Road extraction with despeckled TerraSAR-X data using total variation minimization

Yunpeng Zhang; Manchun Li; Xiaogu Sun; Wei Liu

doi:10.1117/12.833141

30 October 2009 Road extraction with despeckled TerraSAR-X data using total variation minimization

Yunpeng Zhang, Manchun Li, Xiaogu Sun, Wei Liu

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.

Citation Download Citation

Yunpeng Zhang, Manchun Li, Xiaogu Sun, and 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); https://doi.org/10.1117/12.833141

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available