A particle filter for joint detection and tracking of multiple objects in color video sequences

The paper presents a particle filter for integrated detection and tracking of multiple objects in image sequences, using color as the observation feature. The color based feature has been found useful when dealing with non-rigid object deformations, partial occlusions, rapidly changing dynamics and complex backgrounds. The problem of joint detection and tracking is formulated as a hybrid valued sequential state estimation problem, incorporating a discrete variable which represents the number of existing objects. The solution is implemented in the form of a particle filter. The performance of the proposed algorithm is evaluated on various real-world video sequences with objects entering and leaving the scene.