Algorithm of extended terrain classification in high-resolution SAR images

Kun Fu; Gangyao Kuang; Wenxian Yu

doi:10.1117/12.441644

Translator Disclaimer

24 September 2001 Algorithm of extended terrain classification in high-resolution SAR images

Kun Fu, Gangyao Kuang, Wenxian Yu

Author Affiliations +

Proceedings Volume 4554, Object Detection, Classification, and Tracking Technologies; (2001) https://doi.org/10.1117/12.441644
Event: Multispectral Image Processing and Pattern Recognition, 2001, Wuhan, China

Abstract

A target classification algorithm in high resolution and single polarimetric SAR image is presented in this paper. First, a new RCS reconstruction filter base don the modified correlated neighborhood model is used for target and shadow detection. By nonlinear iterated process, the whole image can be classified to 'background', 'shadow' and 'targets'. Secondly, a series of morphological operators are used to terrain filtering and edge extraction, and then through modified Hough Transform technology and the measure of slimming lines, line structures of man-made clutters in 'target' class are linked and grouped. Finally, with spatial association mode, the targets we are interested in are classified.

Citation Download Citation

Kun Fu, Gangyao Kuang, and Wenxian Yu "Algorithm of extended terrain classification in high-resolution SAR images", Proc. SPIE 4554, Object Detection, Classification, and Tracking Technologies, (24 September 2001); https://doi.org/10.1117/12.441644

ACCESS THE FULL ARTICLE