The exploration of building detection plays an important role in urban planning,smart city and military.Aiming at the problem of high overlapping ratio of detection frames for dense building detection in high resoluti...The exploration of building detection plays an important role in urban planning,smart city and military.Aiming at the problem of high overlapping ratio of detection frames for dense building detection in high resolution remote sensing images,we present an effective YOLOv3 framework,corner regression-based YOLOv3(Correg-YOLOv3),to localize dense building accurately.This improved YOLOv3 algorithm establishes a vertex regression mechanism and an additional loss item about building vertex offsets relative to the center point of bounding box.By extending output dimensions,the trained model is able to output the rectangular bounding boxes and the building vertices meanwhile.Finally,we evaluate the performance of the Correg-YOLOv3 on our self-produced data set and provide a comparative analysis qualitatively and quantitatively.The experimental results achieve high performance in precision(96.45%),recall rate(95.75%),F1 score(96.10%)and average precision(98.05%),which were 2.73%,5.4%,4.1%and 4.73%higher than that of YOLOv3.Therefore,our proposed algorithm effectively tackles the problem of dense building detection in high resolution images.展开更多
To address the issue of imbalanced detection performance and detection speed in current mainstream object detection algorithms for optical remote sensing images,this paper proposes a multi-scale object detection model...To address the issue of imbalanced detection performance and detection speed in current mainstream object detection algorithms for optical remote sensing images,this paper proposes a multi-scale object detection model for remote sensing images on complex backgrounds,called DI-YOLO,based on You Only Look Once v7-tiny(YOLOv7-tiny).Firstly,to enhance the model’s ability to capture irregular-shaped objects and deformation features,as well as to extract high-level semantic information,deformable convolutions are used to replace standard convolutions in the original model.Secondly,a Content Coordination Attention Feature Pyramid Network(CCA-FPN)structure is designed to replace the Neck part of the original model,which can further perceive relationships between different pixels,reduce feature loss in remote sensing images,and improve the overall model’s ability to detect multi-scale objects.Thirdly,an Implicitly Efficient Decoupled Head(IEDH)is proposed to increase the model’s flexibility,making it more adaptable to complex detection tasks in various scenarios.Finally,the Smoothed Intersection over Union(SIoU)loss function replaces the Complete Intersection over Union(CIoU)loss function in the original model,resulting in more accurate prediction of bounding boxes and continuous model optimization.Experimental results on the High-Resolution Remote Sensing Detection(HRRSD)dataset demonstrate that the proposed DI-YOLO model outperforms mainstream target detection algorithms in terms of mean Average Precision(mAP)for optical remote sensing image detection.Furthermore,it achieves Frames Per Second(FPS)of 138.9,meeting fast and accurate detection requirements.展开更多
In image processing, one of the most important steps is image segmentation. The objects in remote sensing images often have to be detected in order toperform next steps in image processing. Remote sensing images usua...In image processing, one of the most important steps is image segmentation. The objects in remote sensing images often have to be detected in order toperform next steps in image processing. Remote sensing images usually havelarge size and various spatial resolutions. Thus, detecting objects in remote sensing images is very complicated. In this paper, we develop a model to detectobjects in remote sensing images based on the combination of picture fuzzy clustering and MapReduce method (denoted as MPFC). Firstly, picture fuzzy clustering is applied to segment the input images. Then, MapReduce is used to reducethe runtime with the guarantee of quality. To convert data for MapReduce processing, two new procedures are introduced, including Map_PFC and Reduce_PFC.The formal representation and details of two these procedures are presented in thispaper. The experiments on satellite image and remote sensing image datasets aregiven to evaluate proposed model. Validity indices and time consuming are usedto compare proposed model to picture fuzzy clustering model. The values ofvalidity indices show that picture fuzzy clustering integrated to MapReduce getsbetter quality of segmentation than using picture fuzzy clustering only. Moreover,on two selected image datasets, the run time of MPFC model is much less thanthat of picture fuzzy clustering.展开更多
alient object detection aims at identifying the visually interesting object regions that are consistent with human perception. Multispectral remote sensing images provide rich radiometric information in revealing the ...alient object detection aims at identifying the visually interesting object regions that are consistent with human perception. Multispectral remote sensing images provide rich radiometric information in revealing the physical properties of the observed objects, which leads to great potential to perform salient object detection for remote sensing images. Conventional salient object detection methods often employ handcrafted features to predict saliency by evaluating the pixel-wise or superpixel-wise contrast. With the recent use of deep learning framework, in particular, fully convolutional neural networks, there has been profound progress in visual saliency detection. However, this success has not been extended to multispectral remote sensing images, and existing multispectral salient object detection methods are still mainly based on handcrafted features, essentially due to the difficulties in image acquisition and labeling. In this paper, we propose a novel deep residual network based on a top-down model, which is trained in an end-to-end manner to tackle the above issues in multispectral salient object detection. Our model effectively exploits the saliency cues at different levels of the deep residual network. To overcome the limited availability of remote sensing images in training of our deep residual network, we also introduce a new spectral image reconstruction model that can generate multispectral images from RGB images. Our extensive experimental results using both multispectral and RGB salient object detection datasets demonstrate a significant performance improvement of more than 10% improvement compared with the state-of-the-art methods.展开更多
