Search

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

The population loss in mining areas intensifies the imbalance of the development of resource-based cities (RBCs). How to use night-time light to describe the spatial-temporal evolution pattern of population and compare the agglomeration and migration characteristics of population in coal mine concentration area (CMCA) and cities has become an important issue for sustainable development of RBCs. By fitting the DMSP/OLS and NPP/VIIRS night-time lights, this paper completed the simulation of population distribution of Linfen City in 2003/2008/2013/2018 by constructing the population spatialization model, and measured the urban population agglomeration and migration by using the geographical concentration index of population (GCP) and relative population migration index (RPM). The results show that the population agglomeration and migration of CMCA and cities are not synchronized. The GCP of the whole city shows an upward trend, while the GCP of CMCA shows a trend of substantial decrease first and then increase. From 2013 to 2018, the RPM of CMCA rebounded and reached 0.0307, reflecting the alleviation of population loss in CMCA. It is suggested that night-time lights should be used in the dynamic change assessment of population in RBCs, and measures such as coordinated development, acceleration of industrial transformation and promotion of urbanization should be taken to realize the reasonable distribution of population in RBCs. [ABSTRACT FROM AUTHOR]

Sea haze reduces the visibility of ships and makes the optical imaging system blind, which increases the difficulty of ship remote sensing. In this paper, we propose a new method for polarization remote sensing of ships in sea haze. The method takes advantage of image haze removal and exposure correction to improve the visibility of ships in sea haze. Different from the existing polarization-based image haze removal methods, the proposed method does not depend on any assumptions about the polarization properties of incident light. The exposure correction method is proposed based on the Retinex model and Bayes theorem, which can improve the visibility of ships in haze removal images. To evaluate the effectiveness of the proposed method, we implemented an outdoor experiment on polarization remote sensing of ships in sea haze weather. The experimental results indicate that the method can improve the visibility of ships significantly. In addition, the method outperforms the Stokes parameter-based ship remote sensing method in terms of the image quality metric fog aware density evaluator and can be easily generalized to RGB image haze removal. [ABSTRACT FROM AUTHOR]

In shipborne high-frequency surface wave radar (HFSWR), the change of platform speed or heading will cause variations in the extension of the Doppler spectrum for vessel targets located in different directions, subsequently resulting in alterations to the signal-to-noise ratio (SNR). These alterations in vessel target echo present challenges for manual parameter adjustments in traditional constant false alarm rate (CFAR) methods for shipborne HFSWR, thereby hindering the maintenance of stable target detection capabilities. In this paper, a self-attention-convolutional neural network (SA-CNN)-based CFAR detector is proposed, which transforms the detection problem into signal structure classification. First, the extension characteristics of vessel target echoes resulting from changes in speed or heading of the shipborne platform are quantitatively analysed, thereby guiding the selection of an optimal sliding window and constructing input vectors for the neural network. Subsequently, the SA-CNN is designed to efficiently extract the structural features of the signal and accurately predict the probability of target presence. Finally, the Monte Carlo method is used to control the false alarm rate effectively. Simulation and real dataset verification demonstrate that the proposed method exhibits superior detection performance compared to traditional methods in shipborne HFSWR, especially for detecting extended targets. [ABSTRACT FROM AUTHOR]

Albedo plays a key role in regulating the absorption of solar radiation within ice surfaces and hence strongly regulates the production of meltwater. A combination of Landsat and Sentinel 2 data provides the longest continuous medium resolution (10–30 m) earth surface observatory records. An albedo product (harmonized satellite albedo, hereafter HSA) has already been developed and validated for the Greenland Ice Sheet (GrIS), using harmonized Landsat 4–8 and Sentinel 2 datasets. In this paper, the HSA was validated for various Arctic and alpine glaciers and ice caps using in situ measurements. We determine the optimal spatial window size in point-to-pixel analysis, the best practices in evaluating remote sensing algorithms with groundtruth data, and cross sensor comparison of the Landsat 9 (L9) and Landsat 8 (L8) data. The impact of the spatial window size on measured ice surface homogeneity and albedo validation was analysed at both local and regional scales. Homogeneity statistics calculated from the grey-level co-occurrence matrix (GLCM) suggest that the ice surface becomes more homogeneous as the image resolution becomes coarser. The optimal spatial window size was found to be 90 m, based on maximizing the statistical and graphical measures while minimizing the root mean square error and bias. HSAs generally agree closely with in situ albedo measurements (e.g. Pearson's R ranges from 0.68 to 0.92) across various Arctic and alpine glaciers and ice caps. Cross sensor differences between L9 and L8 are minor, and we suggest that no harmonization is necessary to add L9 to our HSA product. [ABSTRACT FROM AUTHOR]

During floods, updated and accurate information on affected human settlements helps save lives and reduces time to rescue. Therefore, approaches that can provide reliable information during floods via the use of all-weather and real-time functional technology is highly needful. The study presented here attempts to efficiently and precisely map villages in the Indian sub-continent during floods via a three-stage approach which uses PolSAR data. However, an accurate segregation of villages in India even with PolSAR data is challenging because the built-up structures in the villages of rural India are closely placed and are randomly oriented w.r.t. each other. This condition either hinders their segregation or otherwise induces false alarms during extraction. More descriptive land cover characterization features and powerful feature classifiers may address this challenge. The study in this paper proposes a novel approach to efficiently detect and map flood affected villages which utilize polarization signatures from PolSAR imagery, ensemble-of -dilated-convolutions based CNNs, apriori knowledge and image morphology. The approach broadly involves three stages: first, built-up area extraction from a PolSAR image: second, detection of villages in a built-up area image and third, identification and mapping of villages that are affected by the flood. In the first stage, an ensemble of varying dilated-convolutions based novel CNN classifier which directly utilizes PolSAR-2 polarization signatures (PSs) in window-mode as features are developed to extract built-up areas. The second stage provides a novel village detection filter based on apriori knowledge and image morphology to detect actual villages and mask out the false objects. Finally, in the third stage, flood affected villages are mapped via a series of morphological operations based degree-of-intersection measure. Experiments are conducted on both simulated and natural flooded area datasets. Experimental results show 81% detection accuracy and 100% mapping performance of the proposed approach which indicates its potential as an effective flood affected village mapping system. [ABSTRACT FROM AUTHOR]

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

Land surface temperature (LST) is an essential parameter in environmental monitoring. However, due to the cloud contamination and the limitations of sensors, existing thermal infrared LST products are challenging to provide all-weather LST with high spatiotemporal resolution. Therefore, this paper presents a framework for reconstructing hourly LST under clouds based on the moderate resolution imaging spectroradiometer (MODIS) LST products. This framework consists of two main steps: (1) Instantaneous LST estimation for MODIS using a modified annual temperature cycle (ATCM) model and (2) Hourly LST reconstruction under all-weather conditions from atmospheric reanalysis data and MODIS instantaneous LST with the linear model (LM). The proposed framework is evaluated with the full year data of 2019 with tile number H26V05. The results show that the spatial distribution of the estimated LST is similar with the MODIS LST. Additionally, it could provide an accurate indication of the spatial and temporal variability of LST. Comparing the MODIS LST of the selected area for tile number H26V05 in 2019 with the estimated LST of the ATCM, the root mean squared errors (RMSEs) of the model are around 1K ~ 3K. The hourly LST is then reconstructed based on the LM method, and the RMSE is around 2K during the daytime and around 1K during the night-time. Finally, to verify the robustness of the hourly LST reconstruction method, the accuracy of the hourly LST was evaluated by the MODIS LST at different situations in the day. The results show that the missing data at one moment will cause the accuracy of the model decreasing by 0.09 ~ 1.67K at the corresponding moment. In general, the proposed framework has the potential to reconstruct the 1 km all-weather hourly LST with high accuracy and a certain level of robustness. [ABSTRACT FROM AUTHOR]

