With the wide use of high-resolution remotely sensed imagery, the object-oriented remotely sensed informa- tion classification pattern has been intensively studied. Starting with the definition of object-oriented remo...With the wide use of high-resolution remotely sensed imagery, the object-oriented remotely sensed informa- tion classification pattern has been intensively studied. Starting with the definition of object-oriented remotely sensed information classification pattern and a literature review of related research progress, this paper sums up 4 developing phases of object-oriented classification pattern during the past 20 years. Then, we discuss the three aspects of method- ology in detail, namely remotely sensed imagery segmentation, feature analysis and feature selection, and classification rule generation, through comparing them with remotely sensed information classification method based on per-pixel. At last, this paper presents several points that need to be paid attention to in the future studies on object-oriented RS in- formation classification pattern: 1) developing robust and highly effective image segmentation algorithm for multi-spectral RS imagery; 2) improving the feature-set including edge, spatial-adjacent and temporal characteristics; 3) discussing the classification rule generation classifier based on the decision tree; 4) presenting evaluation methods for classification result by object-oriented classification pattern.展开更多
Pine wilt disease(PWD)is currently one of the main causes of large-scale forest destruction.To control the spread of PWD,it is essential to detect affected pine trees quickly.This study investigated the feasibility of...Pine wilt disease(PWD)is currently one of the main causes of large-scale forest destruction.To control the spread of PWD,it is essential to detect affected pine trees quickly.This study investigated the feasibility of using the object-oriented multi-scale segmentation algorithm to identify trees discolored by PWD.We used an unmanned aerial vehicle(UAV)platform equipped with an RGB digital camera to obtain high spatial resolution images,and multiscale segmentation was applied to delineate the tree crown,coupling the use of object-oriented classification to classify trees discolored by PWD.Then,the optimal segmentation scale was implemented using the estimation of scale parameter(ESP2)plug-in.The feature space of the segmentation results was optimized,and appropriate features were selected for classification.The results showed that the optimal scale,shape,and compactness values of the tree crown segmentation algorithm were 56,0.5,and 0.8,respectively.The producer’s accuracy(PA),user’s accuracy(UA),and F1 score were 0.722,0.605,and 0.658,respectively.There were no significant classification errors in the final classification results,and the low accuracy was attributed to the low number of objects count caused by incorrect segmentation.The multi-scale segmentation and object-oriented classification method could accurately identify trees discolored by PWD with a straightforward and rapid processing.This study provides a technical method for monitoring the occurrence of PWD and identifying the discolored trees of disease using UAV-based high-resolution images.展开更多
This paper proposed to use double polarization synthetic aperture radar (SAR) image to classify surface feature, based on DEM. It takes fully use of the polarization information and external information. This pa-per u...This paper proposed to use double polarization synthetic aperture radar (SAR) image to classify surface feature, based on DEM. It takes fully use of the polarization information and external information. This pa-per utilizes ENVISAT ASAR APP double-polarization data of Poyang lake area in Jiangxi Province. Com-pared with traditional pixel-based classification, this paper fully uses object features (color, shape, hierarchy) and accessorial DEM information. The classification accuracy improves from the original 73.7% to 91.84%. The result shows that object-oriented classification technology is suitable for double polarization SAR’s high precision classification.展开更多
UAV remote sensing images have the advantages of high spatial resolution,fast speed,strong real-time performance,and convenient operation,etc.,and have become a recently developed,vital means of acquiring surface info...UAV remote sensing images have the advantages of high spatial resolution,fast speed,strong real-time performance,and convenient operation,etc.,and have become a recently developed,vital means of acquiring surface information.It is an important research task for precision agriculture to make full use of the spectrum,texture,color and other characteristic information of crops,especially the spatial arrangement and structure information of features,to explore effective methods for the classification of multiple varieties of crops.In order to explore the applicability of the object-oriented method to achieve accurate classification of UAV high-resolution images,the paper used the object-oriented classification method in ENVI to classify the UAV high-resolution remote sensing image obtained from the orderly structured 28 species of crops in the test field,which mainly includes image segmentation and object classification.The results showed that the plots obtained after classification were continuous and complete,basically in line with the actual situation,and the overall accuracy of crop classification was 91.73%,with Kappa coefficient of 0.87.Compared with the crop planting area based on remote sensing interpretation and field survey,the area error of 17 species of crops in this study was controlled within 15%,which provides a basis for object-oriented crop classification of UAV remote sensing images.展开更多
Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noti...Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noticeable. Urban administrators and decision-makers seek modern methods and technology to provide information support for urban growth. Recently, with the fast development of high-resolution sensor technology, more relevant data can be obtained, which is an advantage in studying the sustainable development of urban land-use. However, these data are only information sources and are a mixture of ＂information＂ and ＂noise＂. Processing, analysis and information extraction from remote sensing data is necessary to provide useful information. This paper extracts urban land-use information from a high-resolution image by using the multi-feature information of the image objects, and adopts an object-oriented image analysis approach and multi-scale image segmentation technology. A classification and extraction model is set up based on the multi-features of the image objects, in order to contribute to information for reasonable planning and effective management. This new image analysis approach offers a satisfactory solution for extracting information quickly and efficiently.展开更多
Accurate crop distribution mapping is required for crop yield prediction and field management. Due to rapid progress in remote sensing technology, fine spatial resolution(FSR) remotely sensed imagery now offers great ...Accurate crop distribution mapping is required for crop yield prediction and field management. Due to rapid progress in remote sensing technology, fine spatial resolution(FSR) remotely sensed imagery now offers great opportunities for mapping crop types in great detail. However, within-class variance can hamper attempts to discriminate crop classes at fine resolutions. Multi-temporal FSR remotely sensed imagery provides a means of increasing crop classification from FSR imagery, although current methods do not exploit the available information fully. In this research, a novel Temporal Sequence Object-based Convolutional Neural Network(TS-OCNN) was proposed to classify agricultural crop type from FSR image time-series. An object-based CNN(OCNN) model was adopted in the TS-OCNN to classify images at the object level(i.e., segmented objects or crop parcels), thus, maintaining the precise boundary information of crop parcels. The combination of image time-series was first utilized as the input to the OCNN model to produce an ‘original’ or baseline classification. Then the single-date images were fed automatically into the deep learning model scene-by-scene in order of image acquisition date to increase successively the crop classification accuracy. By doing so, the joint information in the FSR multi-temporal observations and the unique individual information from the single-date images were exploited comprehensively for crop classification. The effectiveness of the proposed approach was investigated using multitemporal SAR and optical imagery, respectively, over two heterogeneous agricultural areas. The experimental results demonstrated that the newly proposed TS-OCNN approach consistently increased crop classification accuracy, and achieved the greatest accuracies(82.68% and 87.40%) in comparison with state-of-the-art benchmark methods, including the object-based CNN(OCNN)(81.63% and85.88%), object-based image analysis(OBIA)(78.21% and 84.83%), and standard pixel-wise CNN(79.18%and 82.90%). The proposed approach is the first known attempt to explore simultaneously the joint information from image time-series with the unique information from single-date images for crop classification using a deep learning framework. The TS-OCNN, therefore, represents a new approach for agricultural landscape classification from multi-temporal FSR imagery. Besides, it is readily generalizable to other landscapes(e.g., forest landscapes), with a wide application prospect.展开更多
Due to the small size,variety,and high degree of mixing of herbaceous vegetation,remote sensing-based identification of grassland types primarily focuses on extracting major grassland categories,lacking detailed depic...Due to the small size,variety,and high degree of mixing of herbaceous vegetation,remote sensing-based identification of grassland types primarily focuses on extracting major grassland categories,lacking detailed depiction.This limitation significantly hampers the development of effective evaluation and fine supervision for the rational utilization of grassland resources.To address this issue,this study concentrates on the representative grassland of Zhenglan Banner in Inner Mongolia as the study area.It integrates the strengths of Sentinel-1 and Sentinel-2 active-passive synergistic observations and introduces innovative object-oriented techniques for grassland type classification,thereby enhancing the accuracy and refinement of grassland classification.The results demonstrate the following:(1)To meet the supervision requirements of grassland resources,we propose a grassland type classification system based on remote sensing and the vegetation-habitat classification method,specifically applicable to natural grasslands in northern China.(2)By utilizing the high-spatial-resolution Normalized Difference Vegetation Index(NDVI)synthesized through the Spatial and Temporal Non-Local Filter-based Fusion Model(STNLFFM),we are able to capture the NDVI time profiles of grassland types,accurately extract vegetation phenological information within the year,and further enhance the temporal resolution.(3)The integration of multi-seasonal spectral,polarization,and phenological characteristics significantly improves the classification accuracy of grassland types.The overall accuracy reaches 82.61%,with a kappa coefficient of 0.79.Compared to using only multi-seasonal spectral features,the accuracy and kappa coefficient have improved by 15.94%and 0.19,respectively.Notably,the accuracy improvement of the gently sloping steppe is the highest,exceeding 38%.(4)Sandy grassland is the most widespread in the study area,and the growth season of grassland vegetation mainly occurs from May to September.The sandy meadow exhibits a longer growing season compared with typical grassland and meadow,and the distinct differences in phenological characteristics contribute to the accurate identification of various grassland types.展开更多
This paper proposed a new approach of sample part classification and design, a so called Or-dered-object-oriented method (O-O-O method). Based on the theory of neural networks, fuzzy clustering algorithm and adaptive ...This paper proposed a new approach of sample part classification and design, a so called Or-dered-object-oriented method (O-O-O method). Based on the theory of neural networks, fuzzy clustering algorithm and adaptive pattern recognition, O-O-O method can be used to classify and design the sample parts automatically. The basic theory, the main step as well as the characteristics of the method are analysed. The construction of the ordered object in application is also presented in this paper.展开更多
In order to improve the accuracy of building structure identification using remote sensing images,a building structure classification method based on multi-feature fusion of UAV remote sensing image is proposed in thi...In order to improve the accuracy of building structure identification using remote sensing images,a building structure classification method based on multi-feature fusion of UAV remote sensing image is proposed in this paper.Three identification approaches of remote sensing images are integrated in this method:object-oriented,texture feature,and digital elevation based on DSM and DEM.So RGB threshold classification method is used to classify the identification results.The accuracy of building structure classification based on each feature and the multi-feature fusion are compared and analyzed.The results show that the building structure classification method is feasible and can accurately identify the structures in large-area remote sensing images.展开更多
This paper aims to assess the ways in which multi-resolution object-based classification methods can be used to group urban environments made up of a mixture of buildings, sub-elements such as car parks, roads, shades...This paper aims to assess the ways in which multi-resolution object-based classification methods can be used to group urban environments made up of a mixture of buildings, sub-elements such as car parks, roads, shades and pavements and foliage such as grass and trees. This involves using both unmanned aerial vehicles (UAVs) which provide high-resolution mosaic Orthoimages and generate a Digital Surface Model (DSM). For the study area chosen for this paper, 400 Orthoimages with a spatial resolution of 7 cm each were used to build the Orthoimages and DSM, which were georeferenced using well distributed network of ground control points (GCPs) of 12 reference points (RMSE = 8 cm). As these were combined with onboard RTK-GNSS-enabled 2-frequency receivers, they were able to provide absolute block orientation which had a similar accuracy range if the data had been collected by traditional indirect sensor orientation. Traditional indirect sensor orientation involves the GNSS receiver in the UAV receiving a differential signal from the base station through a communication link. This allows for the precise position of the UAV to be established, as the RTK uses correction, allowing position, velocity, altitude and heading to tracked, as well as the measurement of raw sensor data. By assessing the results of the confusion matrices, it can be seen that the overall accuracy of the object-oriented classification was 84.37%. This has an overall Kappa of 0.74 and the data that had poor classification accuracy included shade, parking lots and concrete pavements. These had a producer accuracy (precision) of 81%, 74% and 74% respectively, while lakes and solar panels each scored 100% in comparison, meaning that they had good classification accuracy.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
The Yellow River Delta wetland is the youngest wetland ecosystem in China's warm temperate zone. To better understand how its landscape pattern has changed over time and the underlying factors responsible, this st...The Yellow River Delta wetland is the youngest wetland ecosystem in China's warm temperate zone. To better understand how its landscape pattern has changed over time and the underlying factors responsible, this study analyzed the dynamic changes of wetlands using five Landsat series of images, namely MSS(Mulri Spectral Scanner), TM(Thematic Mapper), and OLI(Operational Land Imager) sensors in 1976, 1986, 1996, 2006, and 2016. Object-oriented classification and the combination of spatial and spectral features and both the Normalized Difference Vegetation Index(NDVI) and Normalized Difference Water Index(NDWI), as well as brightness characteristic indices, were used to classify the images in eCognition software. Landscape pattern changes in the Yellow River Delta over the past 40 years were then delineated using transition matrix and landscape index methods. Results show that: 1) from1976 to 2016, the total area of wetlands in the study area decreased from 2594.76 to 2491.79 km^2, while that of natural wetlands decreased by 954.03 km^2 whereas human-made wetlands increased by 851.06 km^2. 2) The transformation of natural wetlands was extensive: 31.34% of those covered by Suaeda heteropteras were transformed into reservoirs and ponds, and 24.71% with Phragmites australis coverage were transformed into dry farmland. Some human-made wetlands were transformed into non-wetlands types: 1.55% of reservoirs and ponds became construction land, and likewise 21.27% were transformed into dry farmland. 3) From 1976 to 2016, as the intensity of human activities increased, the number of landscape types in the study area continuously increased. Patches were scattered and more fragmented. The whole landscape became more complex. In short, over the past 40 years, the wetlands of the Yellow River Delta have been degraded, with the area of natural wetlands substantially reduced. Human activities were the dominant forces driving these changes in the Yellow River Delta.展开更多
