Search

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]

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]

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]

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]

To address the recent increase in wildfire severity and incidence, as well as the subsequent financial and physical costs, forest managers and wildland firefighting agencies rely on remotely sensed products for better decision-making and mitigation efforts. To address the remote sensing needs of these agencies, which include high spatial resolution, immunity to atmospheric and solar illumination effects, and day/night capabilities, the use of synthetic aperture radar (SAR) is under investigation for application in current and upcoming systems for all phases of a wildfire. Focusing on the active phase, a method for monitoring wildfire activity is presented based on changes in the radar vegetation index (RVI). L-band backscatter measurements from NASA/JPL's UAVSAR instrument are used to obtain RVI images on multiple dates during the 2020 Bobcat (located in Southern CA, USA) and Hennessey (located in Northern CA, USA) fires and the 2021 Caldor (located in the Sierra Nevada region of CA, USA) fire. Changes in the RVI between measurement dates of a single fire are then compared to indicators of fire activity such as ancillary GIS-based burn extent perimeters and the Landsat 8-based difference normalized burn ratio (dNBR). An RVI-based wildfire "burn" detector/index is then developed by thresholding the RVI change. A combination of the receiver operating characteristic (ROC) curves and F1 scores for this detector are used to derive change detection thresholds at varying spatial resolutions. Six repeat-track UAVSAR lines over the 2020 fires are used to determine appropriate threshold values, and the performance is subsequently investigated for the 2021 Caldor fire. The results show good performance for the Bobcat and Hennessey fires at 100 m resolution, with optimum probability of detections of 67.89% and 71.98%, F1 scores of 0.6865 and 0.7309, and Matthews correlation coefficients of 0.5863 and 0.6207, respectively, with an overall increase in performance for all metrics as spatial resolution becomes coarser. The results for pixels identified as "burned" compare well with other fire indicators such as soil burn severity, known progression maps, and post-fire agency publications. Good performance is also observed for the Caldor fire where the percentage of pixels identified as burned within the known fire perimeters ranges from 37.87% at ~5 m resolution to 88.02% at 500 m resolution, with a general increase in performance as spatial resolution increases. All detections for Caldor show dense collections of burned pixels within the known perimeters, while pixels identified as burned that lie outside of the know perimeters have a sparse spatial distribution similar to noise that decreases as spatial resolution is degraded. The Caldor results also align well with other fire indicators such as soil burn severity and vegetation disturbance. [ABSTRACT FROM AUTHOR]

With the development of satellite technology, the importance of multi-temporal remote sensing (RS) image change detection (CD) in urban planning, environmental monitoring, and other fields is increasingly prominent. Deep learning techniques enable a profound exploration of the intrinsic features within hyperspectral (HS) data, leading to substantial enhancements in CD accuracy while addressing several challenges posed by traditional methodologies. However, existing convolutional neural network (CNN)-based CD approaches frequently encounter issues during the feature extraction process, such as the loss of detailed information due to downsampling, which hampers a model's ability to accurately capture complex spectral features. Additionally, these methods often neglect the integration of multi-scale information, resulting in suboptimal local feature extraction and, consequently, diminished model performance. To address these limitations, we propose a multi-scale fusion network (MsFNet) which leverages dynamic spectral features for effective multi-temporal HS-CD. Our approach incorporates a dynamic convolution module with spectral attention, which adaptively modulates the receptive field size according to the spectral characteristics of different bands. This flexibility enhances the model's capacity to focus on critical bands, thereby improving its ability to identify and differentiate changes across spectral dimensions. Furthermore, we develop a multi-scale feature fusion module which extracts and integrates features from deep feature maps, enriching local information and augmenting the model's sensitivity to local variations. Experimental evaluations conducted on three real-world HS-CD datasets demonstrate that the proposed MsFNet significantly outperforms contemporary advanced CD methods in terms of both efficacy and performance. [ABSTRACT FROM AUTHOR]