To retrieve the object region efficaciously from massive remote sensing image database, a model for content-based retrieval of remote sensing image is given according to the characters of remote sensing image applicat...To retrieve the object region efficaciously from massive remote sensing image database, a model for content-based retrieval of remote sensing image is given according to the characters of remote sensing image application firstly, and then the algorithm adopted for feature extraction and multidimensional indexing, and relevance feedback by this model are analyzed in detail. Finally, the contents intending to be researched about this model are proposed.展开更多
Most of the current object detection algorithms use pretrained models that are trained on ImageNet and then fine-tuned in the network,which can achieve good performance in terms of general object detectors.However,in ...Most of the current object detection algorithms use pretrained models that are trained on ImageNet and then fine-tuned in the network,which can achieve good performance in terms of general object detectors.However,in the field of remote sensing image object detection,as pretrained models are significantly different from remote sensing data,it is meaningful to explore a train-fromscratch technique for remote sensing images.This paper proposes an object detection framework trained from scratch,SRS-Net,and describes the design of a densely connected backbone network to provide integrated hidden layer supervision for the convolution module.Then,two necessary improvement principles are proposed:studying the role of normalization in the network structure,and improving data augmentation methods for remote sensing images.To evaluate the proposed framework,we performed many ablation experiments on the DIOR,DOTA,and AS datasets.The results show that whether using the improved backbone network,the normalization method or training data enhancement strategy,the performance of the object detection network trained from scratch increased.These principles compensate for the lack of pretrained models.Furthermore,we found that SRS-Net could achieve similar to or slightly better performance than baseline methods,and surpassed most advanced general detectors.展开更多
The following article has been retracted due to the investigation of complaints received against it. The Editorial Board found that substantial portions of the text came from other published papers. The scientific com...The following article has been retracted due to the investigation of complaints received against it. The Editorial Board found that substantial portions of the text came from other published papers. The scientific community takes a very strong view on this matter, and the Journal of Geographic Information System treats all unethical behavior such as plagiarism seriously. This paper published in Vol.4 No.3 273-278, 2012, has been removed from this site.展开更多
Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention.However,due to interference occasioned by density,overlap,and coverage,the tiny object detection in re...Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention.However,due to interference occasioned by density,overlap,and coverage,the tiny object detection in remote sensing images has always been a difficult problem.Therefore,we propose a novel TO–YOLOX(Tiny Object–You Only Look Once)model.TO–YOLOX possesses a MiSo(Multiple-in-Singleout)feature fusion structure,which exhibits a spatial-shift structure,and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images.TO–YOLOX utilizes an adaptive IOU-T(Intersection Over Uni-Tiny)loss to enhance the localization accuracy of tiny objects,and it applies attention mechanism Group-CBAM(group-convolutional block attention module)to enhance the perception of tiny objects in remote sensing images.To verify the effectiveness and efficiency of TO–YOLOX,we utilized three aerial-photography tiny object detection datasets,namely VisDrone2021,Tiny Person,and DOTA–HBB,and the following mean average precision(mAP)values were recorded,respectively:45.31%(+10.03%),28.9%(+9.36%),and 63.02%(+9.62%).With respect to recognizing tiny objects,TO–YOLOX exhibits a stronger ability compared with Faster R-CNN,RetinaNet,YOLOv5,YOLOv6,YOLOv7,and YOLOX,and the proposed model exhibits fast computation.展开更多
Efficient and accurate access to coastal land cover information is of great significance for marine disaster prevention and mitigation.Although the popular and common sensors of land resource satellites provide free a...Efficient and accurate access to coastal land cover information is of great significance for marine disaster prevention and mitigation.Although the popular and common sensors of land resource satellites provide free and valuable images to map the land cover,coastal areas often encounter significant cloud cover,especially in tropical areas,which makes the classification in those areas non-ideal.To solve this problem,we proposed a framework of combining medium-resolution optical images and synthetic aperture radar(SAR)data with the recently popular object-based image analysis(OBIA)method and used the Landsat Operational Land Imager(OLI)and Phased Array type L-band Synthetic Aperture Radar(PALSAR)images acquired in Singapore in 2017 as a case study.We designed experiments to confirm two critical factors of this framework:one is the segmentation scale that determines the average object size,and the other is the classification feature.Accuracy assessments of the land cover indicated that the optimal segmentation scale was between 40 and 80,and the features of the combination of OLI and SAR resulted in higher accuracy than any individual features,especially in areas with cloud cover.Based on the land cover generated by this framework,we assessed the vulnerability of the marine disasters of Singapore in 2008 and 2017 and found that the high-vulnerability areas mainly located in the southeast and increased by 118.97 km2 over the past decade.To clarify the disaster response plan for different geographical environments,we classified risk based on altitude and distance from shore.The newly increased high-vulnerability regions within 4 km offshore and below 30 m above sea level are at high risk;these regions may need to focus on strengthening disaster prevention construction.This study serves as a typical example of using remote sensing techniques for the vulnerability assessment of marine disasters,especially those in cloudy coastal areas.展开更多
