Spatial Transformer Part-based Siamese Visual Tracking
文献类型：会议论文
| 作者 | Zhang, Ximing2; Lei, Hao2 ; Ma, Yilong2; Luo, Shujuan1; Fan, Xuewu2
|
| 出版日期 | 2020-07 |
| 会议日期 | 2020-07-27 |
| 会议地点 | Shenyang, China |
| 卷号 | 2020-July |
| DOI | 10.23919/CCC50068.2020.9189662 |
| 页码 | 7269-7274 |
| 英文摘要 | Local appearance representation of tracking objects plays a key role in robust visual tracking. While, holistic appearance representation mostly dominates the feature extraction model when describing the target appearance in existing DNN-based trackers, leading to high sensitivity to appearance variation, such as rotation, appearance change, and partial occlusion. We introduce a spatial transformer local part detector, which provides more robust local representation for tracking object and combine the existing Siamese networks for visual tracking simultaneously. To this end, we explicit the spatial transformer networks in the local part detector to detect the discriminative region of tracking objects. The local part detector further passes the detection results to the local cropping module, which comes up with the local structure for the region of interest. Differentiable operations can perform end-to-end learning during local structure construction. We implement the tracking procedure by matching the combined local pattern between candidates and templates in Siamese networks. We extensively prove the effectiveness of the proposed method through the ablation studies of the tracking benchmark, including OTB-2015, VOT-2018, and UAV123. © 2020 Technical Committee on Control Theory, Chinese Association of Automation. |
| 产权排序 | 1 |
| 会议录 | Proceedings of the 39th Chinese Control Conference, CCC 2020
 |
| 会议录出版者 | IEEE Computer Society |
| 语种 | 英语 |
| ISSN号 | 19341768;21612927 |
| ISBN号 | 9789881563903 |
| 源URL | [http://ir.opt.ac.cn/handle/181661/93719]  |
| 专题 | 西安光学精密机械研究所_空间光学应用研究室 |
| 作者单位 | 1.Northwestern Polytechnical University, Academy of Astronautics, Xi'an; 710072, China 2.Xi'an Institute of Optics and Precision Mechanics, Cas, Xi'an; 710119, China; |
| 推荐引用方式 GB/T 7714 | Zhang, Ximing,Lei, Hao,Ma, Yilong,et al. Spatial Transformer Part-based Siamese Visual Tracking[C]. 见:. Shenyang, China. 2020-07-27. |
入库方式： OAI收割
来源：西安光学精密机械研究所
浏览0
下载0
收藏0
其他版本
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。