Change detection using SAR data has been an active topic in various applications. Because conventional change detection identifies signal changes in single-pol radar observations, they cannot separately detect different kinds of change associated with different ground parameters. In this study, we investigated the comprehensive use of dual-pol parameters and proposed a novel dual-pol-based change detection framework utilizing different dual-pol scatter-type indicators. To optimize the exploitation of dual-pol change information, we presented a two-step processing strategy that divides the multiclass change detection process into a binary detection step that identifies the presence of changes and the classification step that distinguishes the types of change. In the detection stage, each dual-pol parameter was considered as an independent information source. Assuming potential conflict between dual-pol parameters, a disjunctive combination of detection results from different dual-pol parameters was applied to obtain the final detection result. In the classification step, an unsupervised change classification strategy was proposed based on the change direction and magnitude of the dual-pol parameters within the change class. Experimental results exhibited significantly improved detectability across a wide change spectrum compared with previous dual-pol-based change detection approaches. They also demonstrated the possibility of distinguishing different semantic changes without in situ ground data. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) technology has become an important means of flood monitoring because of its large coverage, repeated observation, and all-weather and all-time working capabilities. The commonly used thresholding and change detection methods in emergency monitoring can quickly and simply detect floods. However, these methods still have some problems: (1) thresholding methods are easily affected by low backscattering regions and speckle noise; (2) changes from multi-temporal information include urban renewal and seasonal variation, reducing the precision of flood monitoring. To solve these problems, this paper presents a new flood mapping framework that combines semi-automatic thresholding and change detection. First, multiple lines across land and water are drawn manually, and their local optimal thresholds are calculated automatically along these lines from two ends towards the middle. Using the average of these thresholds, the low backscattering regions are extracted to generate a preliminary inundation map. Then, the neighborhood-based change detection method combined with entropy thresholding is adopted to detect the changed areas. Finally, pixels in both the low backscattering regions and the changed regions are marked as inundated terrain. Two flood datasets, one from Sentinel-1 in the Wharfe and Ouse River basin and another from GF-3 in Chaohu are chosen to verify the effectiveness and practicality of the proposed method. [ABSTRACT FROM AUTHOR]

Change detection aims to identify the difference between dual-temporal images and has garnered considerable attention over the past decade. Recently, deep learning methods have shown robust feature extraction capabilities and have achieved improved detection results; however, they exhibit limitations in preserving clear boundaries for the identified regions, which is attributed to the inadequate contextual information aggregation capabilities of feature extraction, and fail to adequately constrain the delineation of boundaries. To address this issue, a novel dual-branch feature interaction backbone network integrating the CNN and Transformer architectures to extract pixel-level change information was developed. With our method, contextual feature aggregation can be achieved by using a cross-layer feature fusion module, and a dual-branch upsampling module is employed to incorporate both spatial and channel information, enhancing the precision of the identified change areas. In addition, a boundary constraint is incorporated, leveraging an MLP module to consolidate fragmented edge information, which increases the boundary constraints within the change areas and minimizes boundary blurring effectively. Quantitative and qualitative experiments were conducted on three benchmarks, including LEVIR-CD, WHU Building, and the xBD natural disaster dataset. The comprehensive results show the superiority of the proposed method compared with previous approaches. [ABSTRACT FROM AUTHOR]

The distribution of forest-dominant tree species is crucial for ecosystem assessment. Remote sensing monitoring requires annual ground sample data, but consistent field surveys are challenging. This study addresses this by combining sample migration learning and machine learning for multi-year tree species classification in the Three Gorges Reservoir area in China. Using the continuous change detection and classification (CCDC) algorithm, sample data from 2023 were successfully migrated to 2018–2022, achieving high migration accuracy ( R 2 = 0.8303, RMSE = 4.64). Based on migrated samples, random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB) algorithms classified forest tree species with overall accuracies above 70% and Kappa coefficients above 0.6. XGB. They outperformed other algorithms, with classification accuracy of over 80% and Kappa above 0.75 in almost all years. The final map indicates stable distribution from 2018 to 2023, with eucalyptus covering over 40% of the forest area, followed by horsetail pine, fir, cypress, and wetland pine. [ABSTRACT FROM AUTHOR]

