Deep learning has made significant progress in the field of oriented object detection for remote sensing images.However,existing methods still face challenges when dealing with difficult tasks such as multi-scale targ...Deep learning has made significant progress in the field of oriented object detection for remote sensing images.However,existing methods still face challenges when dealing with difficult tasks such as multi-scale targets,complex backgrounds,and small objects in remote sensing.Maintaining model lightweight to address resource constraints in remote sensing scenarios while improving task completion for remote sensing tasks remains a research hotspot.Therefore,we propose an enhanced multi-scale feature extraction lightweight network EM-YOLO based on the YOLOv8s architecture,specifically optimized for the characteristics of large target scale variations,diverse orientations,and numerous small objects in remote sensing images.Our innovations lie in two main aspects:First,a dynamic snake convolution(DSC)is introduced into the backbone network to enhance the model’s feature extraction capability for oriented targets.Second,an innovative focusing-diffusion module is designed in the feature fusion neck to effectively integrate multi-scale feature information.Finally,we introduce Layer-Adaptive Sparsity for magnitude-based Pruning(LASP)method to perform lightweight network pruning to better complete tasks in resource-constrained scenarios.Experimental results on the lightweight platform Orin demonstrate that the proposed method significantly outperforms the original YOLOv8s model in oriented remote sensing object detection tasks,and achieves comparable or superior performance to state-of-the-art methods on three authoritative remote sensing datasets(DOTA v1.0,DOTA v1.5,and HRSC2016).展开更多
The rapid economic development that the Hotan Oasis in Xinjiang Uygur Autonomous Region,China has undergone in recent years may face some challenges in its ecological environment.Therefore,an analysis of the spatiotem...The rapid economic development that the Hotan Oasis in Xinjiang Uygur Autonomous Region,China has undergone in recent years may face some challenges in its ecological environment.Therefore,an analysis of the spatiotemporal changes in ecological environment of the Hotan Oasis is important for its sustainable development.First,we constructed an improved remote sensing-based ecological index(RSEI)in 1990,1995,2000,2005,2010,2015 and 2020 on the Google Earth Engine(GEE)platform and implemented change detection for their spatial distribution.Second,we performed a spatial autocorrelation analysis on RSEI distribution map and used land-use and land-cover change(LUCC)data to analyze the reasons of RSEI changes.Finally,we investigated the applicability of improved RSEI to arid area.The results showed that mean of RSEI rose from 0.41 to 0.50,showing a slight upward trend.During the 30-a period,2.66% of the regions improved significantly,10.74% improved moderately and 32.21% improved slightly,respectively.The global Moran's I were 0.891,0.889,0.847 and 0.777 for 1990,2000,2010 and 2020,respectively,and the local indicators of spatial autocorrelation(LISA)distribution map showed that the high-high cluster was mainly distributed in the central part of the Hotan Oasis,and the low-low cluster was mainly distributed in the outer edge of the oasis.RSEI at the periphery of the oasis changes from low to high with time,with the fragmentation of RSEI distribution within the oasis increasing.Its distribution and changes are predominantly driven by anthropologic factors,including the expansion of artificial oasis into the desert,the replacement of desert ecosystems by farmland ecosystems,and the increase in the distribution of impervious surfaces.The improved RSEI can reflect the eco-environmental quality effectively of the oasis in arid area with relatively high applicability.The high efficiency exhibited with this approach makes it convenient for rapid,high frequency and macroscopic monitoring of eco-environmental quality in study area.展开更多
Water on the Earth’s surface is an essential part of the hydrological cycle. Water resources include surface waters, groundwater, lakes, inland waters, rivers, coastal waters, and aquifers. Monitoring lake dynamics i...Water on the Earth’s surface is an essential part of the hydrological cycle. Water resources include surface waters, groundwater, lakes, inland waters, rivers, coastal waters, and aquifers. Monitoring lake dynamics is critical to favor sustainable management of water resources on Earth. In cryosphere, lake ice cover is a robust indicator of local climate variability and change. Therefore, it is necessary to review recent methods, technologies, and satellite sensors employed for the extraction of lakes from satellite imagery. The present review focuses on the comprehensive evaluation of existing methods for extraction of lake or water body features from remotely sensed optical data. We summarize pixel-based, object-based, hybrid, spectral index based, target and spectral matching methods employed in extracting lake features in urban and cryospheric environments. To our knowledge, almost all of the published research studies on the extraction of surface lakes in cryospheric environments have essentially used satellite remote sensing data and geospatial methods. Satellite sensors of varying spatial, temporal and spectral resolutions have been used to extract and analyze the information regarding surface water. Multispectral remote sensing has been widely utilized in cryospheric studies and has employed a variety of electro-optical satellite sensor systems for characterization and extraction of various cryospheric features, such as glaciers, sea ice, lakes and rivers, the extent of snow and ice, and icebergs. It is apparent that the most common methods for extracting water bodies use single band-based threshold methods, spectral index ratio (SIR)-based multiband methods, image segmentation methods, spectral-matching methods, and target detection methods (unsupervised, supervised and hybrid). A Synergetic fusion of various remote sensing methods is also proposed to improve water information extraction accuracies. The methods developed so far are not generic rather they are specific to either the location or satellite imagery or to the type of the feature to be extracted. Lots of factors are responsible for leading to inaccurate results of lake-feature extraction in cryospheric regions, e.g. the mountain shadow which also appears as a dark pixel is often misclassified as an open lake. The methods which are working well in the cryospheric environment for feature extraction or landcover classification does not really guarantee that they will be working in the same manner for the urban environment. Thus, in coming years, it is expected that much of the work will be done on object-based approach or hybrid approach involving both pixel as well as object-based technology. A more accurate, versatile and robust method is necessary to be developed that would work independent of geographical location (for both urban and cryosphere) and type of optical sensor.展开更多
Traditional methods of extracting the ocean wave eddy information from remotely sensed imagery mainly use the edge detection technology such as Canny and Hough operators. However, due to the complexities of ocean eddi...Traditional methods of extracting the ocean wave eddy information from remotely sensed imagery mainly use the edge detection technology such as Canny and Hough operators. However, due to the complexities of ocean eddies and image itself, it is sometimes difficult to successfully detect ocean eddies using these methods. A mnltifractal filtering technology is proposed for extraction of ocean eddies and demonstrated using NASA MODIS, SeaWiFS and NOAA satellite data set in the typical area, such as ocean west boundary current. Results showed that the new method has a superior performance over the traditional methods.展开更多
