Track Initialization and Re-Identification for~3D Multi-View Multi-Object Tracking

TL;DR

This paper introduces a Bayesian multi-object tracking method using only 2D detections from monocular cameras, capable of automatic track management, re-identification, and occlusion handling, adaptable to camera reconfigurations without retraining.

Contribution

It develops an efficient approximation of the Bayesian filter incorporating features and geometry, enabling robust online 3D multi-view multi-object tracking without retraining.

Findings

Significant improvements over existing methods on challenging datasets.

Robustness to camera reconfiguration without retraining.

Enhanced data association through feature and kinematic integration.

Abstract

We propose a 3D multi-object tracking (MOT) solution using only 2D detections from monocular cameras, which automatically initiates/terminates tracks as well as resolves track appearance-reappearance and occlusions. Moreover, this approach does not require detector retraining when cameras are reconfigured but only the camera matrices of reconfigured cameras need to be updated. Our approach is based on a Bayesian multi-object formulation that integrates track initiation/termination, re-identification, occlusion handling, and data association into a single Bayes filtering recursion. However, the exact filter that utilizes all these functionalities is numerically intractable due to the exponentially growing number of terms in the (multi-object) filtering density, while existing approximations trade-off some of these functionalities for speed. To this end, we develop a more efficient approximation suitable for online MOT by incorporating object features and kinematics into the measurement model, which improves data association and subsequently reduces the number of terms. Specifically, we exploit the 2D detections and extracted features from multiple cameras to provide a better approximation of the multi-object filtering density to realize the track initiation/termination and re-identification functionalities. Further, incorporating a tractable geometric occlusion model based on 2D projections of 3D objects on the camera planes realizes the occlusion handling functionality of the filter. Evaluation of the proposed solution on challenging datasets demonstrates significant improvements and robustness when camera configurations change on-the-fly, compared to existing multi-view MOT solutions. The source code is publicly available at https://github.com/linh-gist/mv-glmb-ab.