The object-oriented approach is a powerful method in making classification.With the segmentation of images to objects,many features can be calculated based on the objects so that the targets can be distinguished.Howev...The object-oriented approach is a powerful method in making classification.With the segmentation of images to objects,many features can be calculated based on the objects so that the targets can be distinguished.However,this method has not been applied to lunar study.In this paper we attempt to apply this method to detecting lunar craters with promising results.Craters are the most obvious features on the moon and they are important for lunar geologic study.One of the important questions in lunar research is to estimate lunar surface ages by examination of crater density per unit area.Hence,proper detection of lunar craters is necessary.Manual crater identification is inefficient,and a more efficient and effective method is needed.This paper describes an object-oriented method to detect lunar craters using lunar reflectance images.In the method,many objects were first segmented from the image based on size,shape,color,and the weights to every layer.Then the feature of"contrast to neighbor objects"was selected to identify craters from the lunar image.In the next step,by merging the adjacent objects belonging to the same class,almost every crater can be taken as an independent object except several very big craters in the study area.To remove the crater rays diagnosed as craters,the feature of"length/width"was further used with suitable parameters to finish recognizing craters.Finally,the result was exported to ArcGIS for manual modification to those big craters and the number of craters was acquired.展开更多
Remote sensing is an important technical means to investigate land resources.Optical imagery has been widely used in crop classification and can show changes in moisture and chlorophyll content in crop leaves,whereas ...Remote sensing is an important technical means to investigate land resources.Optical imagery has been widely used in crop classification and can show changes in moisture and chlorophyll content in crop leaves,whereas synthetic aperture radar(SAR)imagery is sensitive to changes in growth states and morphological structures.Crop-type mapping with a single type of imagery sometimes has unsatisfactory precision,so providing precise spatiotemporal information on crop type at a local scale for agricultural applications is difficult.To explore the abilities of combining optical and SAR images and to solve the problem of inaccurate spatial information for land parcels,a new method is proposed in this paper to improve crop-type identification accuracy.Multifeatures were derived from the full polarimetric SAR data(GaoFen-3)and a high-resolution optical image(GaoFen-2),and the farmland parcels used as the basic for object-oriented classification were obtained from the GaoFen-2 image using optimal scale segmentation.A novel feature subset selection method based on within-class aggregation and between-class scatter(WA-BS)is proposed to extract the optimal feature subset.Finally,crop-type mapping was produced by a support vector machine(SVM)classifier.The results showed that the proposed method achieved good classification results with an overall accuracy of 89.50%,which is better than the crop classification results derived from SAR-based segmentation.Compared with the ReliefF,mRMR and LeastC feature selection algorithms,the WA-BS algorithm can effectively remove redundant features that are strongly correlated and obtain a high classification accuracy via the obtained optimal feature subset.This study shows that the accuracy of crop-type mapping in an area with multiple cropping patterns can be improved by the combination of optical and SAR remote sensing images.展开更多
基金Under the auspices of the National Natural Science Foundation of China (No. 40301038), Talents Recruitment Foun-dation of Nanjing University
文摘With the wide use of high-resolution remotely sensed imagery, the object-oriented remotely sensed informa- tion classification pattern has been intensively studied. Starting with the definition of object-oriented remotely sensed information classification pattern and a literature review of related research progress, this paper sums up 4 developing phases of object-oriented classification pattern during the past 20 years. Then, we discuss the three aspects of method- ology in detail, namely remotely sensed imagery segmentation, feature analysis and feature selection, and classification rule generation, through comparing them with remotely sensed information classification method based on per-pixel. At last, this paper presents several points that need to be paid attention to in the future studies on object-oriented RS in- formation classification pattern: 1) developing robust and highly effective image segmentation algorithm for multi-spectral RS imagery; 2) improving the feature-set including edge, spatial-adjacent and temporal characteristics; 3) discussing the classification rule generation classifier based on the decision tree; 4) presenting evaluation methods for classification result by object-oriented classification pattern.
