Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking

TL;DR

This paper introduces a Deep Continuous Conditional Random Field model for online multi-object tracking that effectively models asymmetric inter-object relations and learns discriminative features end-to-end, improving tracking accuracy.

Contribution

It proposes a novel DCCRF framework with asymmetric pairwise terms and deep CNN-based unary terms, enhancing inter-object relation modeling and feature learning for MOT.

Findings

Outperforms state-of-the-art methods on public benchmarks.

Effectively models asymmetric inter-object relations.

Demonstrates improved tracking accuracy and robustness.

Abstract

Online Multi-Object Tracking (MOT) is a challenging problem and has many important applications including intelligence surveillance, robot navigation and autonomous driving. In existing MOT methods, individual object's movements and inter-object relations are mostly modeled separately and relations between them are still manually tuned. In addition, inter-object relations are mostly modeled in a symmetric way, which we argue is not an optimal setting. To tackle those difficulties, in this paper, we propose a Deep Continuous Conditional Random Field (DCCRF) for solving the online MOT problem in a track-by-detection framework. The DCCRF consists of unary and pairwise terms. The unary terms estimate tracked objects' displacements across time based on visual appearance information. They are modeled as deep Convolution Neural Networks, which are able to learn discriminative visual features for tracklet association. The asymmetric pairwise terms model inter-object relations in an asymmetric way, which encourages high-confidence tracklets to help correct errors of low-confidence tracklets and not to be affected by low-confidence ones much. The DCCRF is trained in an end-to-end manner for better adapting the influences of visual information as well as inter-object relations. Extensive experimental comparisons with state-of-the-arts as well as detailed component analysis of our proposed DCCRF on two public benchmarks demonstrate the effectiveness of our proposed MOT framework.