A Semantic and Occlusion-Aware GM-PHD Filter

TL;DR

This paper introduces a semantic and occlusion-aware GM-PHD filter that improves object tracking in complex driving scenarios by explicitly modeling occlusions and leveraging deep learning-based semantic information.

Contribution

The paper presents a novel birth model for GM-PHD filters that incorporates semantic and occlusion information, enhancing tracking accuracy and reducing initialization delay.

Findings

Reduces initialization delay in occlusion-heavy scenarios.

Matches or outperforms baseline in 70% of cases.

Improves tracking performance by integrating semantic priors.

Abstract

This paper proposes a new birth model including semantic information derived from deep learning to create an occlusion-aware Gaussian Mixture Probability Hypothesis Density (GM-PHD) filter. Unlike prior approaches that rely on simplistic or uniform assumptions, the proposed Semantic-Occlusion Aware (S-OA) birth model defines initialization terms by explicitly considering regions of occlusion and by leveraging semantic information about the environment. This enables the filter to accurately represent where new objects are more likely to appear, thereby improving tracking performance in complex and high-density driving scenarios. The method is evaluated through Monte Carlo simulations and experiments on the KITTI dataset. Performance is assessed by measuring the latency between first detection and track initiation, along with the mean absolute cardinality error and the Optimal Subpattern Assignment (OSPA) metric. Results demonstrate that the S-OA birth model reduces initialization delay in occlusion-heavy settings, matching or outperforming the strongest baseline in approximately 70% of cases. A sensitivity analysis of birth model weights is also provided. Overall, the findings underscore the benefits of integrating occlusion reasoning and semantic priors into Bayesian tracking frameworks for autonomous driving.