Abstract:

In this paper, a real-time background modeling and maintenance based human motion detection and analysis in an indoor and an outdoor environments for visual surveillance system is described. The system operates on monocular gray scale video imagery from a static CCD camera. In order to detect foreground objects, first, background scene model is statistically learned using the redundancy of the pixel intensities in a training stage, even the background is not completely stationary. This redundancy information of the each pixel is separately stored in an history map shows how the pixel intensity values changes till now. Then the highest ratio of the redundancy on the pixel intensity values in the history map in the training sequence is determined to have initial background model of the scene. A background maintenance model is also proposed for preventing some kind of falsies, such as, illumination changes (the sun being blocked by clouds causing changes in brightness), or physical changes (person detection while he is getting out or passing in front of the parked car). At the background modeling and maintenance, the reliability and computational costs of the algorithm presented are comparatively discussed with several algorithms. Based on the background modeling, candidate foreground regions are detected using thresholding, noise cleaning and their boundaries extracted using morphological filters. Then for people detection, object detection and classification approach for distinguishing a person, a group of person from detected foreground objects (e.g., cars) using silhouette shape and periodic motion cues is performed. Finally, the trajectory of the people in motion and several motion parameters produced from the cyclic motion of silhouette of the object under tracking are implemented for analyzing people activities such as walking and running, in the video sequences. Experimental results on the different test image sequences demonstrate that the proposed algorithm has an encouraging real-time background modeling based human motion detection and analysis performance with relatively robust and low computational cost.

Keywords: