Paper Info
Title
UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking
Abstract
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.
Year
DOI
Venue
2020
10.1016/j.cviu.2020.102907
Computer Vision and Image Understanding
Keywords
Field
DocType
Object detection,Object tracking,Benchmark,Evaluation protocol
Computer vision,Truncation,Object detection,Artificial intelligence,Vehicle type,Detector,Visual surveillance,Mathematics,Bounding overwatch
Journal
Volume
Issue
ISSN
193
1
1077-3142
Citations 
PageRank 
References 
11
0.54
26
Authors
9
Name
Order
Citations
PageRank
Longyin Wen164733.89
Dawei Du252932.83
Zhaowei Cai345216.64
Zhen Lei43613157.95
Ming-Ching Chang527528.15
Honggang Qi637929.46
Jongwoo Lim74105144.58
Yang Ming-Hsuan815303620.69
Siwei Lyu91406135.38