Title :
Detecting Moving Shadows in Video Sequences Using Region Level Evaluation for Vision-Based Vehicle Detection
Author :
Wei-Gang, Chen ; Bin, Xu
Author_Institution :
Sch. of Comput. & Inf. Eng., Zhejiang Gongshang Univ., Hangzhou, China
Abstract :
In this paper, a multistage algorithm, which is applicable to vision-based vehicle detection system, for detecting and removing cast shadows is proposed. In the first stage, a novel noise level adapted method is presented to segment foreground which consists the moving objects and moving shadows. In the second stage, the foreground is partitioned into sub-regions using multilevel thresholding. Then, a three-step region-based evaluation is employed to check whether a region is a shadow or not. Results on various real surveillance sequences, which contains shadows range from dark and small to light and large, show the effectiveness of the proposed approach.
Keywords :
image segmentation; object detection; vehicles; video signal processing; foreground segmentation; moving shadows detection; multilevel thresholding; multistage algorithm; noise level adapted method; three-step region-based evaluation; video sequences; vision-based vehicle detection system; Histograms; Image segmentation; Noise; Pixel; Vehicle detection; Vehicle dynamics; Vehicles; Shadow detection; Vehicle Detection; multilevel thresholding; noise level adapted;
Conference_Titel :
Frontier of Computer Science and Technology (FCST), 2010 Fifth International Conference on
Conference_Location :
Changchun, Jilin Province
Print_ISBN :
978-1-4244-7779-1
DOI :
10.1109/FCST.2010.89