An efficient cloud detection method for high resolution remote sensing panchromatic imagery

Chaowei Li; Zaiping Lin; Xinpu Deng

doi:10.1117/12.2302791

10 April 2018 An efficient cloud detection method for high resolution remote sensing panchromatic imagery

Chaowei Li, Zaiping Lin, Xinpu Deng

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.

Citation Download Citation

Chaowei Li, Zaiping Lin, and 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); https://doi.org/10.1117/12.2302791

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