Automatic change detection based on least square image matching

Mi Wang; Baorong Zhang; Xiaogang Ning

doi:10.1117/12.651849

2 December 2005 Automatic change detection based on least square image matching

Mi Wang, Baorong Zhang, Xiaogang Ning

Proceedings Volume 6045, MIPPR 2005: Geospatial Information, Data Mining, and Applications; 604534 (2005) https://doi.org/10.1117/12.651849
Event: MIPPR 2005 SAR and Multispectral Image Processing, 2005, Wuhan, China

Abstract

The key of automatic change detection between multi-temporal images is these images' matching accuracy should reach sub-pixel level. Nevertheless, due to the influence of various factors of geometrical distortion, remote sensing images after precise geometrical correction always still have pixel-level geometrical distortion. Therefore, ideal result of automatic change detection can't be achieved by these images directly. This paper proposes a new automatic change detection approach based on least square image matching. Using least square method to correct images' distortion, we get the Maximum correlation coefficient by iteration and obtain the optimal match point. By correlation coefficient, whether change or not can also be estimated. This approach resolves the multi-temporal image matching accuracy's influence to the change detection result, by which the accuracy of automatic change detection is guaranteed. The experiment results are provided, which indicate the effectiveness and the reliability of the approach.

Citation Download Citation

Mi Wang, Baorong Zhang, and Xiaogang Ning "Automatic change detection based on least square image matching", Proc. SPIE 6045, MIPPR 2005: Geospatial Information, Data Mining, and Applications, 604534 (2 December 2005); https://doi.org/10.1117/12.651849

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