30 October 2009 Road extraction with despeckled TerraSAR-X data using total variation minimization
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74953N (2009) https://doi.org/10.1117/12.833141
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
Abstract
Due to random interference of electromagnetic waves in imaging procedure, SAR images are corrupted by speckle noise which limits the performance of the road extraction algorithm in spatial domain. In this paper, we aimed at the reduction of speckle noise through analytic approaches. To this end, Total Variation (TV) minimization is used to produce despeckled images that are almost photographic in appearance from original SAR images. Then, a semi-automatic road extraction technique based on fast marching algorithm provided in our previous work is applied to the despeckled SAR images. Experiment results for TerraSAR-X data demonstrates that TV minimization could effectively eliminate the false connectivity of extracted road network, which is caused by speckle noise.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yunpeng Zhang, Yunpeng Zhang, Manchun Li, Manchun Li, Xiaogu Sun, Xiaogu Sun, Wei Liu, Wei Liu, } "Road extraction with despeckled TerraSAR-X data using total variation minimization", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74953N (30 October 2009); doi: 10.1117/12.833141; https://doi.org/10.1117/12.833141
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT


Back to Top