Remote sensing technique plays an important role in geological prospecting in Altay because of the remote location and steep terrain with mountains.Pegmatite has important implications for metallogenic prospecting as ...Remote sensing technique plays an important role in geological prospecting in Altay because of the remote location and steep terrain with mountains.Pegmatite has important implications for metallogenic prospecting as most of rare metals occurs in it.Pegmatite information from optical and radar images was extracted,and the spatial distribution and scale of pegmatite were generalized in Azubai,Altay.Three mining targets,that is,Halon-Azubai,Kuermutu-Tuyibaguo and Zhuolute-Akuoyige,were delineated based on the analysis of pegmatite information,structure interpretation and other geological data.展开更多
The classification of hyperspectral remote sensing data is an important problem theoretically and practically.With the increase of spectral bands,the separability of objects on remote sensing image should be improved....The classification of hyperspectral remote sensing data is an important problem theoretically and practically.With the increase of spectral bands,the separability of objects on remote sensing image should be improved.But the effects of traditional algorithm on feature extraction such as principal component analysis(PCA)is not so good for hyperspectral image.The key problem is that PCA can only represent the linear structure of data set;while the data clouds of different objects on hyperspectral image usually distribute on a nonlinear manifold.This paper established an algorithm of nonlinear feature extraction named as nonlinear principal poly lines,based on the algorithm,a classifier is constructed and the classification accuracy of hyperspectral image can be improved.展开更多
According to the characteristics of the road features,an Encoder-Decoder deep semantic segmentation network is designed for the road extraction of remote sensing images.Firstly,as the features of the road target are r...According to the characteristics of the road features,an Encoder-Decoder deep semantic segmentation network is designed for the road extraction of remote sensing images.Firstly,as the features of the road target are rich in local details and simple in semantic features,an Encoder-Decoder network with shallow layers and high resolution is designed to improve the ability to represent detail information.Secondly,as the road area is a small proportion in remote sensing images,the cross-entropy loss function is improved,which solves the imbalance between positive and negative samples in the training process.Experiments on large road extraction datasets show that the proposed method gets the recall rate 83.9%,precision 82.5%and F1-score 82.9%,which can extract the road targets in remote sensing images completely and accurately.The Encoder-Decoder network designed in this paper performs well in the road extraction task and needs less artificial participation,so it has a good application prospect.展开更多
While executing tasks such as ocean pollution monitoring,maritime rescue,geographic mapping,and automatic navigation utilizing remote sensing images,the coastline feature should be determined.Traditional methods are n...While executing tasks such as ocean pollution monitoring,maritime rescue,geographic mapping,and automatic navigation utilizing remote sensing images,the coastline feature should be determined.Traditional methods are not satisfactory to extract coastline in high-resolution panchromatic remote sensing image.Active contour model,also called snakes,have proven useful for interactive specification of image contours,so it is used as an effective coastlines extraction technique.Firstly,coastlines are detected by water segmentation and boundary tracking,which are considered initial contours to be optimized through active contour model.As better energy functions are developed,the power assist of snakes becomes effective.New internal energy has been done to reduce problems caused by convergence to local minima,and new external energy can greatly enlarge the capture region around features of interest.After normalization processing,energies are iterated using greedy algorithm to accelerate convergence rate.The experimental results encompassed examples in images and demonstrated the capabilities and efficiencies of the improvement.展开更多
Automatic extraction of road and linear structure from remote sensing images is a very important problem. This paper analyses several existing methods of the automatic road and linear structure extraction by using som...Automatic extraction of road and linear structure from remote sensing images is a very important problem. This paper analyses several existing methods of the automatic road and linear structure extraction by using some multi-spectral remote sensing images acquired from different spatial resolutions, districts and road characteristics. Their advantages and disadvantages have been generalized.展开更多
Road traffic is the important driving factor for economic and social development. With the rapid increase of vehicle population, road traffic problems such as traffic jam and traffic accident have become the bottlenec...Road traffic is the important driving factor for economic and social development. With the rapid increase of vehicle population, road traffic problems such as traffic jam and traffic accident have become the bottleneck which restricts economic development. In recent years, natural disasters frequently occur in China. Therefore, it is essential to extract road information to compute the degree of road damage for traffic emergency management. A road extraction method based on region growing and mathematical morphology from remote sensing images is proposed in this paper. According to the road features, the remote sensing image is preprocessed to separate road regions from non-road regions preliminarily. After image thresholding, region growing algorithm is used to extract connected regions. Then we sort connected regions by area to exclude the small regions which are probably non-road objects. Finally, the mathematical morphology algorithm is used to fill the holes inside the road regions. The experimental results show that the method proposed can effectively extract roads from remote sensing images. This research also has broad prospects in dealing with traffic emergency management by the government.展开更多
When existing deep learning models are used for road extraction tasks from high-resolution images,they are easily affected by noise factors such as tree and building occlusion and complex backgrounds,resulting in inco...When existing deep learning models are used for road extraction tasks from high-resolution images,they are easily affected by noise factors such as tree and building occlusion and complex backgrounds,resulting in incomplete road extraction and low accuracy.We propose the introduction of spatial and channel attention modules to the convolutional neural network ConvNeXt.Then,ConvNeXt is used as the backbone network,which cooperates with the perceptual analysis network UPerNet,retains the detection head of the semantic segmentation,and builds a new model ConvNeXt-UPerNet to suppress noise interference.Training on the open-source DeepGlobe and CHN6-CUG datasets and introducing the DiceLoss on the basis of CrossEntropyLoss solves the problem of positive and negative sample imbalance.Experimental results show that the new network model can achieve the following performance on the DeepGlobe dataset:79.40%for precision(Pre),97.93% for accuracy(Acc),69.28% for intersection over union(IoU),and 83.56% for mean intersection over union(MIoU).On the CHN6-CUG dataset,the model achieves the respective values of 78.17%for Pre,97.63%for Acc,65.4% for IoU,and 81.46% for MIoU.Compared with other network models,the fused ConvNeXt-UPerNet model can extract road information better when faced with the influence of noise contained in high-resolution remote sensing images.It also achieves multiscale image feature information with unified perception,ultimately improving the generalization ability of deep learning technology in extracting complex roads from high-resolution remote sensing images.展开更多
