DeepAI AI Chat
Log In Sign Up

On the detection-to-track association for online multi-object tracking

by   Xufeng Lin, et al.

Driven by recent advances in object detection with deep neural networks, the tracking-by-detection paradigm has gained increasing prevalence in the research community of multi-object tracking (MOT). It has long been known that appearance information plays an essential role in the detection-to-track association, which lies at the core of the tracking-by-detection paradigm. While most existing works consider the appearance distances between the detections and the tracks, they ignore the statistical information implied by the historical appearance distance records in the tracks, which can be particularly useful when a detection has similar distances with two or more tracks. In this work, we propose a hybrid track association (HTA) algorithm that models the historical appearance distances of a track with an incremental Gaussian mixture model (IGMM) and incorporates the derived statistical information into the calculation of the detection-to-track association cost. Experimental results on three MOT benchmarks confirm that HTA effectively improves the target identification performance with a small compromise to the tracking speed. Additionally, compared to many state-of-the-art trackers, the DeepSORT tracker equipped with HTA achieves better or comparable performance in terms of the balance of tracking quality and speed.


Probabilistic 3D Multi-Modal, Multi-Object Tracking for Autonomous Driving

Multi-object tracking is an important ability for an autonomous vehicle ...

Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking

In multi-object tracking, the tracker maintains in its memory the appear...

3D Multi-Object Tracking Based on Uncertainty-Guided Data Association

In the existing literature, most 3D multi-object tracking algorithms bas...

InterTrack: Interaction Transformer for 3D Multi-Object Tracking

3D multi-object tracking (MOT) is a key problem for autonomous vehicles,...

Local Metrics for Multi-Object Tracking

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

Online Multiple Pedestrian Tracking using Deep Temporal Appearance Matching Association

In online multiple pedestrian tracking it is of great importance to cons...

Online Multi-Object Tracking and Segmentation with GMPHD Filter and Simple Affinity Fusion

In this paper, we propose a highly practical fully online multi-object t...