26 October 2013 Building detection based on saliency for high resolution satellite images
Author Affiliations +
Proceedings Volume 8918, MIPPR 2013: Automatic Target Recognition and Navigation; 89180D (2013) https://doi.org/10.1117/12.2032154
Event: Eighth International Symposium on Multispectral Image Processing and Pattern Recognition, 2013, Wuhan, China
Abstract
For building detection from single very high spatial resolution (VHR) satellite images, we take advantage of visual saliency and Bayesian model to rapidly locate roof-top areas. We firstly generate saliency map of an image by a salient contrast filter using low-level feature. This filter distinguishes salient pixels if a pixel is visually different from its surroundings in color or texture. Secondly, a Bayesian model is proposed to generate all closed rectangular contours as mid-level content in the image. We suggest the area enclosed by contour corresponds to high saliency values. Finally, the roof-top areas are extracted by fusing different level information mentioned above. Experimental results demonstrate the effectiveness of our algorithm.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ping Yang, Ping Yang, Zhiguo Jiang, Zhiguo Jiang, Hao Feng, Hao Feng, Yibing Ma, Yibing Ma, } "Building detection based on saliency for high resolution satellite images", Proc. SPIE 8918, MIPPR 2013: Automatic Target Recognition and Navigation, 89180D (26 October 2013); doi: 10.1117/12.2032154; https://doi.org/10.1117/12.2032154
PROCEEDINGS
6 PAGES


SHARE
Back to Top