BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Prediction

TL;DR

This paper introduces BP-SGCN, a novel graph convolution network that uses behavioral pseudo-labels derived from motion features to improve trajectory prediction for pedestrians and heterogeneous traffic agents.

Contribution

The work proposes a new pseudo-labeling approach and a cascaded training scheme for trajectory prediction, reducing reliance on costly annotations and enhancing accuracy.

Findings

BP-SGCN outperforms existing methods on multiple datasets.

Behavioral pseudo-labels effectively capture behavior clusters.

The cascaded training scheme improves trajectory prediction accuracy.

Abstract

Trajectory prediction allows better decision-making in applications of autonomous vehicles or surveillance by predicting the short-term future movement of traffic agents. It is classified into pedestrian or heterogeneous trajectory prediction. The former exploits the relatively consistent behavior of pedestrians, but is limited in real-world scenarios with heterogeneous traffic agents such as cyclists and vehicles. The latter typically relies on extra class label information to distinguish the heterogeneous agents, but such labels are costly to annotate and cannot be generalized to represent different behaviors within the same class of agents. In this work, we introduce the behavioral pseudo-labels that effectively capture the behavior distributions of pedestrians and heterogeneous agents solely based on their motion features, significantly improving the accuracy of trajectory prediction. To implement the framework, we propose the Behavioral Pseudo-Label Informed Sparse Graph Convolution Network (BP-SGCN) that learns pseudo-labels and informs to a trajectory predictor. For optimization, we propose a cascaded training scheme, in which we first learn the pseudo-labels in an unsupervised manner, and then perform end-to-end fine-tuning on the labels in the direction of increasing the trajectory prediction accuracy. Experiments show that our pseudo-labels effectively model different behavior clusters and improve trajectory prediction. Our proposed BP-SGCN outperforms existing methods using both pedestrian (ETH/UCY, pedestrian-only SDD) and heterogeneous agent datasets (SDD, Argoverse 1).