Infrared hyperspectral is susceptible to clouds, and accurately identifying whether the hyperspectral infrared sounder data is polluted by clouds is of great significance for numerical weather prediction and atmospheric parameter inversion. Since the complex spectral characteristics of clouds, the existing spectral threshold methods and machine learning methods have the difficulties of undetermined threshold and clear field of view (FOV) missed and false detections. In order to improve the cloud recognition accuracy of infrared hyperspectral data, three end-to-end cloud detection models combining deep neural network (DNN) and convolutional neural network (CNN) and long short-term memory network (LSTM) are proposed. In this paper, taking the High Spectral Infrared Atmospheric Sounder (HIRAS) equipped with Fengyun-3D (FY-3D) satellite as the research object, based on the same platform Moderate Resolution Spectral Imager-II (MERSI-II) cloud mask (CLM) product, the HIRAS Cloud dataset is established, and the accuracy test and qualitative analysis are carried out by using the test datasets and Typhoon Siamba, July 3, 2022, as well as the earth observation scene under the conditions of ice and snow surface. The test datasets analysis results show that the cloud detection accuracy of CNN and CNN-LSTM model is stable at 0.96, and the false alarm rate of cloud is 0.035 and 0.036, respectively, and the detection ability of DNN model is slightly inferior to the former two in the same hidden layer, with an accuracyof 0.94. In further qualitative research, we found that the CNN-LSTM model has high accuracy and robustness in infrared hyperspectral cloud detection, and the detection results in a variety of surface scenarios are consistent with the actual situation of whether clouds occur in the FOV of the instrument. Compared with CLM products, it can better identify clear ocean scenes, and provide fast and efficient cloud detection reference for data assimilation systems. [ABSTRACT FROM AUTHOR]

Automatically extracting roads from remote sensing images is increasingly important for autonomous driving and geographic information systems. However, due to factors such as ground objects blocking road boundaries and some roads being narrow and long in high-resolution remote sensing images, it is difficult for the current mainstream pixel-level extraction model to guarantee the continuity of roads and the smoothness of boundaries. To solve this problem, this paper designs a neural network Rse-net based on semantic segmentation, using a two-stream semantic segmentation network algorithm to make the network pay more attention to the boundary information of roads and narrow roads. This structure uses shape stream to process road boundary information (roads' shape stream), and processes it in parallel with classic stream. Use the Gated Shape CNN to connect the two streams of roads' shape stream and classic stream, and use the classical stream to optimize the boundary information in the shape stream. At the same time, a multi-scale convolutional attention mechanism is used between the decoder and the encoder to expand the receptive field through large-core attention, and obtain more semantic information without causing too much calculation. Finally, the effectiveness of the proposed network is verified by comparative experiments. [ABSTRACT FROM AUTHOR]

Global Navigation Satellite System Reflectometry (GNSS-R) is a remote sensing technique that can be regarded as a bistatic radar system. GNSS-R uses GNSS signals as signal sources and obtains the Earth's surface environmental parameters, such as soil moisture (SM), by receiving the L-band microwave signal reflected from the Earth's surface. However, surface vegetation could be one of the main factors influencing the accuracy of GNSS-R land applications since plants, including branches and leaves, attenuate GNSS signals. Additionally, the evaluation of signal attenuation caused by the plant canopy is quite difficult. In this paper, we study the attenuations of received L1- and L2-band GPS signals to the vegetation leaf area index (LAI) for different types of plants. The relationship between the attenuation of the GPS signal-to-noise ratio (SNR) (both above and below the canopy) and the LAI is established through field experiments. The results show that the mean SNR received in the L2 band is lower than that in the L1 band for each satellite but with a larger standard deviation (SD). The sensitivities of L1- and L2-band signals to the LAI are revealed, revealing greater sensitivity and a relatively good Pearson correlation coefficient (R) for lower elevation angles and vegetation biomass. In addition, the sensitivity and R of L2-band signals to the LAI are lower than those of L1-band signals. This study is significantly valuable for improving the quantitative representation of error estimates for GNSS-R SM retrieval. The established model can be employed in GNSS land applications and aid in solving signal surface-scattering problems in which accurate signal estimates are important. [ABSTRACT FROM AUTHOR]

Passive microwave has been used in land surface temperature (LST) inversion because of its all-weather availability. This paper proposed a LST retrieval method based on machine learning by integrating multiple datasets, including Advanced Microwave Scanning Radiometer 2 (AMSR2), Global Forecast System (GFS) reanalysis datasets, ERA5-land reanalysis products, Moderate Resolution Imaging Spectroradiometer (MODIS) products, Shuttle Radar Topography Mission (SRTM), and in situ measurements. Four algorithms, including linear regression (LR), random forests (RF), extreme gradient boosting (XGBoost) and light gradient boosting machine (LightGBM), were explored and compared by ten-fold cross-validation. The best-performing LightGBM algorithm was applied to train the model, and day and night models were developed separately. The models were validated using in situ LST of training stations from 2017 to 2019. The day and night models root mean square error (RMSE) are 3.23 and 2.43 K, and that of bias are −0.24 and −0.36 K, respectively. The in situ LST from 2015 to 2019 that not used for model training were selected to further validate both day and night models, with RMSE = 5.42 and 2.91 K, and bias = −0.60 and 0.06 K, respectively. Validation results indicated that the temporal performance of the models is better than those of spatial performance and the night model performed better than the day model. Additionally, model performance in different seasons and land cover types demonstrated the robustness of the models over complicated surfaces. These results suggest that the LightGBM algorithm has good accuracy in LST estimation, making it possible to apply for the generation of LST at a global scale. [ABSTRACT FROM AUTHOR]

Seawater temperature and salinity are basic marine environmental parameters, which can be used to calculate other marine environmental parameters. However, most of the on-site observation data have the problems of uneven spatial distribution and time discontinuity, and it is difficult for remote sensing observation methods to obtain subsurface information. In this study, we proposed a deep learning model with combining remote sensing temperature and salinity as well as in-situ measured data by Argo profiles, and the nonlinear relationship was revealed. An effective and direct inversion method was realized for underwater three-dimensional thermohaline structure based on remote sensing temperature and salinity at accurate points on global scale. The SST data were obtained from the FY3C-VIRR daily sea surface temperature product, the SSS data were acquired from the SMAP Level 3 8-day running averages sea surface salinity product, and the Argo scatter data were got from the 'Global Ocean Argo Scatter Data Set'. Based on the temporal and spatial location information of the data, this paper matched the remote sensing data from 2016 to 2019 with the Argo data, 64751 valid pairing points were obtained. The deep learning model was constructed as a multilayer perceptron model with 5 hidden layers. The RMSE of temperature had a maximum value of 2.106°C in 130 m depth and a minimum value of 0.367°C in 1000 m with an average of 1.174°C for validation dataset. And the RMSE of salinity had a maximum value of 0.356 psu in 0 m and a minimum value of 0.045 psu in 1000 m with an average of 0.202 psu. Compared with other methods based on fixed mesh products, this study realized a direct inversion method at any location in the global ocean and improved the inversion accuracy, which provides a reliable data support for refined marine monitoring. [ABSTRACT FROM AUTHOR]

