Combining face detection and people tracking in video sequences - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2009

Combining face detection and people tracking in video sequences


Face detection algorithms are widely used in computer vision as they provide fast and reliable results depending on the application domain. A multi view approach is here presented to detect frontal and profile pose of people face using Histogram of Oriented Gradients, i.e. HOG, features. A K-mean clustering technique is used in a cascade of HOG feature classifiers to detect faces. The evaluation of the algorithm shows similar performance in terms of detection rate as state of the art algorithms. Moreover, unlike state of the art algorithms, our system can be quickly trained before detection is possible. Performance is considerably increased in terms of lower computational cost and lower false detection rate when combined with motion constraint given by moving objects in video sequences. The detected HOG features are integrated within a tracking framework and allow reliable face tracking results in several tested surveillance video sequences.
Fichier principal
Vignette du fichier
ecorvee-icdp09.pdf (306.64 Ko) Télécharger le fichier
Vignette du fichier
faces-icdp09-illustration.jpg (424.05 Ko) Télécharger le fichier
ecorvee-comparing-with-violajones.avi (23.03 Mo) Télécharger le fichier
ecorvee-face-people-tracking.avi (21.21 Mo) Télécharger le fichier
presentation-v5.ppt (2.88 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Format : Other
Format : Other
Format : Other

Dates and versions

inria-00502749 , version 1 (15-07-2010)


  • HAL Id : inria-00502749 , version 1


Etienne Corvee, François Bremond. Combining face detection and people tracking in video sequences. The 3rd International Conference on Imaging for Crime Detection and Prevention - ICDP09, Dec 2009, Kingston Upon Thames (London), United Kingdom. pp.1. ⟨inria-00502749⟩


275 View
739 Download


Gmail Facebook X LinkedIn More