Traffic-Aware Pedestrian Intention Prediction

TL;DR

This paper introduces a novel Traffic-Aware Spatio-Temporal Graph Convolutional Network that effectively incorporates traffic signals and scene context to improve pedestrian intention prediction for autonomous vehicles.

Contribution

It presents a new model that integrates traffic signal states and scene information, enhancing prediction accuracy in urban environments.

Findings

Achieves 4.75% higher accuracy than baseline on PIE dataset.

Effectively captures spatial and temporal dependencies in complex scenes.

Demonstrates improved pedestrian intention prediction in real-world scenarios.

Abstract

Accurate pedestrian intention estimation is crucial for the safe navigation of autonomous vehicles (AVs) and hence attracts a lot of research attention. However, current models often fail to adequately consider dynamic traffic signals and contextual scene information, which are critical for real-world applications. This paper presents a Traffic-Aware Spatio-Temporal Graph Convolutional Network (TA-STGCN) that integrates traffic signs and their states (Red, Yellow, Green) into pedestrian intention prediction. Our approach introduces the integration of dynamic traffic signal states and bounding box size as key features, allowing the model to capture both spatial and temporal dependencies in complex urban environments. The model surpasses existing methods in accuracy. Specifically, TA-STGCN achieves a 4.75% higher accuracy compared to the baseline model on the PIE dataset, demonstrating its effectiveness in improving pedestrian intention prediction.