Object contour detection in remote sensing image

Chao Qian; Chu He; Xin-ping Deng; Hong Sun

doi:10.1117/12.836956

30 October 2009 Object contour detection in remote sensing image

Chao Qian, Chu He, Xin-ping Deng, Hong Sun

Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74952G (2009) https://doi.org/10.1117/12.836956
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China

Abstract

This paper presents an effective algorithm frame for obtaining objects contour via automatically extracting the foreground and the background. Based on active basis and muti-scale object detection, object fragments are detected. Instead of changing the scales of the model, the scales of the images are changed for detection. For getting various affine transformation and projective transformation, an algorithm frame is proposed to get the whole contour of the object. Firstly, the fragments which are detected by active basis are connected in accordance with apperceive rules, so the shape of the object can be reconstructed by these fragments. Secondly, successions of morphological methods are employed to get the foreground and the background respectively. Finally combined with Bayesian theory, MRF and graph cut algorithm, the whole contour of the object is drawn. Experiments on remote sensing images show the efficient performance of the novel algorithm frame.

Citation Download Citation

Chao Qian, Chu He, Xin-ping Deng, and Hong Sun "Object contour detection in remote sensing image", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74952G (30 October 2009); https://doi.org/10.1117/12.836956

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