Significant advancements have been achieved in road surface extraction based on high-resolution remote sensingimage processing. Most current methods rely on fully supervised learning, which necessitates enormous human...Significant advancements have been achieved in road surface extraction based on high-resolution remote sensingimage processing. Most current methods rely on fully supervised learning, which necessitates enormous humaneffort to label the image. Within this field, other research endeavors utilize weakly supervised methods. Theseapproaches aim to reduce the expenses associated with annotation by leveraging sparsely annotated data, such asscribbles. This paper presents a novel technique called a weakly supervised network using scribble-supervised andedge-mask (WSSE-net). This network is a three-branch network architecture, whereby each branch is equippedwith a distinct decoder module dedicated to road extraction tasks. One of the branches is dedicated to generatingedge masks using edge detection algorithms and optimizing road edge details. The other two branches supervise themodel’s training by employing scribble labels and spreading scribble information throughout the image. To addressthe historical flaw that created pseudo-labels that are not updated with network training, we use mixup to blendprediction results dynamically and continually update new pseudo-labels to steer network training. Our solutiondemonstrates efficient operation by simultaneously considering both edge-mask aid and dynamic pseudo-labelsupport. The studies are conducted on three separate road datasets, which consist primarily of high-resolutionremote-sensing satellite photos and drone images. The experimental findings suggest that our methodologyperforms better than advanced scribble-supervised approaches and specific traditional fully supervised methods.展开更多
Based on low-altitude remote sensing images,this paper established sample set of typical river vegetation elements and proposed river vegetation extraction technical solution to adaptively extract typical vegetation e...Based on low-altitude remote sensing images,this paper established sample set of typical river vegetation elements and proposed river vegetation extraction technical solution to adaptively extract typical vegetation elements of river basins.The main research of this paper were as follows:(1)a typical vegetation extraction sample set based on low-altitude remote sensing images was established.(2)A low-altitude remote sensing image vegetation extraction model based on the focus perception module was designed to realize the end-to-end automatic extraction of different types of vegetation areas of low-altitude remote sensing images to fully learn the spectral spatial texture information and deep semantic information of the images.(3)By comparison with the baseline method,baseline method with embedded focus perception module showed an improvement in the precision by 7.37%and mIoU by 49.49%.Through visual interpretation and quantitative calculation analysis,the typical river vegetation adaptive extraction network has effectiveness and generalization ability,consistent with the needs of practical applications of vegetation extraction.展开更多
This paper presents algorithmic components and corresponding software routines for extracting shoreline features from remote sensing imagery and LiDAR data. Conceptually, shoreline features are treated as boundary lin...This paper presents algorithmic components and corresponding software routines for extracting shoreline features from remote sensing imagery and LiDAR data. Conceptually, shoreline features are treated as boundary lines between land objects and water objects. Numerical algorithms have been identified and de-vised to segment and classify remote sensing imagery and LiDAR data into land and water pixels, to form and enhance land and water objects, and to trace and vectorize the boundaries between land and water ob-jects as shoreline features. A contouring routine is developed as an alternative method for extracting shore-line features from LiDAR data. While most of numerical algorithms are implemented using C++ program-ming language, some algorithms use available functions of ArcObjects in ArcGIS. Based on VB .NET and ArcObjects programming, a graphical user’s interface has been developed to integrate and organize shoreline extraction routines into a software package. This product represents the first comprehensive software tool dedicated for extracting shorelines from remotely sensed data. Radarsat SAR image, QuickBird multispectral image, and airborne LiDAR data have been used to demonstrate how these software routines can be utilized and combined to extract shoreline features from different types of input data sources: panchromatic or single band imagery, color or multi-spectral image, and LiDAR elevation data. Our software package is freely available for the public through the internet.展开更多
Accurately identifying building distribution from remote sensing images with complex background information is challenging.The emergence of diffusion models has prompted the innovative idea of employing the reverse de...Accurately identifying building distribution from remote sensing images with complex background information is challenging.The emergence of diffusion models has prompted the innovative idea of employing the reverse denoising process to distill building distribution from these complex backgrounds.Building on this concept,we propose a novel framework,building extraction diffusion model(BEDiff),which meticulously refines the extraction of building footprints from remote sensing images in a stepwise fashion.Our approach begins with the design of booster guidance,a mechanism that extracts structural and semantic features from remote sensing images to serve as priors,thereby providing targeted guidance for the diffusion process.Additionally,we introduce a cross-feature fusion module(CFM)that bridges the semantic gap between different types of features,facilitating the integration of the attributes extracted by booster guidance into the diffusion process more effectively.Our proposed BEDiff marks the first application of diffusion models to the task of building extraction.Empirical evidence from extensive experiments on the Beijing building dataset demonstrates the superior performance of BEDiff,affirming its effectiveness and potential for enhancing the accuracy of building extraction in complex urban landscapes.展开更多
Previous studies have often focused on monitoring grassland growth as the primary target of remote sensing investigations on grassland ecological restoration in the northern Tibetan Plateau,overlooking the crucial rol...Previous studies have often focused on monitoring grassland growth as the primary target of remote sensing investigations on grassland ecological restoration in the northern Tibetan Plateau,overlooking the crucial role played by gravel in the ecological restoration of these grasslands.This study utilizes supervised classification and segmentation techniques based on machine learning to extract gravel morphology profiles from field-sampled plot images and calculate their characteristic parameters.Employing a multivariate linear approach combined with Principal Component Analysis(PCA),a model for inferring gravel characteristic parameters is constructed.Statistical features,particle size characteristics,and spatial distribution patterns of gravel are analyzed.Results reveal that gravel predominantly exhibit sub-rounded shapes,with 80%classified as fine gravel.The coefficients of determination(R2)between gravel particle size and coverage,perimeter,and area are 0.444,0.724,and 0.557,respectively,indicating linear relationships.The cumulative contribution rate of the top five remote sensing factors is 95.44%,with the first geological factor contributing 77.64%,collectively reflecting the primary information of the 20 factors used.Modeling shows that areas with larger gravel particle sizes correspond to increased perimeter and coverage.Gravels in the Nagqu Prefecture of northern Xizang have a particle size range of 4-8 mm,primarily comprising fine gravel which accounts for 94.61%.These findings provide a scientific basis for extracting gravel characteristic parameters and understanding their spatial distribution variations in the northern Tibetan Plateau.展开更多