基金supported by the National Natural Science Foundation of China(No.31870620)the National Technology Extension Fund of Forestry([2019]06)the Fundamental Research Funds for the Central Universities(No.PTYX202107)。
文摘Pine wilt disease(PWD)is currently one of the main causes of large-scale forest destruction.To control the spread of PWD,it is essential to detect affected pine trees quickly.This study investigated the feasibility of using the object-oriented multi-scale segmentation algorithm to identify trees discolored by PWD.We used an unmanned aerial vehicle(UAV)platform equipped with an RGB digital camera to obtain high spatial resolution images,and multiscale segmentation was applied to delineate the tree crown,coupling the use of object-oriented classification to classify trees discolored by PWD.Then,the optimal segmentation scale was implemented using the estimation of scale parameter(ESP2)plug-in.The feature space of the segmentation results was optimized,and appropriate features were selected for classification.The results showed that the optimal scale,shape,and compactness values of the tree crown segmentation algorithm were 56,0.5,and 0.8,respectively.The producer’s accuracy(PA),user’s accuracy(UA),and F1 score were 0.722,0.605,and 0.658,respectively.There were no significant classification errors in the final classification results,and the low accuracy was attributed to the low number of objects count caused by incorrect segmentation.The multi-scale segmentation and object-oriented classification method could accurately identify trees discolored by PWD with a straightforward and rapid processing.This study provides a technical method for monitoring the occurrence of PWD and identifying the discolored trees of disease using UAV-based high-resolution images.
文摘This paper proposed to use double polarization synthetic aperture radar (SAR) image to classify surface feature, based on DEM. It takes fully use of the polarization information and external information. This pa-per utilizes ENVISAT ASAR APP double-polarization data of Poyang lake area in Jiangxi Province. Com-pared with traditional pixel-based classification, this paper fully uses object features (color, shape, hierarchy) and accessorial DEM information. The classification accuracy improves from the original 73.7% to 91.84%. The result shows that object-oriented classification technology is suitable for double polarization SAR’s high precision classification.
基金Supported by College Students Innovation and Entrepreneurship Training Program of Jilin University(No.202010183695)。
文摘UAV remote sensing images have the advantages of high spatial resolution,fast speed,strong real-time performance,and convenient operation,etc.,and have become a recently developed,vital means of acquiring surface information.It is an important research task for precision agriculture to make full use of the spectrum,texture,color and other characteristic information of crops,especially the spatial arrangement and structure information of features,to explore effective methods for the classification of multiple varieties of crops.In order to explore the applicability of the object-oriented method to achieve accurate classification of UAV high-resolution images,the paper used the object-oriented classification method in ENVI to classify the UAV high-resolution remote sensing image obtained from the orderly structured 28 species of crops in the test field,which mainly includes image segmentation and object classification.The results showed that the plots obtained after classification were continuous and complete,basically in line with the actual situation,and the overall accuracy of crop classification was 91.73%,with Kappa coefficient of 0.87.Compared with the crop planting area based on remote sensing interpretation and field survey,the area error of 17 species of crops in this study was controlled within 15%,which provides a basis for object-oriented crop classification of UAV remote sensing images.
基金The paper is supported by the Research Foundation for OutstandingYoung Teachers , China University of Geosciences ( Wuhan) ( No .CUGQNL0616) Research Foundationfor State Key Laboratory of Geo-logical Processes and Mineral Resources ( No . MGMR2002-02)Hubei Provincial Depart ment of Education (B) .