Change detection is an essential and widely utilized task in remote sensing that aims to detect and analyze changes occurring in the same geographical area over time, which has broad applications in urban development, agricultural surveys, and land cover monitoring. Detecting changes in remote sensing images is a complex challenge due to various factors, including variations in image quality, noise, registration errors, illumination changes, complex landscapes, and spatial heterogeneity. In recent years, deep learning has emerged as a powerful tool for feature extraction and addressing these challenges. Its versatility has resulted in its widespread adoption for numerous image-processing tasks. This paper presents a comprehensive survey of significant advancements in change detection for remote sensing images over the past decade. We first introduce some preliminary knowledge for the change detection task, such as problem definition, datasets, evaluation metrics, and transformer basics, as well as provide a detailed taxonomy of existing algorithms from three different perspectives: algorithm granularity, supervision modes, and frameworks in the Methodology section. This survey enables readers to gain systematic knowledge of change detection tasks from various angles. We then summarize the state-of-the-art performance on several dominant change detection datasets, providing insights into the strengths and limitations of existing algorithms. Based on our survey, some future research directions for change detection in remote sensing are well identified. This survey paper sheds some light the topic for the community and will inspire further research efforts in the change detection task. [ABSTRACT FROM AUTHOR]

Due to the widespread applications of change detection technology in urban change analysis, environmental monitoring, agricultural surveillance, disaster detection, and other domains, the task of change detection has become one of the primary applications of Earth orbit satellite remote sensing data. However, the analysis of dual-temporal change detection (CD) remains a challenge in high-resolution optical remote sensing images due to the complexities in remote sensing images, such as intricate textures, seasonal variations in imaging time, climatic differences, and significant differences in the sizes of various objects. In this paper, we propose a novel U-shaped architecture for change detection. In the encoding stage, a multi-branch feature extraction module is employed by combining CNN and transformer networks to enhance the network's perception capability for objects of varying sizes. Furthermore, a multi-branch aggregation module is utilized to aggregate features from different branches, providing the network with global attention while preserving detailed information. For dual-temporal features, we introduce a spatiotemporal discrepancy perception module to model the context of dual-temporal images. Particularly noteworthy is the construction of channel attention and token attention modules based on the transformer attention mechanism to facilitate information interaction between multi-level features, thereby enhancing the network's contextual awareness. The effectiveness of the proposed network is validated on three public datasets, demonstrating its superior performance over other state-of-the-art methods through qualitative and quantitative experiments. [ABSTRACT FROM AUTHOR]

Heterogeneous image change detection is a very practical and challenging task because the data in the original image have a large distribution difference and the labeled samples of the remote sensing image are usually very few. In this study, we focus on solving the issue of comparing heterogeneous images without supervision. This paper first designs a self-paced multi-scale joint feature mapper (SMJFM) for the mapping of heterogeneous data to similar feature spaces for comparison and incorporates a self-paced learning strategy to weaken the mapper's capture of non-consistent information. Then, the difference information in the output of the mapper is evaluated from two perspectives, namely noise robustness and detail preservation effectiveness; then, the change detection problem is modeled as a multi-objective optimization problem. We decompose this multi-objective optimization problem into several scalar optimization subproblems with different weights, and use particle swarm optimization to optimize these subproblems. Finally, the robust evaluation strategy is used to fuse the multi-scale change information to obtain a high-precision binary change map. Compared with previous methods, the proposed SMJFM framework has the following three main advantages: First, the unsupervised design alleviates the dilemma of few labels in remote sensing images. Secondly, the introduction of self-paced learning enhances SMJFM's capture of the unchanged region mapping relationship between heterogeneous images. Finally, the multi-scale change information fusion strategy enhances the robustness of the framework to outliers in the original data. [ABSTRACT FROM AUTHOR]

