Detection and tracking of humans by probabilistic body part assembly

Micilotta, AS, Ong, EJ and Bowden, R (2005) Detection and tracking of humans by probabilistic body part assembly BMVC 2005 - Proceedings of the British Machine Vision Conference 2005.

Full text not available from this repository.

Abstract

This paper presents a probabilistic framework of assembling detected human body parts into a full 2D human configuration. The face, torso, legs and hands are detected in cluttered scenes using boosted body part detectors trained by AdaBoost. Body configurations are assembled from the detected parts using RANSAC, and a coarse heuristic is applied to eliminate obvious outliers. An a priori mixture model of upper-body configurations is used to provide a pose likelihood for each configuration. A joint-likelihood model is then determined by combining the pose, part detector and corresponding skin model likelihoods. The assembly with the highest likelihood is selected by RANSAC, and the elbow positions are inferred. This paper also illustrates the combination of skin colour likelihood and detection likelihood to further reduce false hand and face detections.

Item Type:	Article
Authors :	Name Email ORCID Micilotta, AS Ong, EJ Bowden, R r.bowden@surrey.ac.uk
Date :	1 January 2005
DOI :	10.5244/C.19.44
Depositing User :	Symplectic Elements
Date Deposited :	17 May 2017 13:15
Last Modified :	16 Jan 2019 18:42
URI:	http://epubs.surrey.ac.uk/id/eprint/838515

Actions (login required)

View Item

Downloads