Where Do You Go? Pedestrian Trajectory Prediction using Scene Features

TL;DR

This paper introduces a novel pedestrian trajectory prediction model that combines social interactions with environmental context using scene features and advanced neural mechanisms, significantly improving prediction accuracy for autonomous vehicle safety.

Contribution

The study presents an integrated approach that fuses pedestrian interactions and scene features via a cross-attention mechanism, advancing trajectory prediction methods.

Findings

Achieves lower ADE and FDE compared to existing methods.

Effectively captures spatial and temporal pedestrian interactions.

Enhances prediction accuracy by incorporating detailed scene context.

Abstract

Accurate prediction of pedestrian trajectories is crucial for enhancing the safety of autonomous vehicles and reducing traffic fatalities involving pedestrians. While numerous studies have focused on modeling interactions among pedestrians to forecast their movements, the influence of environmental factors and scene-object placements has been comparatively underexplored. In this paper, we present a novel trajectory prediction model that integrates both pedestrian interactions and environmental context to improve prediction accuracy. Our approach captures spatial and temporal interactions among pedestrians within a sparse graph framework. To account for pedestrian-scene interactions, we employ advanced image enhancement and semantic segmentation techniques to extract detailed scene features. These scene and interaction features are then fused through a cross-attention mechanism, enabling the model to prioritize relevant environmental factors that influence pedestrian movements. Finally, a temporal convolutional network processes the fused features to predict future pedestrian trajectories. Experimental results demonstrate that our method significantly outperforms existing state-of-the-art approaches, achieving ADE and FDE values of 0.252 and 0.372 meters, respectively, underscoring the importance of incorporating both social interactions and environmental context in pedestrian trajectory prediction.