Anchor-Free One-Stage Online Multi-Object Tracking | |
Zhou, Zongwei1,2; Li, Yangxi3; Gao, Jin1,2; Xing, Junliang1,2; Li, Liang4; Hu, Weiming5,6 | |
2020-10 | |
会议名称 | Chinese Conference on Pattern Recognition and Computer Vision |
会议日期 | 2020-10 |
会议地点 | 中国,南京 |
出版者 | SPRINGER |
摘要 | Current multi-object tracking (MOT) algorithms are dominated by the tracking-by-detection paradigm, which divides MOT into three independent sub-tasks of target detection, appearance embedding, and data association. To improve the efficiency of this tracking paradigm, this paper presents an anchor-free one-stage learning framework to perform target detection and appearance embedding in a unified network, which learns for each point in the feature pyramid of the input image an object detection prediction and a feature representation. Two effective training strategies are proposed to reduce missed detections in dense pedestrian scenes. Moreover, an improved non-maximum suppression procedure is introduced to obtain more accurate box detections and appearance embeddings by taking the box spatial and appearance similarities into account simultaneously. Experiments show that our MOT algorithm achieves real-time tracking speed while obtaining comparable tracking performance to state-of-the-art MOT trackers. Code will be released to facilitate further studies of this problem. |
关键词 | Anchor-Free · One-Stage · Multi-Object Tracking |
收录类别 | EI |
资助项目 | NSFC-general technology collaborative Fund for basic research[U1636218] ; Natural Science Foundation of China[61751212] ; Natural Science Foundation of China[61721004] ; Beijing Natural Science Foundation[L172051] ; National Natural Science Foundation of Guangdong[2018B030311046] |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44938 |
专题 | 模式识别实验室 |
通讯作者 | Zhou, Zongwei |
作者单位 | 1.University of Chinese Academy of Sciences, Beijing, China 2.Institute of Automation, Chinese Academy of Sciences, Beijing, China 3.National Computer network Emergency Response technical Team/Coordination 4.The Brain Science Center, Beijing Institute of Basic Medical Sciences 5.CAS Center for Excellence in Brian Science and Intelligence Technology, National Laboratory of Pattern Recognition, CASIA 6.School of Artificial Intelligence, University of Chinese Academy of Sciences, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhou, Zongwei,Li, Yangxi,Gao, Jin,et al. Anchor-Free One-Stage Online Multi-Object Tracking[C]:SPRINGER,2020. |
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 | ||
PRCV2020_Anchor_Free(634KB) | 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