Search

The detection and monitoring of burned areas is crucial for vegetation recovery, loss assessment, and anomaly analysis. Although vegetation indices (VIs) have been widely used, accurate vegetation detection is challenging due to potential confusion in the spectra of different types of land cover and the interference of shadow effects caused by terrain. In this work, a novel Vegetation Anomaly Spectral Texture Index (VASTI) is proposed, which leverages the merits of both spectral and spatial texture features to identify abnormal pixels for extracting burned vegetation areas. The performance of the VASTI and its components, the Global Environmental Monitoring Index (GEMI), the Enhanced Vegetation Index (EVI), and the texture feature Autocorrelation (AC) were assessed based on a global dataset previously established, which contains 1774 pairs of samples from 10 different sites. The results illustrated that, compared with the GEMI and EVI, the VASTI improved the user’s accuracy (UA), producer’s accuracy (PA), and kappa coefficient across the ten study areas by approximately 5% to 10%. Compared to AC, the VASTI improved the accuracy of abnormal vegetation detection by 13% to 25%. The improvements were mainly caused by the fact that the incorporation of texture features can reduce spectral confusion between pixels. The innovation of the VASTI is that it considers the relationship between anomalous pixels and surrounding pixels by explicitly integrating spatial texture features with traditional spectral features.

Accurate and reliable mapping of fire extent and severity is critical for assessing the impact of fire on vegetation and informing post-fire recovery trajectories. Classification approaches that combine pixel-wise and neighbourhood statistics including image texture derived from high-resolution satellite data may improve on current methods of fire severity mapping. Texture is an innate property of all land cover surfaces that is known to vary between fire severity classes, becoming increasingly more homogenous as fire severity increases. In this study, we compared candidate backscatter and reflectance indices derived from Sentinel 1 and Sentinel 2, respectively, together with grey-level-co-occurrence-matrix (GLCM)-derived texture indices using a random forest supervised classification framework. Cross-validation (for which the target fire was excluded in training) and target-trained (for which the target fire was included in training) models were compared to evaluate performance between the models with and without texture indices. The results indicated that the addition of texture indices increased the classification accuracies of severity for both sensor types, with the greatest improvements in the high severity class (23.3%) for the Sentinel 1 and the moderate severity class (17.4%) for the Sentinel 2 target-trained models. The target-trained models consistently outperformed the cross-validation models, especially with regard to Sentinel 1, emphasising the importance of local training data in capturing post-fire variation in different forest types and severity classes. The Sentinel 2 models more accurately estimated fire extent and were improved with the addition of texture indices (3.2%). Optical sensor data yielded better results than C-band synthetic aperture radar (SAR) data with respect to distinguishing fire severity and extent. Successful detection using C-band data was linked to significant structural change in the canopy (i.e., partial-complete canopy consumption) and is more successful over sparse, low-biomass forest. Future research will investigate the sensitivity of longer-wavelength (L-band) SAR regarding fire severity estimation and the potential for an integrated fire-mapping system that incorporates both active and passive remote sensing to detect and monitor changes in vegetation cover and structure.

The generation of Digital Elevation Models (DEMs) through stereogrammetry of optical satellite images has gained great popularity across various disciplines. For the analysis of these DEMs, it is important to understand the influence of the input data and different processing steps and parameters employed during stereo correlation. Here, we explore the effects that image texture, as well as the use of different matching algorithms (Block Matching (BM) and More Global Matching (MGM)), can have on optical DEMs derived from the flexible, open-source Ames Stereo Pipeline. Our analysis relies on a ∼2700 km2 clip of a SPOT6 tristereo scene covering the hyperarid, vegetation-free Pocitos Basin and adjacent mountain ranges in the northwestern Argentine Andes. A large, perfectly flat salt pan (paleolake bed) that covers the center of this basin is characterized by strong contrasts in image texture, providing a unique opportunity to quantitatively study the relationship between image texture and DEM quality unaffected by topography. Our findings suggest that higher image texture, measured by panchromatic variance, leads to lower DEM uncertainty. This improvement continues up to ∼103 panchromatic variance, above which further improvements in DEM quality are independent of local image texture but instead may have sensor or geometric origins. Based on this behavior, we propose that image texture may serve as an important proxy of DEM quality prior to stereo correlation and can help to set adequate processing parameters. With respect to matching algorithms, we observe that MGM improves matching in low-texture areas and overall generates a smoother surface that still preserves complex, narrow (i.e., ridge and valley) features. Based on this sharper representation of the landscape, we conclude that MGM should be preferred for geomorphic applications relying on stereo-derived DEMs. However, we note that the correlation kernel selected for stereo-matching must be carefully chosen depending on local image texture, whereby larger kernels generate more accurate matches (less artifacts) at the cost of smoothing results. Overall, our analysis suggests a path forward for the processing and fusion of overlapping satellite images with suitable view-angle differences to improve final DEMs.

Accurate and reliable mapping of fire extent and severity is critical for assessing the impact of fire on vegetation and informing post-fire recovery trajectories. Classification approaches that combine pixel-wise and neighbourhood statistics including image texture derived from high-resolution satellite data may improve on current methods of fire severity mapping. Texture is an innate property of all land cover surfaces that is known to vary between fire severity classes, becoming increasingly more homogenous as fire severity increases. In this study, we compared candidate backscatter and reflectance indices derived from Sentinel 1 and Sentinel 2, respectively, together with grey-level-co-occurrence-matrix (GLCM)-derived texture indices using a random forest supervised classification framework. Cross-validation (for which the target fire was excluded in training) and target-trained (for which the target fire was included in training) models were compared to evaluate performance between the models with and without texture indices. The results indicated that the addition of texture indices increased the classification accuracies of severity for both sensor types, with the greatest improvements in the high severity class (23.3%) for the Sentinel 1 and the moderate severity class (17.4%) for the Sentinel 2 target-trained models. The target-trained models consistently outperformed the cross-validation models, especially with regard to Sentinel 1, emphasising the importance of local training data in capturing post-fire variation in different forest types and severity classes. The Sentinel 2 models more accurately estimated fire extent and were improved with the addition of texture indices (3.2%). Optical sensor data yielded better results than C-band synthetic aperture radar (SAR) data with respect to distinguishing fire severity and extent. Successful detection using C-band data was linked to significant structural change in the canopy (i.e., partial-complete canopy consumption) and is more successful over sparse, low-biomass forest. Future research will investigate the sensitivity of longer-wavelength (L-band) SAR regarding fire severity estimation and the potential for an integrated fire-mapping system that incorporates both active and passive remote sensing to detect and monitor changes in vegetation cover and structure. [ABSTRACT FROM AUTHOR]

