Online Multi-Target Tracking for Maneuvering Vehicles in Dynamic Road Context

TL;DR

This paper introduces an online multi-object tracking framework for maneuvering vehicles in dynamic road environments, integrating point cloud detection, IMM-based data association, and road context for improved tracking accuracy.

Contribution

It presents a novel online MOT method that incorporates road context and maneuvering uncertainty using IMM and hybrid models for robust vehicle tracking.

Findings

Effective multi-vehicle tracking with maneuvering in dynamic environments

Integration of road context improves data association accuracy

Robustness to localization drift demonstrated in experiments

Abstract

Target detection and tracking provides crucial information for motion planning and decision making in autonomous driving. This paper proposes an online multi-object tracking (MOT) framework with tracking-by-detection for maneuvering vehicles under motion uncertainty in dynamic road context. We employ a point cloud based vehicle detector to provide real-time 3D bounding boxes of detected vehicles and conduct the online bipartite optimization of the maneuver-orientated data association between the detections and the targets. Kalman Filter (KF) is adopted as the backbone for multi-object tracking. In order to entertain the maneuvering uncertainty, we leverage the interacting multiple model (IMM) approach to obtain the \textit{a-posterior} residual as the cost for each association hypothesis, which is calculated with the hybrid model posterior (after mode-switch). Road context is integrated to conduct adjustments of the time varying transition probability matrix (TPM) of the IMM to regulate the maneuvers according to road segments and traffic sign/signals, with which the data association is performed in a unified spatial-temporal fashion. Experiments show our framework is able to effectively track multiple vehicles with maneuvers subject to dynamic road context and localization drift.