Translator Disclaimer
Paper
14 December 2015 Automatic aerial image shadow detection through the hybrid analysis of RGB and HIS color space
Author Affiliations +
Proceedings Volume 9815, MIPPR 2015: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications; 981506 (2015) https://doi.org/10.1117/12.2205847
Event: Ninth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2015), 2015, Enshi, China
Abstract
This paper presents our research on automatic shadow detection from high-resolution aerial image through the hybrid analysis of RGB and HIS color space. To this end, the spectral characteristics of shadow are firstly discussed and three kinds of spectral components including the difference between normalized blue and normalized red component - BR, intensity and saturation components are selected as criterions to obtain initial segmentation of shadow region (called primary segmentation). After that, within the normalized RGB color space and HIS color space, the shadow region is extracted again (called auxiliary segmentation) using the OTSU operation, respectively. Finally, the primary segmentation and auxiliary segmentation are combined through a logical AND-connection operation to obtain reliable shadow region. In this step, small shadow areas are removed from combined shadow region and morphological algorithms are apply to fill small holes as well. The experimental results show that the proposed approach can effectively detect the shadow region from high-resolution aerial image and in high degree of automaton.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jun Wu, Huilin Li, and Zhiyong Peng "Automatic aerial image shadow detection through the hybrid analysis of RGB and HIS color space", Proc. SPIE 9815, MIPPR 2015: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications, 981506 (14 December 2015); https://doi.org/10.1117/12.2205847
PROCEEDINGS
6 PAGES


SHARE
Advertisement
Advertisement
Back to Top