10 April 2018 An efficient cloud detection method for high resolution remote sensing panchromatic imagery
Author Affiliations +
Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 106154V (2018) https://doi.org/10.1117/12.2302791
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China
Abstract
In order to increase the accuracy of cloud detection for remote sensing satellite imagery, we propose an efficient cloud detection method for remote sensing satellite panchromatic images. This method includes three main steps. First, an adaptive intensity threshold value combined with a median filter is adopted to extract the coarse cloud regions. Second, a guided filtering process is conducted to strengthen the textural features difference and then we conduct the detection process of texture via gray-level co-occurrence matrix based on the acquired texture detail image. Finally, the candidate cloud regions are extracted by the intersection of two coarse cloud regions above and we further adopt an adaptive morphological dilation to refine them for thin clouds in boundaries. The experimental results demonstrate the effectiveness of the proposed method.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Chaowei Li, Zaiping Lin, Xinpu Deng, "An efficient cloud detection method for high resolution remote sensing panchromatic imagery", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106154V (10 April 2018); doi: 10.1117/12.2302791; https://doi.org/10.1117/12.2302791
PROCEEDINGS
8 PAGES


SHARE
Back to Top