題名: An Unsupervised Shadow Detection Algorithm
作者: Huang, Chung-Hsien
Wu, Ruei-Cheng
關鍵字: Shadow Detection
Video Surveillance
Robust Estimation
期刊名/會議名稱: 2008 ICS會議
摘要: Shadow detection is a critical issue for most applications of video surveillance. In this study, we proposed an unsupervised method to detect shadow caused by moving objects without setting any priori parameters or threshold values. The color histograms of moving objects’ image patch are collected to learn an accumulated distribution in each color domain. The accumulating strategy strengthens the impact of shadow parts in the image patch but reduces the effects of other non-shadow parts. By taking the advantage of robust estimation, the most significant peak, i.e. the shadows, in the accumulated distribution is fitted by a Gaussian function. As a result, if a pixel’s feature value is within the 2σ range of the Gaussian function,, it can thus be determined as shadows.
日期: 2009-02-12T01:27:05Z
分類:2008年 ICS 國際計算機會議

文件中的檔案:
檔案 描述 大小格式 
ce07ics002008000126.pdf326.65 kBAdobe PDF檢視/開啟


在 DSpace 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。