Efficient segmentation of oiled pixels in optical remotely sensed images is the precondition of optical identification and classification of different spilled oils,which remains one of the keys to optical remote sensi...Efficient segmentation of oiled pixels in optical remotely sensed images is the precondition of optical identification and classification of different spilled oils,which remains one of the keys to optical remote sensing of oil spills.Optical remotely sensed images of oil spills are inherently multidimensional and embedded with a complex knowledge framework.This complexity often hinders the effectiveness of mechanistic algorithms across varied scenarios.Although optical remote-sensing theory for oil spills has advanced,the scarcity of curated datasets and the difficulty of collecting them limit their usefulness for training deep learning models.This study introduces a data expansion strategy that utilizes the Segment Anything Model(SAM),effectively bridging the gap between traditional mechanism algorithms and emergent self-adaptive deep learning models.Optical dimension reduction is achieved through standardized preprocessing processes that address the decipherable properties of the input image.After preprocessing,SAM can swiftly and accurately segment spilled oil in images.The unified AI-based workflow significantly accelerates labeled-dataset creation and has proven effective for both rapid emergency intelligence during spill incidents and the rapid mapping and classification of oil footprints across China’s coastal waters.Our results show that coupling a remote sensing mechanism with a foundation model enables near-real-time,large-scale monitoring of complex surface slicks and offers guidance for the next generation of detection and quantification algorithms.展开更多
Imaging hyperspectral technology has distinctive advantages of non-destructive and non-contact measurement,and the integration of spectral and spatial data.These characteristics present new methodologies for intellige...Imaging hyperspectral technology has distinctive advantages of non-destructive and non-contact measurement,and the integration of spectral and spatial data.These characteristics present new methodologies for intelligent geological sensing in tunnels and other underground engineering projects.However,the in situ acquisition and rapid classification of hyperspectral images in underground still faces great challenges,including the difficulty in obtaining uniform hyperspectral images and the complexity of deploying sophisticated models on mobile platforms.This study proposes an intelligent lithology identification method based on partition feature extraction of hyperspectral images.Firstly,pixel-level hyperspectral information from representative lithological regions is extracted and fused to obtain rock hyperspectral image partition features.Subsequently,an SG-SNV-PCA-DNN(SSPD)model specifically designed for optimizing rock hyperspectral data,performing spectral dimensionality reduction,and identifying lithology is integrated.In an experimental study involving 3420 hyperspectral images,the SSPD identification model achieved the highest accuracy in the testing set,reaching 98.77%.Moreover,the speed of the SSPD model was found to be 18.5%faster than that of the unprocessed model,with an accuracy improvement of 5.22%.In contrast,the ResNet-101 model,used for point-by-point identification based on non-partitioned features,achieved a maximum accuracy of 97.86%in the testing set.In addition,the partition feature extraction methods significantly reduce computational complexity.An objective evaluation of various models demonstrated that the SSPD model exhibited superior performance,achieving a precision(P)of 99.46%,a recall(R)of 99.44%,and F1 score(F1)of 99.45%.Additionally,a pioneering in situ detection work was carried out in a tunnel using underground hyperspectral imaging technology.展开更多
Unmanned Aerial Vehicles(UAVs)are increasingly employed in traffic surveillance,urban planning,and infrastructure monitoring due to their cost-effectiveness,flexibility,and high-resolution imaging.However,vehicle dete...Unmanned Aerial Vehicles(UAVs)are increasingly employed in traffic surveillance,urban planning,and infrastructure monitoring due to their cost-effectiveness,flexibility,and high-resolution imaging.However,vehicle detection and classification in aerial imagery remain challenging due to scale variations from fluctuating UAV altitudes,frequent occlusions in dense traffic,and environmental noise,such as shadows and lighting inconsistencies.Traditional methods,including sliding-window searches and shallow learning techniques,struggle with computational inefficiency and robustness under dynamic conditions.To address these limitations,this study proposes a six-stage hierarchical framework integrating radiometric calibration,deep learning,and classical feature engineering.The workflow begins with radiometric calibration to normalize pixel intensities and mitigate sensor noise,followed by Conditional Random Field(CRF)segmentation to isolate vehicles.YOLOv9,equipped with a bi-directional feature pyramid network(BiFPN),ensures precise multi-scale object detection.Hybrid feature extraction employs Maximally Stable Extremal Regions(MSER)for stable contour detection,Binary Robust Independent Elementary Features(BRIEF)for texture encoding,and Affine-SIFT(ASIFT)for viewpoint invariance.Quadratic Discriminant Analysis(QDA)enhances feature discrimination,while a Probabilistic Neural Network(PNN)performs Bayesian probability-based classification.Tested on the Roundabout Aerial Imagery(15,474 images,985K instances)and AU-AIR(32,823 instances,7 classes)datasets,the model achieves state-of-the-art accuracy of 95.54%and 94.14%,respectively.Its superior performance in detecting small-scale vehicles and resolving occlusions highlights its potential for intelligent traffic systems.Future work will extend testing to nighttime and adverse weather conditions while optimizing real-time UAV inference.展开更多
Extracting building contours from aerial images is a fundamental task in remote sensing.Current building extraction methods cannot accurately extract building contour information and have errors in extracting small-sc...Extracting building contours from aerial images is a fundamental task in remote sensing.Current building extraction methods cannot accurately extract building contour information and have errors in extracting small-scale buildings.This paper introduces a novel dense feature iterative(DFI)fusion network,denoted as DFINet,for extracting building contours.The network uses a DFI decoder to fuse semantic information at different scales and learns the building contour knowledge,producing the last features through iterative fusion.The dense feature fusion(DFF)module combines features at multiple scales.We employ the contour reconstruction(CR)module to access the final predictions.Extensive experiments validate the effectiveness of the DFINet on two different remote sensing datasets,INRIA aerial image dataset and Wuhan University(WHU)building dataset.On the INRIA aerial image dataset,our method achieves the highest intersection over union(IoU),overall accuracy(OA)and F 1 scores compared to other state-of-the-art methods.展开更多
基金funded by the Hainan Province Science and Technology Special Fund under Grant ZDYF2024GXJS292.