The generation of Digital Elevation Models (DEMs) through stereogrammetry of optical satellite images has gained great popularity across various disciplines. For the analysis of these DEMs, it is important to understand the influence of the input data and different processing steps and parameters employed during stereo correlation. Here, we explore the effects that image texture, as well as the use of different matching algorithms (Block Matching (BM) and More Global Matching (MGM)), can have on optical DEMs derived from the flexible, open-source Ames Stereo Pipeline. Our analysis relies on a ∼2700 km 2 clip of a SPOT6 tristereo scene covering the hyperarid, vegetation-free Pocitos Basin and adjacent mountain ranges in the northwestern Argentine Andes. A large, perfectly flat salt pan (paleolake bed) that covers the center of this basin is characterized by strong contrasts in image texture, providing a unique opportunity to quantitatively study the relationship between image texture and DEM quality unaffected by topography. Our findings suggest that higher image texture, measured by panchromatic variance, leads to lower DEM uncertainty. This improvement continues up to ∼10 3 panchromatic variance, above which further improvements in DEM quality are independent of local image texture but instead may have sensor or geometric origins. Based on this behavior, we propose that image texture may serve as an important proxy of DEM quality prior to stereo correlation and can help to set adequate processing parameters. With respect to matching algorithms, we observe that MGM improves matching in low-texture areas and overall generates a smoother surface that still preserves complex, narrow (i.e., ridge and valley) features. Based on this sharper representation of the landscape, we conclude that MGM should be preferred for geomorphic applications relying on stereo-derived DEMs. However, we note that the correlation kernel selected for stereo-matching must be carefully chosen depending on local image texture, whereby larger kernels generate more accurate matches (less artifacts) at the cost of smoothing results. Overall, our analysis suggests a path forward for the processing and fusion of overlapping satellite images with suitable view-angle differences to improve final DEMs. [ABSTRACT FROM AUTHOR]

In the present paper, a methodological scheme, bringing together common Acoustic Seabed Classification (ASC) systems and a powerful data decomposition approach, called Independent Component Analysis (ICA), is demonstrated regarding its suitability for detecting small targets in Side Scan Sonar imagery. Traditional ASC systems extract numerous texture descriptors, leading to a large feature vector, the dimensionality of which is reduced by means of data decomposition techniques, usually Principal Component Analysis (PCA), prior to classification. However, in the target detection issue, data decomposition should point towards finding components that represent sub-ordinary image information (i.e., small targets) rather than a dominant one. ICA has long been proved to be suitable for separating targets from a background, and this study represents a novel exhibition of its applicability to Side Scan Sonar (SSS) images. The present study attempts to build a fully automated target detection approach that combines image based feature extraction, ICA, and unsupervised classification. The suitability of the proposed approach has been demonstrated using an SSS data-set containing more than 70 manmade targets, most of them metallic, validated through a marine magnetic survey or ground truthing inspection. The method exhibited very good performance as it was able to detect more than 77% of the targets and it produced less than seven false alarms per km2. Moreover, it was compared to cases where, in the exact same methodological scheme, no decomposition technique is used, or PCA is employed instead of ICA, achieving the highest detection rate, but, more importantly, producing more than six times less false alarms, thus proving that ICA successfully manages to maximize target to background separation.

Compared to multispectral or panchromatic bands, fusion imagery contains both the spectral content of the former and the spatial resolution of the latter. Even though the Estimation of Scale Parameter (ESP), the ESP 2 tool, and some segmentation evaluation methods have been introduced to simplify the choice of scale parameter (SP), shape, and compactness, many challenges remain, including obtaining the natural border of plastic greenhouses (PGs) from a GaoFen-2 (GF-2) fusion imagery, accelerating the progress of follow-up texture analysis, and accurately evaluating over-segmentation and under-segmentation of PG segments in geographic object-based image analysis. Considering the features of high-resolution images, the heterogeneity of fusion imagery was compressed using texture analysis before calculating the optimal scale parameter in ESP 2 in this study. As a result, we quantified the effects of image texture analysis, including increasing averaging operator size (AOS) and decreasing greyscale quantization level (GQL) on PG segments via recognition of a proposed Over-Segmentation Index (OSI)-Under-Segmentation Index (USI)-Error Index of Total Area (ETA)-Composite Error Index (CEI) pattern. The proposed pattern can be used to reasonably evaluate the quality of PG segments obtained from GF-2 fusion imagery and its derivative images, showing that appropriate texture analysis can effectively change the heterogeneity of a fusion image for better segmentation. The optimum setup of GQL and AOS are determined by comparing CEI and visual analysis.

Plant diseases are one of the main reasons behind major economic and production losses in the agricultural field. Current research activities enable large fields monitoring and plant disease detection using innovative and robust technologies. French grapevines have a reputation for producing premium quality wines, however, these major fruit crops are susceptible to many diseases, including Esca, Downy mildew, Powdery mildew, Yellowing, and many others. In this study, we focused on two main infections (Esca and Yellowing), and data were gathered from fields that were located in Aquitaine and Burgundy regions, France. Since plant diseases can be diagnosed from the properties of the leaf, we acquired both Red-Green-Blue (RGB) digital image and hyperspectral reflectance data from infected and healthy leaves. Biophysical parameters that were produced by the PROSPECT model inversion together with texture parameters compiled from the literature were deduced. Then we investigated their relationship to damage caused by Yellowing and Esca. This study examined whether spectral and textural data can identify the two diseases through the use of Neural Networks. We obtained an overall accuracy of 99% for both of the diseases when textural and spectral data are combined. These results suggest that, first, biophysical parameters present a valid dimension reduction tool that could replace the use of complete hyperspectral data. Second, remote sensing using spectral reflectance and digital images can make an overall nondestructive, rapid, cost-effective, and reproducible technique to determine diseases in grapevines with a good level of accuracy.

Leaf chlorophyll content (LCC) is an important indicator of plant nutritional status and can be a guide for plant disease diagnosis. In this study, we took apple leaves infected with mosaic disease as a research object and extracted two types of information on spectral and textural features from hyperspectral images, with a view to realizing non-destructive detection of LCC. First, the collected hyperspectral images were preprocessed and spectral reflectance was extracted in the region of interest. Subsequently, we used the successive projections algorithm (SPA) to select the optimal wavelengths (OWs) and extracted eight basic textural features using the gray-level co-occurrence matrix (GLCM). In addition, composite spectral and textural metrics, including vegetation indices (VIs), normalized difference texture indices (NDTIs), difference texture indices (DTIs), and ratio texture indices (RTIs) were calculated. Third, we applied the maximal information coefficient (MIC) algorithm to select significant VIs and basic textures, as well as the tandem method was used to fuse the spectral and textural features. Finally, we employ support vector regression (SVR), backpropagation neural network (BPNN), and K-nearest neighbors regression (KNNR) methods to explore the efficacy of single and combined feature models for estimating LCC. The results showed that the VIs model (R2 = 0.8532, RMSE = 2.1444, RPD = 2.6179) and the NDTIs model (R2 = 0.7927, RMSE = 2.7453, RPD = 2.2032) achieved the best results among the single feature models for spectra and texture, respectively. However, textural features generally exhibit inferior regression performance compared to spectral features and are unsuitable for standalone applications. Combining textural and spectral information can potentially improve the single feature models. Specifically, when combining NDTIs with VIs as input parameters, three machine learning models outperform the best single feature model. Ultimately, SVR achieves the highest performance among the LCC regression models (R2 = 0.8665, RMSE = 1.8871, RPD = 2.7454). This study reveals that combining textural and spectral information improves the quantitative detection of LCC in apple leaves infected with mosaic disease, leading to higher estimation accuracy.

