Translator Disclaimer
26 July 2018 A CNN-based probability hypothesis density filter for multitarget tracking
Author Affiliations +
Proceedings Volume 10828, Third International Workshop on Pattern Recognition; 108280Z (2018) https://doi.org/10.1117/12.2501761
Event: Third International Workshop on Pattern Recognition, 2018, Jinan, China
Abstract
Recently, the probability hypothesis density filter (PHD) shows excellent multiple targets tracking performance, and it has been applied for tracking targets in video. The PHD filter usually needs to integrate other feature for image object tracking. However, the single hand-crafted feature shows poor robustness while utilizing multiple features fusion will increase the complexity. To alleviate the above problems, a deep convolutional neural networks (CNN) based PHD filter is proposed in this paper. The proposed method utilizes the impressive representability of the CNN feature to improve the robustness without increasing the complexity. Besides this, we also revise the update process of the standard PHD filter to output the continuous track and new birth targets, directly. The experiment tested on MOT17 dataset validate the efficacy of the proposed method in multitarget tracking in image sequences.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Chenming Li, Wenguang Wang, and Yankuan Liang "A CNN-based probability hypothesis density filter for multitarget tracking", Proc. SPIE 10828, Third International Workshop on Pattern Recognition, 108280Z (26 July 2018); https://doi.org/10.1117/12.2501761
PROCEEDINGS
6 PAGES


SHARE
Advertisement
Advertisement
Back to Top