Knowledge Commons of Institute of Automation,CAS
Siamese High-Level Feature Refine Network for Visual Object Tracking | |
Rahman, Md. Maklachur1; Ahmed, Md Rishad2,3,4; Laishram, Lamyanba1; Kim, Seock Ho1; Jung, Soon Ki1 | |
发表期刊 | ELECTRONICS
![]() |
2020-11-01 | |
卷号 | 9期号:11页码:21 |
摘要 | Siamese network-based trackers are broadly applied to solve visual tracking problems due to its balanced performance in terms of speed and accuracy. Tracking desired objects in challenging scenarios is still one of the fundamental concerns during visual tracking. This research paper proposes a feature refined end-to-end tracking framework with real-time tracking speed and considerable performance. The feature refine network has been incorporated to enhance the target feature representation power, utilizing high-level semantic information. Besides, it allows the network to capture the salient information to locate the target and learns to represent the target feature in a more generalized way advancing the overall tracking performance, particularly in the challenging sequences. But, only the feature refine module is unable to handle such challenges because of its less discriminative ability. To overcome this difficulty, we employ an attention module inside the feature refine network that strengths the tracker discrimination ability between the target and background. Furthermore, we conduct extensive experiments to ensure the proposed tracker's effectiveness using several popular tracking benchmarks, demonstrating that our proposed model achieves state-of-the-art performance over other trackers. |
关键词 | siamese network visual object tracking feature refine network attention mechanism |
DOI | 10.3390/electronics9111918 |
关键词[WOS] | BROADCAST |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Basic Science Research Program through the National Research Foundation of Korea (NRF) - Ministry of Education, Science and Technology[NRF-2019R1A2C1010786] |
项目资助者 | Basic Science Research Program through the National Research Foundation of Korea (NRF) - Ministry of Education, Science and Technology |
WOS研究方向 | Engineering |
WOS类目 | Engineering, Electrical & Electronic |
WOS记录号 | WOS:000592789400001 |
出版者 | MDPI |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/41676 |
专题 | 个人空间 |
通讯作者 | Jung, Soon Ki |
作者单位 | 1.Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea 2.Chinese Acad Sci, Inst Automat, Brainnetome Ctr, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
推荐引用方式 GB/T 7714 | Rahman, Md. Maklachur,Ahmed, Md Rishad,Laishram, Lamyanba,et al. Siamese High-Level Feature Refine Network for Visual Object Tracking[J]. ELECTRONICS,2020,9(11):21. |
APA | Rahman, Md. Maklachur,Ahmed, Md Rishad,Laishram, Lamyanba,Kim, Seock Ho,&Jung, Soon Ki.(2020).Siamese High-Level Feature Refine Network for Visual Object Tracking.ELECTRONICS,9(11),21. |
MLA | Rahman, Md. Maklachur,et al."Siamese High-Level Feature Refine Network for Visual Object Tracking".ELECTRONICS 9.11(2020):21. |
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