文摘Deep learning has made significant progress in the field of oriented object detection for remote sensing images.However,existing methods still face challenges when dealing with difficult tasks such as multi-scale targets,complex backgrounds,and small objects in remote sensing.Maintaining model lightweight to address resource constraints in remote sensing scenarios while improving task completion for remote sensing tasks remains a research hotspot.Therefore,we propose an enhanced multi-scale feature extraction lightweight network EM-YOLO based on the YOLOv8s architecture,specifically optimized for the characteristics of large target scale variations,diverse orientations,and numerous small objects in remote sensing images.Our innovations lie in two main aspects:First,a dynamic snake convolution(DSC)is introduced into the backbone network to enhance the model’s feature extraction capability for oriented targets.Second,an innovative focusing-diffusion module is designed in the feature fusion neck to effectively integrate multi-scale feature information.Finally,we introduce Layer-Adaptive Sparsity for magnitude-based Pruning(LASP)method to perform lightweight network pruning to better complete tasks in resource-constrained scenarios.Experimental results on the lightweight platform Orin demonstrate that the proposed method significantly outperforms the original YOLOv8s model in oriented remote sensing object detection tasks,and achieves comparable or superior performance to state-of-the-art methods on three authoritative remote sensing datasets(DOTA v1.0,DOTA v1.5,and HRSC2016).
基金funded by the National Natural Science Foundation of China(42161049,41761019,41061052).
文摘The rapid economic development that the Hotan Oasis in Xinjiang Uygur Autonomous Region,China has undergone in recent years may face some challenges in its ecological environment.Therefore,an analysis of the spatiotemporal changes in ecological environment of the Hotan Oasis is important for its sustainable development.First,we constructed an improved remote sensing-based ecological index(RSEI)in 1990,1995,2000,2005,2010,2015 and 2020 on the Google Earth Engine(GEE)platform and implemented change detection for their spatial distribution.Second,we performed a spatial autocorrelation analysis on RSEI distribution map and used land-use and land-cover change(LUCC)data to analyze the reasons of RSEI changes.Finally,we investigated the applicability of improved RSEI to arid area.The results showed that mean of RSEI rose from 0.41 to 0.50,showing a slight upward trend.During the 30-a period,2.66% of the regions improved significantly,10.74% improved moderately and 32.21% improved slightly,respectively.The global Moran's I were 0.891,0.889,0.847 and 0.777 for 1990,2000,2010 and 2020,respectively,and the local indicators of spatial autocorrelation(LISA)distribution map showed that the high-high cluster was mainly distributed in the central part of the Hotan Oasis,and the low-low cluster was mainly distributed in the outer edge of the oasis.RSEI at the periphery of the oasis changes from low to high with time,with the fragmentation of RSEI distribution within the oasis increasing.Its distribution and changes are predominantly driven by anthropologic factors,including the expansion of artificial oasis into the desert,the replacement of desert ecosystems by farmland ecosystems,and the increase in the distribution of impervious surfaces.The improved RSEI can reflect the eco-environmental quality effectively of the oasis in arid area with relatively high applicability.The high efficiency exhibited with this approach makes it convenient for rapid,high frequency and macroscopic monitoring of eco-environmental quality in study area.
文摘Water on the Earth’s surface is an essential part of the hydrological cycle. Water resources include surface waters, groundwater, lakes, inland waters, rivers, coastal waters, and aquifers. Monitoring lake dynamics is critical to favor sustainable management of water resources on Earth. In cryosphere, lake ice cover is a robust indicator of local climate variability and change. Therefore, it is necessary to review recent methods, technologies, and satellite sensors employed for the extraction of lakes from satellite imagery. The present review focuses on the comprehensive evaluation of existing methods for extraction of lake or water body features from remotely sensed optical data. We summarize pixel-based, object-based, hybrid, spectral index based, target and spectral matching methods employed in extracting lake features in urban and cryospheric environments. To our knowledge, almost all of the published research studies on the extraction of surface lakes in cryospheric environments have essentially used satellite remote sensing data and geospatial methods. Satellite sensors of varying spatial, temporal and spectral resolutions have been used to extract and analyze the information regarding surface water. Multispectral remote sensing has been widely utilized in cryospheric studies and has employed a variety of electro-optical satellite sensor systems for characterization and extraction of various cryospheric features, such as glaciers, sea ice, lakes and rivers, the extent of snow and ice, and icebergs. It is apparent that the most common methods for extracting water bodies use single band-based threshold methods, spectral index ratio (SIR)-based multiband methods, image segmentation methods, spectral-matching methods, and target detection methods (unsupervised, supervised and hybrid). A Synergetic fusion of various remote sensing methods is also proposed to improve water information extraction accuracies. The methods developed so far are not generic rather they are specific to either the location or satellite imagery or to the type of the feature to be extracted. Lots of factors are responsible for leading to inaccurate results of lake-feature extraction in cryospheric regions, e.g. the mountain shadow which also appears as a dark pixel is often misclassified as an open lake. The methods which are working well in the cryospheric environment for feature extraction or landcover classification does not really guarantee that they will be working in the same manner for the urban environment. Thus, in coming years, it is expected that much of the work will be done on object-based approach or hybrid approach involving both pixel as well as object-based technology. A more accurate, versatile and robust method is necessary to be developed that would work independent of geographical location (for both urban and cryosphere) and type of optical sensor.
文摘Traditional methods of extracting the ocean wave eddy information from remotely sensed imagery mainly use the edge detection technology such as Canny and Hough operators. However, due to the complexities of ocean eddies and image itself, it is sometimes difficult to successfully detect ocean eddies using these methods. A mnltifractal filtering technology is proposed for extraction of ocean eddies and demonstrated using NASA MODIS, SeaWiFS and NOAA satellite data set in the typical area, such as ocean west boundary current. Results showed that the new method has a superior performance over the traditional methods.