In the study of oriented bounding boxes(OBB)object detection in high-resolution remote sensing images,the problem of missed and wrong detection of small targets occurs because the targets are too small and have differ...In the study of oriented bounding boxes(OBB)object detection in high-resolution remote sensing images,the problem of missed and wrong detection of small targets occurs because the targets are too small and have different orientations.Existing OBB object detection for remote sensing images,although making good progress,mainly focuses on directional modeling,while less consideration is given to the size of the object as well as the problem of missed detection.In this study,a method based on improved YOLOv8 was proposed for detecting oriented objects in remote sensing images,which can improve the detection precision of oriented objects in remote sensing images.Firstly,the ResCBAMG module was innovatively designed,which could better extract channel and spatial correlation information.Secondly,the innovative top-down feature fusion layer network structure was proposed in conjunction with the Efficient Channel Attention(ECA)attention module,which helped to capture inter-local cross-channel interaction information appropriately.Finally,we introduced an innovative ResCBAMG module between the different C2f modules and detection heads of the bottom-up feature fusion layer.This innovative structure helped the model to better focus on the target area.The precision and robustness of oriented target detection were also improved.Experimental results on the DOTA-v1.5 dataset showed that the detection Precision,mAP@0.5,and mAP@0.5:0.95 metrics of the improved model are better compared to the original model.This improvement is effective in detecting small targets and complex scenes.展开更多
Earth surveillance through aerial images allows more accurate identification and characterization of objects present on the surface from space and airborne platforms.The progression of deep learning and computer visio...Earth surveillance through aerial images allows more accurate identification and characterization of objects present on the surface from space and airborne platforms.The progression of deep learning and computer vision methods and the availability of heterogeneous multispectral remote sensing data make the field more fertile for research.With the evolution of optical sensors,aerial images are becoming more precise and larger,which leads to a new kind of problem for object detection algorithms.This paper proposes the“Sliding Region-based Convolutional Neural Network(SRCNN),”which is an extension of the Faster Region-based Convolutional Neural Network(RCNN)object detection framework to make it independent of the image’s spatial resolution and size.The sliding box strategy is used in the proposed model to segment the image while detecting.The proposed framework outperforms the state-of-the-art Faster RCNN model while processing images with significantly different spatial resolution values.The SRCNN is also capable of detecting objects in images of any size.展开更多
The majority of the population and economic activity of the northern half of Vietnam is clustered in the Red River Delta and about half of the country’s rice production takes place here. There are significant problem...The majority of the population and economic activity of the northern half of Vietnam is clustered in the Red River Delta and about half of the country’s rice production takes place here. There are significant problems associated with its geographical position and the intensive exploitation of resources by an overabundant population (population density of 962 inhabitants/km2). Some thirty years after the economic liberalization and the opening of the country to international markets, agricultural land use patterns in the Red River Delta, particularly in the coastal area, have undergone many changes. Remote sensing is a particularly powerful tool in processing and providing spatial information for monitoring land use changes. The main methodological objective is to find a solution to process the many heterogeneous coastal land use parameters, so as to describe it in all its complexity, specifically by making use of the latest European satellite data (Sentinel-2). This complexity is due to local variations in ecological conditions, but also to anthropogenic factors that directly and indirectly influence land use dynamics. The methodological objective was to develop a new Geographic Object-based Image Analysis (GEOBIA) approach for mapping coastal areas using Sentinel-2 data and Landsat 8. By developing a new segmentation, accuracy measure, in this study was determined that segmentation accuracies decrease with increasing segmentation scales and that the negative impact of under-segmentation errors significantly increases at a large scale. An Estimation of Scale Parameter (ESP) tool was then used to determine the optimal segmentation parameter values. A popular machine learning algorithms (Random Forests-RFs) is used. For all classifications algorithm, an increase in overall accuracy was observed with the full synergistic combination of available data sets.展开更多
Object recognition in very high-resolution remote sensing images is a basic problem in the field of aerial and satellite image analysis.With the development of sensor technology and aerospace remote sensing technology...Object recognition in very high-resolution remote sensing images is a basic problem in the field of aerial and satellite image analysis.With the development of sensor technology and aerospace remote sensing technology,the quality and quantity of remote sensing images are improved.Traditional recognition methods have a certain limitation in describing higher-level features,but object recognition method based on convolutional neural network(CNN)can not only deal with large scale images,but also train features automatically with high efficiency.It is mainly used on object recognition for remote sensing images.In this paper,an AlexNet CNN model is trained using 2100 remote sensing images,and correction rate can reach 97.6%after 2000 iterations.Then based on trained model,a parallel design of CNN for remote sensing images object recognition based on data-driven array processor(DDAP)is proposed.The consuming cycles are counted.Simultaneously,the proposed architecture is realized on Xilinx V6 development board,and synthesized based on SMIC 130 nm complementary metal oxid semiconductor(CMOS)technology.The experimental results show that the proposed architecture has a certain degree of parallelism to achieve the purpose of accelerating calculations.展开更多
The object-oriented information extraction technique was used to improve classification accuracy,and addressed the problem that HJ-1 CCD remote sensing images have only four spectral bands with moderate spatial resolu...The object-oriented information extraction technique was used to improve classification accuracy,and addressed the problem that HJ-1 CCD remote sensing images have only four spectral bands with moderate spatial resolution.We used two key techniques:the selection of optimum image segmentation scale and the development of an appropriate object-oriented information extraction strategy.With the principle of minimizing merge cost of merging neighboring pixels/objects,we used spatial autocorrelation index Moran's I and the variance index to select the optimum segmentation scale.The Nearest Neighborhood(NN) classifier based on sampling and a knowledge-based fuzzy classifier were used in the object-oriented information extraction strategy.In this classification step,feature optimization was used to improve information extraction accuracy using reduced data dimension.These two techniques were applied to land cover information extraction for Shanghai city using a HJ-1 CCD image.Results indicate that the information extraction accuracy of the object-oriented method was much higher than that of the pixel-based method.展开更多
Due to the bird’s eye view of remote sensing sensors,the orientational information of an object is a key factor that has to be considered in object detection.To obtain rotating bounding boxes,existing studies either ...Due to the bird’s eye view of remote sensing sensors,the orientational information of an object is a key factor that has to be considered in object detection.To obtain rotating bounding boxes,existing studies either rely on rotated anchoring schemes or adding complex rotating ROI transfer layers,leading to increased computational demand and reduced detection speeds.In this study,we propose a novel internal-external optimized convolutional neural network for arbitrary orientated object detection in optical remote sensing images.For the internal opti-mization,we designed an anchor-based single-shot head detector that adopts the concept of coarse-to-fine detection for two-stage object detection networks.The refined rotating anchors are generated from the coarse detection head module and fed into the refining detection head module with a link of an embedded deformable convolutional layer.For the external optimiza-tion,we propose an IOU balanced loss that addresses the regression challenges related to arbitrary orientated bounding boxes.Experimental results on the DOTA and HRSC2016 bench-mark datasets show that our proposed method outperforms selected methods.展开更多
Within the context of global change, marine sensitive factors or Marine Essential Climate Variables have been defined by many projects, and their sensitive spatial regions and time phases play significant roles in reg...Within the context of global change, marine sensitive factors or Marine Essential Climate Variables have been defined by many projects, and their sensitive spatial regions and time phases play significant roles in regional sea-air interactions and better understanding of their dynamic process. In this paper, we propose a cluster-based method for marine sensitive region extraction and representation. This method includes a kernel expansion algorithm for extracting marine sensitive regions, and a field-object triple form, integration of object-oriented and field-based model, for representing marine sensitive objects. Firstly, this method recognizes ENSO-related spatial patterns using empirical orthogonal decomposition of long term marine sensitive factors and correlation analysis with multiple ENSO index. The cluster kernel, defined by statistics of spatial patterns, is initialized to carry out spatial expansion and cluster mergence with spatial neighborhoods recursively, then all the related lattices with similar behavior are merged into marine sensitive regions. After this, the Field-object triple form of < O, A, F > is used to represent the marine sensitive objects, both with the discrete object with a precise extend and boundary, and the continuous field with variations dependent on spatial locations. Finally, the marine sensitive objects about sea surface temperature are extracted, represented and analyzed as a case of study, which proves the effectiveness and the efficiency of the proposed method.展开更多
Measurement of vegetation coverage on a small scale is the foundation for the monitoring of changes in vegetation coverage and of the inversion model of monitoring vegetation coverage on a large scale by remote sensin...Measurement of vegetation coverage on a small scale is the foundation for the monitoring of changes in vegetation coverage and of the inversion model of monitoring vegetation coverage on a large scale by remote sensing. Using the object-oriented analytical software, Definiens Professional 5, a new method for calculating vegetation coverage based on high-resolution images （aerial photographs or near-surface photography） is proposed. Our research supplies references to remote sensing measurements of vegetation coverage on a small scale and accurate fundamental data for the inversion model of vegetation coverage on a large and intermediate scale to improve the accuracy of remote sensing monitoring of changes in vegetation coverage.展开更多
基金National Natural Science Foundation of China(No.41871305)National Key Research and Development Program of China(No.2017YFC0602204)+2 种基金Fundamental Research Funds for the Central Universities,China University of Geosciences(Wuhan)(No.CUGQY1945)Open Fund of Key Laboratory of Geological Survey and Evaluation of Ministry of Education and the Fundamental Research Funds for the Central Universities(No.GLAB2019ZR02)Open Fund of Laboratory of Urban Land Resources Monitoring and Simulation,Ministry of Natural Resources,China(No.KF-2020-05-068)。
文摘The exploration of building detection plays an important role in urban planning,smart city and military.Aiming at the problem of high overlapping ratio of detection frames for dense building detection in high resolution remote sensing images,we present an effective YOLOv3 framework,corner regression-based YOLOv3(Correg-YOLOv3),to localize dense building accurately.This improved YOLOv3 algorithm establishes a vertex regression mechanism and an additional loss item about building vertex offsets relative to the center point of bounding box.By extending output dimensions,the trained model is able to output the rectangular bounding boxes and the building vertices meanwhile.Finally,we evaluate the performance of the Correg-YOLOv3 on our self-produced data set and provide a comparative analysis qualitatively and quantitatively.The experimental results achieve high performance in precision(96.45%),recall rate(95.75%),F1 score(96.10%)and average precision(98.05%),which were 2.73%,5.4%,4.1%and 4.73%higher than that of YOLOv3.Therefore,our proposed algorithm effectively tackles the problem of dense building detection in high resolution images.
