Multiple Objects Tracking and Identification Based on Sparse Representation in Surveillance Video

In the field of multiple-camera video surveillance, object tracking is attracting more and more attention. Problems such as objects' abrupt motion, occlusion and complex target structures make this field full of challenges. In the paper, a method based on particle filter and sparse representation for large-scale object tracking is proposed. At first, the features of target objects are trained, then we detect the motion region in the high resolution video, using human crowd segmentation algorithm to separate person from the crowd. After getting the region of single person, the features of the region such as color histogram and hash code would be extracted to match with trained features of target objects. According to the performance of feature matching, we find the true targeted object and its smallest rectangle area. In tracking process, discriminative Sparse Similarity Map (SSM) is used to guarantee a good performance of target tracking. Experiment results demonstrate our method can provide high accuracy and robustness.