UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking

doi:10.1016/j.cviu.2020.102907

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 生物识别与安全技术研究中心

	UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking
	Wen, Longyin 5; Du, Dawei 6; Cai, Zhaowei 3; Lei, Zhen 2; Chang, Ming-Ching 6; Qi, Honggang 1; Lim, Jongwoo 4; Yang, Ming-Hsuan 7; Lyu, Siwei 6
刊名	COMPUTER VISION AND IMAGE UNDERSTANDING
	2020-04-01
卷号	193 页码:20
关键词	Object detection Object tracking Benchmark Evaluation protocol
ISSN号	1077-3142
DOI	10.1016/j.cviu.2020.102907
通讯作者	Lyu, Siwei(slyu@albany.edu)
英文摘要	Effective multi-object tracking (MOT) methods have been developed in recent years for a wide range of applications including visual surveillance and behavior understanding. Existing performance evaluations of MOT methods usually separate the tracking step from the detection step by using one single predefined setting of object detection for comparisons. In this work, we propose a new University at Albany DEtection and TRACking (UA-DETRAC) dataset for comprehensive performance evaluation of MOT systems especially on detectors. The UA-DETRAC benchmark dataset consists of 100 challenging videos captured from real-world traffic scenes (over 140,000 frames with rich annotations, including illumination, vehicle type, occlusion, truncation ratio, and vehicle bounding boxes) for multi-object detection and tracking. We evaluate complete MOT systems constructed from combinations of state-of-the-art object detection and tracking methods. Our analysis shows the complex effects of detection accuracy on MOT system performance. Based on these observations, we propose effective and informative evaluation metrics for MOT systems that consider the effect of object detection for comprehensive performance analysis.
资助项目	US Natural Science Foundation[IIS1816227] ; National Nature Science Foundation of China[61472388] ; National Nature Science Foundation of China[61771341]
WOS关键词	MULTITARGET TRACKING ; ROBUST ; APPEARANCE ; HISTOGRAMS
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ACADEMIC PRESS INC ELSEVIER SCIENCE
WOS记录号	WOS:000518876100004
资助机构	US Natural Science Foundation ; National Nature Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/38603]
专题	自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心
通讯作者	Lyu, Siwei
作者单位	1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 3.Univ Calif San Diego, Dept Elect & Comp Engn, San Diego, CA 92103 USA 4.Hanyang Univ, Div Comp Sci & Engn, Seoul, South Korea 5.JD Finance Amer Corp, Mountain View, CA USA 6.SUNY Albany, Dept Comp Sci, Albany, NY 12222 USA 7.Univ Calif Merced, Sch Engn, Merced, CA USA
推荐引用方式 GB/T 7714	Wen, Longyin,Du, Dawei,Cai, Zhaowei,et al. UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2020,193:20.
APA	Wen, Longyin.,Du, Dawei.,Cai, Zhaowei.,Lei, Zhen.,Chang, Ming-Ching.,...&Lyu, Siwei.(2020).UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking.COMPUTER VISION AND IMAGE UNDERSTANDING,193,20.
MLA	Wen, Longyin,et al."UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking".COMPUTER VISION AND IMAGE UNDERSTANDING 193(2020):20.