Who Walks With You Matters: Perceiving Social Interactions with Groups for Pedestrian Trajectory Prediction

TL;DR

This paper introduces the GPCC model that improves pedestrian trajectory prediction by perceiving social interactions through grouping and multimodal perception, inspired by human social perception, and demonstrates its effectiveness across multiple datasets.

Contribution

The paper proposes the GPCC model that combines grouping and perception modules to enhance trajectory prediction by modeling social interactions more human-like.

Findings

Significant improvements in trajectory prediction accuracy.

Effective modeling of social and individual dynamics.

Enhanced explainability through human-like perception cues.

Abstract

Understanding and anticipating human movement has become more critical and challenging in diverse applications such as autonomous driving and surveillance. The complex interactions brought by different relations between agents are a crucial reason that poses challenges to this task. Researchers have put much effort into designing a system using rule-based or data-based models to extract and validate the patterns between pedestrian trajectories and these interactions, which has not been adequately addressed yet. Inspired by how humans perceive social interactions with different level of relations to themself, this work proposes the GrouP ConCeption (short for GPCC) model composed of the Group method, which categorizes nearby agents into either group members or non-group members based on a long-term distance kernel function, and the Conception module, which perceives both visual and acoustic information surrounding the target agent. Evaluated across multiple datasets, the GPCC model demonstrates significant improvements in trajectory prediction accuracy, validating its effectiveness in modeling both social and individual dynamics. The qualitative analysis also indicates that the GPCC framework successfully leverages grouping and perception cues human-like intuitively to validate the proposed model's explainability in pedestrian trajectory forecasting.