The necessity for precise and current data concerning the dynamics of land cover change in Indonesia is crucial for efforts to reduce natural vegetation cover due to agricultural expansion. The functionality of monitoring systems that incorporate Terra-MODIS is currently compromised by the limited availability of data for the immediate future. This study seeks to assess the potential of VIIRS satellite imagery in developing an early warning system for monitoring vegetation cover change in Indonesia. The normalized differential open-area index (NDOAI) computed from 8-day VIIRS data was employed to detect changes in vegetation cover based on pixel-by-pixel subtraction in the NDOAI data time series. Evaluating the pixel-level accuracy of change detection is complicated due to the fact that we evaluate a change map at a coarser resolution than the Landsat-based reference map. The results revealed that increasing the threshold percentage is associated with improved accuracy. In change detection, there is often a trade-off between accuracy and sensitivity. A threshold that is too low may result in false positives, while a threshold that is too high may lead to missed changes. This study demonstrates that when a threshold value of less than 20% is applied, Landsat can identify vegetation cover changes at an earlier stage. Conversely, when a threshold value greater than 20% is employed, the VIIRS will detect the change 4.5 days earlier than Landsat. Additionally, the VIIRS is capable of detecting changes 25.4 days and 54.8 days faster than Landsat, respectively, when using thresholds of 40% and 70%. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) change detection provides a powerful tool for continuous, reliable, and objective observation of the Earth, supporting a wide range of applications that require regular monitoring and assessment of changes in the natural and built environment. In this paper, we introduce a novel SAR image change detection method based on principal component analysis and two-level clustering. First, two difference images of the log-ratio and mean-ratio operators are computed, then the principal component analysis fusion model is used to fuse the two difference images, and a new difference image is generated. To incorporate contextual information during the feature extraction phase, Gabor wavelets are used to obtain the representation of the difference image across multiple scales and orientations. The maximum magnitude across all orientations at each scale is then concatenated to form the Gabor feature vector. Following this, a cascading clustering algorithm is developed within this discriminative feature space by merging the first-level fuzzy c-means clustering with the second-level neighbor rule. Ultimately, the two-level combination of the changed and unchanged results produces the final change map. Five SAR datasets are used for the experiment, and the results show that our algorithm has significant advantages in SAR change detection. [ABSTRACT FROM AUTHOR]

The challenge of detecting changes in high-resolution remote sensing imagery often stems from the difficulties in effectively extracting features and constructing appropriate change detection models considering the scale characteristics of ground objects. To solve these issues, we propose a novel UNet 3+ change detection method that considers the scale characteristics inherent in various land-cover change types. Our method includes three key steps: a multi-scale segmentation method, a class-specific UNet 3+ method, and an object-oriented change detection method based on UNet 3+. To verify the effectiveness of this method, we select two datasets for experiments and compare our proposed method with the UNet 3+ single-scale sampling method, the class-specific UNet 3+ single-scale sampling method, and the UNet 3+ multi-scale hierarchical sampling method. Our experimental results show that our proposed method has higher overall accuracy and F1, lower missed detection rate and false detection rate, and can detect more changes in ground features than other methods. To verify the scalability of this method, we compare this method with traditional change detection methods such as PCA-k-means, OCVA, a single-scale sampling method based on random forest, and a class-specific object-based method. Experimental results and accuracy indexes show that our proposed method better considers the scale characteristics of ground objects and achieves higher accuracy. Additionally, we compared our proposed method with other DLCD methods including LamboiseNet, BIT, CDNet, FCSiamConc, and FCSiamDiff. Our results show that our proposed method effectively considers edge information and has an acceptable time consumption. Our approach not only considers the full-scale characteristics of the feature extraction but also the scale characteristics of the change detection model. In addition, it considers a more practical feature extraction unit (object), making it more accurate. [ABSTRACT FROM AUTHOR]

Change detection is crucial for evaluating land use, land cover changes, and sustainable development, constituting a significant component of Earth observation tasks. The difficulty in extracting features from high-resolution images, coupled with the complexity of image content, poses challenges for traditional change detection algorithms in terms of accuracy and applicability. The recent emergence of deep learning methods has led to substantial progress in the field of change detection. However, existing frameworks often involve the simplistic integration of bi-temporal features in specific areas, lacking the fusion of temporal information and semantic details in the images. In this paper, we propose an attention-guided multi-scale fusion network (AMFNet), which effectively integrates bi-temporal image features and diverse semantics at both the encoding and decoding stages. AMFNet utilizes a unique attention-guided mechanism to dynamically adjust feature fusion, enhancing adaptability and accuracy in change detection tasks. Our method intelligently incorporates temporal information into the deep learning model, considering the temporal dependency inherent in these tasks. We decode based on an interactive feature map, which improves the model's understanding of evolving patterns over time. Additionally, we introduce multi-level supervised training to facilitate the learning of fused features across multiple scales. In comparison with different algorithms, our proposed method achieves F1 values of 0.9079, 0.8225, and 0.8809 in the LEVIR-CD, GZ-CD, and SYSU-CD datasets, respectively. Our model outperforms the SOTA model, SAGNet, by 0.69% in terms of F1 and 1.15% in terms of IoU on the LEVIR-CD dataset, by 2.8% in terms of F1 and 1.79% in terms of IoU on the GZ-CD dataset, and by 0.54% in terms of F1 and 0.38% in terms of IoU on the SYSU-CD dataset. The method proposed in this study can be applied to various complex scenarios, establishing a change detection method with strong model generalization capabilities. [ABSTRACT FROM AUTHOR]