Due to its impact on our ecosystem (i.e. vegetation, soil, water, etc.), global change has become more significant over time. Therefore, several biophysical indices (e.g. NDVI, NDWI, NDBI, etc.) have been developed to quantify, assess, and monitor the ecosystem reaction to these changes. Numerous and various satellite imagery can be integrated into multiple analysis approaches to carry out this assessment. One of the efficient methods in this field is Time Series Analysis (TSA), which allows the decomposition of data into three components (i.e. seasonality, irregularity, and trend). In this paper, we considered 100 biophysical indices, which we classified into six categories (i.e. vegetation, water, soil, burn, building, and others). These indices were computed using images of different satellite sensors ranging from coarse to high resolution [i.e. AVHRR, MODIS, Landsat-8, Sentinel-2, etc.] considering two study cases. The first case involved monitoring the Mediterranean basin from 2010 to 2014. The second focused on four specific climate zones -most dominant within the Mediterranean basin- (i.e. San Severo, Tangier, Tobruk, and Murcia), which were conducted from 2015 to 2022. High-performance computing of biophysical indices in both study cases resulted in more than 30,000 images used in generating a significant number of time series. To examine these results and quantify the relationship between satellites across different parameters, two analysis methods (i.e. trend analysis and correlation analysis) were employed. Trend analysis results showed that in the first case, 87% of indices trends are harmonized between AVHRR and SPOT-VGT. Moreover, in the second case, the percentages of biophysical indices that showed harmonized trends among all satellites are 55% for San Severo and Tobruk, 49% for Tangier, and 34% for Murcia. Finally, this study shows that satellite-derived biophysical indices and their trends may be significantly impacted by spatial scale, climate, satellite resolution, time series length, and outliers. [ABSTRACT FROM AUTHOR]

An urban agglomeration represents a mature stage in the development of urban areas with a highly concentrated spatial form. This research paper aimed to comprehend the spatio-temporal evolution characteristics of the Beijing-Tianjin-Hebei urban agglomeration, identify its spatial structure, and interconnections based on the NPP-VIIRS night light remote sensing data from 2012 to 2021. Additionally, the study was supplemented with statistical data from corresponding years to extract the range of urban built-up areas in the study region over the past ten years. The data were analysed using various methods such as light value statistics, urban rank-size rule, standard deviation ellipse, fractal dimension, and measure of urban association. The analysis was conducted based on three aspects: scale, morphology, and spatial structure. The findings indicated that the total amount of light in the Beijing-Tianjin-Hebei urban agglomeration had been increasing steadily, with Baoding showing the highest rate of increase, followed by Langfang. Furthermore, the urban agglomeration had a decreasing trend in fragmentation and fractal dimension, with concentrated built-up areas and regular geometry. The urban centre of gravity was shifting towards the northeast, i.e. closer to the geometric centre of the urban agglomeration. The primacy ratio of the urban agglomerations followed an undulating declining pattern, and the gap between cities in the urban agglomerations gradually narrowed. Although transport integration had led to increased urban connectivity, the northern and southern regions were still not sufficiently connected. [ABSTRACT FROM AUTHOR]

Efficiently and accurately identifying the spatial distribution of tea plantations in the subtropical plateau regions of southwest China is of great significance for ecological and environmental protection. However, the lands of those regions are fragmented with complex vegetation types. Moreover, there is much cloudy and rainy weather over those areas, making it very difficult to identify tea plantations using only optical remote sensing data. In order to solve these problems, this paper uses Sentinel-1 (S1) Synthetic Aperture Radar (SAR) data and Sentinel-2 (S2) optical data to design seven classification feature combinations to explore the influence of red edge features, radar features and texture features on the identification accuracy of tea plantations. The feasibility of Jeffreys-Matusita distance (JM) feature selection and Recursive Feature Elimination (RFE) feature selection algorithm to find the optimal feature combination is verified, and the distribution of tea plantations in the study area is acquired by using the object-oriented random forest algorithm. The study shows that (1) the combination of SAR data and optical data can effectively improve the identification accuracy of tea plantations. (2) S2 red edge features and S1 radar features can significantly improve the accuracy of the identification results of tea plantations. (3) After applying the JM distance and RFE feature selection algorithms, the producer's accuracy of tea plantations is improved by 1.39% and 2.38%, and the user's accuracy is improved by 1.02% and 1.3%, respectively, compared with the identification of all features. The overall accuracy of the random forest algorithm combined with RFE is 93.43%. This study proposes the application of feature selection algorithms in identification of tea plantations, which improves accuracy and increases efficiency while minimizing redundant features and provides an effective approach to identify tea plantations in cloudy and rainy areas in the subtropical plateau of southern China. [ABSTRACT FROM AUTHOR]

Due to the unique climatic characteristics and vegetation features of tropical regions, the correlation R2 of gross primary productivity (GPP) estimation in tropical regions using remote sensing models was generally lower than 0.3. Therefore, for the cloudy and rainy tropical regions, the influence brought by clouds on remote sensing images needed to be considered in GPP estimation. This paper developed a corrected vegetation photosynthesis model (VPM) for estimating GPP under cloudy conditions. It mainly corrected the two parameters, Wscalar and Enhanced Vegetation Index (EVI), which were obtained from remote sensing images and were therefore greatly influenced by clouds in the model. First, the water stress factor Wscalar was replaced by Evaporation Fraction (EF). Secondly, using the good correlation between near surface temperature and EVI, the conversion coefficient between near surface temperature and EVI was fitted to achieve the effective reconstruction of EVI contaminated by clouds. The correction of the two factors improved the estimation accuracy of the VPM model, and the comparison with the observed values of the GPP site in 4 years showed that the correction of EVI had a better improvement, with an increase of 0.22 in R2 compared with the pre-correction, and the correction of Wscalar was increased by 0.11 in R2. To verify the proposed method, the in-situ observation data of Xishuangbanna flux site from 2007 to 2010 were used. The results showed that the proposed method effectively improved the accuracy of GPP estimation by VPM model, especially in 2007 it was strongly influenced by clouds, and the improvement was significant, with R2 increasing from 0.2 to 0.82. In general, the accuracy of GPP estimation by the proposed method had been significantly improved, with RMSE (gC·m−2·8 day−1) decreasing from 15,14.4, 18.1, 14.2 to 8.07, 6.56, 10.33, 11.44, respectively. Therefore, the proposed method can be used to estimate the GPP for tropical seasonal rain forests in Xishuangbanna. [ABSTRACT FROM AUTHOR]

A distributed multichannel synthetic aperture radar system refers to a multichannel synthetic aperture radar system with channels distributed and installed at different locations on the platform. It is a promising system for high-resolution wide-swath imaging. The channels of the distributed multichannel synthetic aperture radar are sparsely distributed and have long cross-track baselines. The range-variant envelope migration and phase mismatch in the echoes between different channels are introduced by the long cross-track baselines and affect the performance of azimuth signal reconstruction. The sparsity of channels results in the poor correlation of data between channels, so the time-domain cross-correlation method typically used in azimuth multichannel synthetic aperture radar cannot be used in distributed multichannel synthetic aperture radar to estimate channel phase error directly. In this paper, the gain-phase error, sampling time delay and slant range difference introduced by cross-track baselines are modelled uniformly as channel mismatches. Firstly, a two-step channel mismatch estimation and compensation method for distributed multichannel synthetic aperture radar is proposed. Secondly, a range-variant envelope migration compensation method based on the chirp scaling principle is given. Thirdly, this paper also presents the processing of data rearrangement based on the distribution of spatial sampling points to make the time-domain cross-correlation method suitable for distributed multichannel synthetic aperture radar. Point target simulation and scene simulation are provided to show the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

