期刊
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
卷 29, 期 12, 页码 3660-3672出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2018.2881123
关键词
Target tracking; Object tracking; Trajectory; Benchmark testing; Visualization; Feature extraction; Multiple object tracking; tracking-by-detection; multiple hypothesis tracking; iterative maximum weighted independent set; polynomial-time approximation
资金
- National Key R&D Program of China [2017YFB1002000]
- National Natural Science Foundation of China [6181101065]
- Macao Science and Technology Development Fund [138/2016/A3]
- Open Fund of the State Key Laboratory of Software Development Environment [SKLSDE-2017ZX-09]
- Project of Experimental Verification of the Basic Commonness and Key Technical Standards of the Industrial Internet Network Architecture
- Technology Innovation Fund of China Electronic Technology Group Corporation
- HAWKEYE Group
This paper proposes a novel iterative maximum weighted independent set (MWIS) algorithm for multiple hypothesis tracking (MHT) in a tracking-by-detection framework. MHT converts the tracking problem into a series of MWIS problems across the tracking time. Previous works solve these NP-hard MWIS problems independently without the use of any prior information from each frame, and they ignore the relevance between adjacent frames. In this paper, we iteratively solve the MWIS problems by using the MWIS solution from the previous frame rather than solving the problem from scratch each time. First, we define five hypothesis categories and a hypothesis transfer model, which explicitly describes the hypothesis relationship between adjacent frames. We also propose a polynomial-time approximation algorithm for the MWIS problem in MHT. In addition to that, we present a confident short tracklet generation method and incorporate tracklet-level association into MHT, which further improves the computational efficiency. Our experiments on both MOT16 and MOT17 benchmarks show that our tracker outperforms all the previously published tracking algorithms on both MOT16 and MOT17 benchmarks. Finally, we demonstrate that the polynomial-time approximate tracker reaches nearly the same tracking performance.
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