Reliable and up-to-date training reference samples are imperative for land cover (LC) classification. However, such training datasets are not always available in practice. The sample migration method has shown remarkable success in addressing this challenge in recent years. This work investigated the application of Sentinel-1 (S1) and Sentinel-2 (S2) data in training sample migration. In addition, the impact of various spectral bands and polarizations on the accuracy of the migrated training samples was also assessed. Subsequently, combined S1 and S2 images were classified using the Support Vector Machines (SVM) and Random Forest (RF) classifiers to produce annual LC maps from 2017 to 2021. The results showed a higher accuracy (98.25%) in training sample migrations using both images in comparison to using S1 (87.68%) and S2 (96.82%) data independently. Among the LC classes, the highest accuracy in migrated training samples was found for water, built-up, bare land, grassland, cropland, and wetland. Inquiries on the efficiency of different spectral bands and polarization used in training sample migration showed that bands 4 and 8 and VV polarization in the water class were more important, while for the wetland class, bands 5, 6, 7, 8, and 8A together with VV polarization showed superior performance. The results showed that the RF classifier provided better performance than the SVM (higher overall, producer, and user accuracy). Overall, our findings suggested that shared use of S1 and S2 data can be used as a suitable means for producing up-to-date and high-quality training samples. [ABSTRACT FROM AUTHOR]

In the domains of geographic information systems and remote sensing image analysis, change detection is vital for examining surface variations in high-resolution remote sensing pictures. However, the intricate texture characteristics and rich details found in high-resolution remote sensing photos are difficult for conventional change detection systems to deal with. Target misdetection, missed detections, and edge blurring are further problems with current deep learning-based methods. This research proposes a high-resolution city change detection network based on difference and attention mechanisms under multi-scale feature fusion (MDANet) to address these issues and improve the accuracy of change detection. First, to extract features from dual-temporal remote sensing pictures, we use the Siamese architecture as the encoder network. The Difference Feature Module (DFM) is employed to learn the difference information between the dual-temporal remote sensing images. Second, the extracted difference features are optimized with the Attention Refinement Module (ARM). The Cross-Scale Fusion Module (CSFM) combines and enhances the optimized attention features, effectively capturing subtle differences in remote sensing images and learning the finer details of change targets. Finally, thorough tests on the BTCDD dataset, LEVIR-CD dataset, and CDD dataset show that the MDANet algorithm performs at a cutting-edge level. [ABSTRACT FROM AUTHOR]

Tracking long-term tidal flat dynamics is crucial for coastal restoration decision making. Accurately capturing the loss and gain of tidal flats due to human-induced disturbances is challenging in the micro-tidal areas. In this study, we developed an automated method for mapping the annual tidal flat changes in the micro-tidal areas under intense human activities, by integrating spectral harmonization, time series segmentation from dual spectral indices, and the tide-independent hierarchical classification strategy. Our method has two key novelties. First, we adopt flexible temporal segments for each pixel based on the dual full-time series spectral indices, instead of solely using a fixed period window, to help obtain more reliable inundation frequency features. Second, a tide-independent hierarchical classification strategy based on the inundation features and the Otsu algorithm capture the tidal flat changes well. Our method performed well in Guangdong, Hong Kong, and Macao (GHKM), a typical area with micro-tidal range and intense human activities, with overall accuracies of 89% and 92% for conversion types and turning years, respectively. The tidal flats in GHKM decreased by 24% from 1986 to 2021, resulting from the loss of 504.45 km2, partially offset by an accretion of 179.88 km2. Further, 70.9% of the total loss was in the Great Bay Area, concentrated in 1991–1998 and 2001–2016. The historical trajectories of tidal flat loss were driven by various policies implemented by the national, provincial, and local governments. Our method is promising for extension to other micro-tidal areas to provide more scientific support for coastal resource management and restoration. [ABSTRACT FROM AUTHOR]

