Systems, Man, and Cybernetics

 

Home

• [P706] A Shadow Detection Method for Remote Sensing Images Using Affinity Propagation Algorithm
  Author(s): Xinyu Chen, Huaiying Xia, Ping Guo
  
  

  Abstract
  Shadow detection in high spatial resolution remote sensing image is very critical for locating geographical targets. In this paper, we propose a new shadow detection method based on the Affinity Propagation (AP) algorithm in the Hue-Saturation-Intensity (HSI) color space. However, pixel matrix is a large-scale matrix. If we use AP directly, it will consume a large amount of system resources and spend a lot of time to calculate the similarity matrix, we divide the matrix into several blocks and then applying AP to detect shadows in H, S, and I components respectively. Finally, three detected result images are fused to obtain a final shadow detection image. The experimental results show the effectiveness of the proposed approach, and it can solve the problems of threshold false dismissals and has higher precision than other clustering algorithms such as K-means.

  
   

Full Text (PDF)