Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Science & Technology Review》 2009-21
Add to Favorite Get Latest Update

An Object-Oriented Optimal Scale Choice Method for High Spatial Resolution Remote Sensing Image

ZHANG Jun1, WANG Yunjia2, LI Yan2, WANG Xingfeng2 1. No.3 Topographic Survey Team, State Bureau of Surveying and Mapping, Harbin 150081, China 2. School of Environment & Spatial Informatics, China University of Mining and Technology, Xuzhou 221008, Jiangsu Province, China  
The traditional pixel-based information extraction and classification method is not suitable for processing high spatial resolution remote sensing images because it only focuses on spectral information and ignores information concerning texture, shape and structure related with adjacent pixels. The object-oriented information and classification extraction approach can solve this problem, with the basic unit being the image object, which enjoys good integrity and uniqueness in a multi-scale segmentation algorithm. The related experimental researches show that it is necessary to extract the region of interest in optimal scale images. In view of this, the RMAS method is based on analysis of the limitations of two optimal scale selecting methods, according to the best classification principle as "homogeneity in class, heterogeneity between classes". This method makes the heterogeneity in class the minimum and that between class the maximum when RMAS is the maximum, so the segmentation scale is optimal. According to the principle of the highest information extraction accuracy based on the optimal scale, the experiment has verified the feasibility of this method and the classification results are found to be better. It is shown that several local peaks appear in the curve of RMAS and that the optimal scale is relative and usually in a range of values. So, it is difficult to extract information using only one scale for the class with a large area. The optimal scale should be very carefully chosen according to specific application cases.
【Fund】: 西部测图项目;; 国家自然科学基金重点项目(50534050);; 矿山空间信息技术国家测绘局重点实验室开放基金项目(KLM200819)
【CateGory Index】: TP751
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
【References】
Chinese Journal Full-text Database 1 Hits
1 ZHANG Jun WANG Baoshan ZHANG Zhiqiang(3 Topographic Survey Team of SBSM,2 Ceihui Road Nangang District,Hrbin 150081,China);HIGH SPATIAL RESOLUTION REMOTE SENSING IMAGE CLASSIFICATION BASED ON OBJECT-ORIENTED MULTI-FEATURES[J];Journal of Geomatics;2010-03
【Co-references】
Chinese Journal Full-text Database 10 Hits
1 XU Gao-cheng et al(College of Environment and Resource College,Southwest Science and Technology University,Mianyang,Sichuan 621010);Application of Supporting Vector Machine Technology in Extraction of Remote Sensing Image of Landslide[J];Journal of Anhui Agricultural Sciences;2009-06
2 Wang Wenyu~1,Li Bo~2(1.School of Geomatics and Urban Information,Beijing 100044;2.School of Geography and Remote Sensing,Beijing Normal University,Beijing 100875);Auto-identify Classification Technology Adopted to High-resolution Remote Sensing Image by eCognition Software[J];Journal of Beijing Institute of Civil Engineering and Architecture;2006-04
3 LI Ying 1, ZHAO Wen_ji 2, LI Xiao_lin 1 (1.College of Geoexploration and Technology, Jilin University, Changchun 130026,China; 2.Capital Normal University, Beijing 100037,China);CLASSIFICATION OF RS-IMAGE AND RECOGNITION TECHNIQUE UTILIZE IN LAND AND SOURCES INVESTIGATING[J];Journal of Changchun University of Science and Technology;2001-03
4 Qin Qiming(Institute of Remote Sensing & GIS of Peking University,Beijing,100871);The Problem and Approach in the Auto-interpretation of Remote Sensing Imagery[J];DEVELOPMENTS IN SURVEYING AND MAPPING;2000-02
5 LIU Zheng-jun,ZHANG Ji-xian,MENG Ya-bin,LIANG Xin-lian,SUN Xiao-xia(Chinese Academy of Surveying and Mapping, Beijing 100039,China);Method of building extraction from high resolution image based on classification and shape generalization[J];Science of Surveying and Mapping;2007-03
6 WANG Mu-hua①②,ZHANG Jix-ian①,LI Hai-tao①,XU Hua-long①②(①Chinese Acadamy of Surveying and Mapping,Beijing 100039,China,②Liaoning Technical University,Liaoning Fuxin 123000,China);High resolution images change detection based on region feature[J];Science of Surveying and Mapping;2009-01
7 MA Li1, 2, CHEN Jun2 School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China; 2.National Geomatics Center of China, Beijing 100044, China);Classification and Application of Context Information in Road Extraction[J];Geomatics World;2008-04
8 SHEN Shao-hong,LAI Zu-long,WAN You-chuan;Change Detection of High-resolution RS Imagery Based on Fusion[J];Bulletin of Surveying and Mapping;2009-03
9 WU Hong-tao1,LIU Jing-dong2(1.Tianjin Institute of Surveying and Mapping,Tianjin 300381,China;2.The Second Heilongjiang Institute of Surveying and Mapping Engineering,Harbin 150086,China);Analysis and Discussion on Classification Techniques Based on High Resolution Remote Sensing Image[J];Geomatics & Spatial Information Technology;2008-02
10 LI Jun-mei,HU Yi-hua,CHEN Xiu-qiao(Electronic Engineering Institute of PLA,Hefei 230037,China);Feature optimizing expert system for pattern recognition[J];Electronics Optics & Control;2006-01
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved