Detección y Seguimiento de Personas Basado en Estereovisión y Filtro de Kalman

García, Juan de Dios; Gardel, Alfredo; Bravo, Ignácio; Martínez, Miguel; Rodríguez, D.

doi:10.1016/j.riai.2012.09.012

Cited by 3 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pedestrian detection and tracking has been proposed by García et al (2012). It uses stereo cameras mounted on a static position to detect the pedestrians and a multiplehypothesis Kalman Filter to perform tracking.…”

Section: Related Workmentioning

confidence: 99%

Tracking and following pedestrian trajectories, an approach for autonomous surveillance of critical infrastructures

Oviedo

Barrientos

Cerro

et al. 2015

Industrial Robot: An International Journal

View full text Add to dashboard Cite

Purpose – This paper aims to present a system that is fully capable of addressing the issue of detection, tracking and following pedestrians, which is a very challenging task, especially when it is considered for using in large outdoors infrastructures. Three modules, detection, tracking and following, are integrated and tested over long distances in semi-structured scenarios, where static or dynamic obstacles, including other pedestrians, can be found. Design/methodology/approach – The detection is based on the probabilistic fusion of a laser scanner and a camera. The tracking module pairs observations with previously detected targets by using Kalman Filters and a Mahalanobis-distance. The following module allows to safely pursue the target by using a well-defined navigation scheme. Findings – The system can track pedestrians from static position to 3.46 m/s (running). It handles occlusions, crossings or miss-detections, keeping track of the position even if the pedestrian is only detected in 55/per cent of the observations. Moreover, it autonomously selects and follows a target at a maximum speed of 1.46 m/s. Originality/value – The main novelty of this study is the integration of the three algorithms in a fully operational system, tested in real outdoor scenarios. Furthermore, the addition of labelling to the detection algorithm allows using the full range of a single sensor while preserving the high performance of a combined detection. False-positives’ rate is reduced by handling the uncertainty level when pairing observations. The inclusion of pedestrian speed in the model speeds up and simplifies tracking process. Finally, the most suitable target is automatically selected by a scoring system.

show abstract

Section: Related Workmentioning

confidence: 99%

Tracking and following pedestrian trajectories, an approach for autonomous surveillance of critical infrastructures

Oviedo

Barrientos

Cerro

et al. 2015

Industrial Robot: An International Journal

View full text Add to dashboard Cite

show abstract

“…A pedestrian detection and tracking system for surveillance applications has been proposed by Garcia et al [69]. It uses stereo cameras in order to detect the pedestrians and a multiple-hypothesis Kalman filter in order to perform tracking.…”

Section: Related Workmentioning

confidence: 99%

Tracking and intercepting pedestrians: a robotic approach to surveillance of critical infrastructures

Oviedo¹

View full text Add to dashboard Cite

Conteo de personas con un sensor RGBD comercial

Castrillón-Santan

Lorenzo-Navarro

Hernández-Sosa

2014

Revista Iberoamericana de Automática e Informática Industrial R

View full text Add to dashboard Cite

En este trabajo se demuestra que la información de profundidad proporcionada por una cámara RGBD comercial de bajo coste, es una fuente fiable de datos para realizar de forma robusta el conteo automático de personas. La adopción de una configuración de vista cenital reduce la complejidad del problema, al mismo tiempo que permite preservar la privacidad de las personas monitorizadas. Para llevar a cabo el estudio experimental se han considerado dos técnicas propias del campo de análisis de imágenes 2D trasladadas al contexto de imágenes de profundidad. Las pruebas evaluaron su rendimiento con vídeos reales sin restricciones de iluminación, incluyendo episodios de iluminación cambiante o muy baja. En este conjunto experimental se realizó la detección, seguimiento y análisis de patrones de comportamiento de las personas que cruzaban el campo de visión. Los resultados obtenidos alcanzan una tasa de acierto próxima al 95 %, superando los obtenidos con técnicas actuales basadas exclusivamente en información visual. Estos resultados sugieren la utilidad del uso de información de profundidad en esta tarea particular.

show abstract

Detección y Seguimiento de Personas Basado en Estereovisión y Filtro de Kalman

Cited by 3 publications

References 13 publications

Tracking and following pedestrian trajectories, an approach for autonomous surveillance of critical infrastructures

Tracking and following pedestrian trajectories, an approach for autonomous surveillance of critical infrastructures

Tracking and intercepting pedestrians: a robotic approach to surveillance of critical infrastructures

Conteo de personas con un sensor RGBD comercial

Contact Info

Product

Resources

About