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

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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computer vision and image understanding Ročník 193; s. 102907
Hlavní autoři: Wen, Longyin, Du, Dawei, Cai, Zhaowei, Lei, Zhen, Chang, Ming-Ching, Qi, Honggang, Lim, Jongwoo, Yang, Ming-Hsuan, Lyu, Siwei
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Inc 01.04.2020
Témata:
Benchmark
Evaluation protocol
Object detection
Object tracking
Benchmark
Evaluation protocol
Object tracking
Object detection
ISSN:1077-3142
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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. •New large scale dataset for both detection and multi-object tracking evaluation.•New protocol and evaluation metrics for multi-object tracking.•Comprehensive evaluation of complete multi-object tracking systems.
ISSN:1077-3142
DOI:10.1016/j.cviu.2020.102907