Head detection for video surveillance based on categorical hair and skin colour models

Authors:
Zui Zhang;Hatice Gunes;Massimo Piccardi
Affiliations:
Faculty of Engineering and Information Technology, University of Technology, Sydney, Australia;Faculty of Engineering and Information Technology, University of Technology, Sydney, Australia;Faculty of Engineering and Information Technology, University of Technology, Sydney, Australia
Venue:
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Year:
2009

Citing 5
Cited 1

Face Detection From Color Images Using a Fuzzy Pattern Matching Method

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Detection in Color Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face and Head Detection for a Real-Time Surveillance System

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Head Tracking with Shape Modeling and Detection

CRV '05 Proceedings of the 2nd Canadian conference on Computer and Robot Vision
Tracking People in Crowds by a Part Matching Approach

AVSS '08 Proceedings of the 2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance

Contextual information and covariance descriptors for people surveillance: an application for safety of construction workers

Journal on Image and Video Processing - Special issue on advanced video-based surveillance

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a new robust head detection algorithm that is capable of handling significantly different conditions in terms of viewpoint, tilt angle, scale and resolution. To this aim, we built a new model for the head based on appearance distributions and shape constraints. We construct a categorical model for hair and skin, separately, and train the models for four categories of hair (brown, red, blond and black) and three categories of skin representing the different illumination conditions (bright, standard and dark). The shape constraint fits an elliptical model to the candidate region and compares its parameters with priors based on human anatomy. The experimental results validate the usability of the proposed algorithm in various video surveillance and multimedia applications.