Tracking of multiple people in crowds using laser range scanners - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Tracking of multiple people in crowds using laser range scanners

Résumé

In everyday life, we can see amazing choreographies of movements of crowds of pedestrians. Pedestrians run into and avoid each other but do not seem to consciously cooperate. In this paper, we track a crowd of pedestrians in a large covered and cluttered area to understand their social behavior. Additionally, we try to analyze the characteristics of crowds of pedestrians such as traffic density, velocity, and trajectory. We introduce a stable feature extraction method based on accumulated distribution of successive laser frames. To isolate pedestrians, we propose a nonparametric method exploiting the Parzen windowing technique. We apply the new method of Rao-Blackwellized Monte Carlo data association to track a highly variable number of pedestrians. The algorithm is quantitatively evaluated through a social behavior experiment taking place in the lobby of a school. During this experiment, nearly 300 students are tracked.

Domaines

Autre
Fichier non déposé

Dates et versions

hal-01277892 , version 1 (23-02-2016)

Identifiants

Citer

Ladji Adiaviakoye, Patrick Plainchault, Marc Bourcerie, Jean Michel Auberlet. Tracking of multiple people in crowds using laser range scanners. International Conference on Intelligent Sensors, Sensor Networks and Information Processing - IEEE ISSNIP, Apr 2014, SINGAPOUR, France. 7p, ⟨10.1109/ISSNIP.2014.6827668⟩. ⟨hal-01277892⟩
99 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More