Noticing Motion Patterns: Temporal CNN with a Novel Convolution Operator for Human Trajectory Prediction

TL;DR

This paper introduces Social-PEC, a CNN-based method for human trajectory prediction that effectively learns motion patterns, improves interpretability over previous pooling-based models, and performs competitively with state-of-the-art approaches.

Contribution

The paper presents a novel convolution operator and a CNN architecture that enhances pattern detection and interpretability in human trajectory prediction.

Findings

Model performs comparably to state-of-the-art methods.

Outperforms existing models in certain scenarios.

Provides a more explainable decision-making process.

Abstract

We propose a Convolutional Neural Network-based approach to learn, detect,and extract patterns in sequential trajectory data, known here as Social Pattern Extraction Convolution (Social-PEC). A set of experiments carried out on the human trajectory prediction problem shows that our model performs comparably to the state of the art and outperforms in some cases. More importantly,the proposed approach unveils the obscurity in the previous use of pooling layer, presenting a way to intuitively explain the decision-making process.