Using UWB for Human Trajectory Extraction

TL;DR

This paper presents a UWB-based methodology for modeling pedestrian behavior and extracting human trajectories, demonstrating its effectiveness in single-file scenarios and potential for emergency evacuation applications.

Contribution

The study introduces a novel UWB data collection approach for human trajectory extraction, showing advantages over traditional methods in modeling pedestrian flow.

Findings

UWB data effectively characterizes pedestrian trajectories.

The approach accurately models macroscopic pedestrian flow.

UWB outperforms traditional trajectory extraction methods.

Abstract

In this paper we report on a methodology to model pedestrian behaviours whilst aggregate variables are concerned, with potential applications to different situations, such as evacuating a building in emergency events. The approach consists of using UWB (ultra-wide band) based data collection to characterise behaviour in specific scenarios. From a number of experiments carried out, we detail the single-file scenario to demonstrate the ability of this approach to represent macroscopic characteristics of the pedestrian flow. Results are discussed and we can conclude that UWB-based data collection shows great potential and suitability for human trajectory extraction, when compared to other traditional approaches.