期刊
IEEE ACCESS
卷 7, 期 -, 页码 173393-173406出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2019.2955809
关键词
Multi-target tracking; data association; high-order features; multi-feature fusion
资金
- Natural Science Foundation of China (NSFC) [61871445, 61302156]
- Scientific Research Foundation of the Nanjing University of Posts and Telecommunications [NY218044, NY218066]
- Provincial Natural Science Foundation of Science and Technology Bureau of Jiangsu Province [BK20180088]
- Key Research and Development Foundation Project of Jiangsu Province [BE2016001-4]
Multi-target tracking (MTT) is among the fundamental problems in the field of video analysis and monitoring. In the tracking-by-detection framework, data association is one of the most important and difficult problems. In this paper, we propose a framework to obtain the appearance features of a target in an end-to-end fashion, which fuses high-level and low-level semantic information. The high-order feature map is abstracted using the high-order apparent relationship for each target between the current frame and the previous frames, whereas the similarity matrix is used to describe the high-order features of the target. The best matching relationships between targets are obtained using hierarchical data association and the Hungarian algorithm. This proposed method is called Multi-target tracking Based on High-order Appearance Feature Fusion (MTT-HAFF), which can handle a large number of input sequences, local association failures, and identity exchanges that result from unreliable detections. The results show that the proposed algorithm has a good robustness for long-term occlusion tracking.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据