文摘Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noticeable. Urban administrators and decision-makers seek modern methods and technology to provide information support for urban growth. Recently, with the fast development of high-resolution sensor technology, more relevant data can be obtained, which is an advantage in studying the sustainable development of urban land-use. However, these data are only information sources and are a mixture of ＂information＂ and ＂noise＂. Processing, analysis and information extraction from remote sensing data is necessary to provide useful information. This paper extracts urban land-use information from a high-resolution image by using the multi-feature information of the image objects, and adopts an object-oriented image analysis approach and multi-scale image segmentation technology. A classification and extraction model is set up based on the multi-features of the image objects, in order to contribute to information for reasonable planning and effective management. This new image analysis approach offers a satisfactory solution for extracting information quickly and efficiently.
基金supported by the Strategic Priority Research Program of the Chinese Academy of Sciences (XDA28070503)the National Key Research and Development Program of China(2021YFD1500100)+2 种基金the Open Fund of State Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University (20R04)Land Observation Satellite Supporting Platform of National Civil Space Infrastructure Project(CASPLOS-CCSI)a PhD studentship ‘‘Deep Learning in massive area,multi-scale resolution remotely sensed imagery”(EAA7369),sponsored by Lancaster University and Ordnance Survey (the national mapping agency of Great Britain)。
文摘Accurate crop distribution mapping is required for crop yield prediction and field management. Due to rapid progress in remote sensing technology, fine spatial resolution(FSR) remotely sensed imagery now offers great opportunities for mapping crop types in great detail. However, within-class variance can hamper attempts to discriminate crop classes at fine resolutions. Multi-temporal FSR remotely sensed imagery provides a means of increasing crop classification from FSR imagery, although current methods do not exploit the available information fully. In this research, a novel Temporal Sequence Object-based Convolutional Neural Network(TS-OCNN) was proposed to classify agricultural crop type from FSR image time-series. An object-based CNN(OCNN) model was adopted in the TS-OCNN to classify images at the object level(i.e., segmented objects or crop parcels), thus, maintaining the precise boundary information of crop parcels. The combination of image time-series was first utilized as the input to the OCNN model to produce an ‘original’ or baseline classification. Then the single-date images were fed automatically into the deep learning model scene-by-scene in order of image acquisition date to increase successively the crop classification accuracy. By doing so, the joint information in the FSR multi-temporal observations and the unique individual information from the single-date images were exploited comprehensively for crop classification. The effectiveness of the proposed approach was investigated using multitemporal SAR and optical imagery, respectively, over two heterogeneous agricultural areas. The experimental results demonstrated that the newly proposed TS-OCNN approach consistently increased crop classification accuracy, and achieved the greatest accuracies(82.68% and 87.40%) in comparison with state-of-the-art benchmark methods, including the object-based CNN(OCNN)(81.63% and85.88%), object-based image analysis(OBIA)(78.21% and 84.83%), and standard pixel-wise CNN(79.18%and 82.90%). The proposed approach is the first known attempt to explore simultaneously the joint information from image time-series with the unique information from single-date images for crop classification using a deep learning framework. The TS-OCNN, therefore, represents a new approach for agricultural landscape classification from multi-temporal FSR imagery. Besides, it is readily generalizable to other landscapes(e.g., forest landscapes), with a wide application prospect.
基金supported by the National Natural Science Foundation of China[grant number 42001386,42271407]within the ESA-MOST China Dragon 5 Cooperation(ID:59313).