Cultivated land plays a fundamental role in the sustainable development of the world. Monitoring the non-agricultural changes is important for the development of land-use policies. A bitemporal image transformer (BIT) can achieve high accuracy for change detection (CD) tasks and also become a key scientific tool to support decision-making. Because of the diversity of high-resolution RSIs in series, the complexity of agricultural types, and the irregularity of hierarchical semantics in different types of changes, the accuracy of non-agricultural CD is far below the need for the management of the land and for resource planning. In this paper, we proposed a novel non-agricultural CD method to improve the accuracy of machine processing. First, multi-resource surveying data are collected to produce a well-tagged dataset with cultivated land and non-agricultural changes. Secondly, a hierarchical semantic aggregation mechanism and attention module (HSAA) bitemporal image transformer method named HSAA-CD is performed for non-agricultural CD in cultivated land. The proposed HSAA-CD added a hierarchical semantic aggregation mechanism for clustering the input data for U-Net as the backbone network and an attention module to improve the feature edge. Experiments were performed on the open-source LEVIR-CD and WHU Building-CD datasets as well as on the self-built RSI dataset. The F1-score, intersection over union (IoU), and overall accuracy (OA) of these three datasets were 88.56%, 84.29%, and 68.50%; 79.84%, 73.41%, and 59.29%; and 98.83%, 98.39%, and 93.56%, respectively. The results indicated that the proposed HSAA-CD method outperformed the BIT and some other state-of-the-art methods and proved to be suitable accuracy for non-agricultural CD in cultivated land. [ABSTRACT FROM AUTHOR]

Deep models may have disappointing performance in real applications due to the domain shifts in data distributions between the source and target domain. Although a few unsupervised domain adaptation methods have been proposed to make the pre-train models effective on target domain datasets, constraints like data privacy, security, and transmission limits restrict access to VHR remote sensing images, making existing unsupervised domain adaptation methods almost ineffective in specific change detection areas. Therefore, we propose a source-free unsupervised domain adaptation change detection structure to complete specific change detection tasks, using only the pre-trained source model and unlabelled target data. The GAN-based source generation component is designed to generate synthetic source data, which, to some extent, reflects the distribution of the source domain. Moreover, these data can be utilised in model knowledge transfer. The model adaptation component facilitates knowledge transfer between models by minimising the differences between deep features, using AAM (Attention Adaptation Module) to extract the difference between high-level features, meanwhile we proposed ISM (Intra-domain Self-supervised Module) to train target model in a self-supervised strategy in order to improve the knowledge adaptation. Our SFDA-CD framework demonstrates superior accuracy over existing unsupervised domain adaptation change detection methods, which has 0.6% cIoU and 1.5% F1 score up in cross-regional tasks and 1.4% cIoU and 1.9% F1 score up in cross-scenario tasks, proving that it can effectively reduce the domain shift between the source and target domains even without access to source data. Additionally, it can facilitate knowledge transfer from the source model to the target model. [ABSTRACT FROM AUTHOR]

Change detection is widely used in the field of building monitoring. In recent years, the progress of remote sensing image technology has provided high-resolution data. However, unlike other tasks, change detection focuses on the difference between dual-input images, so the interaction between bi-temporal features is crucial. However, the existing methods have not fully tapped the potential of multi-scale bi-temporal features to interact layer by layer. Therefore, this paper proposes a multi-scale feature interaction network (MFINet). The network realizes the information interaction of multi-temporal images by inserting a bi-temporal feature interaction layer (BFIL) between backbone networks at the same level, guides the attention to focus on the difference region, and suppresses the interference. At the same time, a double temporal feature fusion layer (BFFL) is used at the end of the coding layer to extract subtle difference features. By introducing the transformer decoding layer and improving the recovery effect of the feature size, the ability of the network to accurately capture the details and contour information of the building is further improved. The F1 of our model on the public dataset LEVIR-CD reaches 90.12%, which shows better accuracy and generalization performance than many state-of-the-art change detection models. [ABSTRACT FROM AUTHOR]

