Visual tracking with complementary deep feature optimization
文献类型：期刊论文
| 作者 | Wang, Wei1,2; Chen, Zhaoming1 ; Shi, Mingquan1
|
| 刊名 | JOURNAL OF ELECTRONIC IMAGING
 |
| 出版日期 | 2018-07-01 |
| 卷号 | 27期号:4页码:10 |
| 关键词 | semantic tracking convolutional networks complementary convolutional feature optimization hard negative mining bounding box regression |
| ISSN号 | 1017-9909 |
| DOI | 10.1117/1.JEI.27.4.043052 |
| 英文摘要 | The challenges of rotation, occlusion, and scale change in visual object tracking have been an urgent problem to be solved. In recent years, the online learning ability and discriminative power of convolutional neural network (CNN) features have gained great attention in many computer vision tasks. Previous studies have shown that individual layer CNN features can be used for dealing with specific tracking challenges, such as target accurate positioning, rotation, and deformation. However, tracking with single CNN features is not enough to deal with serious challenges, such as the above-mentioned. To handle this problem, we evaluate the contribution of specific CNN layers features in tracking tasks and present a complementary CNN features tracking framework, which treats tracking procedure as a deep CNN features optimizing. Our tracker does not merely fuse the CNN features but is a semantic level method, which adds a competition mechanism to optimize the target appearance encoding of CNN layers. Therefore, the proposed tracker is robust not only to target location but also to rotation and deformation. We also embed hard negative mining to enhance the discriminative power of the tracking model and use bounding box regression to refine the tracking result. Having compared our tracker performance with other state-of-the-art trackers, the obtained experimental results in a large-scale dataset demonstrate that the effectiveness of our proposed tracker outperforms state-of-the-art ones. (C) 2018 SPIE and IS&T |
| 资助项目 | National Natural Science Foundation of China (NSFC)[61605205] |
| WOS研究方向 | Engineering ; Optics ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:000445139400004 |
| 出版者 | IS&T & SPIE |
| 源URL | [http://119.78.100.138/handle/2HOD01W0/6709]  |
| 专题 | 智能工业设计工程中心 |
| 通讯作者 | Shi, Mingquan |
| 作者单位 | 1.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Wei,Chen, Zhaoming,Shi, Mingquan. Visual tracking with complementary deep feature optimization[J]. JOURNAL OF ELECTRONIC IMAGING,2018,27(4):10. |
| APA | Wang, Wei,Chen, Zhaoming,&Shi, Mingquan.(2018).Visual tracking with complementary deep feature optimization.JOURNAL OF ELECTRONIC IMAGING,27(4),10. |
| MLA | Wang, Wei,et al."Visual tracking with complementary deep feature optimization".JOURNAL OF ELECTRONIC IMAGING 27.4(2018):10. |
入库方式： OAI收割
来源：重庆绿色智能技术研究院
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。