In the present paper, a methodological scheme, bringing together common Acoustic Seabed Classification (ASC) systems and a powerful data decomposition approach, called Independent Component Analysis (ICA), is demonstrated regarding its suitability for detecting small targets in Side Scan Sonar imagery. Traditional ASC systems extract numerous texture descriptors, leading to a large feature vector, the dimensionality of which is reduced by means of data decomposition techniques, usually Principal Component Analysis (PCA), prior to classification. However, in the target detection issue, data decomposition should point towards finding components that represent sub-ordinary image information (i.e., small targets) rather than a dominant one. ICA has long been proved to be suitable for separating targets from a background, and this study represents a novel exhibition of its applicability to Side Scan Sonar (SSS) images. The present study attempts to build a fully automated target detection approach that combines image based feature extraction, ICA, and unsupervised classification. The suitability of the proposed approach has been demonstrated using an SSS data-set containing more than 70 manmade targets, most of them metallic, validated through a marine magnetic survey or ground truthing inspection. The method exhibited very good performance as it was able to detect more than 77% of the targets and it produced less than seven false alarms per km². Moreover, it was compared to cases where, in the exact same methodological scheme, no decomposition technique is used, or PCA is employed instead of ICA, achieving the highest detection rate, but, more importantly, producing more than six times less false alarms, thus proving that ICA successfully manages to maximize target to background separation. [ABSTRACT FROM AUTHOR]

Although remote sensing technology has long been used in wetland inventory and monitoring, the accuracy and detail level of wetland maps derived with moderate resolution imagery and traditional techniques have been limited and often unsatisfactory. We explored and evaluated the utility of a newly launched high-resolution, eight-band satellite system (Worldview-2; WV2) for identifying and classifying freshwater deltaic wetland vegetation and aquatic habitats in the Selenga River Delta of Lake Baikal, Russia, using a hybrid approach and a novel application of Indicator Species Analysis (ISA). We achieved an overall classification accuracy of 86.5% (Kappa coefficient: 0.85) for 22 classes of aquatic and wetland habitats and found that additional metrics, such as the Normalized Difference Vegetation Index and image texture, were valuable for improving the overall classification accuracy and particularly for discriminating among certain habitat classes. Our analysis demonstrated that including WV2’s four spectral bands from parts of the spectrum less commonly used in remote sensing analyses, along with the more traditional bandwidths, contributed to the increase in the overall classification accuracy by ~4% overall, but with considerable increases in our ability to discriminate certain communities. The coastal band improved differentiating open water and aquatic (i.e., vegetated) habitats, and the yellow, red-edge, and near-infrared 2 bands improved discrimination among different vegetated aquatic and terrestrial habitats. The use of ISA provided statistical rigor in developing associations between spectral classes and field-based data. Our analyses demonstrated the utility of a hybrid approach and the benefit of additional bands and metrics in providing the first spatially explicit mapping of a large and heterogeneous wetland system.

Urban sprawl related increase of built-in areas requires reliable monitoring methods and remote sensing can be an efficient technique. Aerial surveys, with high spatial resolution, provide detailed data for building monitoring, but archive images usually have only visible bands. We aimed to reveal the efficiency of visible orthophotographs and photogrammetric dense point clouds in building detection with segmentation-based machine learning (with five algorithms) using visible bands, texture information, and spectral and morphometric indices in different variable sets. Usually random forest (RF) had the best (99.8%) and partial least squares the worst overall accuracy (~60%). We found that >95% accuracy can be gained even in class level. Recursive feature elimination (RFE) was an efficient variable selection tool, its result with six variables was like when we applied all the available 31 variables. Morphometric indices had 82% producer’s and 85% user’s Accuracy (PA and UA, respectively) and combining them with spectral and texture indices, it had the largest contribution in the improvement. However, morphometric indices are not always available but by adding texture and spectral indices to red-green-blue (RGB) bands the PA improved with 12% and the UA with 6%. Building extraction from visual aerial surveys can be accurate, and archive images can be involved in the time series of a monitoring.

Effective forest management necessitates spatially explicit information about tree species composition. This information supports the safeguarding of native species, sustainable timber harvesting practices, precise mapping of wildlife habitats, and identification of invasive species. Tree species identification and geo-location by machine learning classification of UAV aerial imagery offer an alternative to tedious ground surveys. However, the timing (season) of the aerial surveys, input variables considered for classification, and the model type affect the classification accuracy. This work evaluates how the seasons and input variables considered in the species classification model affect the accuracy of species classification in a temperate broadleaf and mixed forest. Among the considered models, a Random Forest (RF) classifier demonstrated the highest performance, attaining an overall accuracy of 83.98% and a kappa coefficient of 0.80. Simultaneously using input data from summer, winter, autumn, and spring seasons improved tree species classification accuracy by 14–18% from classifications made using only single-season input data. Models that included vegetation indices, image texture, and elevation data obtained the highest accuracy. These results strengthen the case for using multi-seasonal data for species classification in temperate broadleaf and mixed forests since seasonal differences in the characteristics of species (e.g., leaf color, canopy structure) improve the ability to discern species. [ABSTRACT FROM AUTHOR]

Image super-resolution (SR) algorithms based on deep learning yield good visual performances on visible images. Due to the blurred edges and low contrast of infrared (IR) images, methods transferred directly from visible images to IR images have a poor performance and ignore the demands of downstream detection tasks. Therefore, an Inception Dilated Super-Resolution (IDSR) network with multiple branches is proposed. A dilated convolutional branch captures high-frequency information to reconstruct edge details, while a non-local operation branch captures long-range dependencies between any two positions to maintain the global structure. Furthermore, deformable convolution is utilized to fuse features extracted from different branches, enabling adaptation to targets of various shapes. To enhance the detection performance of low-resolution (LR) images, we crop the images into patches based on target labels before feeding them to the network. This allows the network to focus on learning the reconstruction of the target areas only, reducing the interference of background areas in the target areas' reconstruction. Additionally, a feature-driven module is cascaded at the end of the IDSR network to guide the high-resolution (HR) image reconstruction with feature prior information from a detection backbone. This method has been tested on the FLIR Thermal Dataset and the M3FD Dataset and compared with five mainstream SR algorithms. The final results demonstrate that our method effectively maintains image texture details. More importantly, our method achieves 80.55% mAP, outperforming other methods on FLIR Dataset detection accuracy, and with 74.7% mAP outperforms other methods on M3FD Dataset detection accuracy. [ABSTRACT FROM AUTHOR]

Optical remote sensing images are of considerable significance in a plethora of applications, including feature recognition and scene semantic segmentation. However, the quality of remote sensing images is compromised by the influence of various types of noise, which has a detrimental impact on their practical applications in the aforementioned fields. Furthermore, the intricate texture characteristics inherent to remote sensing images present a significant hurdle in the removal of noise and the restoration of image texture details. In order to address these challenges, we propose a feature interaction complementary learning (FICL) strategy for remote sensing image denoising. In practical terms, the network is comprised of four main components: noise predictor (NP), reconstructed image predictor (RIP), feature interaction module (FIM), and fusion module. The combination of these modules serves to not only complete the fusion of the prediction results of NP and RIP, but also to achieve a deep coupling of the characteristics of the two predictors. Consequently, the advantages of noise prediction and reconstructed image prediction can be combined, thereby enhancing the denoising capability of the model. Furthermore, comprehensive experimentation on both synthetic Gaussian noise datasets and real-world denoising datasets has demonstrated that FICL has achieved favorable outcomes, emphasizing the efficacy and robustness of the proposed framework. [ABSTRACT FROM AUTHOR]

Thermal infrared cameras can image stably in complex scenes such as night, rain, snow, and dense fog. Still, humans are more sensitive to visual colors, so there is an urgent need to convert infrared images into color images in areas such as assisted driving. This paper studies a colorization method for infrared images based on a generative adversarial model. The proposed dual-branch feature extraction network ensures the stability of the content and structure of the generated visible light image; the proposed discrimination strategy combining spatial and frequency domain hybrid constraints effectively improves the problem of undersaturated coloring and the loss of texture details in the edge area of the generated visible light image. The comparative experiment of the public infrared visible light paired data set shows that the algorithm proposed in this paper has achieved the best performance in maintaining the consistency of the content structure of the generated image, restoring the image color distribution, and restoring the image texture details. [ABSTRACT FROM AUTHOR]

