SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking

doi:10.1609/aaai.v34i07.6733

CORC > 光电技术研究所 > 中国科学院光电技术研究所 > 光电工程总体研究室（一室）

	SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking
	Hu, Qintao; Zhou, Lijun; Wang, Xiaoxiao; Mao, Yao; Zhang, Jianlin; Ye, Qixiang
	2020-05-03
会议日期	February 7–12, 2020
会议地点	New York, New York, USA
关键词	Computer Science - Computer Vision and Pattern Recognition
卷号	34
期号	7
DOI	10.1609/aaai.v34i07.6733
页码	10989-10996
英文摘要	Modern visual trackers usually construct online learning models under the assumption that the feature response has a Gaussian distribution with target-centered peak response. Nevertheless, such an assumption is implausible when there is progressive interference from other targets and/or background noise, which produce sub-peaks on the tracking response map and cause model drift. In this paper, we propose a rectified online learning approach for sub-peak response suppression and peak response enforcement and target at handling progressive interference in a systematic way. Our approach, referred to as SPSTracker, applies simple-yet-efficient Peak Response Pooling (PRP) to aggregate and align discriminative features, as well as leveraging a Boundary Response Truncation (BRT) to reduce the variance of feature response. By fusing with multi-scale features, SPSTracker aggregates the response distribution of multiple sub-peaks to a single maximum peak, which enforces the discriminative capability of features for robust object tracking. Experiments on the OTB, NFS and VOT2018 benchmarks demonstrate that SPSTrack outperforms the state-of-the-art real-time trackers with significant margins.
会议录	THE THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE （AAAI2020）
文献子类	会议论文
语种	英语
ISSN号	2374-3468
内容类型	会议论文
源URL	[http://ir.ioe.ac.cn/handle/181551/9906]
专题	光电技术研究所_光电工程总体研究室（一室）
作者单位	Chinese Acad Sci, Inst Opt & Elect, Chengdu 610209
推荐引用方式 GB/T 7714	Hu, Qintao,Zhou, Lijun,Wang, Xiaoxiao,et al. SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking[C]. 见:. New York, New York, USA. February 7–12, 2020.