Sorry, you need to enable JavaScript to visit this website.

Hard Shadows Removal Using An Approximate Illumination Invariant

Citation Author(s):
Bingshu Wang, C.L. Philip Chen, Yuyuan Li, Yong Zhao
Submitted by:
Bingshu Wang
Last updated:
20 April 2018 - 1:49am
Document Type:
Poster
Document Year:
2018
Event:
Presenters:
Bingshu Wang
Paper Code:
1759
 

Hard shadows detection and removal from foreground masks is a challenging step in change detection. This paper gives a simple and effective method to address hard shadows. There are inside portion and boundary portion in hard shadows. Pixel-wise neighborhood ratio is calculated to remove the most of inside shadow points. For the boundaries of shadow regions, we take advantage of color constancy to eliminate the edges of hard shadows and obtain relative accurate objects contours. Then, morphology processing is explored to enhance the integrity of objects. The main contribution of this paper is to design an approximate estimation strategy for illumination invariant based on Lambertian reflectance model without prior knowledge. The proposed method is unsupervised and experimental results on six challenging sequences show the effectiveness and robustness of our approach.

up
0 users have voted: