| MULTI-OBJECT TRACKING USING ONLINE METRIC LEARNING WITH LONG SHORT-TERM MEMORY | |
| Wan, Xingyu1; Zhao, Qing2; Wang, Jinjun1; Deng, Shunming3; Kong, Zhifeng1 | |
| 2018 | |
| 会议录名称 | 2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
 |
| 页码 | 788-792 |
| 会议名称 | 25th IEEE International Conference on Image Processing (ICIP) |
| 会议日期 | OCT 07-10, 2018 |
| 会议地点 | Athens, GREECE |
| 出版地 | NEW YORK |
| 出版者 | IEEE |
| 摘要 | The capacity to model temporal dependency by Recurrent Neural Networks (RNNs) makes it a plausible selection for the multi-object tracking (MOT) problem. Due to the nonlinear transformations and the unique memory mechanism, Long Short-Term Memory (LSTM) can consider a window of history when learning discriminative features, which suggests that the LSTM is suitable for state estimation of target objects as they move around. This paper focuses on association based MOT, and we propose a novel Siamese LSTM Network to interpret both temporal and spatial components nonlinearly by learning the feature of trajectories, and outputs the similarity score of two trajectories for data association. In addition, we also introduce an online metric learning scheme to update the state estimation of each trajectory dynamically. Experimental evaluation on MOT16 benchmark shows that the proposed method achieves competitive performance compared with other state-of-the-art works. |
| 关键词 | Multiple Object Tracking Long Short-Term Memory Metric Learning Data Association |
| ISSN | 1522-4880 |
| 收录类别 | CPCI-S |
| 语种 | 英语 |
| WOS研究方向 | Computer Science ; Imaging Science & Photographic Technology |
| WOS类目 | Computer Science, Software Engineering ; Imaging Science & Photographic Technology |
| WOS记录号 | WOS:000455181500159 |
| 原始文献类型 | Proceedings Paper |
| 引用统计 | |
| 文献类型 | 会议论文 |
| 条目标识符 | https://ir.cqcet.edu.cn/handle/39TD4454/4209 |
| 专题 | 重庆电子科技职业大学 |
| 作者单位 | 1.Xi An Jiao Tong Univ, Inst Artificial Intelligence & Robot, 28 West Xianning Rd, Xian 710049, Shaanxi, Peoples R China; 2.1 Tanhu 2nd Rd, Wuhan, Hubei, Peoples R China; 3.Chongqing Vocat Inst Engn, Chongqing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wan, Xingyu,Zhao, Qing,Wang, Jinjun,et al. MULTI-OBJECT TRACKING USING ONLINE METRIC LEARNING WITH LONG SHORT-TERM MEMORY[C]. NEW YORK:IEEE,2018:788-792. |
| 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