BiTrack: Bidirectional Offline 3D Multi-Object Tracking Using Camera-LiDAR Data

TL;DR

BiTrack is a novel 3D offline multi-object tracking framework that fuses camera and LiDAR data, employing bidirectional re-optimization to improve accuracy and reliability in tracking objects.

Contribution

The paper introduces a point-level object registration, advanced data association, and a trajectory re-optimization scheme for enhanced 3D offline multi-object tracking.

Findings

Achieves state-of-the-art accuracy on KITTI dataset

Demonstrates improved tracking reliability and efficiency

Outperforms existing methods in 3D OMOT tasks

Abstract

Compared with real-time multi-object tracking (MOT), offline multi-object tracking (OMOT) has the advantages to perform 2D-3D detection fusion, erroneous link correction, and full track optimization but has to deal with the challenges from bounding box misalignment and track evaluation, editing, and refinement. This paper proposes "BiTrack", a 3D OMOT framework that includes modules of 2D-3D detection fusion, initial trajectory generation, and bidirectional trajectory re-optimization to achieve optimal tracking results from camera-LiDAR data. The novelty of this paper includes threefold: (1) development of a point-level object registration technique that employs a density-based similarity metric to achieve accurate fusion of 2D-3D detection results; (2) development of a set of data association and track management skills that utilizes a vertex-based similarity metric as well as false alarm rejection and track recovery mechanisms to generate reliable bidirectional object trajectories; (3) development of a trajectory re-optimization scheme that re-organizes track fragments of different fidelities in a greedy fashion, as well as refines each trajectory with completion and smoothing techniques. The experiment results on the KITTI dataset demonstrate that BiTrack achieves the state-of-the-art performance for 3D OMOT tasks in terms of accuracy and efficiency.