Title :
A Robust Algorithm for Shadow Removal of Foreground Detection in Video Surveillance
Author :
Wang, Chuanxu ; Zhang, Weijuan
Author_Institution :
Inst. of Inf., Qingdao Univ. of Sci. & Technol., Qingdao, China
Abstract :
We proposed an accurate algorithm to prevent moving shadows from being misclassified as part of moving objects in video target segmentation in this paper. Firstly, moving objects were achieved through background subtraction using adaptive Gaussian mixture models. Then, moving shadows were eliminated by a shadow detection algorithm. Finally, we performed a morphological reconstruction algorithm to recover the foreground distorted after shadow removal process. The experimental results proved its validity and accuracy in various fixed outdoor video scenes.
Keywords :
Gaussian processes; image colour analysis; image reconstruction; image segmentation; object detection; video signal processing; video surveillance; Gaussian mixture model; HSV color space; foreground detection; morphological reconstruction algorithm; moving object detection; robust algorithm; shadow removal process; video image; video surveillance; video target segmentation; Data mining; Gaussian distribution; Image segmentation; Layout; Object detection; Reconstruction algorithms; Robustness; Shape; Space technology; Video surveillance; Gaussian mixture models; HSV color space; morphological reconstruction; shadow removal; video segmentation;
Conference_Titel :
Information Processing, 2009. APCIP 2009. Asia-Pacific Conference on
Conference_Location :
Shenzhen
Print_ISBN :
978-0-7695-3699-6
DOI :
10.1109/APCIP.2009.240
