Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervision

TL;DR

This paper introduces a hierarchical temporal pyramid network with multi-supervision for pedestrian trajectory prediction, effectively capturing both long-range and short-range motion information to improve prediction accuracy.

Contribution

It proposes a novel temporal pyramid framework with multi-supervision and a coarse-to-fine fusion strategy for better trajectory modeling.

Findings

Outperforms existing methods on benchmark datasets.

Effectively captures multi-temporal motion features.

Demonstrates improved prediction accuracy.

Abstract

Predicting human motion behavior in a crowd is important for many applications, ranging from the natural navigation of autonomous vehicles to intelligent security systems of video surveillance. All the previous works model and predict the trajectory with a single resolution, which is rather inefficient and difficult to simultaneously exploit the long-range information (e.g., the destination of the trajectory), and the short-range information (e.g., the walking direction and speed at a certain time) of the motion behavior. In this paper, we propose a temporal pyramid network for pedestrian trajectory prediction through a squeeze modulation and a dilation modulation. Our hierarchical framework builds a feature pyramid with increasingly richer temporal information from top to bottom, which can better capture the motion behavior at various tempos. Furthermore, we propose a coarse-to-fine fusion strategy with multi-supervision. By progressively merging the top coarse features of global context to the bottom fine features of rich local context, our method can fully exploit both the long-range and short-range information of the trajectory. Experimental results on several benchmarks demonstrate the superiority of our method.