Natural hazards are considered to have a strong link with climate change and human activities. With the rapid advancements in remote sensing technology, real-time monitoring and high-resolution remote-sensing images have become increasingly available, which provide precise details about the Earth's surface and enable prompt updates to support risk identification and management. This paper proposes a new network framework with Transformer architecture and a Residual network for detecting the changes in high-resolution remote-sensing images. The proposed model is trained using remote-sensing images from Shandong and Anhui Provinces of China in 2021 and 2022 while one district in 2023 is used to test the prediction accuracy. The performance of the proposed model is evaluated by using five matrices and further compared to both convention-based and attention-based models. The results demonstrated that the proposed structure integrates the great capability of conventional neural networks for image feature extraction with the ability to obtain global context from the attention mechanism, resulting in significant improvements in balancing positive sample identification while avoiding false positives in complex image change detection. Additionally, a toolkit supporting image preprocessing is developed for practical applications. [ABSTRACT FROM AUTHOR]

This paper introduces an AI-based approach to detect human-made objects and changes in these on land parcels. To this end, we used binary image classification performed by a convolutional neural network. Binary classification requires the selection of a decision boundary, and we provided a deterministic method for this selection. Furthermore, we varied different parameters to improve the performance of our approach, leading to a true positive rate of 91.3% and a true negative rate of 63.0%. A specific application of our work supports the administration of agricultural land parcels eligible for subsidiaries. As a result of our findings, authorities could reduce the effort involved in the detection of human made changes by approximately 50%. [ABSTRACT FROM AUTHOR]

Change detection in remote sensing imagery is vital for Earth monitoring but faces challenges such as background complexity and pseudo-changes. Effective interaction between bitemporal images is crucial for accurate change information extraction. This paper presents a multistage interaction network designed for effective change detection, incorporating interaction at the image, feature, and decision levels. At the image level, change information is directly extracted from intensity changes, mitigating potential change information loss during feature extraction. Instead of separately extracting features from bitemporal images, the feature-level interaction jointly extracts features from bitemporal images. By enhancing relevance to spatial variant information and shared semantic channels, the network excels in overcoming background complexity and pseudo-changes. The decision-level interaction combines image-level and feature-level interactions, producing multiscale feature differences for precise change prediction. Extensive experiments demonstrate the superior performance of our method compared to existing approaches, establishing it as a robust solution for remote sensing image change detection. [ABSTRACT FROM AUTHOR]

Our study addresses the need for universal monitoring solutions given the diverse environmental impacts of surface mining operations. We present a solution combining remote sensing and machine learning techniques, utilizing a dataset of over 2000 satellite images annotated with ten distinct labels indicating mining area components. We tested various approaches to develop comprehensive yet universal machine learning models for mining area segmentation. This involved considering different types of mines, raw materials, and geographical locations. We evaluated multiple satellite data set combinations to determine optimal outcomes. The results suggest that radar and multispectral data fusion did not significantly improve the models' performance, and the addition of further channels led to the degradation of the metrics. Despite variations in mine type or extracted material, the models' effectiveness remained within an Intersection over Union value range of 0.65–0.75. Further, in this research, we conducted a detailed visual analysis of the models' outcomes to identify areas requiring additional attention, contributing to the discourse on effective mining area monitoring and management methodologies. The visual examination of models' outputs provides insights for future model enhancement and highlights unique segmentation challenges within mining areas. [ABSTRACT FROM AUTHOR]

