DeepAI AI Chat
Log In Sign Up

STURE: Spatial-Temporal Mutual Representation Learning for Robust Data Association in Online Multi-Object Tracking

by   Haidong Wang, et al.
Hunan University

Online multi-object tracking (MOT) is a longstanding task for computer vision and intelligent vehicle platform. At present, the main paradigm is tracking-by-detection, and the main difficulty of this paradigm is how to associate the current candidate detection with the historical tracklets. However, in the MOT scenarios, each historical tracklet is composed of an object sequence, while each candidate detection is just a flat image, which lacks the temporal features of the object sequence. The feature difference between current candidate detection and historical tracklets makes the object association much harder. Therefore, we propose a Spatial-Temporal Mutual Representation Learning (STURE) approach which learns spatial-temporal representations between current candidate detection and historical sequence in a mutual representation space. For the historical trackelets, the detection learning network is forced to match the representations of sequence learning network in a mutual representation space. The proposed approach is capable of extracting more distinguishing detection and sequence representations by using various designed losses in object association. As a result, spatial-temporal feature is learned mutually to reinforce the current detection features, and the feature difference can be relieved. To prove the robustness of the STURE, it is applied to the public MOT challenge benchmarks and performs well compared with various state-of-the-art online MOT trackers based on identity-preserving metrics.


page 4

page 10

page 12


Online Multi-Object Tracking with Dual Matching Attention Networks

In this paper, we propose an online Multi-Object Tracking (MOT) approach...

Spatial-Temporal Relation Networks for Multi-Object Tracking

Recent progress in multiple object tracking (MOT) has shown that a robus...

ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking

Multi-Camera Multi-Object Tracking (MC-MOT) utilizes information from mu...

Tracking Objects with 3D Representation from Videos

Data association is a knotty problem for 2D Multiple Object Tracking due...

Local Metrics for Multi-Object Tracking

This paper introduces temporally local metrics for Multi-Object Tracking...

BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection

Single frame data contains finite information which limits the performan...