摘 要：視頻中運動物體的檢測是用當前圖像減去背景圖像，背景提取是一個重要環節，本文利用傳統的高斯背景建模的方法提取背景。由于光照等因素的影響，得到的前景圖像會包含陰影區域，影響了運動物體檢測。本文提出了一種簡單有效的方法，即利用RGB顏色信息檢測出前景區域中的陰影部分，從而檢測到真正的運動物體區域。
Abstract: In moving detection, moving objects are gained after current image minus background image. So background extraction is a very important step. We use Gaussian Background Modeling – a traditional method to detect moving objects. But because of illumination, the moving objects we get contain shadow regions which affect moving detection deeply. In this paper, a simple and effective method with RGB information is proposed to detect the real moving regions.
Key words: Gaussian Background Modeling, RGB information, shadow detection.
參考文獻
[1] Jun-Wei Hsieh, Wen-Fong Hu, Chia-Jung Chang, Yung-Sheng Chen. Shadow elimination for effective moving object detection by Gaussian shadow modeling. Image and Vision Computing, 21(2): 505-516, 2003.
[2] Jun-Wei Hsieh, Shih-Hao Yu, Yung-Sheng Chen, Wen-Fong Hu. A shadow elimination method for vehicle analysis. Proc. ICPR, Cambridge, UK, 2004, Vol. 4, pp. 372-375.
[3] A. Yoneyama, C. H. Yeh, and C. -C. J. Kuo. Moving cast shadow elimination for robust vehicle extraction based on 2-D joint vehicle/shadow models. Proc. ICAVSBS, Miami, FL, 2003, pp. 21-22.
[4] S. Nadimi and B. Bhanu. Physical models for moving shadow and object detection in video. IEEE Trans. Pattern Anal. Mach. Intell., 26(8): 1079-1087, 2004.
[5] A. Prati, I. Mikic, M. M. Trivedi, and R. Cucchiara. Detecting moving shadows: Algorithms and evaluation. IEEE Trans. Pattern Anal. Mach. Intell., 25(7): 918-923, 2003.
[6] Rita. Cucchiara, Costantino. Grana, M. Piccardi, Andrea Prati and Stefano Sirotti. Improving Shadow Suppression in Moving Object Detection with HSV Color Information. Proc. ICITS, Oakland (CA), USA, 2001, pp: 334-339.
[7] Pankaj Kumar, Kuntal Sengupta and Adrian Lee. A Comparative Study of Different Color Spaces for Foreground and Shadow Detection for Traffic Monitoring System. Proc. ICITS, Singapore, 2002, pp.100-105.
[8] T. Gevers, H. Stokman. Classifying color edges in video into shadow-geometry, highlight, or material transitions. IEEE Trans. Multimedia, 5(2): 237-243, 2003.
[9] Kai-Tai Song, Jen-Chao Tai. Image-Based Traffic Monitoring With Shadow Suppression. Proceedings of the IEEE, 95(2): 413-426, 2007.
[10] L. G. Shapiro and G. C. Stockman, Computer Vision. Englewood Cliffs, NJ: Prentice-Hall, 2001.
作者簡介
奚穩（1988 - ）男，安徽六安人。2009年7月獲得東南大學生物醫學工程學士學位�，F就讀于東南大學生物科學與醫學工程學院，主要研究方向為視頻中運動物體的檢測與識別。