The differences in sensor imaging mechanisms, observation angles, and scattering characteristics of terrestrial objects significantly limit the registration performance of synthetic aperture radar (SAR) and optical heterologous images. Traditional methods particularly struggle in weak feature regions, such as harbors and islands with substantial water coverage, as well as in desolate areas like deserts. This paper introduces a robust heterologous image registration technique based on region-adaptive keypoint selection that integrates image texture features, targeting two pivotal aspects: feature point extraction and matching point screening. Initially, a dual threshold criterion based on block region information entropy and variance products effectively identifies weak feature regions. Subsequently, it constructs feature descriptors to generate similarity maps, combining histogram parameter skewness with non-maximum suppression (NMS) to enhance matching point accuracy. Extensive experiments have been conducted on conventional SAR-optical datasets and typical SAR-optical images with different weak feature regions to assess the method's performance. The findings indicate that this method successfully removes outliers in weak feature regions and completes the registration task of SAR and optical images with weak feature regions. [ABSTRACT FROM AUTHOR]

Survey data describing land cover information such as type and diversity over several decades are scarce. Therefore, our capacity to reconstruct historical land cover using field data and archived remotely sensed data over large areas and long periods of time is somewhat limited. This study explores the relationship between CORONA texture—a surrogate for actual land cover type and complexity—with spectral vegetation indices and texture variables derived from Landsat MSS under the Spectral Variation Hypothesis (SVH) such as to reconstruct historical continuous land cover type and complexity. Image texture of CORONA was calculated using a mean occurrence measure while image textures of Landsat MSS were calculated by occurrence and co-occurrence measures. The relationship between these variables was evaluated using correlation and regression techniques. The reconstruction procedure was undertaken through regression kriging. The results showed that, as expected, texture based on the visible bands and corresponding indices indicated larger correlation with CORONA texture, a surrogate of land cover (correlation >0.65). In terms of prediction, the combination of the first-order mean of band green, second-order measure of tasseled cap brightness, second-order mean of Normalized Visible Index (NVI) and second-order entropy of NIR yielded the best model with respect to Akaike’s Information Criterion (AIC), r-square, and variance inflation factors (VIF). The regression model was then used in regression kriging to map historical continuous land cover. The resultant maps indicated the type and degree of complexity in land cover. Moreover, the proposed methodology minimized the impacts of topographic shadow in the region. The performance of this approach was compared with two conventional classification methods: hard classifiers and continuous classifiers. In contrast to conventional techniques, the technique could clearly quantify land cover complexity and type. Future applications of CORONA datasets such as this one could include: improved quality of CORONA imagery, studies of the CORONA texture measures for extracting ecological parameters (e.g., species distributions), change detection and super resolution mapping using CORONA and Landsat MSS.

The loop closure detection (LCD) methods in Unmanned Aerial Vehicle (UAV) Visual Inertial Navigation System (VINS) are often affected by issues such as insufficient image texture information and limited observational perspectives, resulting in constrained UAV positioning accuracy and reduced capability to perform complex tasks. This study proposes a Bag-of-Words (BoW) LCD method based on Neural Radiance Field (NeRF), which estimates camera poses from existing images and achieves rapid scene reconstruction through NeRF. A method is designed to select virtual viewpoints and render images along the flight trajectory using a specific sampling approach to expand the limited observational angles, mitigating the impact of image blur and insufficient texture information at specific viewpoints while enlarging the loop closure candidate frames to improve the accuracy and success rate of LCD. Additionally, a BoW vector construction method that incorporates the importance of similar visual words and an adapted virtual image filtering and comprehensive scoring calculation method are designed to determine loop closures. Applied to VINS-Mono and ORB-SLAM3, and compared with the advanced BoW model LCDs of the two systems, results indicate that the NeRF-based BoW LCD method can detect more than 48% additional accurate loop closures, while the system's navigation positioning error mean is reduced by over 46%, validating the effectiveness and superiority of the proposed method and demonstrating its significant importance for improving the navigation accuracy of VINS. [ABSTRACT FROM AUTHOR]

Since Neural Radiation Field (NeRF) was first proposed, a large number of studies dedicated to them have emerged. These fields achieved very good results in their respective contexts, but they are not sufficiently practical for our project. If we want to obtain novel images of satellites photographed in space by another satellite, we must face problems like inaccurate camera focal lengths and poor image texture. There are also some small structures on satellites that NeRF-like algorithms cannot render well. In these cases, the NeRF's performance cannot sufficiently meet the project's needs. In fact, the images rendered by the NeRF will have many incomplete structures, while the MipNeRF will blur the edges of the structures on the satellite and obtain unrealistic colors. In response to these problems, we proposed STs-NeRF, which improves the quality of the new perspective images through an encoding module and a new network structure. We found a method for calculating poses that are suitable for our dataset and that enhance the network's input learning effect by recoding the sampling points and viewing directions through a dynamic encoding (DE) module. Then, we input them into our layer-by-layer normalized multi-layer perceptron (LLNMLP). By simultaneously inputting points and directions into the network, we avoid the mutual influence between light rays, and through layer-by-layer normalization, we ease the model's overfitting from a training perspective. Since real images should not be made public, we created a synthetic dataset and conducted a series of experiments. The experiments showed that our method achieves the best results in reconstructing captured satellite images, compared with the NeRF, the MipNeRF, the NeuS and the NeRF2Mesh, and improves the Peak Signal-to-Noise Ratio (PSNR) by 19%. We have also tested on public datasets, and our NeRF can still render acceptable images on datasets with better textures. [ABSTRACT FROM AUTHOR]

Pasture degradation poses significant economic, social, and environmental impacts in the Brazilian savanna ecosystem. Despite these impacts, effectively detecting varying intensities of agronomic and biological degradation through remote sensing remains challenging. This study explores the potential of the eight-band PlanetScope SuperDove satellite constellation to discriminate between five classes of pasture degradation: non-degraded pasture (NDP); pastures with low- (LID) and moderate-intensity degradation (MID); severe agronomic degradation (SAD); and severe biological degradation (SBD). Using a set of 259 cloud-free images acquired in 2022 across five sites located in central Brazil, the study aims to: (i) identify the most suitable period for discriminating between various degradation classes; (ii) evaluate the Random Forest (RF) classification performance of different SuperDove attributes; and (iii) compare metrics of accuracy derived from two predicted scenarios of pasture degradation: a more challenging one involving five classes (NDP, LID, MID, SAD, and SBD), and another considering only non-degraded and severely degraded pastures (NDP, SAD, and SBD). The study assessed individual and combined sets of SuperDove attributes, including band reflectance, vegetation indices, endmember fractions from spectral mixture analysis (SMA), and image texture variables from Gray-level Co-occurrence Matrix (GLCM). The results highlighted the effectiveness of the transition from the rainy to the dry season and the period towards the beginning of a new seasonal rainy cycle in October for discriminating pasture degradation. In comparison to the dry season, more favorable discrimination scenarios were observed during the rainy season. In the dry season, increased amounts of non-photosynthetic vegetation (NPV) complicate the differentiation between NDP and SBD, which is characterized by high soil exposure. Pastures exhibiting severe biological degradation showed greater sensitivity to water stress, manifesting earlier reflectance changes in the visible and near-infrared bands of SuperDove compared to other classes. Reflectance-based classification yielded higher overall accuracy (OA) than the approaches using endmember fractions, vegetation indices, or texture metrics. Classifications using combined attributes achieved an OA of 0.69 and 0.88 for the five-class and three-class scenarios, respectively. In the five-class scenario, the highest F1-scores were observed for NDP (0.61) and classes of agronomic (0.71) and biological (0.88) degradation, indicating the challenges in separating low and moderate stages of pasture degradation. An initial comparison of RF classification results for the five categories of degraded pastures, utilizing reflectance data from MultiSpectral Instrument (MSI)/Sentinel-2 (400–2500 nm) and SuperDove (400–900 nm), demonstrated an enhanced OA (0.79 versus 0.66) with Sentinel-2 data. This enhancement is likely to be attributed to the inclusion of shortwave infrared (SWIR) spectral bands in the data analysis. Our findings highlight the potential of satellite constellation data, acquired at high spatial resolution, for remote identification of pasture degradation. [ABSTRACT FROM AUTHOR]

