|Table of Contents|

Hyperspectral RS image road feature extraction based on SVM

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2012年05期
Page:
34-38
Research Field:
Publishing date:

Info

Title:
Hyperspectral RS image road feature extraction based on SVM
Author(s):
SHEN Zhao-qing1;  HUANG Liang2;  TAO Jian-bin3
1. School of Highway, Chang’an University, Xi’an 710064, Shaanxi, China; 2. Shenzhen ZondySoftware Engineering Co Ltd, Shenzhen 518001, Guangdong, China; 3. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, Hubei, China
Keywords:
road engineering;  hyperspectral RS image;  support vector machine;  feature extraction
PACS:
U412.24
DOI:
-
Abstract:
In order to accurately extract various types of linear road from hyperspectral remote sensing(RS)images, a road feature fast extraction algorithm was proposed based on support vector machine(SVM). The reasonable image compression was conducted by PCA firstly. It was derived that SVM can extract road network information fast and accurately by SVM pattern recognition theory. Because hyperspectral RS image had a big amount of data and road network was very complex, we proposed the classification strategy based on 1Vm which could extract multi-class road fast and accurately at once. The new algorithm improved both efficiency and accuracy of road recognition.The experimental results show that the linear road feature recognition of SVM has better advantages than conventional method, especially for small sample road identification.The new algorithm can recognize not only linear feature of road but also its material and type. The algorithm multi-class strategy is constructed to recognize multi-class road with higher operation efficiency. 2 tabs, 6 figs, 11 refs.

References:

[1] 王培忠,严卫东,边 辉,等.提取蚀变信息时TM影像的最佳波段组合研究[J].地球科学与环境学报,2010,32(2):173-175.WANG Pei-zhong,YAN Wei-dong,BIAN Hui,et al. Study on optimal bands composite of TM image while extracting alteration information[J].Journal of Earth Sciences and Environment,2010,32(2):173-175.(in Chinese)
[2]于 欢,张树清,赵 军,等.基于ALOS遥感影像的湿地地表覆被信息提取研究[J].地球科学与环境学报,2010,32(3):324-330.YU Huan,ZHANG Shu-qing,ZHAO Jun,et al.Study on Wetland Cover Information Extraction Based on ALOS Remote Sensing Image[J].Journal of Earth Sciences and Environment,2010,32(3):324-330.(in Chinese)
[3]刘志刚.支撑向量机在光谱遥感影像分类中的若干问题研究[D].武汉:武汉大学,2004.LIU Zhi-gang.Key problems of applying support vector machines to the classification of spectral remote sensing imagery[D].Wuhan:Wuhan University,2004.
[4]Dalpoz A P,Dovale G M.Dynamic programming for semi automated road extraction from medium and high resolution images[J].International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences,2003,34:17-19.
[5]Dalpoz A P,Oliveira M A.Active testing and edge analysis for road centreline extraction[J].ISPRS Commission,2003(9):96-201.
[6]Lee H Y,Park W K,Lee H K,et al.Towards knowledge based extraction of roads from 1m-resolution satellite images[C]//IEEE.Southwest on Image Analysis and Interpretation.New York:LEEE,2000:171-176.
[7]邓乃扬,田英杰.数据挖掘中的新方法-支持向量机[M].北京:科学出版社,2004.DENG Nai-yang,TIAN Ying-jie.The new method of data mining-support vector machine[M].Beijing:Science Press,2004.(in Chinese)
[8]惠文华.基于支持向量机的遥感图像分类方法[J].地球科学与环境学报,2006,28(2):93-95.HUI Wen-hua.TM image classification based on support vector machine[J].Journal of Earth Sciences and Environment,2006,28(2):93-95.(in Chinese)
[9]杨国鹏,余旭初,陈 伟,等.基于核Fisher判别分析的高光谱遥感影像分类[J].遥感学报,2008,12(4):579-585.YANG Guo-peng,YU Xu-chu,CHEN Wei,et al.Hyperspectral remote sensing image classification based on kernel fisher discriminate analysis[J].Journal of Remoting Sensing,2008,12(4):579-585.(in Chinese)
[10]唐炉亮,杨必胜,徐开明.基于线状图形相似性的道路数据变化检测[J],武汉大学学报:信息科学版,2008,33(4):367-370.TANG Lu-liang,YANG Bi-sheng,XU Kai-ming.The road data change detection based on linear shape similarity[J].Journal of Wuhan University:Geomatics and Information Science,2008,33(4):367-370.(in Chinese)
[11]吴 冰,张占睦,秦志远,等.遥感影像上基于特征的道路提取方法[J].测绘学院学报,2004,21(3):190-192.WU Bing,ZHANG Zhan-mu,QIN Zhi-yuan,et al.The theory of the road extraction based on road character [J].Journal of Institute of Surveying and Mapping,2004,21(3):190-192.(in Chinese)

Memo

Memo:
-
Last Update: 2012-10-30