Dark Object-Free Shadow Detection from a Single Image
Jihee Han, Wonjun Kim · 2018
This paper presents a novel method for detecting shadow regions from a single image. The key idea of the proposed method is to filter out dark objects, which still give a great difficulty in shadow detection, by using the very-high order residual model. To reduce the mismatching problem at the boundary of shadow regions, we also propose to apply the edge-aware matting technique to our detection results. Experimental results show that the proposed method is effective for shadow detection under various environments.