基金Project(11JJ6029)supported by Natural Science Foundation of Hunan Province,ChinaProject(2011QNZT006)supported by Fundamental Research Funds for the Central Universities,China
文摘Remote sensing technique plays an important role in geological prospecting in Altay because of the remote location and steep terrain with mountains.Pegmatite has important implications for metallogenic prospecting as most of rare metals occurs in it.Pegmatite information from optical and radar images was extracted,and the spatial distribution and scale of pegmatite were generalized in Azubai,Altay.Three mining targets,that is,Halon-Azubai,Kuermutu-Tuyibaguo and Zhuolute-Akuoyige,were delineated based on the analysis of pegmatite information,structure interpretation and other geological data.
基金Project(40174003)supported by the National Natural Science Foundation of China
文摘The classification of hyperspectral remote sensing data is an important problem theoretically and practically.With the increase of spectral bands,the separability of objects on remote sensing image should be improved.But the effects of traditional algorithm on feature extraction such as principal component analysis(PCA)is not so good for hyperspectral image.The key problem is that PCA can only represent the linear structure of data set;while the data clouds of different objects on hyperspectral image usually distribute on a nonlinear manifold.This paper established an algorithm of nonlinear feature extraction named as nonlinear principal poly lines,based on the algorithm,a classifier is constructed and the classification accuracy of hyperspectral image can be improved.
基金National Natural Science Foundation of China(Nos.61673017,61403398)and Natural Science Foundation of Shaanxi Province(Nos.2017JM6077,2018ZDXM-GY-039)。
文摘According to the characteristics of the road features,an Encoder-Decoder deep semantic segmentation network is designed for the road extraction of remote sensing images.Firstly,as the features of the road target are rich in local details and simple in semantic features,an Encoder-Decoder network with shallow layers and high resolution is designed to improve the ability to represent detail information.Secondly,as the road area is a small proportion in remote sensing images,the cross-entropy loss function is improved,which solves the imbalance between positive and negative samples in the training process.Experiments on large road extraction datasets show that the proposed method gets the recall rate 83.9%,precision 82.5%and F1-score 82.9%,which can extract the road targets in remote sensing images completely and accurately.The Encoder-Decoder network designed in this paper performs well in the road extraction task and needs less artificial participation,so it has a good application prospect.
基金Sponsoreds by the National Natural Science Foundation of China (Grant No. 60575016)
文摘While executing tasks such as ocean pollution monitoring,maritime rescue,geographic mapping,and automatic navigation utilizing remote sensing images,the coastline feature should be determined.Traditional methods are not satisfactory to extract coastline in high-resolution panchromatic remote sensing image.Active contour model,also called snakes,have proven useful for interactive specification of image contours,so it is used as an effective coastlines extraction technique.Firstly,coastlines are detected by water segmentation and boundary tracking,which are considered initial contours to be optimized through active contour model.As better energy functions are developed,the power assist of snakes becomes effective.New internal energy has been done to reduce problems caused by convergence to local minima,and new external energy can greatly enlarge the capture region around features of interest.After normalization processing,energies are iterated using greedy algorithm to accelerate convergence rate.The experimental results encompassed examples in images and demonstrated the capabilities and efficiencies of the improvement.
文摘Automatic extraction of road and linear structure from remote sensing images is a very important problem. This paper analyses several existing methods of the automatic road and linear structure extraction by using some multi-spectral remote sensing images acquired from different spatial resolutions, districts and road characteristics. Their advantages and disadvantages have been generalized.
文摘Road traffic is the important driving factor for economic and social development. With the rapid increase of vehicle population, road traffic problems such as traffic jam and traffic accident have become the bottleneck which restricts economic development. In recent years, natural disasters frequently occur in China. Therefore, it is essential to extract road information to compute the degree of road damage for traffic emergency management. A road extraction method based on region growing and mathematical morphology from remote sensing images is proposed in this paper. According to the road features, the remote sensing image is preprocessed to separate road regions from non-road regions preliminarily. After image thresholding, region growing algorithm is used to extract connected regions. Then we sort connected regions by area to exclude the small regions which are probably non-road objects. Finally, the mathematical morphology algorithm is used to fill the holes inside the road regions. The experimental results show that the method proposed can effectively extract roads from remote sensing images. This research also has broad prospects in dealing with traffic emergency management by the government.
基金This work was supported in part by the Key Project of Natural Science Research of Anhui Provincial Department of Education under Grant KJ2017A416in part by the Fund of National Sensor Network Engineering Technology Research Center(No.NSNC202103).
文摘When existing deep learning models are used for road extraction tasks from high-resolution images,they are easily affected by noise factors such as tree and building occlusion and complex backgrounds,resulting in incomplete road extraction and low accuracy.We propose the introduction of spatial and channel attention modules to the convolutional neural network ConvNeXt.Then,ConvNeXt is used as the backbone network,which cooperates with the perceptual analysis network UPerNet,retains the detection head of the semantic segmentation,and builds a new model ConvNeXt-UPerNet to suppress noise interference.Training on the open-source DeepGlobe and CHN6-CUG datasets and introducing the DiceLoss on the basis of CrossEntropyLoss solves the problem of positive and negative sample imbalance.Experimental results show that the new network model can achieve the following performance on the DeepGlobe dataset:79.40%for precision(Pre),97.93% for accuracy(Acc),69.28% for intersection over union(IoU),and 83.56% for mean intersection over union(MIoU).On the CHN6-CUG dataset,the model achieves the respective values of 78.17%for Pre,97.63%for Acc,65.4% for IoU,and 81.46% for MIoU.Compared with other network models,the fused ConvNeXt-UPerNet model can extract road information better when faced with the influence of noise contained in high-resolution remote sensing images.It also achieves multiscale image feature information with unified perception,ultimately improving the generalization ability of deep learning technology in extracting complex roads from high-resolution remote sensing images.
基金the National Natural Science Foundation of China(42001408,61806097).
