A Unified Object Motion and Affinity Model for Online Multi-Object Tracking
METADATA ONLY
Loading...
Author / Producer
Date
2020
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
Current popular online multi-object tracking (MOT) solutions apply single object trackers (SOTs) to capture object motions, while often requiring an extra affinity network to associate objects, especially for the occluded ones. This brings extra computational overhead due to repetitive feature extraction for SOT and affinity computation. Meanwhile, the model size of the sophisticated affinity network is usually non-trivial. In this paper, we propose a novel MOT framework that unifies object motion and affinity model into a single network, named UMA, in order to learn a compact feature that is discriminative for both object motion and affinity measure. In particular, UMA integrates single object tracking and metric learning into a unified triplet network by means of multi-task learning. Such design brings advantages of unproved computation efficiency, low memory requirement and simplified training procedure. In addition, we equip our model with a task-specific attention module, which is used to boost task-aware feature learning. The proposed UMA can be easily trained end-to-end, and is elegant - requiring only one training stage. Experimental results show that it achieves promising performance on several MOT Challenge benchmarks.
Permanent link
Publication status
published
External links
Editor
Book title
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Journal / series
Volume
Pages / Article No.
6767 - 6776
Publisher
IEEE
Event
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020) (virtual)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Organisational unit
Notes
Due to the Coronavirus (COVID-19) the conference was conducted virtually.