To solve the problem of poor anti-noise performance of the traditional fuzzy C-means (FCM) algorithm in image segmentation, a novel two-dimensional FCM clustering algorithm for image segmentation was proposed. In this...To solve the problem of poor anti-noise performance of the traditional fuzzy C-means (FCM) algorithm in image segmentation, a novel two-dimensional FCM clustering algorithm for image segmentation was proposed. In this method, the image segmentation was converted into an optimization problem. The fitness function containing neighbor information was set up based on the gray information and the neighbor relations between the pixels described by the improved two-dimensional histogram. By making use of the global searching ability of the predator-prey particle swarm optimization, the optimal cluster center could be obtained by iterative optimization, and the image segmentation could be accomplished. The simulation results show that the segmentation accuracy ratio of the proposed method is above 99%. The proposed algorithm has strong anti-noise capability, high clustering accuracy and good segment effect, indicating that it is an effective algorithm for image segmentation.展开更多
In order to deal with the complex association relationships between classes in an object-oriented software system,a novel approach for identifying refactoring opportunities is proposed.The approach can be used to dete...In order to deal with the complex association relationships between classes in an object-oriented software system,a novel approach for identifying refactoring opportunities is proposed.The approach can be used to detect complex and duplicated many-to-many association relationships in source code,and to provide guidance for further refactoring.In the approach,source code is first transformed to an abstract syntax tree from which all data members of each class are extracted,then each class is characterized in connection with a set of association classes saving its data members.Next,classes in common associations are obtained by comparing different association classes sets in integrated analysis.Finally,on condition of pre-defined thresholds,all class sets in candidate for refactoring and their common association classes are saved and exported.This approach is tested on 4 projects.The results show that the precision is over 96%when the threshold is 3,and 100%when the threshold is 4.Meanwhile,this approach has good execution efficiency as the execution time taken for a project with more than 500 classes is less than 4 s,which also indicates that it can be applied to projects of different scales to identify their refactoring opportunities effectively.展开更多
The Koshi River Basin is in the middle of the Himalayas,a tributary of the Ganges River and a very important cross-border watershed.Across the basin there are large changes in altitude,habitat complexity,ecosystem int...The Koshi River Basin is in the middle of the Himalayas,a tributary of the Ganges River and a very important cross-border watershed.Across the basin there are large changes in altitude,habitat complexity,ecosystem integrity,land cover diversity and regional difference and this area is sensitive to global climate change.Based on Landsat TM images,vegetation mapping,field investigations and 3S technology,we compiled high-precision land cover data for the Koshi River Basin and analyzed current land cover characteristics.We found that from source to downstream,land cover in the Koshi River Basin in 2010 was composed of water body（glacier）,bare land,sparse vegetation,grassland,wetland,shrubland,forest,cropland,water body（river or lake） and built-up areas.Among them,grassland,forest,bare land and cropland are the main types,accounting for 25.83%,21.19%,19.31% and 15.09% of the basin＇s area respectively.The composition and structure of the Koshi River Basin land cover types are different between southern and northern slopes.The north slope is dominated by grassland,bare land and glacier;forest,bare land and glacier are mainly found on northern slopes.Northern slopes contain nearly seven times more grassland than southern slopes;while 97.13% of forest is located on southern slopes.Grassland area on northern slope is 6.67 times than on southern slope.The vertical distribution of major land cover types has obvious zonal characteristics.Land cover types from low to high altitudes are cropland,forest,Shrubland and mixed cropland,grassland,sparse vegetation,bare land and water bodies.These results provide a scientific basis for the study of land use and cover change in a critical region and will inform ecosystem protection,sustainability and management in this and other alpine transboundary basins.展开更多
Conventional image classification based on pixels hinders the possibilities to obtain information contained in images, while modern object-based classification methods increase the acquisition of information about the...Conventional image classification based on pixels hinders the possibilities to obtain information contained in images, while modern object-based classification methods increase the acquisition of information about the object and the context in which it is inserted in the image. The objective of this study was to investigate the performance of different classification methods for land cover mapping in the vicinity of the Alto Ribeira Tourist State Park, a Brazilian Atlantic rainforest area. Two classification methods were tested, including i） a hybrid per-pixel classification using the image processing software ERDAS Imagine version 9.1 and ii） an object-based classification using the software eCognition version 5. In the first method, six different classes were established, while in the second method, another two classes were established in addition to the six classes in the first method. Accuracy assessment of the classification results presented showed that the object-based classification with a Kappa index value of 0.8687 outperformed the per-pixel classification with a Kappa index value of 0.2224. Application of the user＇s knowledge during the object-based classification process achieved the desired quality; therefore, the use of inter-relationships between objects, superelasses, subclasses, and neighboring classes were critical to improving the efficiency of land cover classification.展开更多
基金Project(06JJ50110) supported by the Natural Science Foundation of Hunan Province, China
文摘To solve the problem of poor anti-noise performance of the traditional fuzzy C-means (FCM) algorithm in image segmentation, a novel two-dimensional FCM clustering algorithm for image segmentation was proposed. In this method, the image segmentation was converted into an optimization problem. The fitness function containing neighbor information was set up based on the gray information and the neighbor relations between the pixels described by the improved two-dimensional histogram. By making use of the global searching ability of the predator-prey particle swarm optimization, the optimal cluster center could be obtained by iterative optimization, and the image segmentation could be accomplished. The simulation results show that the segmentation accuracy ratio of the proposed method is above 99%. The proposed algorithm has strong anti-noise capability, high clustering accuracy and good segment effect, indicating that it is an effective algorithm for image segmentation.
