Pedestrian detection and tracking using deformable part models and Kalman filtering

Both detection and tracking people are challenging problems, especially in complex real world scenes that commonly involve multi-person, complicated occlusions, and cluttered backgrounds. In this paper, we propose a novel approach for multi-person tracking-by-detection using deformable part models in Kalman filtering framework. The Kalman filter is used to keep track of each person and a unique label is assigned to each tracked individual. Based on this approach, people can enter and leave the scene at random. We test and demonstrate our results on the Caltech Pedestrian benchmark, which is the largest available dataset and consists of pedestrians varying widely in appearance, pose and scale. Complex situations such as people merging together are handled gracefully and individual persons can be tracked correctly after a group of people split. Experiments demonstrate the real-time performance and robustness of our system working in complex scenes. Our tracking model gives a tracking accuracy of 72.8% and a tracking precision of 82.3%.