Occlusion-Aware Diffusion Model for Pedestrian Intention Prediction

TL;DR

This paper introduces an occlusion-aware diffusion model that reconstructs occluded pedestrian motion patterns to improve intention prediction accuracy in scenarios with incomplete observations, enhancing robustness over existing methods.

Contribution

The paper proposes a novel diffusion transformer architecture with occlusion mask-guided reverse process for better pedestrian intention prediction under occlusion conditions.

Findings

Outperforms existing methods on PIE and JAAD benchmarks.

Achieves more robust pedestrian intention prediction in occluded scenarios.

Effectively reconstructs occluded motion patterns to guide future predictions.

Abstract

Predicting pedestrian crossing intentions is crucial for the navigation of mobile robots and intelligent vehicles. Although recent deep learning-based models have shown significant success in forecasting intentions, few consider incomplete observation under occlusion scenarios. To tackle this challenge, we propose an Occlusion-Aware Diffusion Model (ODM) that reconstructs occluded motion patterns and leverages them to guide future intention prediction. During the denoising stage, we introduce an occlusion-aware diffusion transformer architecture to estimate noise features associated with occluded patterns, thereby enhancing the model's ability to capture contextual relationships in occluded semantic scenarios. Furthermore, an occlusion mask-guided reverse process is introduced to effectively utilize observation information, reducing the accumulation of prediction errors and enhancing the accuracy of reconstructed motion features. The performance of the proposed method under various occlusion scenarios is comprehensively evaluated and compared with existing methods on popular benchmarks, namely PIE and JAAD. Extensive experimental results demonstrate that the proposed method achieves more robust performance than existing methods in the literature.