Robust Visual Tracking via Hierarchical Particle Filter and Ensemble Deep Features
文献类型：期刊论文
| 作者 | Li, Shengjie1,2; Zhao, Shuai1,2; Cheng, Bo1,2; Zhao, Erhu3; Chen, Junliang1 |
| 刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
 |
| 出版日期 | 2020 |
| 卷号 | 30期号:1页码:179-191 |
| 关键词 | Object tracking correlation filter hierarchical particle filter convolutional neural networks |
| ISSN号 | 1051-8215 |
| DOI | 10.1109/TCSVT.2018.2889457 |
| 英文摘要 | Particle filter algorithms are a very important branch for visual object tracking in the past decades, showing strong robustness to challenging scenarios with partial occlusion and large-scale variations. However, since a large number of particles need to be extracted for the accurate target state estimation, their tracking efficiency typically suffers especially when meeting deep convolutional features, which have been developed for handling significant variations of the target appearance in the visual tracking community. In this paper, we propose to elegantly exploit deep convolutional features with few particles in a novel hierarchical particle filter, which formulates correlation filters as observation models and breaks the standard particle filter framework down into two constituent particle layers, namely, particle translation layer and particle scale layer. The particle translation layer focuses on the object location with the deep convolutional features capturing semantics but failing to precisely estimate the object scale, while the particle scale layer pays attention to large-scale variations with the lightweight hand-crafted features handling spatial details of the object size. Moreover, an efficient ensemble method is proposed to help explore deeper convolutional features with more semantics in the particle translation layer. Extensive experiments on four challenging tracking datasets, including OTB-2013, OTB-2015, VOT2014, and VOT2015 demonstrate that the proposed method performs favorably against a number of state-of-the-art trackers. |
| 资助项目 | National Natural Science Foundation of China[61501048] ; Beijing Natural Science Foundation[4182042] ; Fundamental Research Funds for the Central Universities[2017RC12] |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000521641800015 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/14031]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Zhao, Shuai |
| 作者单位 | 1.Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing 100876, Peoples R China 2.Beijing Adv Innovat Ctr Future Internet Technol, Beijing 100124, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Shengjie,Zhao, Shuai,Cheng, Bo,et al. Robust Visual Tracking via Hierarchical Particle Filter and Ensemble Deep Features[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2020,30(1):179-191. |
| APA | Li, Shengjie,Zhao, Shuai,Cheng, Bo,Zhao, Erhu,&Chen, Junliang.(2020).Robust Visual Tracking via Hierarchical Particle Filter and Ensemble Deep Features.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,30(1),179-191. |
| MLA | Li, Shengjie,et al."Robust Visual Tracking via Hierarchical Particle Filter and Ensemble Deep Features".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 30.1(2020):179-191. |
入库方式： OAI收割
来源：计算技术研究所
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。