Knowledge Commons of Institute of Automation,CAS
Exploring Motion Information for Distractor Suppression in Visual Tracking | |
Liu, Kaiwen1,2; Gao, Jin1,2; Liu, Haowei1,2; Li, Liang4; Li, Bing1,2; Hu, Weiming1,2,3 | |
2022-06 | |
会议名称 | IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2022 |
会议录名称 | 2022 |
页码 | 1924-1932 |
会议日期 | 2022.6.19 |
会议地点 | New Orleans , United States |
出版者 | IEEE |
摘要 | In the past few years, Siamese networks have achieved outstanding improvements in visual object tracking. However, visual distractors with similar semantics can be easily misclassified as the target by Siamese networks and may consequently result in the drift problem. Besides, the Hanning window penalty, which is generally used to suppress distractors, could fail in many challengeable scenes. Notably, most failures violate the assumption of motion continuity. Thus, in this work, we explore motion information to mitigate the drift problem in visual tracking. First, we introduce a simple linear Kalman filter to predict the bounding box of the target in the current frame, which acts as a reference for decisions. Second, an IoU-Guided penalty is assembled in the post-processing to suppress distractors effectively. It’s worth mentioning that our method is almost cost-free. We conduct numerous experimental validations and analyses of our approach on several challenging sequences and datasets. Our tracker runs at approximately 40 fps and performs well on those sequences which include the Background Clutter attribute. Finally, by simultaneously integrating the IoU-Guided penalty and the Hanning window penalty with a strong baseline tracker TransT, our method achieves favorable gains by 69.1→71.5, 65.7→66.7, 64.9→65.9 success on OTB-100, LaSOT, NFS. |
收录类别 | EI |
资助项目 | Natural Science Foundation of China[61721004] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC040] |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48843 |
专题 | 多模态人工智能系统全国重点实验室_视频内容安全 |
通讯作者 | Gao, Jin |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of AI, University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology 4.Beijing Institute of Basic Medical Sciences |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Liu, Kaiwen,Gao, Jin,Liu, Haowei,et al. Exploring Motion Information for Distractor Suppression in Visual Tracking[C]:IEEE,2022:1924-1932. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Liu_Exploring_Motion(1747KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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