Observatorio de I+D+i UPM

Descripción
A novel pedestrian motion prediction technique is presented in this paper. Its main achievement regards to none previous observation, any knowledge of pedestrian trajectories nor the existence of possible destinations is required; hence making it useful for autonomous surveillance applications. Prediction only requires initial position of the pedestrian and a 2D representation of the scenario as occupancy grid. First, it uses the Fast Marching Method (FMM) to calculate the pedestrian arrival time for each position in the map and then, the likelihood that the pedestrian reaches those positions is estimated. The technique has been tested with synthetic and real scenarios. In all cases, accurate probability maps as well as their representative graphs were obtained with low computational cost.
Internacional	No
Nombre congreso	RoboCity16 Open Conference on Future Trends in Robotics
Tipo de participación	960
Lugar del congreso	Madrid, España
Revisores	Si
ISBN o ISSN	978-84-608-8452-1
DOI
Fecha inicio congreso	26/05/2016
Fecha fin congreso	27/05/2016
Desde la página	309
Hasta la página	316
Título de las actas	Actas del RoboCity16 Open Conference on Future Trends in Robotics

Esta actividad pertenece a memorias de investigación

• Autor: David Alfredo Garzon Ramos
• Autor: Mario Andrei Garzon Oviedo (UPM)
• Autor: Antonio Barrientos Cruz (UPM)

• Creador: Centro o Instituto I+D+i: Centro de Automática y Robótica (CAR). Centro Mixto UPM-CSIC
• Departamento: Automática, Ingeniería Eléctrica y Electrónica e Informática Industrial