Ahmed Mahmoud HAMAD^1* and Norimichi TSUMURA

Graduate School of Advanced Integration Science, Chiba University, Chiba 263-8522, Japan ¹Department of Information Technology, Faculty of Computers and Information, Menofia University, Egypt

(Received August 15, 2011; Accepted December 14, 2011)

This paper proposes a robust method to detect and extract silhouettes of foreground objects from a video sequence of a static camera based on the improved background subtraction technique. The proposed method analyses statistically the pixel history as time series observations. The proposed method presents a robust technique to detect motions based on kernel density estimation. Two consecutive stages of the k-means clustering algorithm are utilized to identify the most reliable background regions and decrease the detection of false positives. Pixel and object based updating mechanism for the background model is presented to cope with challenges like gradual and sudden illumination changes, ghost appearance, non-stationary background objects, and moving objects that remain stable for more than the half of the training period. Experimental results show the efficiency and the robustness of the proposed method to detect and extract the silhouettes of moving objects in outdoor and indoor environments compared with conventional methods.

Key words: background subtraction, motion detection, kernel density estimation, statistical modeling, k-means clustering

^*E-mail address: hamad@graduate.chiba-u.jp