Knowledge Commons of Institute of Automation,CAS
High-Speed and Accurate Scale Estimation for Visual Tracking with Gaussian Process Regression | |
Linyu Zheng1,2; Ming Tang1,2; Yingying Chen1,2; Jinqiao Wang1,2; Hanqing Lu1,2 | |
2020-07 | |
会议名称 | IEEE International Conference on Multimedia and Expo |
页码 | 1-6 |
会议日期 | 2020-7 |
会议地点 | London, United Kingdom |
摘要 | Recent years have seen remarkable progress in the visual tracking domain. However, it remains a challenging task to estimate the scale of target efficiently and accurately. In this paper, we present a novel and high-performance scale estimation approach for tracking-by-detection framework. The proposed approach, named GPAS, formulates the scale estimation as a Gaussian process regression problem based on scale pyramid representation. In general, it enjoys the following there advantages. (i) Efficient. It only takes 2ms to estimate the scale of a target on a single CPU. (ii) Accurate. Without bells and whistles, its accuracy surpasses all previous hand-crafted features based scale estimation methods by large margins. (iii) Generic. It can be incorporated into any tracking-by-detection framework based trackers easily. Experiment results show that compared to the latest and classical scale estimation method, fDSST, our GPAS significantly improves the performance by 6.2% in mean distance precision, 8.9% in mean overlap precision, and 5.5% in mean AUC on 28 sequences of OTB2013 with significant scale variations. |
收录类别 | EI |
资助项目 | National Natural Science Foundation of China[61772527] ; National Natural Science Foundation of China[61806200] ; National Nature Science Foundation of China[61876086] |
语种 | 英语 |
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/173211/44852 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
通讯作者 | Linyu Zheng |
作者单位 | 1.NLPR 2.CASIA |
第一作者单位 | 模式识别国家重点实验室; 中国科学院自动化研究所 |
通讯作者单位 | 模式识别国家重点实验室; 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Linyu Zheng,Ming Tang,Yingying Chen,et al. High-Speed and Accurate Scale Estimation for Visual Tracking with Gaussian Process Regression[C],2020:1-6. |
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 | ||
HIGH-SPEED AND ACCUR(1144KB) | 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