Title :
Shadow Removal Based on Shadow Direction and Shadow Attributes
Author :
Lu, Yinghua ; Xin, Huijie ; Kong, Jun ; Li, Bingbing ; Wang, Yan
Author_Institution :
Comput. Sch., Northeast Normal Univ., Jilin
fDate :
Nov. 28 2006-Dec. 1 2006
Abstract :
Moving shadow removal is critical for robust moving object tracking system. A shadow removal algorithm based on shadow attributes is presented in this paper. The direction of shadow is estimated first, and then shadow points are sampled based on the direction of shadow. At last the shadow attributes is calculated using the sampled shadow points. The shadow is removed based on shadow attributes. Experimental results are presented to show that our algorithm is better than some other methods.
Keywords :
estimation theory; image motion analysis; object detection; sampling methods; tracking; traffic engineering computing; intelligent traffic system; moving object tracking system; moving shadow removal; shadow attributes; shadow direction estimation; shadow points sampling; Cameras; Computational intelligence; Laboratories; Layout; Object detection; Shape measurement; Statistics; Surveillance; Traffic control; Vehicle detection;
Conference_Titel :
Computational Intelligence for Modelling, Control and Automation, 2006 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, International Conference on
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7695-2731-0
DOI :
10.1109/CIMCA.2006.196