Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Beijing University of Aeronautics and Astronautics》 2003-04
Add to Favorite Get Latest Update

Extraction of Linear Features of SAR Images Based on Fuzzy and Least Square

Wang Yanli Chen Zhe (School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics)  
A linear feature extraction method is proposed for SAR image. Firstly, the speckle noise in the radar image is filtered out. Secondly, the SAR image is processed by fuzzy transition and enhancement. Then, the low-pass and high-pass filters are designed by the least squares methods and the gradient strength map and direction map are acquired. Lastly, the gradient profile maximum method is adopted to detect feature points, which are connected to form the linear feature map of the SAR image. Simulation results show that the proposed method has the characteristic of anti-noise, the precision of positioning can reach 1 pixel.
【Fund】: 航空基础科学基金资助项目 ( 99E5 10 18)
【CateGory Index】: TN957.522
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved