Pedestrian tracking is a critical problem in the field of computer vision. Particle filters have been proven to be very useful in\npedestrian tracking for nonlinear and non-Gaussian estimation problems.However, pedestrian many problems due to changes of pedestrian postures and scale,moving background,mutual occlusion, and presence of\npedestrian. To surmount these difficulties, this paper presents tracking algorithm of multiple pedestrians based on particle filters in\nvideo sequences. The algorithm acquires confidence value of the object and the background through extracting a priori knowledge\nthus to achieve multi pedestrian detection; it adopts color and texture features into particle filter to get better observation results and\nthen automatically adjusts weight value of each feature according to current tracking environment. During the process of tracking,\nthe algorithm processes severe occlusion condition to prevent drift and loss phenomena caused by object occlusion and associates\ndetection results with particle state to propose discriminated method for object disappearance and emergence thus to achieve robust\ntracking of multiple pedestrians. Experimental verification and analysis in video sequences demonstrate that proposed algorithm\nimproves the tracking performance and has better tracking results.
Loading....