基金Funding for this research was provided by 511 Shaanxi Province’s Key Research and Development Plan(No.2022NY-087).
文摘To address the issue of imbalanced detection performance and detection speed in current mainstream object detection algorithms for optical remote sensing images,this paper proposes a multi-scale object detection model for remote sensing images on complex backgrounds,called DI-YOLO,based on You Only Look Once v7-tiny(YOLOv7-tiny).Firstly,to enhance the model’s ability to capture irregular-shaped objects and deformation features,as well as to extract high-level semantic information,deformable convolutions are used to replace standard convolutions in the original model.Secondly,a Content Coordination Attention Feature Pyramid Network(CCA-FPN)structure is designed to replace the Neck part of the original model,which can further perceive relationships between different pixels,reduce feature loss in remote sensing images,and improve the overall model’s ability to detect multi-scale objects.Thirdly,an Implicitly Efficient Decoupled Head(IEDH)is proposed to increase the model’s flexibility,making it more adaptable to complex detection tasks in various scenarios.Finally,the Smoothed Intersection over Union(SIoU)loss function replaces the Complete Intersection over Union(CIoU)loss function in the original model,resulting in more accurate prediction of bounding boxes and continuous model optimization.Experimental results on the High-Resolution Remote Sensing Detection(HRRSD)dataset demonstrate that the proposed DI-YOLO model outperforms mainstream target detection algorithms in terms of mean Average Precision(mAP)for optical remote sensing image detection.Furthermore,it achieves Frames Per Second(FPS)of 138.9,meeting fast and accurate detection requirements.
基金funded by Thuyloi University Foundation for Science and Technologyunder Grant Number TLU.STF.19-02.
文摘In image processing, one of the most important steps is image segmentation. The objects in remote sensing images often have to be detected in order toperform next steps in image processing. Remote sensing images usually havelarge size and various spatial resolutions. Thus, detecting objects in remote sensing images is very complicated. In this paper, we develop a model to detectobjects in remote sensing images based on the combination of picture fuzzy clustering and MapReduce method (denoted as MPFC). Firstly, picture fuzzy clustering is applied to segment the input images. Then, MapReduce is used to reducethe runtime with the guarantee of quality. To convert data for MapReduce processing, two new procedures are introduced, including Map_PFC and Reduce_PFC.The formal representation and details of two these procedures are presented in thispaper. The experiments on satellite image and remote sensing image datasets aregiven to evaluate proposed model. Validity indices and time consuming are usedto compare proposed model to picture fuzzy clustering model. The values ofvalidity indices show that picture fuzzy clustering integrated to MapReduce getsbetter quality of segmentation than using picture fuzzy clustering only. Moreover,on two selected image datasets, the run time of MPFC model is much less thanthat of picture fuzzy clustering.
基金National 1000 Young Talents Plan of ChinaNational Natural Science Foundation of China(61420106007,61671387,61871325)DECRA of Australica Resenrch Council (DE140100180).
文摘alient object detection aims at identifying the visually interesting object regions that are consistent with human perception. Multispectral remote sensing images provide rich radiometric information in revealing the physical properties of the observed objects, which leads to great potential to perform salient object detection for remote sensing images. Conventional salient object detection methods often employ handcrafted features to predict saliency by evaluating the pixel-wise or superpixel-wise contrast. With the recent use of deep learning framework, in particular, fully convolutional neural networks, there has been profound progress in visual saliency detection. However, this success has not been extended to multispectral remote sensing images, and existing multispectral salient object detection methods are still mainly based on handcrafted features, essentially due to the difficulties in image acquisition and labeling. In this paper, we propose a novel deep residual network based on a top-down model, which is trained in an end-to-end manner to tackle the above issues in multispectral salient object detection. Our model effectively exploits the saliency cues at different levels of the deep residual network. To overcome the limited availability of remote sensing images in training of our deep residual network, we also introduce a new spectral image reconstruction model that can generate multispectral images from RGB images. Our extensive experimental results using both multispectral and RGB salient object detection datasets demonstrate a significant performance improvement of more than 10% improvement compared with the state-of-the-art methods.
