Abstract
In recent years, multi-object tracking has attracted more and more attention, both in academia and engineering, but most of the recent works do not pay attention to the speed of the algorithm and only pursue the accuracy. In this paper, we propose an online multi-pedestrian tracking algorithm, taking into account both the accuracy and the speed. First, the motion models of the targets are established by the Kalman filter. At the same time, the appearance models of the targets are extracted by the convolutional neural network. Moreover, a data association algorithm is proposed, which integrates the motion information, including scale, intersection-over-union, and distance, and the appearance information, including the current appearance model and the long-term appearance model. With the data association algorithm, the matching between detections and tracklets is realized, and the goal of tracking by detection is achieved. We compare the proposed algorithm with other algorithms on the MOT15 benchmark and the MOT16 benchmark. The experiment results show that the algorithm has high accuracy and good real-time performance.
Highlights
Multi-pedestrian tracking is a key technology in the field of image processing
Compared with detection-free tracking [10], [11], tracking-by-detection does not need to initialize the target manually, and is better at coping with the emergence of new targets and the disappearance of old targets [2]. In this kind of method, the targets of each frame are firstly detected by a detector, and these detections between frames are connected into tracklets by a data association algorithm
When the predicted result matches the observed result of a detector successfully in the data association algorithm, the state of the target is the optimal estimation updated by the observed result with Kalman filter
Summary
Multi-pedestrian tracking is a key technology in the field of image processing. It has important applications in many fields, such as public security, intelligent transportation, video surveillance and robot vision [1]. Compared with detection-free tracking [10], [11], tracking-by-detection does not need to initialize the target manually, and is better at coping with the emergence of new targets and the disappearance of old targets [2] In this kind of method, the targets of each frame are firstly detected by a detector, and these detections between frames are connected into tracklets by a data association algorithm. He et al.: Fast Online Multi-Pedestrian Tracking via Integrating Motion Model and Deep Appearance Model advantages in tracking accuracy. These algorithms have great limitations in practical applications, and are more used in video post-processing [15].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