In the process of using ground penetrating radar (GPR) to locate concealed power facilities such as underground cables, it is difficult to search the hyperbola generated by concealed facilities. To solve this problem, this paper proposes a two-step detection method to detect and locate the concealed facilities. First, the original echo image is pre-processed to enhance the weak signal and provide high-quality image for hyperbolic detection. And then, the first step of the two-step detection method is performed to extract the possible hyperbolic region. In this part, threshold processing method is used to reduce the clutter interference in the image, and the possible hyperbolic regions are detected and extracted based on the hyperbolic south open feature. In the second step, the trained faster Region-based Convolutional Neural Networks (faster-RCNN) is used to identify the extracted region, so as to obtain the position information of all hyperbolas in the echo image. By combining the hyperbolic detection results with the design drawings, the location of underground concealed facilities can be obtained. The proposed method is tested on the measured data, the experimental results show that the proposed method can accurately locate hyperbola from GPR data. [ABSTRACT FROM AUTHOR]

Remote sensing image segmentation has large uncertainty related to the heterogeneity of similar objects and complex spectrum in satellite images, causing the traditional segmentation methods to be greatly limited. Existing semantic segmentation methods represented by deep learning have made breakthrough progress. However, traditional deep learning methods, such as deep convolution neural network, are a completely deterministic model, which cannot describe the uncertainty of remote sensing image well. To solve this problem, a new deep neural network combined with fuzzy logic units is proposed in this paper, called RSFCNN (Remote Sensing image segmentation with Fuzzy Convolutional Neural Network). The network integrates convolution units and fuzzy logic units. Convolution units are used to extract discriminant features with different proportions, thus providing comprehensive information for pixel-level remote sensing image segmentation. Fuzzy logic units are used to deal with various uncertainties and provide more reliable segmentation results, and each unit handles the feature maps at a particular image scale by Gaussian blur function. Experiments were carried out on two data sets, and the results showed that RSFCNN has higher segmentation accuracy and better performance than state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

The hybrid baseline Multi-Channel Synthetic Aperture Radar (MC-SAR) refers to a MC-SAR with both along-track baselines and cross-track baselines. In the hybrid baseline MC-SAR, the phase induced by the target motion couples with the phase induced by terrain, which leads to the difficulty of ground moving target parameters estimation. In this paper, A novel maximum likelihood method based on the migration feature of a moving target in the complex image domain is proposed to estimate the velocity and height of the moving target. Compared with the original maximum likelihood method, the proposed method can decrease the computational load, has a smaller estimated error, and could resolve the ambiguity. The signal model of the terrain clutter and moving target in the hybrid baseline is analysed. A nonlinear antenna configuration is used to decouple the phase induced by moving target and terrain. Finally, some numerical experiments and scene simulation are also provided to demonstrate the estimated performance with different system parameters and the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Remote sensing has become an important technique for monitoring vegetation phenology. The quality of remote-sensing images and derived products is key to successful extraction of vegetation phenophases. There is a need to develop quality management methods to evaluate the data uncertainty and assist the removal of the noises. This paper developed a shape quality assurance score threshold (SQAT) method which accounts for the trend in satellite-derived vegetation index associated with the process of vegetation growth. The proposed method was tested on six widely used methods for extracting vegetation phenophases. Results showed that the SQAT method can effectively identify noises in the vegetation index time series and improve the accuracies of estimated start of season (SOS) and end of season (EOS) of the six methods. After removal of identified noises, the Pearson correlation coefficient (r) averagely increased by 8% for SOS, and 11% for EOS. Regression analyses of vegetation phenophases between the PhenoCam observations and MCD12Q2 product showed that the proposed method performs better than the QA score of MCD12Q2 for quality management. This paper provides promising method for quality management; it has the potential to reduce the uncertainty of the vegetation index time series that can support studies of vegetation phenology monitoring. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar systems are capable of acquiring high-resolution images by modulating and transmitting waves in high frequency levels towards the ground. Synthetic Aperture Radar (SAR) images are generated by demodulating and processing the backscattered waves by the targets. New SAR systems produce high-resolution images by raising the modulation frequency. The sampling time becomes shorter and a large number of samples are generated, which costs for processing and storage. Compressed Sensing (CS) is a compression technique capable of reconstructing a sparse signal from a small number of samples inferior to the conventional sampling. The representation basis, that projects a signal to a sparse form is the key of the application of CS. CS becomes unusable in the acquisition of heterogeneous scenes that present many scatterings types because the representation matrices are unknown and require intensive computing to generate them. In the literature, most proposed researches in the CS field apply CS on simulated sparse scenes, where only a few number of strong scatters are present to avoid the representation matrix computing. The purpose of this paper is to apply CS on non-sparse images and to avoid heavy computation to generate a representation matrix at the same time by combining the CS with the Gaussian Process regression (GPR). A small number of backscattered signals are acquired and sampled with respect to the Nyquist theory, sparsified and used as a feature vector for the training of the GPR model. The remaining signals are processed by the CS theory. After reconstruction, the zero values of the image are predicted using the model generated by the GPR algorithm. Five strategies are proposed in this paper and several evaluations are performed. These methods reconstruct an exploitable image from 40 % of samples. [ABSTRACT FROM AUTHOR]

In the process of mineral deposits formation, elements often show abnormal enrichment. Therefore, the inversion of element contents (the prediction of element contents in mineral deposits through hyperspectral data) has some indicative significance to the exploration of mineral resources. In order to solve the problem of nonlinear copper contents inversion using hyperspectral remote sensing, this paper put forward an improved Gradient Boosting Regression Tree (IGBRT) method to invert copper contents. The main innovations of this paper are: (1) replacing the simple average function with the k-nearest-neighbour weighted average function as the node prediction function to improve the accuracy; (2) using the adaptive reduction step instead of the fixed reduction step to improve the efficiency. At the end of the paper, taking the Altun region, Xinjiang province, China as the experimental area, the iron element which was high correlated with the copper was chosen as the intermediate variable, and the contents relationship between them was established to solve the problem of the small number of copper samples in the study area. Using the improved Gradient Boosting Regression Tree method to predict the iron contents, then the copper contents could be predicted through the relationship between them. The results showed that the IGBRT algorithm had the coefficient of determination (R2) of 0.744, which were 0.185 more than the traditional one, and the learning efficiency was increased by 39.4%. The results of this study can provide a reference for remote sensing inversion of copper contents in mineral deposits of uninhabited areas, and have some important significance for the delineation of copper prospects. [ABSTRACT FROM AUTHOR]

With the rapid development of remote sensing technologies, the frequency of observations of the same location is increasing, and many satellites and sensors produced a large amount of time series images. These images make long-term change detection and dynamic characteristic estimation of ground features possible. However, conventional remote sensing image change detection methods mostly rely on manual visual interpretation and supervised or unsupervised computer-aided classification. Traditional methods always face many bottlenecks when processing big and fast-growing datasets, such as low computational efficiency, low level of automation, and different identification standards and accuracies caused by different operators. With the rapid accumulation of remote sensing data, it has become an important but more challenging task to conduct change detection in a more precise, automated and standardized way. The development of geointelligent computing technologies provides a means of solving these problems and improve the accuracy and efficiency of remote sensing image change detection. In this paper, we presented a novel deep learning model called nest network(NestNet) based on a convolutional neural network to improve the accuracy of the automatic change detection task by using remotely sensed time series images. NestNet extracts the respective features of bi-temporal images using an encoding parallel module and subsequently employs absolute different operations to process the features of two images. Compared with change detection method based on U-Shaped network plus plus (UNet++), the parallel module improves the efficiency of NestNet. Finally, a decoding module is used to generate a predicted change image. This paper compares NestNet to traditional methods and state-of-the-art deep learning models on two datasets. The experimental results demonstrate that the accuracy of NestNet is better than that of state-of-the-art methods. It can be concluded that the NestNet model is a potential approach for change detection using high resolution remote sensing images. [ABSTRACT FROM AUTHOR]

