DocumentCode :
2721936
Title :
A nonparametric Bayesian approach for enhanced pedestrian detection and foreground segmentation
Author :
Elguebaly, Tarek ; Bouguila, Nizar
Author_Institution :
ECE, Concordia Univ., Montreal, QC, Canada
fYear :
2011
fDate :
20-25 June 2011
Firstpage :
21
Lastpage :
26
Abstract :
With the continuous improvements in computer vision techniques, automatic low-cost video surveillance is becoming feasible. In the context of automatic surveillance, an important problem is the development of accurate models for foreground segmentation and pedestrians detection in outdoor scenes. In this paper we study an unsupervised algorithm based on infinite generalized Gaussian mixture models, that take into consideration the disadvantage of visible-light images (i.e. sensitivity to variations in illumination and lights) and infrared images (i.e. sensitivity to outdoor climate and temperature changes).
Keywords :
Bayes methods; Gaussian processes; computer vision; image segmentation; object detection; traffic engineering computing; video signal processing; video surveillance; computer vision; enhanced pedestrian detection; foreground segmentation; generalized Gaussian mixture models; nonparametric Bayesian approach; video surveillance; visible light images; Humans; Lighting; Mathematical model; Meteorology; Thermal sensors; Video surveillance;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition Workshops (CVPRW), 2011 IEEE Computer Society Conference on
Conference_Location :
Colorado Springs, CO
ISSN :
2160-7508
Print_ISBN :
978-1-4577-0529-8
Type :
conf
DOI :
10.1109/CVPRW.2011.5981800
Filename :
5981800
Link To Document :
بازگشت