文摘To retrieve the object region efficaciously from massive remote sensing image database, a model for content-based retrieval of remote sensing image is given according to the characters of remote sensing image application firstly, and then the algorithm adopted for feature extraction and multidimensional indexing, and relevance feedback by this model are analyzed in detail. Finally, the contents intending to be researched about this model are proposed.
基金supported by the Natural Science Foundation of China(No.61906213).
文摘Most of the current object detection algorithms use pretrained models that are trained on ImageNet and then fine-tuned in the network,which can achieve good performance in terms of general object detectors.However,in the field of remote sensing image object detection,as pretrained models are significantly different from remote sensing data,it is meaningful to explore a train-fromscratch technique for remote sensing images.This paper proposes an object detection framework trained from scratch,SRS-Net,and describes the design of a densely connected backbone network to provide integrated hidden layer supervision for the convolution module.Then,two necessary improvement principles are proposed:studying the role of normalization in the network structure,and improving data augmentation methods for remote sensing images.To evaluate the proposed framework,we performed many ablation experiments on the DIOR,DOTA,and AS datasets.The results show that whether using the improved backbone network,the normalization method or training data enhancement strategy,the performance of the object detection network trained from scratch increased.These principles compensate for the lack of pretrained models.Furthermore,we found that SRS-Net could achieve similar to or slightly better performance than baseline methods,and surpassed most advanced general detectors.
文摘The following article has been retracted due to the investigation of complaints received against it. The Editorial Board found that substantial portions of the text came from other published papers. The scientific community takes a very strong view on this matter, and the Journal of Geographic Information System treats all unethical behavior such as plagiarism seriously. This paper published in Vol.4 No.3 273-278, 2012, has been removed from this site.
基金funded by the Innovative Research Program of the International Research Center of Big Data for Sustainable Development Goals(Grant No.CBAS2022IRP04)the Sichuan Natural Resources Department Project(Grant NO.510201202076888)+3 种基金the Project of the Geological Exploration Management Department of the Ministry of Natural Resources(Grant NO.073320180876/2)the Key Research and Development Program of Guangxi(Guike-AB22035060)the National Natural Science Foundation of China(Grant No.42171291)the Chengdu University of Technology Postgraduate Innovative Cultivation Program:Tunnel Geothermal Disaster Susceptibility Evaluation in Sichuan-Tibet Railway Based on Deep Learning(CDUT2022BJCX015).
文摘Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention.However,due to interference occasioned by density,overlap,and coverage,the tiny object detection in remote sensing images has always been a difficult problem.Therefore,we propose a novel TO–YOLOX(Tiny Object–You Only Look Once)model.TO–YOLOX possesses a MiSo(Multiple-in-Singleout)feature fusion structure,which exhibits a spatial-shift structure,and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images.TO–YOLOX utilizes an adaptive IOU-T(Intersection Over Uni-Tiny)loss to enhance the localization accuracy of tiny objects,and it applies attention mechanism Group-CBAM(group-convolutional block attention module)to enhance the perception of tiny objects in remote sensing images.To verify the effectiveness and efficiency of TO–YOLOX,we utilized three aerial-photography tiny object detection datasets,namely VisDrone2021,Tiny Person,and DOTA–HBB,and the following mean average precision(mAP)values were recorded,respectively:45.31%(+10.03%),28.9%(+9.36%),and 63.02%(+9.62%).With respect to recognizing tiny objects,TO–YOLOX exhibits a stronger ability compared with Faster R-CNN,RetinaNet,YOLOv5,YOLOv6,YOLOv7,and YOLOX,and the proposed model exhibits fast computation.