文摘Significant advancements have been achieved in road surface extraction based on high-resolution remote sensingimage processing. Most current methods rely on fully supervised learning, which necessitates enormous humaneffort to label the image. Within this field, other research endeavors utilize weakly supervised methods. Theseapproaches aim to reduce the expenses associated with annotation by leveraging sparsely annotated data, such asscribbles. This paper presents a novel technique called a weakly supervised network using scribble-supervised andedge-mask (WSSE-net). This network is a three-branch network architecture, whereby each branch is equippedwith a distinct decoder module dedicated to road extraction tasks. One of the branches is dedicated to generatingedge masks using edge detection algorithms and optimizing road edge details. The other two branches supervise themodel’s training by employing scribble labels and spreading scribble information throughout the image. To addressthe historical flaw that created pseudo-labels that are not updated with network training, we use mixup to blendprediction results dynamically and continually update new pseudo-labels to steer network training. Our solutiondemonstrates efficient operation by simultaneously considering both edge-mask aid and dynamic pseudo-labelsupport. The studies are conducted on three separate road datasets, which consist primarily of high-resolutionremote-sensing satellite photos and drone images. The experimental findings suggest that our methodologyperforms better than advanced scribble-supervised approaches and specific traditional fully supervised methods.
文摘Based on low-altitude remote sensing images,this paper established sample set of typical river vegetation elements and proposed river vegetation extraction technical solution to adaptively extract typical vegetation elements of river basins.The main research of this paper were as follows:(1)a typical vegetation extraction sample set based on low-altitude remote sensing images was established.(2)A low-altitude remote sensing image vegetation extraction model based on the focus perception module was designed to realize the end-to-end automatic extraction of different types of vegetation areas of low-altitude remote sensing images to fully learn the spectral spatial texture information and deep semantic information of the images.(3)By comparison with the baseline method,baseline method with embedded focus perception module showed an improvement in the precision by 7.37%and mIoU by 49.49%.Through visual interpretation and quantitative calculation analysis,the typical river vegetation adaptive extraction network has effectiveness and generalization ability,consistent with the needs of practical applications of vegetation extraction.
文摘This paper presents algorithmic components and corresponding software routines for extracting shoreline features from remote sensing imagery and LiDAR data. Conceptually, shoreline features are treated as boundary lines between land objects and water objects. Numerical algorithms have been identified and de-vised to segment and classify remote sensing imagery and LiDAR data into land and water pixels, to form and enhance land and water objects, and to trace and vectorize the boundaries between land and water ob-jects as shoreline features. A contouring routine is developed as an alternative method for extracting shore-line features from LiDAR data. While most of numerical algorithms are implemented using C++ program-ming language, some algorithms use available functions of ArcObjects in ArcGIS. Based on VB .NET and ArcObjects programming, a graphical user’s interface has been developed to integrate and organize shoreline extraction routines into a software package. This product represents the first comprehensive software tool dedicated for extracting shorelines from remotely sensed data. Radarsat SAR image, QuickBird multispectral image, and airborne LiDAR data have been used to demonstrate how these software routines can be utilized and combined to extract shoreline features from different types of input data sources: panchromatic or single band imagery, color or multi-spectral image, and LiDAR elevation data. Our software package is freely available for the public through the internet.
基金supported by the National Natural Science Foundation of China(Nos.61906168,62202429 and 62272267)the Zhejiang Provincial Natural Science Foundation of China(No.LY23F020023)the Construction of Hubei Provincial Key Laboratory for Intelligent Visual Monitoring of Hydropower Projects(No.2022SDSJ01)。
文摘Accurately identifying building distribution from remote sensing images with complex background information is challenging.The emergence of diffusion models has prompted the innovative idea of employing the reverse denoising process to distill building distribution from these complex backgrounds.Building on this concept,we propose a novel framework,building extraction diffusion model(BEDiff),which meticulously refines the extraction of building footprints from remote sensing images in a stepwise fashion.Our approach begins with the design of booster guidance,a mechanism that extracts structural and semantic features from remote sensing images to serve as priors,thereby providing targeted guidance for the diffusion process.Additionally,we introduce a cross-feature fusion module(CFM)that bridges the semantic gap between different types of features,facilitating the integration of the attributes extracted by booster guidance into the diffusion process more effectively.Our proposed BEDiff marks the first application of diffusion models to the task of building extraction.Empirical evidence from extensive experiments on the Beijing building dataset demonstrates the superior performance of BEDiff,affirming its effectiveness and potential for enhancing the accuracy of building extraction in complex urban landscapes.
基金funded by the Major R&D and Achievement Transformation Projects of Xizang(CGZH2024000416)Science and Technology Program of Xizang(XZ202402ZD0001)Major R&D and Achievement Transformation Projects of Qinghai(2022-QY-224)。
文摘Previous studies have often focused on monitoring grassland growth as the primary target of remote sensing investigations on grassland ecological restoration in the northern Tibetan Plateau,overlooking the crucial role played by gravel in the ecological restoration of these grasslands.This study utilizes supervised classification and segmentation techniques based on machine learning to extract gravel morphology profiles from field-sampled plot images and calculate their characteristic parameters.Employing a multivariate linear approach combined with Principal Component Analysis(PCA),a model for inferring gravel characteristic parameters is constructed.Statistical features,particle size characteristics,and spatial distribution patterns of gravel are analyzed.Results reveal that gravel predominantly exhibit sub-rounded shapes,with 80%classified as fine gravel.The coefficients of determination(R2)between gravel particle size and coverage,perimeter,and area are 0.444,0.724,and 0.557,respectively,indicating linear relationships.The cumulative contribution rate of the top five remote sensing factors is 95.44%,with the first geological factor contributing 77.64%,collectively reflecting the primary information of the 20 factors used.Modeling shows that areas with larger gravel particle sizes correspond to increased perimeter and coverage.Gravels in the Nagqu Prefecture of northern Xizang have a particle size range of 4-8 mm,primarily comprising fine gravel which accounts for 94.61%.These findings provide a scientific basis for extracting gravel characteristic parameters and understanding their spatial distribution variations in the northern Tibetan Plateau.