文摘Due to the small size,variety,and high degree of mixing of herbaceous vegetation,remote sensing-based identification of grassland types primarily focuses on extracting major grassland categories,lacking detailed depiction.This limitation significantly hampers the development of effective evaluation and fine supervision for the rational utilization of grassland resources.To address this issue,this study concentrates on the representative grassland of Zhenglan Banner in Inner Mongolia as the study area.It integrates the strengths of Sentinel-1 and Sentinel-2 active-passive synergistic observations and introduces innovative object-oriented techniques for grassland type classification,thereby enhancing the accuracy and refinement of grassland classification.The results demonstrate the following:(1)To meet the supervision requirements of grassland resources,we propose a grassland type classification system based on remote sensing and the vegetation-habitat classification method,specifically applicable to natural grasslands in northern China.(2)By utilizing the high-spatial-resolution Normalized Difference Vegetation Index(NDVI)synthesized through the Spatial and Temporal Non-Local Filter-based Fusion Model(STNLFFM),we are able to capture the NDVI time profiles of grassland types,accurately extract vegetation phenological information within the year,and further enhance the temporal resolution.(3)The integration of multi-seasonal spectral,polarization,and phenological characteristics significantly improves the classification accuracy of grassland types.The overall accuracy reaches 82.61%,with a kappa coefficient of 0.79.Compared to using only multi-seasonal spectral features,the accuracy and kappa coefficient have improved by 15.94%and 0.19,respectively.Notably,the accuracy improvement of the gently sloping steppe is the highest,exceeding 38%.(4)Sandy grassland is the most widespread in the study area,and the growth season of grassland vegetation mainly occurs from May to September.The sandy meadow exhibits a longer growing season compared with typical grassland and meadow,and the distinct differences in phenological characteristics contribute to the accurate identification of various grassland types.
文摘This paper proposed a new approach of sample part classification and design, a so called Or-dered-object-oriented method (O-O-O method). Based on the theory of neural networks, fuzzy clustering algorithm and adaptive pattern recognition, O-O-O method can be used to classify and design the sample parts automatically. The basic theory, the main step as well as the characteristics of the method are analysed. The construction of the ordered object in application is also presented in this paper.
基金sponsored by National Key R&D Program of China(2018YFC1504504)Youth Foundation of Yunnan Earthquake Agency(2021K01)Project of Yunnan Earthquake Agency“Chuan bang dai”(CQ3-2021001).
文摘In order to improve the accuracy of building structure identification using remote sensing images,a building structure classification method based on multi-feature fusion of UAV remote sensing image is proposed in this paper.Three identification approaches of remote sensing images are integrated in this method:object-oriented,texture feature,and digital elevation based on DSM and DEM.So RGB threshold classification method is used to classify the identification results.The accuracy of building structure classification based on each feature and the multi-feature fusion are compared and analyzed.The results show that the building structure classification method is feasible and can accurately identify the structures in large-area remote sensing images.
文摘This paper aims to assess the ways in which multi-resolution object-based classification methods can be used to group urban environments made up of a mixture of buildings, sub-elements such as car parks, roads, shades and pavements and foliage such as grass and trees. This involves using both unmanned aerial vehicles (UAVs) which provide high-resolution mosaic Orthoimages and generate a Digital Surface Model (DSM). For the study area chosen for this paper, 400 Orthoimages with a spatial resolution of 7 cm each were used to build the Orthoimages and DSM, which were georeferenced using well distributed network of ground control points (GCPs) of 12 reference points (RMSE = 8 cm). As these were combined with onboard RTK-GNSS-enabled 2-frequency receivers, they were able to provide absolute block orientation which had a similar accuracy range if the data had been collected by traditional indirect sensor orientation. Traditional indirect sensor orientation involves the GNSS receiver in the UAV receiving a differential signal from the base station through a communication link. This allows for the precise position of the UAV to be established, as the RTK uses correction, allowing position, velocity, altitude and heading to tracked, as well as the measurement of raw sensor data. By assessing the results of the confusion matrices, it can be seen that the overall accuracy of the object-oriented classification was 84.37%. This has an overall Kappa of 0.74 and the data that had poor classification accuracy included shade, parking lots and concrete pavements. These had a producer accuracy (precision) of 81%, 74% and 74% respectively, while lakes and solar panels each scored 100% in comparison, meaning that they had good classification accuracy.
