Knowledge Commons of Institute of Automation,CAS
Deep Kalman Filter with Optical Flow for Multiple Object Tracking | |
Yaran Chen![]() ![]() ![]() | |
2019-10 | |
会议名称 | IEEE International Conference on Systems, Man and Cybernetics (SMC) |
会议日期 | October 6-9 |
会议地点 | Bari, Italy. |
摘要 | Deep matching and Kalman filter-based multi- ple object tracking (DK-tracking) have been demonstrated to be promising. However, most of existing DK-tracking trackers assume that objects are slow-varying movement with a constant velocity. The assumption is hard to be satisfied in the real world, especially in the image space due to the sight distance. In this paper, we propose a novel multiple object tracking method combining deep feature matching, Kalman filter and flow information, which is called DK- Flow-tracking, to improve tracking performance. In DK-flow- tracking, optical flow in consecutive frames is used to provide accurate object motion information for guiding Kalman fil- ter to track objects. Experiments are performed on public datasets: MOT2016, MOT2017, and the proposed method achieves better performances compared to the DK-tracking with the assumption of a constant velocity movement. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 强化与进化学习 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40614 |
专题 | 多模态人工智能系统全国重点实验室_深度强化学习 |
作者单位 | Institute of Automation, Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yaran Chen,Dongbin Zhao,Haoran Li. Deep Kalman Filter with Optical Flow for Multiple Object Tracking[C],2019. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论