| Thermal Infrared Tracking using Multi-stages Deep Features Fusion | |
Zhang, Ximing1; Chen, Rongli1 ; Liu, Gang1; Li, Xuyang1; Luo, Shujuan2; Fan, Xuewu1
| |
| 2020-08 | |
| 会议名称 | 32nd Chinese Control and Decision Conference, CCDC 2020 |
| 会议录名称 | Proceedings of the 32nd Chinese Control and Decision Conference, CCDC 2020 |
| 页码 | 1883-1888 |
| 会议日期 | 2020-08-22 |
| 会议地点 | Hefei, China |
| 出版者 | Institute of Electrical and Electronics Engineers Inc., United States |
| 产权排序 | 1 |
| 摘要 | Thermal infrared (TIR) tracking can be utilized to track the target in the images generated by thermal infrared sensors due to the weak influence by illumination changes. However, there are still some challenges to do thermal infrared tracking when suffering drastic appearance variation, heavy occlusion and background clutters. The absence of RGB patterns and low resolution also constrain the tracking performance in complex scenarios. The deep convolutional features are widely utilized to solve visual tracking problems which successfully extracted the spatial and semantic information though object representation. Motivated by these methods, we firstly propose to combine multi-stages cascaded Siamese networks to achieve deep features fusion in three stages, then achieve the tracking procedure by candidates matching strategy. The final results are obtained by non-maximum suppression and scale penalty. The proposed method can inherit the advantages by fusing multi-stages deep features and achieve end-to-end learning simultaneously. The experiments are evaluated with state-of-the-art methods on VOT-TIR2016 benchmark and attributes based comparison. The tracking results demonstrate that our proposed method outperforms the compared methods in terms of accuracy and robustness. © 2020 IEEE. |
| 关键词 | Thermal Infrared Tracking Multi-stages Networks Deep Features Fusion Siamese Networks Region Proposal Networks |
| 作者部门 | 空间光学技术研究室 |
| DOI | 10.1109/CCDC49329.2020.9164750 |
| 收录类别 | EI |
| ISBN号 | 9781728158549 |
| 语种 | 英语 |
| EI入藏号 | 20204009255169 |
| 引用统计 | |
| 文献类型 | 会议论文 |
| 条目标识符 | http://ir.opt.ac.cn/handle/181661/93722 |
| 专题 | 空间光学技术研究室 |
| 作者单位 | 1.Institute of Optics and Precision Mechanics of CAS, Xi'an; 710119, China; 2.Northwestern Polytechnical University, Academy of Astronautics, Xi'an; 710072, China |
| 推荐引用方式 GB/T 7714 | Zhang, Ximing,Chen, Rongli,Liu, Gang,et al. Thermal Infrared Tracking using Multi-stages Deep Features Fusion[C]:Institute of Electrical and Electronics Engineers Inc., United States,2020:1883-1888. |
| 条目包含的文件 | ||||||
| 文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
| Thermal Infrared Tra（655KB） | 会议论文 | 限制开放 | CC BY-NC-SA | 请求全文 | ||
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