Generic Vehicle Tracking Framework Capable of Handling Occlusions Based on Modified Mixture Particle Filter

TL;DR

This paper introduces a generic vehicle tracking framework using a modified mixture particle filter that adaptively tracks multiple vehicles in real-time without explicit data association, effectively handling occlusions and sudden maneuvers.

Contribution

It proposes a novel adaptive tracking framework that replaces traditional kinematic models with learning-based behavioral models for improved prediction during occlusions.

Findings

Effective in lane keeping and lane change scenarios.

Handles occlusions and sudden maneuvers robustly.

Tracks multiple vehicles simultaneously without explicit data association.

Abstract

Accurate and robust tracking of surrounding road participants plays an important role in autonomous driving. However, there is usually no prior knowledge of the number of tracking targets due to object emergence, object disappearance and false alarms. To overcome this challenge, we propose a generic vehicle tracking framework based on modified mixture particle filter, which can make the number of tracking targets adaptive to real-time observations and track all the vehicles within sensor range simultaneously in a uniform architecture without explicit data association. Each object corresponds to a mixture component whose distribution is non-parametric and approximated by particle hypotheses. Most tracking approaches employ vehicle kinematic models as the prediction model. However, it is hard for these models to make proper predictions when sensor measurements are lost or become low quality due to partial or complete occlusions. Moreover, these models are incapable of forecasting sudden maneuvers. To address these problems, we propose to incorporate learning-based behavioral models instead of pure vehicle kinematic models to realize prediction in the prior update of recursive Bayesian state estimation. Two typical driving scenarios including lane keeping and lane change are demonstrated to verify the effectiveness and accuracy of the proposed framework as well as the advantages of employing learning-based models.