Condensation-based multi-person detection and tracking with HOG and LBP

摘要

Multi-person tracking and detection is widely used in human robot interaction, which has been a hot topic in computer vision. In this paper, we utilize a tracking-by-detection framework to track many persons at the same time. We use HOG and LBP features to describe person's characteristics in a scene and train a strong classifier using Adaboost algorithm. In the tracking part, we use a particle filter to estimate the targets' position. Besides, we train an on-line SVM classifier to improve the accuracy of the tracking results by learning and updating the detector's results. The particles' velocity is also utilized to improve the accuracy of the data association, which relates the detector's output to the tracker's results. Our method is validated feasible on UBC-Hockey benchmark datasets.