文摘In order to deal with the complex association relationships between classes in an object-oriented software system,a novel approach for identifying refactoring opportunities is proposed.The approach can be used to detect complex and duplicated many-to-many association relationships in source code,and to provide guidance for further refactoring.In the approach,source code is first transformed to an abstract syntax tree from which all data members of each class are extracted,then each class is characterized in connection with a set of association classes saving its data members.Next,classes in common associations are obtained by comparing different association classes sets in integrated analysis.Finally,on condition of pre-defined thresholds,all class sets in candidate for refactoring and their common association classes are saved and exported.This approach is tested on 4 projects.The results show that the precision is over 96%when the threshold is 3,and 100%when the threshold is 4.Meanwhile,this approach has good execution efficiency as the execution time taken for a project with more than 500 classes is less than 4 s,which also indicates that it can be applied to projects of different scales to identify their refactoring opportunities effectively.
基金National Natural Science Foundation of China(41371120)Australian Government-funded Koshi Basin Programme at the International Centre for Integrated Mountain Development(ICIMOD)Key Research Program of the Chinese Academy of Sciences(ZDRW-ZS-2016-6)
文摘The Koshi River Basin is in the middle of the Himalayas,a tributary of the Ganges River and a very important cross-border watershed.Across the basin there are large changes in altitude,habitat complexity,ecosystem integrity,land cover diversity and regional difference and this area is sensitive to global climate change.Based on Landsat TM images,vegetation mapping,field investigations and 3S technology,we compiled high-precision land cover data for the Koshi River Basin and analyzed current land cover characteristics.We found that from source to downstream,land cover in the Koshi River Basin in 2010 was composed of water body（glacier）,bare land,sparse vegetation,grassland,wetland,shrubland,forest,cropland,water body（river or lake） and built-up areas.Among them,grassland,forest,bare land and cropland are the main types,accounting for 25.83%,21.19%,19.31% and 15.09% of the basin＇s area respectively.The composition and structure of the Koshi River Basin land cover types are different between southern and northern slopes.The north slope is dominated by grassland,bare land and glacier;forest,bare land and glacier are mainly found on northern slopes.Northern slopes contain nearly seven times more grassland than southern slopes;while 97.13% of forest is located on southern slopes.Grassland area on northern slope is 6.67 times than on southern slope.The vertical distribution of major land cover types has obvious zonal characteristics.Land cover types from low to high altitudes are cropland,forest,Shrubland and mixed cropland,grassland,sparse vegetation,bare land and water bodies.These results provide a scientific basis for the study of land use and cover change in a critical region and will inform ecosystem protection,sustainability and management in this and other alpine transboundary basins.
基金Supported by the Sa o Paulo Research Foundation (FAPESP), Brazil
文摘Conventional image classification based on pixels hinders the possibilities to obtain information contained in images, while modern object-based classification methods increase the acquisition of information about the object and the context in which it is inserted in the image. The objective of this study was to investigate the performance of different classification methods for land cover mapping in the vicinity of the Alto Ribeira Tourist State Park, a Brazilian Atlantic rainforest area. Two classification methods were tested, including i） a hybrid per-pixel classification using the image processing software ERDAS Imagine version 9.1 and ii） an object-based classification using the software eCognition version 5. In the first method, six different classes were established, while in the second method, another two classes were established in addition to the six classes in the first method. Accuracy assessment of the classification results presented showed that the object-based classification with a Kappa index value of 0.8687 outperformed the per-pixel classification with a Kappa index value of 0.2224. Application of the user＇s knowledge during the object-based classification process achieved the desired quality; therefore, the use of inter-relationships between objects, superelasses, subclasses, and neighboring classes were critical to improving the efficiency of land cover classification.