基金Supported by the National Key Research and Development Program of China(No.2016YFC1402003)the CAS Earth Big Data Science Project(No.XDA19060303)the Innovation Project of the State Key Laboratory of Resources and Environmental Information System(No.O88RAA01YA)
文摘Efficient and accurate access to coastal land cover information is of great significance for marine disaster prevention and mitigation.Although the popular and common sensors of land resource satellites provide free and valuable images to map the land cover,coastal areas often encounter significant cloud cover,especially in tropical areas,which makes the classification in those areas non-ideal.To solve this problem,we proposed a framework of combining medium-resolution optical images and synthetic aperture radar(SAR)data with the recently popular object-based image analysis(OBIA)method and used the Landsat Operational Land Imager(OLI)and Phased Array type L-band Synthetic Aperture Radar(PALSAR)images acquired in Singapore in 2017 as a case study.We designed experiments to confirm two critical factors of this framework:one is the segmentation scale that determines the average object size,and the other is the classification feature.Accuracy assessments of the land cover indicated that the optimal segmentation scale was between 40 and 80,and the features of the combination of OLI and SAR resulted in higher accuracy than any individual features,especially in areas with cloud cover.Based on the land cover generated by this framework,we assessed the vulnerability of the marine disasters of Singapore in 2008 and 2017 and found that the high-vulnerability areas mainly located in the southeast and increased by 118.97 km2 over the past decade.To clarify the disaster response plan for different geographical environments,we classified risk based on altitude and distance from shore.The newly increased high-vulnerability regions within 4 km offshore and below 30 m above sea level are at high risk;these regions may need to focus on strengthening disaster prevention construction.This study serves as a typical example of using remote sensing techniques for the vulnerability assessment of marine disasters,especially those in cloudy coastal areas.
文摘In the study of oriented bounding boxes(OBB)object detection in high-resolution remote sensing images,the problem of missed and wrong detection of small targets occurs because the targets are too small and have different orientations.Existing OBB object detection for remote sensing images,although making good progress,mainly focuses on directional modeling,while less consideration is given to the size of the object as well as the problem of missed detection.In this study,a method based on improved YOLOv8 was proposed for detecting oriented objects in remote sensing images,which can improve the detection precision of oriented objects in remote sensing images.Firstly,the ResCBAMG module was innovatively designed,which could better extract channel and spatial correlation information.Secondly,the innovative top-down feature fusion layer network structure was proposed in conjunction with the Efficient Channel Attention(ECA)attention module,which helped to capture inter-local cross-channel interaction information appropriately.Finally,we introduced an innovative ResCBAMG module between the different C2f modules and detection heads of the bottom-up feature fusion layer.This innovative structure helped the model to better focus on the target area.The precision and robustness of oriented target detection were also improved.Experimental results on the DOTA-v1.5 dataset showed that the detection Precision,mAP@0.5,and mAP@0.5:0.95 metrics of the improved model are better compared to the original model.This improvement is effective in detecting small targets and complex scenes.
文摘Earth surveillance through aerial images allows more accurate identification and characterization of objects present on the surface from space and airborne platforms.The progression of deep learning and computer vision methods and the availability of heterogeneous multispectral remote sensing data make the field more fertile for research.With the evolution of optical sensors,aerial images are becoming more precise and larger,which leads to a new kind of problem for object detection algorithms.This paper proposes the“Sliding Region-based Convolutional Neural Network(SRCNN),”which is an extension of the Faster Region-based Convolutional Neural Network(RCNN)object detection framework to make it independent of the image’s spatial resolution and size.The sliding box strategy is used in the proposed model to segment the image while detecting.The proposed framework outperforms the state-of-the-art Faster RCNN model while processing images with significantly different spatial resolution values.The SRCNN is also capable of detecting objects in images of any size.
文摘The majority of the population and economic activity of the northern half of Vietnam is clustered in the Red River Delta and about half of the country’s rice production takes place here. There are significant problems associated with its geographical position and the intensive exploitation of resources by an overabundant population (population density of 962 inhabitants/km2). Some thirty years after the economic liberalization and the opening of the country to international markets, agricultural land use patterns in the Red River Delta, particularly in the coastal area, have undergone many changes. Remote sensing is a particularly powerful tool in processing and providing spatial information for monitoring land use changes. The main methodological objective is to find a solution to process the many heterogeneous coastal land use parameters, so as to describe it in all its complexity, specifically by making use of the latest European satellite data (Sentinel-2). This complexity is due to local variations in ecological conditions, but also to anthropogenic factors that directly and indirectly influence land use dynamics. The methodological objective was to develop a new Geographic Object-based Image Analysis (GEOBIA) approach for mapping coastal areas using Sentinel-2 data and Landsat 8. By developing a new segmentation, accuracy measure, in this study was determined that segmentation accuracies decrease with increasing segmentation scales and that the negative impact of under-segmentation errors significantly increases at a large scale. An Estimation of Scale Parameter (ESP) tool was then used to determine the optimal segmentation parameter values. A popular machine learning algorithms (Random Forests-RFs) is used. For all classifications algorithm, an increase in overall accuracy was observed with the full synergistic combination of available data sets.
基金This work was supported by the National Natural Science Foundation of China(61802304,61834005,61772417,61634004,61602377)the Shaanxi Provincial Co-ordination Innovation Project of Science and Technology(20I6KTZDGY02-04-02)the Shaanxi Provincial Key Research and Development Plan(2017GY-060).