In this paper, the energy characteristics of Gabor texture are used for cloud detection in high-resolution multispectral images. First, the satellite remote-sensing image is divided into superpixels using simple linear iterative clustering (SLIC), and then, the energy characteristics of Gabor texture and spectral characteristics are computed by extracting the texture features of the superpixels. The features of the cloud superpixels are used as the learning sample of the support vector machine (SVM) classifier, and a classification model is obtained by training the SVM classifier. Finally, a cloud-detection experiment is conducted for various sensor images with three visible bands and one near-infrared band. The experimental results showed that the proposed method provides an excellent average overall accuracy for thick and thin clouds in a complex background of forests, harbours, snow and mountains. The characteristic parameters of this paper are not limited by the image parameters; thus, they provide good results and universality for various types of sensors. [ABSTRACT FROM AUTHOR]

Research on land change has a long history, has generated numerous publications and continues to receive international research attention. To facilitate the understanding of the patterns and trends of land-change research, this article uses a content-based text-retrieval approach and self-organizing map to analyse more than 700 peer-reviewed remote-sensing and natural-science papers on land-use/cover change (LUCC) from the past two decades. We present the results in map-like displays and discuss papers within the identified clusters to examine the research activities. A new cluster of research, which has emerged in the last 5 years of analysis, has focused on mixed-pixel issues for land-use/cover mapping, particularly in the context of forest catchments. Studies of LUCC consequences after 2000 have been concerned with the effects of forest conversion on soil-nutrient pools and nitrate cycling. Incorporating information on resolutions and extents into the representations reveals a dominant scale of analysis for some research activities. Analysing time frames of examination in the papers suggests that research on long-term LUCC consequences started to use presettlement land survey records. Few attempts, however, have been made to investigate the uncertainties in the historical sources of information for LUCC research, thereby presenting a future research topic. [ABSTRACT FROM AUTHOR]

Traditional Light Detection and Rangings (LiDARs) can quickly collect high-accuracy of three-dimensional (3D) point cloud data at a designated wavelength (i.e., cannot obtain hyperspectral data), while the passive hyperspectral imager can collect rich spectral data of ground objects, but are lack of 3D spatial data. This paper presents one innovative study on the design of airborne-oriented supercontinuum laser hyperspectral (SCLaHS) LiDAR with 50 bands covering 400 nm to 900 nm at a spectral resolution of 10 nm and ground sampling distance (GSD) of 0.5 m. The major innovations include (1) development of the high-power narrow-pulse supercontinuum laser source covering 400 nm to 900 nm with 50 bands using multi-core microstructure fibre, all-polarization maintaining fibre and ultra-long cavity structure, (2) a miniaturized aberration correction holographic concave grating spectroscopic and streak tube technique are developed for 50 bands laser echoes detection at high spectral-spatial-temporal resolution and dynamic airborne platform, and (3) the algorithm theoretic basis for SCLaHS LiDAR point cloud data 3D geodetic coordination calculation, including in-flight airborne calibration algorithm. The initial experimental results demonstrated that the designed SCLaHS LiDAR is doable, and a prototype of the (SCLaHS) LiDAR intends to be implemented. [ABSTRACT FROM AUTHOR]

Convolutional Neural Network (CNN) is widely used for semantic segmentation and land-use and land-cover (LULC) mapping of very high-resolution (VHR) remote sensing images. The convolution operation is a powerful method for VHR classification, but the loss of high-frequency detail information caused during its operation decreases the classification accuracy, particularly in the boundary. Thus, it is necessary to supply additional boundary information to the CNN for alleviating this situation. In the classification task (and in LULC mapping), providing more effective information generates a better classification result. Current methods regard the boundary of images as the same category object and process it uniformly, which loses a notable amount of useful information because of the different properties, such as ambiguity and transition, between remote sensing images and their boundaries. Thus, a semantic segmentation method with category boundary for LULC mapping is proposed in this paper. First, a multi-task CNN called the category boundary detection network (CBDN) is designed to extract the boundary information of different category objects. Second, this category boundary and VHR images are used for initial semantic segmentation. Finally, the category boundary and the initial semantic segmentation result (ISSR) are fused to obtain the final LULC map by a two-step strategy, including the explicit fusion and the boundary attention loss function. To verify whether category boundary improved the classification accuracy, a set of comparative experiments were conducted on the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen and Potsdam datasets. The method in this paper was compared with a semantic segmentation method with no boundary information and a semantic segmentation method with global boundary. The results showed that the proposed method in this paper achieved good performances in the Vaihingen (overall accuracy (OA) = 0.924, Kappa coefficient (K) = 0.898, mean F1 score (mF1) = 0.896 and mean Intersection over Union (mIoU) = 0.817) and Potsdam datasets (OA = 0.890, K = 0.857, mF1 = 0.923, and mIoU = 0.860) based on the eroded labels. [ABSTRACT FROM AUTHOR]

Hyperspectral images are rich in spectral data, lending themselves well to pixel-level image classification tasks. Previous studies primarily focus on closed-set classification within the realm of hyperspectral image classification. However, real-world scenarios present the challenge of dealing with object classes not encountered during the training phase, a scenario known as open set classification, which has garnered less attention compared to the closed set paradigm. In this paper, we propose a methodology anchored on ConvMixer for tackling open-set classification by utilizing energybased models. We incorporate a Selective Kernel Attention (SKA) to capture the notion that different feature maps usually correspond to different objects in deep neural networks. Our experimental validation, conducted on two datasets, specifically the WHU-Hi-HanChuan and WHU-Hi-HongHu datasets, showcases promising outcomes of the introduced method. [ABSTRACT FROM AUTHOR]

Wildfires pose a serious threat to the environment, ecosystems, property, biodiversity, and human life. Early detection of wildland fires is crucial for effective firefighting and mitigation. In this paper, we propose an ensemble learning method, called CT-Fire, which combines the deep CNN RegNetY and the vision transformer EfficientFormer v2 to recognize and detect forest fires on ground and aerial images. Testing results showed that CT-Fire achieved excellent performance with fast speed and accuracy of 99.62% and 87.77% using ground and aerial images, respectively. CT-Fire also outperformed benchmark CNNs and vision transformer methods, showing its accurate reliability in detecting wildfires. It also surpassed various challenges, including the detection of very small wildfires, background complexity, image quality, and wildland fire variability in terms of intensity, size, and shape. [ABSTRACT FROM AUTHOR]

Power line maintenance and inspection are essential to avoid power supply interruptions, reducing its high social and financial impacts yearly. Automating power line visual inspections remains a relevant open problem for the industry due to the lack of public real-world datasets of power line components and their various defects to foster new research. This paper introduces InsPLAD, a Power Line Asset Inspection Dataset and Benchmark containing 10,607 high-resolution Unmanned Aerial Vehicles colour images. The dataset contains 17 unique power line assets captured from real-world operating power lines. Additionally, five of those assets present six defects: four of which are corrosion, one is a broken component, and one is a bird's nest presence. All assets were labelled according to their condition, whether normal or the defect name found on an image level. We thoroughly evaluate state-of-the-art and popular methods for three image-level computer vision tasks covered by InsPLAD: object detection, through the AP metric; defect classification, through Balanced Accuracy; and anomaly detection, through the AUROC metric. InsPLAD offers various vision challenges from uncontrolled environments, such as multi-scale objects, multi-size class instances, multiple objects per image, intra-class variation, cluttered background, distinct point-of-views, perspective distortion, occlusion, and varied lighting conditions. To the best of our knowledge, InsPLAD is the first large real-world dataset and benchmark for power line asset inspection with multiple components and defects for various computer vision tasks, with a potential impact to improve state-of-the-art methods in the field. It will be publicly available in its integrity on a repository with a thorough description. It can be found at . [ABSTRACT FROM AUTHOR]

