OptiPMB: Enhancing 3D Multi-Object Tracking with Optimized Poisson Multi-Bernoulli Filtering

2025-03-17

AI Summary

To address low accuracy and challenges in data association and trajectory management for 3D multi-object tracking (MOT) in complex autonomous driving scenarios, this paper proposes an optimized Poisson multi-Bernoulli (PMB) filtering framework grounded in random finite set (RFS) theory. Key contributions include: (1) a novel measurement-driven hybrid adaptive birth model to enhance robustness in detecting newborn objects; (2) dynamic modeling of detection probability to mitigate occlusion effects; and (3) joint optimization of density pruning and trajectory extraction to improve interpretability and data efficiency. Evaluated on nuScenes and KITTI benchmarks, the method significantly outperforms existing model-based 3D MOT approaches—achieving +3.2% in MOTA and +4.7% in IDF1—thereby establishing a new state-of-the-art benchmark for model-driven 3D MOT.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: State Estimation
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Accurate 3D multi-object tracking (MOT) is crucial for autonomous driving, as it enables robust perception, navigation, and planning in complex environments. While deep learning-based solutions have demonstrated impressive 3D MOT performance, model-based approaches remain appealing for their simplicity, interpretability, and data efficiency. Conventional model-based trackers typically rely on random vector-based Bayesian filters within the tracking-by-detection (TBD) framework but face limitations due to heuristic data association and track management schemes. In contrast, random finite set (RFS)-based Bayesian filtering handles object birth, survival, and death in a theoretically sound manner, facilitating interpretability and parameter tuning. In this paper, we present OptiPMB, a novel RFS-based 3D MOT method that employs an optimized Poisson multi-Bernoulli (PMB) filter while incorporating several key innovative designs within the TBD framework. Specifically, we propose a measurement-driven hybrid adaptive birth model for improved track initialization, employ adaptive detection probability parameters to effectively maintain tracks for occluded objects, and optimize density pruning and track extraction modules to further enhance overall tracking performance. Extensive evaluations on nuScenes and KITTI datasets show that OptiPMB achieves superior tracking accuracy compared with state-of-the-art methods, thereby establishing a new benchmark for model-based 3D MOT and offering valuable insights for future research on RFS-based trackers in autonomous driving.

Problem

• Improves 3D multi-object tracking for autonomous driving
• Addresses limitations of heuristic data association in trackers
• Enhances tracking accuracy with optimized PMB filter

Innovation

• Optimized Poisson multi-Bernoulli filter for 3D MOT
• Measurement-driven hybrid adaptive birth model
• Adaptive detection probability for occluded objects