Novel radon transform-based method for linear feature detection in open water SAR images

Jie Chen; Jiyin Sun

doi:10.1117/12.741410

14 November 2007 Novel radon transform-based method for linear feature detection in open water SAR images

Jie Chen, Jiyin Sun

Proceedings Volume 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications; 67900C (2007) https://doi.org/10.1117/12.741410
Event: International Symposium on Multispectral Image Processing and Pattern Recognition, 2007, Wuhan, China

Abstract

Open water SAR images frequently exhibit long dark or bright linear features, some of which are ship wakes, internal wave or internal wave wakes of under water moving objects. The detection of these line features is very impotent in both civil and military fields. Considering to the drawbacks of conventional Radon transform, this paper proposed a novel liner feature detection method. It use the gliding window and firstly apply a Radon transform to the aim image, use a "mean matrix" to normalize the aim image in the Radon domain, and then search for the peaks or troughs in an ellipse region instead of the whole region. This algorithm is tested on a set of simulated SAR images of ship wakes. The results demonstrate that this algorithm's robustness in the presence of noise, as well as its ability to detect and localize linear features that are somewhat not so straight.

Citation Download Citation

Jie Chen and Jiyin Sun "Novel radon transform-based method for linear feature detection in open water SAR images", Proc. SPIE 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications, 67900C (14 November 2007); https://doi.org/10.1117/12.741410

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