Faced with the problem of incompatibility between traditional information acquisition mode and spaceborne earth observation tasks, starting from the general mathematical model of compressed sensing, a theoretical model of block compressed sensing was established, and a full-process adaptive coding and decoding compressed sensing framework for remote sensing images was proposed, which includes five parts: mode selection, feature factor extraction, adaptive shape segmentation, adaptive sampling rate allocation and image reconstruction. Unlike previous semi-adaptive or local adaptive methods, the advantages of the adaptive encoding and decoding method proposed in this paper are mainly reflected in four aspects: (1) Ability to select encoding modes based on image content, and maximizing the use of the richness of the image to select appropriate sampling methods; (2) Capable of utilizing image texture details for adaptive segmentation, effectively separating complex and smooth regions; (3) Being able to detect the sparsity of encoding blocks and adaptively allocate sampling rates to fully explore the compressibility of images; (4) The reconstruction matrix can be adaptively selected based on the size of the encoding block to alleviate block artifacts caused by non-stationary characteristics of the image. Experimental results show that the method proposed in this article has good stability for remote sensing images with complex edge textures, with the peak signal-to-noise ratio and structural similarity remaining above 35 dB and 0.8. Moreover, especially for ocean images with relatively simple image content, when the sampling rate is 0.26, the peak signal-to-noise ratio reaches 50.8 dB, and the structural similarity is 0.99. In addition, the recovered images have the smallest BRISQUE value, with better clarity and less distortion. In the subjective aspect, the reconstructed image has clear edge details and good reconstruction effect, while the block effect is effectively suppressed. The framework designed in this paper is superior to similar algorithms in both subjective visual and objective evaluation indexes, which is of great significance for alleviating the incompatibility between traditional information acquisition methods and satellite-borne earth observation missions. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Systems (UASs) are increasingly vital in precision agriculture, offering detailed, real-time insights into plant health across multiple spectral domains. However, this technology's precision in estimating plant traits associated with Nitrogen Use Efficiency (NUE), and the factors affecting this precision, are not well-documented. This review examines the capabilities of UASs in assessing NUE in crops. Our analysis specifically highlights how different growth stages critically influence NUE and biomass assessments in crops and reveals a significant impact of specific signal processing techniques and sensor types on the accuracy of remote sensing data. Optimized flight parameters and precise sensor calibration are underscored as key for ensuring the reliability and validity of collected data. Additionally, the review delves into how different canopy structures, like planophile and erect leaf orientations, uniquely influence spectral data interpretation. The study also recognizes the untapped potential of image texture features in UAV-based remote sensing for detailed analysis of canopy micro-architecture. Overall, this research not only underscores the transformative impact of UAS technology on agricultural productivity and sustainability but also demonstrates its potential in providing more accurate and comprehensive insights for effective crop health and nutrient management strategies. [ABSTRACT FROM AUTHOR]

Area-based analyses of airborne laser scanning (ALS) data are an established approach to obtain wall-to-wall predictions of forest characteristics for vast areas. The analyses of sparse data in particular are based on the height value distributions, which do not produce optimal information on the horizontal forest structure. We evaluated the complementary potential of features quantifying the textural variation of ALS-based canopy height models (CHMs) for both supervised (linear regression) and unsupervised (k-Means clustering) analyses. Based on a comprehensive literature review, we identified a total of four texture analysis methods that produced rotation-invariant features of different order and scale. The CHMs and the textural features were derived from practical sparse-density, leaf-off ALS data originally acquired for ground elevation modeling. The features were extracted from a circular window of 254 m2 and related with boreal forest characteristics observed from altogether 155 field sample plots. Features based on gray-level histograms, distribution of forest patches, and gray-level co-occurrence matrices were related with plot volume, basal area, and mean diameter with coefficients of determination (R2) of up to 0.63–0.70, whereas features that measured the uniformity of local binary patterns of the CHMs performed poorer. Overall, the textural features compared favorably with benchmark features based on the point data, indicating that the textural features contain additional information useful for the prediction of forest characteristics. Due to the developed processing routines for raster data, the CHM features may potentially be extracted with a lower computational burden, which promotes their use for applications such as pre-stratification or guiding the field plot sampling based solely on ALS data.

We tested the Moment Distance Index (MDI) in combination with texture features for the summer vegetation mapping in the eastern Pamir Mountains, Tajikistan using the 2014 Landsat OLI (Operational Land Imager) image. The five major classes identified were sparse vegetation, medium-dense vegetation, dense vegetation, barren land, and water bodies. By utilizing object features in a random forest (RF) classifier, the overall classification accuracy of the land cover maps were 92% using a set of variables including texture features and MDI, and 84% using a set of variables including texture but without MDI. A decrease of the Kappa statistics, from 0.89 to 0.79, was observed when MDI was removed from the set of predictor variables. McNemar’s test showed that the increase in the classification accuracy due to the addition of MDI was statistically significant (p < 0.05). The proposed method provides an effective way of discriminating sparse vegetation from barren land in an arid environment, such as the Pamir Mountains.

Leaf Area Index (LAI) is a fundamental indicator of plant growth status in agronomy and environmental research. With the rapid development of drone technology, the estimation of crop LAI based on drone imagery and vegetation indices is becoming increasingly popular. However, there is still a lack of detailed research on the feasibility of using image texture to estimate LAI and the impact of combining texture indices with vegetation indices on LAI estimation accuracy. In this study, two key growth stages of winter wheat (i.e., the stages of green-up and jointing) were selected, and LAI was calculated using digital hemispherical photography. The feasibility of predicting winter wheat LAI was explored under three conditions: vegetation index, texture index, and a combination of vegetation index and texture index, at flight heights of 20 m and 40 m. Two feature selection methods (Lasso and recursive feature elimination) were combined with four machine learning regression models (multiple linear regression, random forest, support vector machine, and backpropagation neural network). The results showed that during the vegetative growth stage of winter wheat, the model combining texture information with vegetation indices performed better than the models using vegetation indices alone or texture information alone. Among them, the best prediction result based on vegetation index was RFECV-MLR at a flight height of 40 m (R2 = 0.8943, RMSE = 0.4139, RRMSE = 0.1304, RPD = 3.0763); the best prediction result based on texture index was RFECV-RF at a flight height of 40 m (R2 = 0.8894, RMSE = 0.4236, RRMSE = 0.1335, RPD = 3.0063); and the best prediction result combining texture and index was RFECV-RF at a flight height of 40 m (R2 = 0.9210, RMSE = 0.3579, RRMSE = 0.1128, RPD = 3.5575). The results of this study demonstrate that combining vegetation indices and texture from multispectral drone imagery can improve the accuracy of LAI estimation during the vegetative growth stage of winter wheat. In addition, selecting a flight height of 40 m can improve efficiency in large-scale agricultural field monitoring, as this study showed that drone data at flight heights of 20 m and 40 m did not significantly affect model accuracy. [ABSTRACT FROM AUTHOR]

