Spatial-Temporal Block and LSTM Network for Pedestrian Trajectories Prediction

TL;DR

This paper introduces a novel LSTM-based model combining graph and temporal convolutional networks to predict pedestrian trajectories in crowded scenes, effectively capturing social interactions and scene context.

Contribution

It proposes a new Spatio-Temporal Block integrated with LSTM and graph embedding to improve multi-modal trajectory prediction accuracy.

Findings

Achieved state-of-the-art results on ETH and UCY datasets.

Effectively models social interactions and scene context.

Outperforms existing methods in trajectory prediction accuracy.

Abstract

Pedestrian trajectory prediction is a critical to avoid autonomous driving collision. But this prediction is a challenging problem due to social forces and cluttered scenes. Such human-human and human-space interactions lead to many socially plausible trajectories. In this paper, we propose a novel LSTM-based algorithm. We tackle the problem by considering the static scene and pedestrian which combine the Graph Convolutional Networks and Temporal Convolutional Networks to extract features from pedestrians. Each pedestrian in the scene is regarded as a node, and we can obtain the relationship between each node and its neighborhoods by graph embedding. It is LSTM that encode the relationship so that our model predicts nodes trajectories in crowd scenarios simultaneously. To effectively predict multiple possible future trajectories, we further introduce Spatio-Temporal Convolutional Block to make the network flexible. Experimental results on two public datasets, i.e. ETH and UCY, demonstrate the effectiveness of our proposed ST-Block and we achieve state-of-the-art approaches in human trajectory prediction.