test) between the stable and growing IA groups, while the mean dICDD was significantly different between all the three groups. The cross-sectional features has sensitivity to growing IAs in range 0.05–0.86, while novel features had generally higher sensitivity in range 0.81–0.90, making them promising candidates as surrogate follow-up imaging-based biomarkers for IA growth detection. These findings may offer valuable information for clinical management of patients with IAs based on follow-up imaging.

Background Subtraction (BgS) is a widely researched technique to develop online Change Detection algorithms for static video cameras. Many BgS methods have employed the unsupervised, adaptive approach of Gaussian Mixture Model (GMM) to produce decent backgrounds, but they lack proper consideration of scene semantics to produce better foregrounds. On the other hand, with considerable computational expenses, BgS with Deep Neural Networks (DNN) is able to produce accurate background and foreground segments. In our research, we blend both approaches for the best. First, we formulated a network called Convolutional Density Approximation (CDA) for direct density estimation of background models. Then, we propose a self-supervised training strategy for CDA to adaptively capture high-frequency color distributions for the corresponding backgrounds. Finally, we show that background models can indeed assist foreground extraction by an efficient Neural Motion Subtraction (NeMos) network. Our experiments verify competitive results in the balance between effectiveness and efficiency.

The ecological quality of a region is significantly influenced by its geographical conditions, which can yield different effects on ecosystems. Nevertheless, the lack of adequate technology has impeded quantitative investigations into these differences. Consequently, there is an increasing demand for effective techniques to quantitatively measure differences in ecological quality resulting from variations in geographical conditions. This study applied the novel Remote Sensing-based Ecological Index (RSEI) concurrently to two distinct provincial-level regions in China, Fujian and Ningxia, to quantitatively detect their ecological differences. These two regions possess contrasting geographical conditions, with Fujian having high forest coverage and abundant rainfall, while Ningxia features low forest coverage and extensive loess plateau and desert terrain. By linking geographical factors with their corresponding ecological responses, we conducted a comprehensive analysis to determine whether the contrasting geographical conditions between the two regions had caused significant disparities in their ecological status. The results indicate that the contrasting geographical conditions have indeed led to marked ecological differences, with Fujian exhibiting excellent ecological status, while Ningxia lags behind due to unfavorable geographical conditions. In terms of RSEI scores, Fujian consistently achieved higher RSEI values (>0.8) in the study years, reaching an excellent ecological level, whereas Ningxia recorded scores lower than 0.45 during the comparable years, corresponding to a poor to moderate ecological level. Regarding the impact of geographical factors on ecological conditions, the positive contributions of greenness and wetness indicators to the ecology in Fujian were significantly greater than those in Ningxia (58% vs. 39%), whereas the contributions of negative indicators, dryness and hotness, were notably higher in Ningxia compared to Fujian (|–61|% vs. |–42|%). The successful concurrent application of RSEI to these two geographically distant regions also demonstrates the robustness of the RSEI technique.

Integration of GIS and remote sensing is a powerful source for implementing temporal analysis. The focus of this paper was to use Landsat 5 and 8 imageries to monitor changes in the Ranya city throughout five time periods (2000, 2005, 2010, 2015, and 2020). Image classification was done using iso cluster unsupervised classification tool via ArcGIS. To calculate the kappa coefficient and assess the accuracy, random points of the outcome were compared with ground truth data using Google Earth Pro, which produced highly accurate results. According to this study, the Ranya city had the highest proportion of green space (52%) in 2000. Though, after 20 years due to rapid urbanization, Ranya's built-up regions had quickly outgrown both bare land and agricultural land, growing in size by 223.53%. However, from the year 2000 to 2020, green spaces and bare land both showed a clear downward trend, losing, respectively, 44.9% and 41.3% of their space. Being an independent administration is one of the key causes of Ranya city's rapid urbanization and subsequent development between 2000 and 2020, in addition to other aspects like the building of numerous government and residential facilities.