In order to obtain high-quality images, the application of low-illumination image enhancement techniques plays a vital role in enhancing the overall visual appeal. However, it is particularly difficult to enhance an image while maintaining the original information of the scene. The augmentation method based on Retinex theory is widely considered as one of the representative techniques for such problems, but this method still has some limitations. First of all, noise is easily ignored in the process of model building, and the robustness of the model needs to be improved. Secondly, the image decomposition is less effective, so that part of the image information is not effectively presented. Finally, the optimization procedure is computationally complicated. This paper introduces a novel approach for enhancing low-illumination images by utilizing the relative deviation of local gradients. The proposed method aims to address the challenges associated with low-illumination images and offers a solution to these issues. In this paper, local gradient relative deviation is used as a constraint term and a noise term is added to highlight the image texture and structure and improve the robustness of the models, considering that L P achieves piecewise smoothing with better sparsity compared to the sum norm commonly used by L 1 and L 2 norms. In this paper, the L 2 − L P norm is used to constrain the model, which smooths the illumination component and better preserves the details of the reflectance component. In addition, to efficiently solve the optimization problem, the alternating direction multiplier method is chosen to transform the optimization process into the solution of several sub-problems. In comparison to traditional Retinex models, the proposed method excels in its ability to simultaneously enhance the image and suppress noise effectively. The experimental outcomes demonstrate the effectiveness of the proposed model in enhancing both simulated and real data. This approach can be applied to low-illumination remote sensing images to obtain high-quality remote sensing image data. [ABSTRACT FROM AUTHOR]

Quantifying the kinematic evolution patterns of mountain glaciers near Yarlung Tsanpo River performs a major role in evaluating the glacial instability and the secondary disasters. For the Sedongpu Basin near the Yarlung Tsanpo River Valley, the dramatic geomorphic landscape variations triggered by the ice-rock avalanche events were visually identified as the dominant texture deficiencies in time-series optical images. To improve the image correlation quality broken by these image texture deficiencies, the Landsat-8/Sentinel-2 optical images were divided into different groups, then a stepwise combination strategy was innovatively proposed to derive the glacier time-series displacement velocities in different temporal stages. The standard deviations (STD) of the optical measurements in the stable area maintained around 0.04 m/yr for the normalized displacement velocity and maintained from 0.6 to 1.7 m for the cumulative displacement time series. The obvious variations in glacier displacement velocity were identified before each collapse event. Subsequently, the offset-tracking procedures were performed on 7 Sentinel-1A Synthetic Aperture Radar (SAR) images to acquire the range and azimuth displacement velocities. To better reveal the dynamic mechanism of the glacier activity, the three-dimensional (3D) glacial displacement velocity was also derived by using optical and SAR results. The precipitation, temperature, and seismic activities were assumed as the main triggering factors of controlling the glacial dynamic mechanism and final collapse events. Additionally, the dynamic mechanism of the active glaciers in Sedongpu Basin conformed to a power law, which was limited by the changes of the internal stress friction force on the sliding base surface. The aim of this study is to shed a light on interpreting the precursory displacement patterns and their implicit failure mechanism of these ice-rock avalanche events with the conventional freely optical and SAR observations. [ABSTRACT FROM AUTHOR]

Intensified complementary metal-oxide semiconductor (ICMOS) sensors can capture images under extremely low-light conditions (≤0.01 lux illumination), but the results exhibit spatially clustered noise that seriously damages the structural information. Existing image-denoising methods mainly focus on simulated noise and real noise from normal CMOS sensors, which can easily mistake the ICMOS noise for the latent image texture. To solve this problem, we propose a low-light cross-scale transformer (LL-CSFormer) that adopts multi-scale and multi-range learning to better distinguish between the noise and signal in ICMOS sensing images. For multi-scale aspects, the proposed LL-CSFormer designs parallel multi-scale streams and ensures information exchange across different scales to maintain high-resolution spatial information and low-resolution contextual information. For multi-range learning, the network contains both convolutions and transformer blocks, which are able to extract noise-wise local features and signal-wise global features. To enable this, we establish a novel ICMOS image dataset of still noisy bursts under different illumination levels. We also designed a two-stream noise-to-noise training strategy for interactive learning and data augmentation. Experiments were conducted on our proposed ICMOS image dataset, and the results demonstrate that our method is able to effectively remove ICMOS image noise compared with other image-denoising methods using objective and subjective metrics. [ABSTRACT FROM AUTHOR]

With the development of deep learning, convolutional neural networks (CNNs) have been successfully applied in the field of change detection in heterogeneous remote sensing (RS) images and achieved remarkable results. However, most of the existing methods of heterogeneous RS image change detection only extract deep features to realize the whole image transformation and ignore the description of the topological structure composed of the image texture, edge, and direction information. The occurrence of change often means that the topological structure of the ground object has changed. As a result, these algorithms severely limit the performance of change detection. To solve these problems, this paper proposes a new topology-coupling-based heterogeneous RS image change detection network (TSCNet). TSCNet transforms the feature space of heterogeneous images using an encoder–decoder structure and introduces wavelet transform, channel, and spatial attention mechanisms. The wavelet transform can obtain the details of each direction of the image and effectively capture the image's texture features. Unnecessary features are suppressed by allocating more weight to areas of interest via channels and spatial attention mechanisms. As a result of the organic combination of a wavelet, channel attention mechanism, and spatial attention mechanism, the network can focus on the texture information of interest while suppressing the difference of images from different domains. On this basis, a bitemporal heterogeneous RS image change detection method based on the TSCNet framework is proposed. The experimental results on three public heterogeneous RS image change detection datasets demonstrate that the proposed change detection framework achieves significant improvements over the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Area-based analyses of airborne laser scanning (ALS) data are an established approach to obtain wall-to-wall predictions of forest characteristics for vast areas. The analyses of sparse data in particular are based on the height value distributions, which do not produce optimal information on the horizontal forest structure. We evaluated the complementary potential of features quantifying the textural variation of ALS-based canopy height models (CHMs) for both supervised (linear regression) and unsupervised (k-Means clustering) analyses. Based on a comprehensive literature review, we identified a total of four texture analysis methods that produced rotation-invariant features of different order and scale. The CHMs and the textural features were derived from practical sparse-density, leaf-off ALS data originally acquired for ground elevation modeling. The features were extracted from a circular window of 254 m² and related with boreal forest characteristics observed from altogether 155 field sample plots. Features based on gray-level histograms, distribution of forest patches, and gray-level co-occurrence matrices were related with plot volume, basal area, and mean diameter with coefficients of determination (R²) of up to 0.63-0.70, whereas features that measured the uniformity of local binary patterns of the CHMs performed poorer. Overall, the textural features compared favorably with benchmark features based on the point data, indicating that the textural features contain additional information useful for the prediction of forest characteristics. Due to the developed processing routines for raster data, the CHM features may potentially be extracted with a lower computational burden, which promotes their use for applications such as pre-stratification or guiding the field plot sampling based solely on ALS data. [ABSTRACT FROM AUTHOR]