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Under the auspices of National Key Research&Development Program of China(No.2017YFC0505901,2017YFA0604904)
文摘The Yellow River Delta wetland is the youngest wetland ecosystem in China's warm temperate zone. To better understand how its landscape pattern has changed over time and the underlying factors responsible, this study analyzed the dynamic changes of wetlands using five Landsat series of images, namely MSS(Mulri Spectral Scanner), TM(Thematic Mapper), and OLI(Operational Land Imager) sensors in 1976, 1986, 1996, 2006, and 2016. Object-oriented classification and the combination of spatial and spectral features and both the Normalized Difference Vegetation Index(NDVI) and Normalized Difference Water Index(NDWI), as well as brightness characteristic indices, were used to classify the images in eCognition software. Landscape pattern changes in the Yellow River Delta over the past 40 years were then delineated using transition matrix and landscape index methods. Results show that: 1) from1976 to 2016, the total area of wetlands in the study area decreased from 2594.76 to 2491.79 km^2, while that of natural wetlands decreased by 954.03 km^2 whereas human-made wetlands increased by 851.06 km^2. 2) The transformation of natural wetlands was extensive: 31.34% of those covered by Suaeda heteropteras were transformed into reservoirs and ponds, and 24.71% with Phragmites australis coverage were transformed into dry farmland. Some human-made wetlands were transformed into non-wetlands types: 1.55% of reservoirs and ponds became construction land, and likewise 21.27% were transformed into dry farmland. 3) From 1976 to 2016, as the intensity of human activities increased, the number of landscape types in the study area continuously increased. Patches were scattered and more fragmented. The whole landscape became more complex. In short, over the past 40 years, the wetlands of the Yellow River Delta have been degraded, with the area of natural wetlands substantially reduced. Human activities were the dominant forces driving these changes in the Yellow River Delta.
基金National Natural Science Foundation of China(Grant No.40573047)National High-Tech Research&Development Program of China(Grant No.2008AA12A212)
文摘The object-oriented approach is a powerful method in making classification.With the segmentation of images to objects,many features can be calculated based on the objects so that the targets can be distinguished.However,this method has not been applied to lunar study.In this paper we attempt to apply this method to detecting lunar craters with promising results.Craters are the most obvious features on the moon and they are important for lunar geologic study.One of the important questions in lunar research is to estimate lunar surface ages by examination of crater density per unit area.Hence,proper detection of lunar craters is necessary.Manual crater identification is inefficient,and a more efficient and effective method is needed.This paper describes an object-oriented method to detect lunar craters using lunar reflectance images.In the method,many objects were first segmented from the image based on size,shape,color,and the weights to every layer.Then the feature of"contrast to neighbor objects"was selected to identify craters from the lunar image.In the next step,by merging the adjacent objects belonging to the same class,almost every crater can be taken as an independent object except several very big craters in the study area.To remove the crater rays diagnosed as craters,the feature of"length/width"was further used with suitable parameters to finish recognizing craters.Finally,the result was exported to ArcGIS for manual modification to those big craters and the number of craters was acquired.
基金The authors acknowledge that this study was financially supported by the National Key R&D Programs of China(No.2017YFB0504201)the Strategic Priority Research Program of Chinese Academy of Sciences(No.XDA20020101)+1 种基金and the Natural Science Foundation of China(No.61473286 and No.61375002)Our sincere thanks go to the students at the State Key Laboratory of Remote Sensing Science for their assistance during the field survey campaigns.
文摘Remote sensing is an important technical means to investigate land resources.Optical imagery has been widely used in crop classification and can show changes in moisture and chlorophyll content in crop leaves,whereas synthetic aperture radar(SAR)imagery is sensitive to changes in growth states and morphological structures.Crop-type mapping with a single type of imagery sometimes has unsatisfactory precision,so providing precise spatiotemporal information on crop type at a local scale for agricultural applications is difficult.To explore the abilities of combining optical and SAR images and to solve the problem of inaccurate spatial information for land parcels,a new method is proposed in this paper to improve crop-type identification accuracy.Multifeatures were derived from the full polarimetric SAR data(GaoFen-3)and a high-resolution optical image(GaoFen-2),and the farmland parcels used as the basic for object-oriented classification were obtained from the GaoFen-2 image using optimal scale segmentation.A novel feature subset selection method based on within-class aggregation and between-class scatter(WA-BS)is proposed to extract the optimal feature subset.Finally,crop-type mapping was produced by a support vector machine(SVM)classifier.The results showed that the proposed method achieved good classification results with an overall accuracy of 89.50%,which is better than the crop classification results derived from SAR-based segmentation.Compared with the ReliefF,mRMR and LeastC feature selection algorithms,the WA-BS algorithm can effectively remove redundant features that are strongly correlated and obtain a high classification accuracy via the obtained optimal feature subset.This study shows that the accuracy of crop-type mapping in an area with multiple cropping patterns can be improved by the combination of optical and SAR remote sensing images.
