Using UWB for Human Trajectory Extraction

2013/03/15 by Vasconcelos, Gonçalo, Petry, Marcelo, Almeida, João Emílio +2
#FOS: Computer and information sciences #Other Computer Science (cs.OH)

paper · doi:10.48550/arxiv.1303.4696

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.

Related

• Top-view Trajectories: A Pedestrian Dataset of Vehicle-Crowd Interaction\n from Controlled Experiments and Crowded Campus
• High precision analysis of unidirectional pedestrian flow within the Hermes Project
• WiDEVIEW: An UltraWideBand and Vision Dataset for Deciphering Pedestrian-Vehicle Interactions
• Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches
• Preliminary Study on Space Utilization and Emergent Behaviors of Group vs. Single Pedestrians in Real-World Trajectories