We tested the Moment Distance Index (MDI) in combination with texture features for the summer vegetation mapping in the eastern Pamir Mountains, Tajikistan using the 2014 Landsat OLI (Operational Land Imager) image. The five major classes identified were sparse vegetation, medium-dense vegetation, dense vegetation, barren land, and water bodies. By utilizing object features in a random forest (RF) classifier, the overall classification accuracy of the land cover maps were 92% using a set of variables including texture features and MDI, and 84% using a set of variables including texture but without MDI. A decrease of the Kappa statistics, from 0.89 to 0.79, was observed when MDI was removed from the set of predictor variables. McNemar's test showed that the increase in the classification accuracy due to the addition of MDI was statistically significant (p < 0.05). The proposed method provides an effective way of discriminating sparse vegetation from barren land in an arid environment, such as the Pamir Mountains. [ABSTRACT FROM AUTHOR]

The majority of the aboveground biomass on the Earth's land surface is stored in forests. Thus, forest biomass plays a critical role in the global carbon cycle. Yet accurate estimate of forest aboveground biomass (FAGB) remains elusive. This study proposed a new conceptual model to map FAGB using remotely sensed data from multiple sensors. The conceptual model, which provides guidance for selecting remotely sensed data, is based on the principle of estimating FAGB on the ground using allometry, which needs species, diameter at breast height (DBH), and tree height as inputs. Based on the conceptual model, we used multiseasonal Landsat images to provide information about species composition for the forests in the study area, LiDAR data for canopy height, and the image texture and image texture ratio at two spatial resolutions for tree crown size, which is related to DBH. Moreover, we added RaDAR data to provide canopy volume information to the model. All the data layers were fed to a Random Forest (RF) regression model. The study was carried out in eastern North Carolina. We used biomass from the USFS Forest Inventory and Analysis plots to train and test the model performance. The best model achieved an R2 of 0.625 with a root mean squared error (RMSE) of 18.8 Mg/ha (47.6%) with the "out-of-bag" samples at 30 × 30 m spatial resolution. The top five most important variables include the 95th, 85th, 75th, and 50th percentile heights of the LiDAR points and their standard deviations of 85th heights. Numerous features from multiseasonal Sentinel-1 C-Band SAR, multiseasonal Landsat 8 imagery along with image texture features from very high-resolution imagery were selected. But the importance of the height metrics dwarfed all other variables. More tests of the conceptual model in places with a broader range of biomass and more diverse species composition are needed to evaluate the importance of other input variables. [ABSTRACT FROM AUTHOR]

The integration of remote sensing technology and machine learning algorithms represents a new research direction for the rapid and large-scale detection of water stress in modern agricultural crops. However, in solving practical agricultural problems, single machine learning algorithms cannot fully explore the potential information within the data, lacking stability and accuracy. Stacking ensemble learning (SEL) can combine the advantages of multiple single machine learning algorithms to construct more stable predictive models. In this study, threshold values of stomatal conductance (gs) under different soil water stress indices (SWSIs) were proposed to assist managers in irrigation scheduling. In the present study, six irrigation treatments were established for winter wheat to simulate various soil moisture supply conditions. During the critical growth stages, gs was measured and the SWSI was calculated. A spectral camera mounted on an unmanned aerial vehicle (UAV) captured reflectance images in five bands, from which vegetation indices and texture information were extracted. The results indicated that gs at different growth stages of winter wheat was sensitive to soil moisture supply conditions. The correlation between the gs value and SWSI value was high (R2 > 0.79). Therefore, the gs value threshold can reflect the current soil water stress level. Compared with individual machine learning models, the SEL model exhibited higher prediction accuracy, with R2 increasing by 6.67–17.14%. Using a reserved test set, the SEL model demonstrated excellent performance in various evaluation metrics across different growth stages (R2: 0.69–0.87, RMSE: 0.04–0.08 mol m−2 s−1; NRMSE: 12.3–23.6%, MAE: 0.03–0.06 mol m−2 s−1) and exhibited excellent stability and accuracy. This research can play a significant role in achieving large-scale monitoring of crop growth status through UAV, enabling the real-time capture of winter wheat water deficit changes, and providing technical support for precision irrigation. [ABSTRACT FROM AUTHOR]

In recent years, remote sensing has experienced a significant transformation due to rapid advancements in deep learning technology, which have greatly outpaced traditional methodologies. This integration has attracted substantial interest within the academic community. To address the complex challenges of extracting data on intricate water bodies during disaster scenarios, this study developed a post-disaster floodwater body dataset and an enhanced multi-scale transformer model architecture. Through end-to-end training, the precision of the model in extracting floodwater contours has been significantly improved. Additionally, by utilizing the vast amounts of unannotated data in remote sensing through an unsupervised pre-training task, the model's backbone network has been fortified, greatly enhancing its performance in remote sensing applications. Experimental analyses have shown that the multi-scale transformer-based algorithm for floodwater contour extraction proposed in this study is not only widely applicable but also excels in delivering precise segmentation results in complex environments. This refined approach ensures that the model adeptly handles the intricacies of floodwater body delineation, providing a robust solution for accurate extraction, even in disaster-stricken areas. This innovation represents a substantial leap forward in remote sensing, offering valuable insights and tools for disaster management and environmental monitoring. [ABSTRACT FROM AUTHOR]

The Police Robot for Inspection and Mapping of Underwater Evidence (PRIME) is an uncrewed surface vehicle (USV) currently being developed for underwater search and recovery teams to assist in crime scene investigation. The USV maps underwater scenes using sidescan sonar (SSS). Test exercises use a clothed mannequin lying on the seafloor as a target object to evaluate system performance. A robust, automated method for detecting human body-shaped objects is required to maximise operational functionality. The use of a convolutional neural network (CNN) for automatic target recognition (ATR) is proposed. SSS image data acquired from four different locations during previous missions were used to build a dataset consisting of two classes, i.e., a binary classification problem. The target object class consisted of 166 196 × 196 pixel image snippets of the underwater mannequin, whereas the non-target class consisted of 13,054 examples. Due to the large class imbalance in the dataset, CNN models were trained with six different imbalance ratios. Two different pre-trained models (ResNet-50 and Xception) were compared, and trained via transfer learning. This paper presents results from the CNNs and details the training methods used. Larger datasets are shown to improve CNN performance despite class imbalance, achieving average F1 scores of 97% in image classification. Average F1 scores for target vs background classification with unseen data are only 47% but the end result is enhanced by combining multiple weak classification results in an ensemble average. The combined output, represented as a georeferenced heatmap, accurately indicates the target object location with a high detection confidence and one false positive of low confidence. The CNN approach shows improved object detection performance when compared to the currently used ATR method. [ABSTRACT FROM AUTHOR]

