A CRF-based Framework for Tracklet Inactivation in Online Multi-Object Tracking

TL;DR

This paper introduces a CRF-based framework to improve tracklet inactivation in online multi-object tracking, addressing limitations of fixed-threshold methods and enhancing robustness in practical scenarios.

Contribution

It proposes a novel CRF framework with feature functions and strategies for varying nodes, improving tracklet inactivation in online MOT.

Findings

Outperforms baseline on MOT16 and MOT17 benchmarks

Enhances robustness of tracklet inactivation

Validates extensibility through extensive experiments

Abstract

Online multi-object tracking (MOT) is an active research topic in the domain of computer vision. Although many previously proposed algorithms have exhibited decent results, the issue of tracklet inactivation has not been sufficiently studied. Simple strategies such as using a fixed threshold on classification scores are adopted, yielding undesirable tracking mistakes and limiting the overall performance. In this paper, a conditional random field (CRF) based framework is put forward to tackle the tracklet inactivation issue in online MOT problems. A discrete CRF which exploits the intra-frame relationship between tracking hypotheses is developed to improve the robustness of tracklet inactivation. Separate sets of feature functions are designed for the unary and binary terms in the CRF, which take into account various tracking challenges in practical scenarios. To handle the problem of varying CRF nodes in the MOT context, two strategies named as hypothesis filtering and dummy nodes are employed. In the proposed framework, the inference stage is conducted by using the loopy belief propagation algorithm, and the CRF parameters are determined by utilizing the maximum likelihood estimation method followed by slight manual adjustment. Experimental results show that the tracker combined with the CRF-based framework outperforms the baseline on the MOT16 and MOT17 benchmarks. The extensibility of the proposed framework is further validated by an extensive experiment.