基金The National Natural Science Foundation of China under contract No.42371380the National Key Research and Development Program of China under contract No.2023YFC2811800the Fundamental Research Funds for the Central Universities under contract No.0904-14380035.
文摘Efficient segmentation of oiled pixels in optical remotely sensed images is the precondition of optical identification and classification of different spilled oils,which remains one of the keys to optical remote sensing of oil spills.Optical remotely sensed images of oil spills are inherently multidimensional and embedded with a complex knowledge framework.This complexity often hinders the effectiveness of mechanistic algorithms across varied scenarios.Although optical remote-sensing theory for oil spills has advanced,the scarcity of curated datasets and the difficulty of collecting them limit their usefulness for training deep learning models.This study introduces a data expansion strategy that utilizes the Segment Anything Model(SAM),effectively bridging the gap between traditional mechanism algorithms and emergent self-adaptive deep learning models.Optical dimension reduction is achieved through standardized preprocessing processes that address the decipherable properties of the input image.After preprocessing,SAM can swiftly and accurately segment spilled oil in images.The unified AI-based workflow significantly accelerates labeled-dataset creation and has proven effective for both rapid emergency intelligence during spill incidents and the rapid mapping and classification of oil footprints across China’s coastal waters.Our results show that coupling a remote sensing mechanism with a foundation model enables near-real-time,large-scale monitoring of complex surface slicks and offers guidance for the next generation of detection and quantification algorithms.
基金support from the National Natural Science Foundation of China(Grant Nos.52379103,52279103)the Natural Science Foundation of Shandong Province(Grant No.ZR2023YQ049).
文摘Imaging hyperspectral technology has distinctive advantages of non-destructive and non-contact measurement,and the integration of spectral and spatial data.These characteristics present new methodologies for intelligent geological sensing in tunnels and other underground engineering projects.However,the in situ acquisition and rapid classification of hyperspectral images in underground still faces great challenges,including the difficulty in obtaining uniform hyperspectral images and the complexity of deploying sophisticated models on mobile platforms.This study proposes an intelligent lithology identification method based on partition feature extraction of hyperspectral images.Firstly,pixel-level hyperspectral information from representative lithological regions is extracted and fused to obtain rock hyperspectral image partition features.Subsequently,an SG-SNV-PCA-DNN(SSPD)model specifically designed for optimizing rock hyperspectral data,performing spectral dimensionality reduction,and identifying lithology is integrated.In an experimental study involving 3420 hyperspectral images,the SSPD identification model achieved the highest accuracy in the testing set,reaching 98.77%.Moreover,the speed of the SSPD model was found to be 18.5%faster than that of the unprocessed model,with an accuracy improvement of 5.22%.In contrast,the ResNet-101 model,used for point-by-point identification based on non-partitioned features,achieved a maximum accuracy of 97.86%in the testing set.In addition,the partition feature extraction methods significantly reduce computational complexity.An objective evaluation of various models demonstrated that the SSPD model exhibited superior performance,achieving a precision(P)of 99.46%,a recall(R)of 99.44%,and F1 score(F1)of 99.45%.Additionally,a pioneering in situ detection work was carried out in a tunnel using underground hyperspectral imaging technology.
基金supported through Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R508)Princess Nourah bint Abdulrahman University,Riyadh,Saudi ArabiaThe research team thanks the Deanship of Graduate Studies and Scientific Research at Najran University for supporting the research project through the Nama’a program,with the project code NU/GP/SERC/13/18-5.
文摘Unmanned Aerial Vehicles(UAVs)are increasingly employed in traffic surveillance,urban planning,and infrastructure monitoring due to their cost-effectiveness,flexibility,and high-resolution imaging.However,vehicle detection and classification in aerial imagery remain challenging due to scale variations from fluctuating UAV altitudes,frequent occlusions in dense traffic,and environmental noise,such as shadows and lighting inconsistencies.Traditional methods,including sliding-window searches and shallow learning techniques,struggle with computational inefficiency and robustness under dynamic conditions.To address these limitations,this study proposes a six-stage hierarchical framework integrating radiometric calibration,deep learning,and classical feature engineering.The workflow begins with radiometric calibration to normalize pixel intensities and mitigate sensor noise,followed by Conditional Random Field(CRF)segmentation to isolate vehicles.YOLOv9,equipped with a bi-directional feature pyramid network(BiFPN),ensures precise multi-scale object detection.Hybrid feature extraction employs Maximally Stable Extremal Regions(MSER)for stable contour detection,Binary Robust Independent Elementary Features(BRIEF)for texture encoding,and Affine-SIFT(ASIFT)for viewpoint invariance.Quadratic Discriminant Analysis(QDA)enhances feature discrimination,while a Probabilistic Neural Network(PNN)performs Bayesian probability-based classification.Tested on the Roundabout Aerial Imagery(15,474 images,985K instances)and AU-AIR(32,823 instances,7 classes)datasets,the model achieves state-of-the-art accuracy of 95.54%and 94.14%,respectively.Its superior performance in detecting small-scale vehicles and resolving occlusions highlights its potential for intelligent traffic systems.Future work will extend testing to nighttime and adverse weather conditions while optimizing real-time UAV inference.
基金National Natural Science Foundation of China(No.61903078)Fundamental Research Funds for the Central Universities,China(No.2232021A-10)+1 种基金Shanghai Sailing Program,China(No.22YF1401300)Natural Science Foundation of Shanghai,China(No.20ZR1400400)。
文摘Extracting building contours from aerial images is a fundamental task in remote sensing.Current building extraction methods cannot accurately extract building contour information and have errors in extracting small-scale buildings.This paper introduces a novel dense feature iterative(DFI)fusion network,denoted as DFINet,for extracting building contours.The network uses a DFI decoder to fuse semantic information at different scales and learns the building contour knowledge,producing the last features through iterative fusion.The dense feature fusion(DFF)module combines features at multiple scales.We employ the contour reconstruction(CR)module to access the final predictions.Extensive experiments validate the effectiveness of the DFINet on two different remote sensing datasets,INRIA aerial image dataset and Wuhan University(WHU)building dataset.On the INRIA aerial image dataset,our method achieves the highest intersection over union(IoU),overall accuracy(OA)and F 1 scores compared to other state-of-the-art methods.