The management of crop residues in farmland is crucial for increasing soil organic matter and reducing soil erosion. Identifying the regional extent of crop residue cover (CRC) is vital for implementing conservation tillage and formulating agricultural subsidy policies. The Google Earth Engine (GEE) and remote sensing images from 2019 to 2023 were used to obtain spectral characteristics before the maize seedling stage in Northeast China, followed by constructing the CRC estimation models using machine learning algorithms. To avoid the impact of multicollinearity among data, three machine learning algorithms—ridge regression (RR), partial least squares regression (PLSR), and least absolute shrinkage and selection operator (LASSO)—were employed. By comparing the accuracy of these methods, the most accurate model was determined and applied to subsequent CRC estimation. Based on the estimated CRC and Conservation Technology Information Center definitions of tillage practices, the conservation tillage mapping was completed, and the spatiotemporal distribution characteristics were thoroughly analyzed. The following findings were demonstrated: (1) the PLSR-based model outperformed RR (Pearson's correlation coefficient (r) = 0.8875, R2 = 0.7877, RMSE = 6.99%) and LASSO (r = 0.8903, R2 = 0.7926, RMSE = 6.88%) with higher accuracy (r = 0.9264, R2 = 0.8582, RMSE = 4.93%). (2) Over the five years, the average no-tillage (NT) proportion in the study area was 15.9%, reduced tillage (RT) was 17.8%, and conventional tillage (CT) was 66.3%. In 2020 and 2022, NT rates were significantly higher at 27.5% and 15.5%, while RT were 15.7% and 30.0%, respectively. (3) Compared to the Sanjiang and Liaohe Plains (RT = 1907 km2 and 1336 km2, and NT = 559 km2 and 585 km2, respectively), the Songnen Plain exhibited higher conservation tillage rates (where RT was 3791 km2 and NT was 1265 km2). This provides crucial scientific evidence for the management and planning of conservation tillage, thereby optimizing farmland production planning, enhancing production efficiency, and promoting the development of sustainable agricultural production systems. [ABSTRACT FROM AUTHOR]

Aboveground carbon stocks (AGCs) in forests play an important role in understanding carbon cycle processes. The global forestry sector has been working to find fast and accurate methods to estimate forest AGCs and implement dynamic monitoring. The aim of this study was to explore the effects of backpack LiDAR and UAV multispectral imagery on AGC estimation for two tree species (Larix gmelinii and Betula platyphylla) and to emphasize the accuracy of the models used. We estimated the AGC of Larix gmelinii and B. platyphylla forests using multivariate stepwise linear regression and random forest regression models using backpack LiDAR data and multi-source remote sensing data, respectively, and compared them with measured data. This study revealed that (1) the diameter at breast height (DBH) extracted from backpack LiDAR and vegetation indices (RVI and GNDVI) extracted from UAV multispectral imagery proved to be extremely effective in modeling for estimating AGCs, significantly improving the accuracy of the model. (2) Random forest regression models estimated AGCs with higher precision (Xing'an larch R2 = 0.95, RMSE = 3.99; white birch R2 = 0.96, RMSE = 3.45) than multiple linear regression models (Xing'an larch R2 = 0.92, RMSE = 6.15; white birch R2 = 0.96, RMSE = 3.57). (3) After combining backpack LiDAR and UAV multispectral data, the estimation accuracy of AGCs for both tree species (Xing'an larch R2 = 0.95, white birch R2 = 0.96) improved by 2% compared to using backpack LiDAR alone (Xing'an larch R2 = 0.93, white birch R2 = 0.94). [ABSTRACT FROM AUTHOR]

Accurate estimation of gross primary production (GPP) of paddy rice fields is essential for understanding cropland carbon cycles, yet remains challenging due to spatial heterogeneity. In this study, we integrated high-resolution unmanned aerial vehicle (UAV) imagery into a leaf biochemical properties-based model for improving GPP estimation. The key parameter, maximum carboxylation rate at the top of the canopy ( V c m a x , 0 25 ), was quantified using various spatial information representation methods, including mean (μref) and standard deviation (σref) of reflectance, gray-level co-occurrence matrix (GLCM)-based features, local binary pattern histogram (LBPH), and convolutional neural networks (CNNs). Our models were evaluated using a two-year eddy covariance (EC) system and UAV measurements. The result shows that incorporating spatial information can vastly improve the accuracy of V c m a x , 0 25 and GPP estimation. CNN methods achieved the best V c m a x , 0 25 estimation, with an R of 0.94, an RMSE of 19.44 μmol m−2 s−1, and an MdAPE of 11%, and further produced highly accurate GPP estimates, with an R of 0.92, an RMSE of 6.5 μmol m−2 s−1, and an MdAPE of 23%. The μref-GLCM texture features and μref-LBPH joint-driven models also gave promising results. However, σref contributed less to V c m a x , 0 25 estimation. The Shapley value analysis revealed that the contribution of input features varied considerably across different models. The CNN model focused on nir and red-edge bands and paid much attention to the subregion with high spatial heterogeneity. The μref-LBPH joint-driven model mainly prioritized reflectance information. The μref-GLCM-based features joint-driven model emphasized the role of GLCM texture indices. As the first study to leverage the spatial information from high-resolution UAV imagery for GPP estimation, our work underscores the critical role of spatial information and provides new insight into monitoring the carbon cycle. [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]

Carbon dioxide is one of the most influential greenhouse gases affecting human life. CO2 data can be obtained through three methods: ground-based, airborne, and satellite-based observations. However, ground-based monitoring is typically composed of sparsely distributed stations, while airborne monitoring has limited coverage and spatial resolution; they cannot fully reflect the spatiotemporal distribution of CO2. Satellite remote sensing plays a crucial role in monitoring the global distribution of atmospheric CO2, offering high observation accuracy and wide coverage. However, satellite remote sensing still faces spatiotemporal constraints, such as interference from clouds (or aerosols) and limitations from satellite orbits, which can lead to significant data loss. Therefore, the reconstruction of satellite-based CO2 data becomes particularly important. This article summarizes methods for the reconstruction of satellite-based CO2 data, including interpolation, data fusion, and super-resolution reconstruction techniques, and their advantages and disadvantages, it also provides a comprehensive overview of the classification and applications of super-resolution reconstruction techniques. Finally, the article offers future perspectives, suggesting that ideas like image super-resolution reconstruction represent the future trend in the field of satellite-based CO2 data reconstruction. [ABSTRACT FROM AUTHOR]

This study was designed to develop a 30 m resolution land cover dataset to improve the performance of regional weather forecasting models in East China. A 10-class land cover mapping scheme was established, reflecting East China's diverse landscape characteristics and incorporating a new category for plastic greenhouses. Plastic greenhouses are key to understanding surface heterogeneity in agricultural regions, as they can significantly impact local climate conditions, such as heat flux and evapotranspiration, yet they are often not represented in conventional land cover classifications. This is mainly due to the lack of high-resolution datasets capable of detecting these small yet impactful features. For the six-province study area, we selected and processed Landsat 8 imagery from 2015–2018, filtering for cloud cover. Complementary datasets, such as digital elevation models (DEM) and nighttime lighting data, were integrated to enrich the inputs for the Random Forest classification. A comprehensive training dataset was compiled to support Random Forest training and classification accuracy. We developed an automated workflow to manage the data processing, including satellite image selection, preprocessing, classification, and image mosaicking, thereby ensuring the system's practicality and facilitating future updates. We included three Weather Research and Forecasting (WRF) model experiments in this study to highlight the impact of our land cover maps on daytime and nighttime temperature predictions. The resulting regional land cover dataset achieved an overall accuracy of 83.2% and a Kappa coefficient of 0.81. These accuracy statistics are higher than existing national and global datasets. The model results suggest that the newly developed land cover, combined with a mosaic option in the Unified Noah scheme in WRF, provided the best overall performance for both daytime and nighttime temperature predictions. In addition to supporting the WRF model, our land cover map products, with a planned 3–5-year update schedule, could serve as a valuable data source for ecological assessments in the East China region, informing environmental policy and promoting sustainability. [ABSTRACT FROM AUTHOR]