Road extraction from high resolution dual-polarization SAR images over urban areas

Su-yuan Li; Wen Yang; Hang Yang; Hong Sun

doi:10.1117/12.814904

29 December 2008 Road extraction from high resolution dual-polarization SAR images over urban areas

Su-yuan Li, Wen Yang, Hang Yang, Hong Sun

Proceedings Volume 7285, International Conference on Earth Observation Data Processing and Analysis (ICEODPA); 72850Q (2008) https://doi.org/10.1117/12.814904
Event: International Conference on Earth Observation Data Processing and Analysis, 2008, Wuhan, China

Abstract

This paper aims at the extraction of roads and road network from high-resolution dual-polarization synthetic aperture radar data over urban areas. According to the different features and applications for road network, the errors will be brought in the detection algorithm if it was not selected correctly. We proposed a modified extraction method making full use of available information to reduce such errors. In particular, we want to show how to implement road extraction algorithms based on the D-S evidence theory to establish the frame of discernment. The responses of two line detectors at the local analysis process were combined, which was done at the feature level by balancing the weight of two propositions constructed by responses of two line detectors. Then the road network optimization is accomplished using a Markov random field model of road, where both some contextual knowledge and global constraints were taken into account. The experimental results indicate that the proposed method is promising for main roads detection of urban areas.

Citation Download Citation

Su-yuan Li, Wen Yang, Hang Yang, and Hong Sun "Road extraction from high resolution dual-polarization SAR images over urban areas", Proc. SPIE 7285, International Conference on Earth Observation Data Processing and Analysis (ICEODPA), 72850Q (29 December 2008); https://doi.org/10.1117/12.814904

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