Accurately estimating the collapse height of buildings during earthquakes holds great significance. Acquiring precise height information of buildings using dual-phase high-resolution stereo satellite images (HRSSIs) requires high-precision ground control points, which are difficult to obtain in earthquake-stricken areas. Spaceborne laser data has been validated to significantly improve the vertical accuracy of HRSSIs. Therefore, this paper first proposes the application of a combined stereo adjustment model in building collapse estimation and thoroughly verifies its feasibility. Firstly, the laser altimetry points (LAPs) acquired by GF-7 and ICESat-1 serve as elevation control points (ECPs), and the tie points from HRSSIs were used as constraint to conduct combined adjustment to improve the consistency of stereoscopic positioning accuracy between HRSSIs before and after the earthquake. Subsequently, a footprints-to-conners, coarse-to-fine, automatic building corners extraction method was performed. Avoiding the time-consuming generation of large-scale DSM while also improving the accuracy of building collapse assessment. Finally, according to the height change of building corners calculated from HRSSIs, building damage assessment was completed. According to the above methods, independent experiments were carried out respectively for the Oaxaca earthquake in Mexico in 2020 and the Kahramanmaras earthquake in Türkiye in 2023. GF-7 HRSSIs was used to verify the accuracy and stability of the proposed method for 3D assessment of building damage. The results indicate that the RMSE of elevation positioning accuracy has been greatly reduced in both regions, ranging from 10.29 m to 0.95 m and from 6.67 m to 0.99 m, respectively. This accuracy guarantees the feasibility of detecting the building floor-level collapse. And 2541 building corner points were extracted from two disaster areas, with correct corner points accounting for 85.18%. A total of 520 buildings were correctly extracted corner points, with an accuracy rate of 94.12% for assessing the degree of damage. [ABSTRACT FROM AUTHOR]

Atmospheric correction eliminates corruption in reflectance captured by satellite images due to atmospheric elements like gases, aerosols, and water vapours. Existing physics-based approaches employ radiative transfer models constructed using lookup tables computed for different atmospheric parameters. However, these approaches are computationally expensive and rely on estimates of parameters that are difficult to sense accurately. This paper proposes a deep learning model as an alternative to physics-based approaches. We present an end-to-end deep neural network trained on seasonally and spatially rich Landsat 8 satellite images without explicit atmospheric parameterization along with our analysis and its validation. We validate the model's effectiveness vis-a-vis Landsat 8's Land Surface Reflectance Code – LaSRC results in $RMSE \sim 0.042$ R M S E ∼ 0.042 , $SSIM \sim 0.97$ S S I M ∼ 0.97 , and correlation coefficient $r \sim 0.99$ r ∼ 0.99. For ground measurements by RadCalNet, the proposed model has an $RMSE \sim 0.053$ R M S E ∼ 0.053 , $SSIM \sim 0.90$ S S I M ∼ 0.90 , and $r \sim 0.88$ r ∼ 0.88. The results show that the model accurately predicts surface reflectance and correlates highly with reference data. [ABSTRACT FROM AUTHOR]

The mostly subterranean nature of district heating system pipelines makes pinpointing any occurring leakages a challenge. Airborne thermography offers a means for widespread monitoring, allowing thermal anomalies to be identified within multitudes of infrared images. This paper details a program developed to automate the entire image analysis process using mainly open-source software. Thermal images are acquired via unmanned aircraft system (UAS), pre-processed, and georeferenced individually or combined to orthomosaics. The search space is minimized to areas around the pipelines. Regions of interest are determined by image segmentation via tailored triangle histogram thresholding. The majority of resulting false alarms are removed by comparison with characteristic traits and results classified by their severity. The algorithm is applied to images newly acquired in Germany as part of a case study. The implemented methodology allows for a reduction of between 92 and 99% of thermal anomalies to a manageable amount of potential leakages for network operators to view. The use of orthomosaiking software in this context, though helpful in coalescing data, is found to lack robustness, precision and therefore reliability. Despite some limitations, the developed program is able to confidently detect and categorize leakages of varying severity and can be used directly by network operators. Future research will focus on further data pre-processing to eliminate thermal drift and remove the remaining false alarms, which mostly pertain to common urban features. [ABSTRACT FROM AUTHOR]

Nitrogen is an essential nutrient element for the growth of citrus tree. The accurate estimation of leaf nitrogen content (LNC) is important to guarantee fruit quality and yield. The unmanned aerial vehicle (UAV) remote sensing has shown great potential for monitoring the LNC of crops. However, the number of training samples is always limited due to the high cost and time consumption of acquiring LNC samples. Obtaining satisfactory results is difficult for most machine-learning models with insufficient samples. Thus, a semi-supervised regression model is designed in this paper to improve the performance of estimating citrus LNC from UAV images under the condition of small samples. First, the local binary pattern (LBP) operator is employed to fully extract textural features in UAV images. Second, semi-supervised cooperative regression models based on ridge regression (Ridge), support vector regression (SVR), and random forest (RF) are constructed by combining spectral and textural features. Finally, the best learning model is used to realize the accurate limited sample LNC estimation from the available training samples. The experiments confirm that the semi-supervised cooperative regression model has better and promising results than other machine-learning methods under the condition of small samples. The RF-based cooperative regression model (CoRF) performs best among other models, with a determination coefficient (R2) of 0.716 and a root mean square error (RMSE) of 0.620 g·kg−1. The CoRF model also achieves superior performance when combining LBP textural features. The results estimated by the semi-supervised cooperative regression model is capable of providing instructions for the production and management of citrus orchard. [ABSTRACT FROM AUTHOR]

Hyperspectral image classification involves assigning a land cover class to each pixel of a hyperspectral image (HSI). Recently, several classification methods based on deep learning with spatial information from HSI have been proposed. These methods typically demonstrate strong classification capabilities. However, spatial information often comprises complex data, making it challenging to extract valuable information. To address this issue, this paper proposes a novel image preprocessing method for classification based on metric learning. This method aims to reduce the complexity of spatial information to facilitate network learning. First, the method assesses the similarity between the central pixel and other pixels in each image patch using a relation network. It replaces pixels that are dissimilar to the central pixel with pixels that are similar to the central pixel to simplify the image patch. This approach reduces interference information in the image patch, allowing the network to focus more on the central pixel features that represent category information during the classification task. This greatly reduces the complexity of the required network, the difficulty of the network learning, and the number of training samples needed. Experimental results on three popular hyperspectral image datasets demonstrate that the proposed preprocessing method significantly improves classification accuracy compared to the baseline network. The study also compares our method to the state-of-the-art attention mechanism CNN, demonstrating how our method excels at hyperspectral classification in data-smoothing and feature preservation. [ABSTRACT FROM AUTHOR]

Satellite observations of precipitation have greatly improved our understanding of its temporal and spatial distribution. In view of the high spatiotemporal heterogeneity and severely skewed distribution characteristics of precipitation, it is necessary and of considerable application value to understand the ability of satellite-derived precipitation products (SPPs) to characterize the variations of precipitation in the time and space dimensions separately. However, to date, research concerning this is scarce. In this study, we explore the ability of 13 SPPs to characterize the temporal and spatial variations of precipitation based on observations from more than 2400 meteorological stations in Chinese mainland from 2001 to 2018. The results show that (1) SPPs tend to perform better in identifying the temporal than the spatial variation of precipitation. Most SPPs can reliably monitor the temporal and spatial variation of monthly and seasonal precipitation in Chinese mainland, although the identification of the spatial variation of daily precipitation involves larger uncertainty; (2) CMORPH-B, IMERG-F, 3B42, and MSWEP generally had better performance in identifying the temporal and spatial variations of precipitation, while PERSIANN and GSMaP-N performed poorly. However, no single SPP outperformed others in all scenarios; (3) with respect to monitoring the temporal variation of daily precipitation, SPPs performed better in southern China than in the north, with three-quarters and half of median KGE values above 0.5 In comparison, no significant spatial difference was observed in their ability to monitor the spatial variation of daily precipitation; and (4) SPPs had large uncertainties in capturing the temporal and spatial variations of precipitation in winter, while they performed best in identifying the temporal and spatial variations of daily precipitation in summer. The results of this paper provide an important reference for data users needing to select suitable SPPs and for satellite developers desiring to further improve data quality. [ABSTRACT FROM AUTHOR]

