Pedestrian Volume Prediction Using a Diffusion Convolutional Gated Recurrent Unit Model

TL;DR

This paper introduces DCGRU-DTW, a deep learning model that predicts pedestrian flow by capturing spatial and temporal dependencies, outperforming traditional models using real-world data from Melbourne.

Contribution

The paper presents a novel extension of DCGRU with dynamic time warping for improved pedestrian flow prediction using city-wide data.

Findings

DCGRU-DTW outperforms classic VAR and original DCGRU models

Model effectively captures spatial and temporal dependencies

Demonstrated superior accuracy on real-world Melbourne data

Abstract

Effective models for analysing and predicting pedestrian flow are important to ensure the safety of both pedestrians and other road users. These tools also play a key role in optimising infrastructure design and geometry and supporting the economic utility of interconnected communities. The implementation of city-wide automatic pedestrian counting systems provides researchers with invaluable data, enabling the development and training of deep learning applications that offer better insights into traffic and crowd flows. Benefiting from real-world data provided by the City of Melbourne pedestrian counting system, this study presents a pedestrian flow prediction model, as an extension of Diffusion Convolutional Grated Recurrent Unit (DCGRU) with dynamic time warping, named DCGRU-DTW. This model captures the spatial dependencies of pedestrian flow through the diffusion process and the temporal dependency captured by Gated Recurrent Unit (GRU). Through extensive numerical experiments, we demonstrate that the proposed model outperforms the classic vector autoregressive model and the original DCGRU across multiple model accuracy metrics.