文摘Object recognition in very high-resolution remote sensing images is a basic problem in the field of aerial and satellite image analysis.With the development of sensor technology and aerospace remote sensing technology,the quality and quantity of remote sensing images are improved.Traditional recognition methods have a certain limitation in describing higher-level features,but object recognition method based on convolutional neural network(CNN)can not only deal with large scale images,but also train features automatically with high efficiency.It is mainly used on object recognition for remote sensing images.In this paper,an AlexNet CNN model is trained using 2100 remote sensing images,and correction rate can reach 97.6%after 2000 iterations.Then based on trained model,a parallel design of CNN for remote sensing images object recognition based on data-driven array processor(DDAP)is proposed.The consuming cycles are counted.Simultaneously,the proposed architecture is realized on Xilinx V6 development board,and synthesized based on SMIC 130 nm complementary metal oxid semiconductor(CMOS)technology.The experimental results show that the proposed architecture has a certain degree of parallelism to achieve the purpose of accelerating calculations.
基金supported by National Key Technology Research and Development Program of China (Grant Nos.2008BAC34B02 and 2008BAC3403)
文摘The object-oriented information extraction technique was used to improve classification accuracy,and addressed the problem that HJ-1 CCD remote sensing images have only four spectral bands with moderate spatial resolution.We used two key techniques:the selection of optimum image segmentation scale and the development of an appropriate object-oriented information extraction strategy.With the principle of minimizing merge cost of merging neighboring pixels/objects,we used spatial autocorrelation index Moran's I and the variance index to select the optimum segmentation scale.The Nearest Neighborhood(NN) classifier based on sampling and a knowledge-based fuzzy classifier were used in the object-oriented information extraction strategy.In this classification step,feature optimization was used to improve information extraction accuracy using reduced data dimension.These two techniques were applied to land cover information extraction for Shanghai city using a HJ-1 CCD image.Results indicate that the information extraction accuracy of the object-oriented method was much higher than that of the pixel-based method.
基金This work is supported by the National Natural Science Foundation of China[grant numbers 41890820,41771452,41771454,and 41901340]。
文摘Due to the bird’s eye view of remote sensing sensors,the orientational information of an object is a key factor that has to be considered in object detection.To obtain rotating bounding boxes,existing studies either rely on rotated anchoring schemes or adding complex rotating ROI transfer layers,leading to increased computational demand and reduced detection speeds.In this study,we propose a novel internal-external optimized convolutional neural network for arbitrary orientated object detection in optical remote sensing images.For the internal opti-mization,we designed an anchor-based single-shot head detector that adopts the concept of coarse-to-fine detection for two-stage object detection networks.The refined rotating anchors are generated from the coarse detection head module and fed into the refining detection head module with a link of an embedded deformable convolutional layer.For the external optimiza-tion,we propose an IOU balanced loss that addresses the regression challenges related to arbitrary orientated bounding boxes.Experimental results on the DOTA and HRSC2016 bench-mark datasets show that our proposed method outperforms selected methods.
基金supported by the director projects of Centre for Earth Observation and Digital Earth(CEODE)(Nos.Y2ZZ06101B and Y2ZZ18101B)the State Key Laboratory of Resources and Environmental Information System project+1 种基金the National Natural Science Foundation of China(project No.41371385)the National High Technology Research and Development Program of China(project No.2012AA12A403-5)
文摘Within the context of global change, marine sensitive factors or Marine Essential Climate Variables have been defined by many projects, and their sensitive spatial regions and time phases play significant roles in regional sea-air interactions and better understanding of their dynamic process. In this paper, we propose a cluster-based method for marine sensitive region extraction and representation. This method includes a kernel expansion algorithm for extracting marine sensitive regions, and a field-object triple form, integration of object-oriented and field-based model, for representing marine sensitive objects. Firstly, this method recognizes ENSO-related spatial patterns using empirical orthogonal decomposition of long term marine sensitive factors and correlation analysis with multiple ENSO index. The cluster kernel, defined by statistics of spatial patterns, is initialized to carry out spatial expansion and cluster mergence with spatial neighborhoods recursively, then all the related lattices with similar behavior are merged into marine sensitive regions. After this, the Field-object triple form of < O, A, F > is used to represent the marine sensitive objects, both with the discrete object with a precise extend and boundary, and the continuous field with variations dependent on spatial locations. Finally, the marine sensitive objects about sea surface temperature are extracted, represented and analyzed as a case of study, which proves the effectiveness and the efficiency of the proposed method.
基金funded by the National Natural Science Foundation of China(Grant No.40571029).
文摘Measurement of vegetation coverage on a small scale is the foundation for the monitoring of changes in vegetation coverage and of the inversion model of monitoring vegetation coverage on a large scale by remote sensing. Using the object-oriented analytical software, Definiens Professional 5, a new method for calculating vegetation coverage based on high-resolution images （aerial photographs or near-surface photography） is proposed. Our research supplies references to remote sensing measurements of vegetation coverage on a small scale and accurate fundamental data for the inversion model of vegetation coverage on a large and intermediate scale to improve the accuracy of remote sensing monitoring of changes in vegetation coverage.
