FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking

Multi-object tracking (MOT) is an important problem in computer vision which has a wide range of applications. Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficie...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International journal of computer vision Ročník 129; číslo 11; s. 3069 - 3087
Hlavní autori: Zhang, Yifu, Wang, Chunyu, Wang, Xinggang, Zeng, Wenjun, Liu, Wenyu
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Springer US 01.11.2021
Springer
Springer Nature B.V
Predmet:
Accuracy
Artificial Intelligence
Computer Imaging
Computer Science
Computer vision
Datasets
Human-computer interaction
Image Processing and Computer Vision
Machine vision
Multiple target tracking
Object recognition
Optimization
Pattern Recognition
Pattern Recognition and Graphics
Source code
Vision
FairMOT
Multi-object tracking
One-shot
Anchor-free
Real-time inference
ISSN:0920-5691, 1573-1405
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Multi-object tracking (MOT) is an important problem in computer vision which has a wide range of applications. Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency. However, we find that the two tasks tend to compete with each other which need to be carefully addressed. In particular, previous works usually treat re-ID as a secondary task whose accuracy is heavily affected by the primary detection task. As a result, the network is biased to the primary detection task which is not fair to the re-ID task. To solve the problem, we present a simple yet effective approach termed as FairMOT based on the anchor-free object detection architecture CenterNet. Note that it is not a naive combination of CenterNet and re-ID. Instead, we present a bunch of detailed designs which are critical to achieve good tracking results by thorough empirical studies. The resulting approach achieves high accuracy for both detection and tracking. The approach outperforms the state-of-the-art methods by a large margin on several public datasets. The source code and pre-trained models are released at https://github.com/ifzhang/FairMOT .
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-021-01513-4