This paper introduces a novel edge detection operator called 'vision transformer-based Dexinet (ViT-DexiNet)' to address the challenges of detecting small objects in synthetic aperture radar (SAR) images. SAR images are typically impacted by strong multiplicative noise, making edge detection difficult. Existing traditional methods have limited spectral data preservation capabilities and often result in a loss of clarity and integrity of salient features in SAR images. The proposed ViT-DexiNet operator employs a series of interconnected layers to extract and refine salient edge features from SAR images. It utilizes a vision transformer self-attention layer to capture the pattern and structural details of image features crucial for determining edges. The extracted feature maps are then processed by the DexiNet architecture, which consists of a dense block, transfer block, and upsampling network. This architecture helps preserve edge information at different scales in deeper layers. The series of layered blocks generate edge maps, which are concatenated and averaged through smoothing to remove noise and enhance edge details in SAR images, resulting in a final high-quality edge map. To evaluate the proposed ViT-DexiNet method, both qualitative and quantitative analyses are conducted using standard edge detection operators such as Canny and Sobel. The empirical results demonstrate that the ViT-DexiNet surpasses baseline edge detection operators. The achieved values of proposed edge detection operator are 97.92%, 97.72%, 97.64% and 97.41%, respectively for the metrics accuracy, precision, recall and f1-score. The ViT-DexiNet offers high-quality edge maps, simplifying the interpretation of data for small object detection. Overall, the ViT-DexiNet method shows promise in overcoming the limitations of traditional approaches and improving the detection of edges in SAR images. [ABSTRACT FROM AUTHOR]

Semantic segmentation is a fundamental but meaningful task in the remote sensing image understanding community. Great progress has been made in optical sensor photography technology, which poses an opportunity and a challenge for remote sensing image segmentation task. But, in fact, a longstanding and intractable problem is that many hard pixels in special position, i.e. the prevalent intra-class noise and a poor boundary delineation, is difficult to classify due to their inherent uncertainty. In this paper, we comprehensively consider the characteristics of deep learning and introduce traditional pattern recognition methods to drive structure learning, which can leverage the corresponding fuzzy logic model to alleviate the aforementioned problem in remote sensing images. Specifically, this paper designs a multiscale bidirectional fuzzy-driven learning network (MBFNet), which takes advantage of both deep learning and fuzzy logic to effectively alleviate the inherent uncertainty of these hard pixels. The structure of convolutional neural networks driven by fuzzy systems also provides a new modelling paradigm for solving the uncertain problem in remote sensing images. Meanwhile, multiscale techniques and bidirectional fusion are introduced to enhance feature aggregation and avoid the potential adverse effects of fuzzy systems, respectively. Experimental results on two datasets demonstrate qualitatively and quantitatively that the proposed MBFNet is competitive. [ABSTRACT FROM AUTHOR]

As a classic problem of high-resolution remote sensing image tasks, land cover classification has many challenges, for instance, variable scales and low-edge discrimination. Traditional spatial semantic segmentation methods based on single-scale feature extraction are challenging to model multi-scale features. They cannot effectively fit high-resolution remote sensing images with variable scales and are prone to misclassification issues. On the other hand, spatial multi-scale semantic segmentation methods lack edge constraints, which can easily lead to edge segmentation ambiguity issues. We propose a segmentation network based on a multi-scale frequency-domain attention gating mechanism (MFAGNet) to solve the above problems. Specifically, we obtain multi-scale features through multi-scale input and design the discrete cosine transform channel attention module (DCTCAM). In DCTCAM, we extract global low-frequency features and effectively alleviate misclassification caused by scale changes. The edge features of the image are obtained through the high-frequency feature extraction module (HFEM) by using edge detection operators to enhance the model's ability to recognize edges. Additionally, no further pooling operations are employed except for a single max pooling layer in the backbone network. In this paper, we design a new gating mechanism to dynamically control the extraction ratio of various frequency features so that it can adapt to input images of different scales. This paper conducts comparative experiments on three high-resolution land cover datasets: GID, Vaihingen, and Potsdam. The new algorithm proposed compares with classic semantic segmentation models such as DANet, PSPNet, SegNet, UNet, DeepLabv3+, FcaNet, BiSeNet, AFN, and FastFCN. The experimental results show that MFAGNet is superior to the comparison models. With no significant increase in computing overhead, MFAGNet obtains MIoU of 69.05%, 73.40%, and 79.42% on the standard data sets GID, Vaihingen, and Potsdam, respectively. [ABSTRACT FROM AUTHOR]

For spaceborne ISAR imaging of space targets, due to the high-speed relative motion between the radar and targets, both the translational and rotational motion exhibit the high-order characteristics. Conventional translational motion compensation (TMC) methods are ineffective in handling such high-order translational motion. Moreover, the migration through resolution cell (MTRC) stems from the presence of the high-order spatial variant phase of the echo signal, resulting in severe defocusing of ISAR images. In this paper, a novel spaceborne ISAR imaging approach for space targets is proposed, which incorporates the high-order TMC and the high-order MTRC correction. First, the slant range model for spaceborne ISAR imaging is derived as a third-order polynomial form. Based on this model, a modified high-order TMC method is proposed, which utilizes the minimum entropy method combined with the Broyden – Fletcher – Goldfarb – Shanno (BFGS) algorithm. The proposed method leverages orbital model information to obtain the initial TMC coefficients, enabling TMC to be completed more accurately and effectively. Then, a modified polynomial keystone transform (PKT) is proposed to correct the high-order MTRC. The PKT-based method effectively addresses both the high-order and first-order MTRC corrections simultaneously. Finally, a spaceborne ISAR imaging approach is proposed to obtain well-focused ISAR images. Simulated and real data results validate the analysis of the spaceborne ISAR imaging model and demonstrate the effectiveness of the spaceborne imaging approach for space targets proposed in this paper. [ABSTRACT FROM AUTHOR]

One of the limitations of remote sensing is the low spatial resolution of the open-access multispectral sensors, generating a mixture of spatial information. The mixed pixels can be modelled as the linear combination of fundamental components, called endmember, with a weighted contribution or abundance. The development of linear unmixing algorithms considering spatial and spectral information has recently increased. Some unmixing methods have relied on segmentation to integrate spatial data, and one of the most used is superpixel-based segmentation. However, previous work in superpixel-based unmixing focuses on using superpixels as uniform regions. Commonly, linear unmixing is used on hyperspectral imagery, and limited literature is found with multispectral images. This paper aims to propose a new preprocessing approach for multispectral linear unmixing called Superpixel Linear Independent Preprocessing. The proposed approach generates a set of candidates to endmembers based on spatial-spectral information; these are the input of traditional endmember extraction methods for multispectral unmixing. Experimental results show that the proposed preprocessing improves the performance of endmember extraction. [ABSTRACT FROM AUTHOR]

We analysed nine years (2012–2019) of fire observations from the Visible Infrared Imaging Radiometer Suite (VIIRS) onboard the Suomi-NPP satellite to assess the post-monsoon crop stubble burning activities over northern India. The 2020 fire season (September-November) was analysed extensively, and spatiotemporal trends were examined. Our analysis indicates that about 60% of post-monsoon fires occurred in the state of Punjab, followed by Madhya Pradesh (11%), Haryana (4%), and Uttar Pradesh (3%). The year 2020 saw the greatest fire activity in Punjab and across the country since 2016. Over the nine years, Punjab did not show any systematic trends in fire activities, whereas Haryana and Madhya Pradesh demonstrated an overall decreasing (45% lower in 2020 compared to the 2012–2019 mean) and increasing (185% more in 2020 compared to 2012–2019 mean) trends, respectively. The high fire occurance in the Punjab are related to high percentage of crop area with specific variety of rice, which produces high straw load and mature in shorter time. The increase in Madhya Pradesh is directly related to an increase in rice crop planting area over the years, whereas the decrease in Haryana is related to changes in crop residue management. The uncertainty analysis in this paper shows that over a given region, day-to-day variability in fire counts can have sampling biases due to changing satellite viewing geometry. Furthermore, long-term trends can also be impacted by the reduced sampling of satellite fire detections under cloudy conditions. However, large scale spatiotemporal analysis of fires in this area provides crucial and well sought-after information for crop fire control and air quality management in north India. The district level analysis for the four states signifies the critical information that satellites can provide for identifying hotspots and planning regionally focused mitigation strategies to curb pollution from crop burning fires. [ABSTRACT FROM AUTHOR]

Unlike natural images, remote sensing scene images usually contain one scene label and many object labels, and many object labels are arranged dispersedly, which brings great difficulties to feature extraction of scene label. To accurately identify scene labels from remote sensing scene images with multiple object labels, it is important to fully understand the global context of the image. In order to solve the challenges of multi-label scene images and improve the classification performance, a global context feature extraction module is proposed in this paper. The module combines the semantics information of different regions through a global pooling and three different scale sub-regions pooling, which makes the module have stronger ability of global feature representation. In addition, in order to fully understand the semantic content of remote sensing images, a three branch joint feature extraction module is constructed, which consists of the global context feature module, 3 × 3 convolution branch and identity branch are fused. Finally, a lightweight convolution neural network based on joint features (LCNN-JF) is constructed using traditional convolution, depthwise separable convolution, joint feature extraction module and classifier for remote sensing scene image classification. A series of experimental results on four datasets, UCM, AID, RSSCN and NWPU, demonstrate that the proposed method has better feature representation ability and can achieve better classification of remote sensing scene images. [ABSTRACT FROM AUTHOR]

Timely detection of underground natural gas leakage is significant for the safe production of gas storage and the protection of ecological environment. Direct detection makes it difficult to identify natural gas micro-leakage accurately, while hyperspectral remote sensing can identify micro-leakage based on spectral changes of vegetation near the leakage area. However, the spectral morphological characteristics of vegetation leaves under natural gas micro-leakage will undergo complex changes over time, making it difficult to identify vegetation stress. Temporal spectral characteristics improve the capability of capturing spectral differences of stressed vegetation at different times, allowing for indirect evaluation of leaked information. This study simulates the stress of underground natural gas storage micro leaks on bean growth through field experiments. Based on the changes in spectral reflectance and chlorophyll content of leaves, temporal features were constructed based on multi-temporal reflectance data, and feature selection methods were used to obtain bands sensitive to natural gas stress. This paper proposed a leaf scale natural gas micro-leakage identification index based on temporal spectral features (TNII) to identify bean stress under natural gas leakage. The results are summarized as follows: (1) With the leakage of underground natural gas, the spectral reflectance of leaves increased in the visible and near-infrared range, and the chlorophyll content decreased. (2) The TNII (R 676 − R 526 ) T n − (R 676 − R 526 ) T 1 (R 676 − R 526 ) T n + (R 676 − R 526 ) T 1 constructed based on sensitive wavebands (676 and 526 nm) can be employed to identify bean stress under natural gas after 17 days of leakage. The JM (Jefferies Matusita) distance test indicates that TNII could timely and stably identify bean stress under natural gas micro-leakage (JM > 1.8). This study provides the theoretical basis and technology support for micro-leakage detection of underground gas storage or pipelines. [ABSTRACT FROM AUTHOR]

This paper proposes an automatic method for land cover change detection in very-high-spatial-resolution optical remote sensing images based on the automatic selection of training samples using expectation-maximization (EM) and an extreme learning machine classifier, which has two key characteristics: (1) combining the advantages of supervised and unsupervised methods with progressive mask classification. (2) training samples of three classes (changed, unchanged, and unknown) were automatically selected by K-Means and EM, and then further refined by the likelihood function. The method was validated by one dataset of SuperView-1 imagery with a spatial resolution of 2.0 m, two datasets of TripleSat-2 imagery with a spatial resolution of 3.2 m, and one open dataset of Zi-Yuan-3 imagery with a spatial resolution of 5.8 m, and the results were compared with that of three unsupervised methods (iterative slow feature analysis, multivariate alteration detection, and adaptive object-oriented spatial-contextual extraction algorithm), two deep learning methods (convolutional-wavelet neural networks and dual-domain networks), and three supervised classifiers (support vector machine, random forest, and Naive Bayes), showing the effectiveness of this method in decrease of false-positive rates and increase of change detection accuracy. The average and maximum of the accuracy metric F1 score of our method are 0.6842 and 0.8708, respectively; the average F1 score of the unsupervised, deep learning, and supervised methods are 0.5049, 0.4943, and 0.633, respectively. [ABSTRACT FROM AUTHOR]

As an important load of airborne/spaceborne passive microwave remote sensing, fully polarized microwave radiometer is widely used to the measurement of wind vector and salinity on sea surface. The retrieval of ocean surface parameters requires high accuracy data of radiometer. In recent years, the data correction scheme of fully polarized radiometer is common, but the attitude problem of radiometer is not paid enough attention. This paper establishes a full link transfer model for a fully polarized microwave radiometer, and focus on analysing the impact of aircraft attitude on various parameters. This paper aims to draw researchers' attention to attitude control of fully polarized microwave radiometer. Through the model established in this paper, the influence of attitude on fully polarized microwave radiometers is clarified and corrected, then rapidly correction can be achieved. Through simulation model, the impact of different attitudes on data can be calculated in advance before flight tests, and can provide guidance for attitude control. Using the corrected data for wind vector analysis, the deviation of wind direction is within 10°, which also verifies the accuracy of the model in this paper. The model proposed in this paper can achieve fast and accurate correction of radiometer parameters and the error prediction caused by attitude, which provides a strong guarantee for the inversion of sea surface parameters. [ABSTRACT FROM AUTHOR]

Pansharpening refers to the fusion of a multispectral image (MS) and a panchromatic image (PAN) to obtain a new image with the same spatial resolution as the PAN image and the same spectral resolution as the MS image. This paper describes a new, efficient, and accurate pansharpening architecture. The Vector-Quantized Variational AutoEncoder (VQ-VAE) is the foundation of the proposed method. The VQ-VAE model is trained to learn the nonlinear mapping of degraded panchromatic image patches to highresolution patches. This approach ensures that high-resolution patches can be recovered from low-resolution ones. After training on PAN patches, the VQ-VAE estimates high-resolution multispectral patches for each band of the original multispectral image before reconstructing the high-resolution multispectral image from the patches. The original multispectral image, the panchromatic image, and the estimated high-resolution multispectral image are combined through a modified Component Substitution (CS) process to obtain the pansharpened image. Three large satellite datasets from urban areas with 4-band spectral resolution (blue, green, red, and near-infrared) were used to evaluate the proposed pansharpening method's performance. The effectiveness of the proposed method is demonstrated by the quantitative and visual results obtained compared to several literature approaches. [ABSTRACT FROM AUTHOR]