Deep learning has dramatically enhanced remote sensing change detection. However, existing neural network models often face challenges like false positives and missed detections due to factors like lighting changes, scale differences, and noise interruptions. Additionally, change detection results often fail to capture target contours accurately. To address these issues, we propose a novel transformer-based hybrid network. In this study, we analyze the structural relationship in bi-temporal images and introduce a cross-attention-based transformer to model this relationship. First, we use a tokenizer to express the high-level features of the bi-temporal image into several semantic tokens. Then, we use a dual temporal transformer (DTT) encoder to capture dense spatiotemporal contextual relationships among the tokens. The features extracted at the coarse scale are refined into finer details through the DTT decoder. Concurrently, we input the backbone's low-level features into a contour-guided graph interaction module (CGIM) that utilizes joint attention to capture semantic relationships between object regions and the contour. Then, we use the feature pyramid decoder to integrate the multi-scale outputs of the CGIM. The convolutional block attention modules (CBAMs) employ channel and spatial attention to reweight feature maps. Finally, the classifier discriminates change pixels and generates the final change map of the difference feature map. Several experiments have demonstrated that our model shows significant advantages over other methods in terms of efficiency, accuracy, and visual effects. [ABSTRACT FROM AUTHOR]

Human activities and natural phenomena continually transform the Earth's surface, presenting ongoing challenges to the environment. Therefore, the accurate and timely monitoring and prediction of these alterations are essential for devising effective solutions and mitigating environmental impacts in advance. This study introduces a novel framework, called HCD-Net, for detecting changes using bi-temporal hyperspectral images. HCD-Net is built upon a dual-stream deep feature extraction process, complemented by an attention mechanism. The first stream employs 3D convolution layers and 3D Squeeze-and-Excitation (SE) blocks to extract deep features, while the second stream utilizes 2D convolution and 2D SE blocks for the same purpose. The deep features from both streams are then concatenated and processed through dense layers for decision-making. The performance of HCD-Net is evaluated against existing state-of-the-art change detection methods. For this purpose, the bi-temporal Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) hyperspectral dataset was utilized to assess the change detection performance. The findings indicate that HCD-Net achieves superior accuracy and the lowest false alarm rate among the compared methods, with an overall classification accuracy exceeding 96%, and a kappa coefficient greater than 0.9. [ABSTRACT FROM AUTHOR]

Change detection (CD) in remote sensing (RS) imagery is a pivotal method for detecting changes in the Earth's surface, finding wide applications in urban planning, disaster management, and national security. Recently, deep learning (DL) has experienced explosive growth and, with its superior capabilities in feature learning and pattern recognition, it has introduced innovative approaches to CD. This review explores the latest techniques, applications, and challenges in DL-based CD, examining them through the lens of various learning paradigms, including fully supervised, semi-supervised, weakly supervised, and unsupervised. Initially, the review introduces the basic network architectures for CD methods using DL. Then, it provides a comprehensive analysis of CD methods under different learning paradigms, summarizing commonly used frameworks. Additionally, an overview of publicly available datasets for CD is offered. Finally, the review addresses the opportunities and challenges in the field, including: (a) incomplete supervised CD, encompassing semi-supervised and weakly supervised methods, which is still in its infancy and requires further in-depth investigation; (b) the potential of self-supervised learning, offering significant opportunities for Few-shot and One-shot Learning of CD; (c) the development of Foundation Models, with their multi-task adaptability, providing new perspectives and tools for CD; and (d) the expansion of data sources, presenting both opportunities and challenges for multimodal CD. These areas suggest promising directions for future research in CD. In conclusion, this review aims to assist researchers in gaining a comprehensive understanding of the CD field. [ABSTRACT FROM AUTHOR]

In the change detection (CD) task, the substantial variation in feature distributions across different CD datasets significantly limits the reusability of supervised CD models. To alleviate this problem, we propose an illumination–reflection decoupled change detection multi-scale unsupervised domain adaptation model, referred to as IRD-CD-UDA. IRD-CD-UDA maintains its performance on the original dataset (source domain) and improves its performance on unlabeled datasets (target domain) through a novel CD-UDA structure and methodology. IRD-CD-UDA synergizes mid-level global feature marginal distribution domain alignment, classifier layer feature conditional distribution domain alignment, and an easy-to-hard sample selection strategy to increase the generalization performance of CD models on cross-domain datasets. Extensive experiments conducted on the LEVIR, SYSU, and GZ optical remote sensing image datasets demonstrate that the IRD-CD-UDA model effectively mitigates feature distribution discrepancies between source and target CD data, thereby achieving optimal recognition performance on unlabeled target domain datasets. [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.

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.

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.

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.

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.

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.

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.

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.

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.