Use of nested K-means for robust head location in visual surveillance system

Authors:
Hyun Jea Joo;Bong Won Jang;Sedai Suman;Phill Kyu Rhee
Affiliations:
Dept. of Computer Science & Engineering, Inha University, Incheon, South Korea;Dept. of Computer Science & Engineering, Inha University, Incheon, South Korea;Dept. of Computer Science & Engineering, Inha University, Incheon, South Korea;Dept. of Computer Science & Engineering, Inha University, Incheon, South Korea
Venue:
PRICAI'06 Proceedings of the 9th Pacific Rim international conference on Artificial intelligence
Year:
2006

Citing 7
Cited 0

W4: Real-Time Surveillance of People and Their Activities

IEEE Transactions on Pattern Analysis and Machine Intelligence
Moving Target Classification and Tracking from Real-time Video

WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
Model Based Extraction of Articulated Objects in Image Sequences for Gait Analysis

ICIP '97 Proceedings of the 1997 International Conference on Image Processing (ICIP '97) 3-Volume Set-Volume 3 - Volume 3
A robust elliptical head tracker

FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
A survey on visual surveillance of object motion and behaviors

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
A Bayesian discriminating features method for face detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
A real-time system for video surveillance of unattended outdoor environments

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a head detection method for frontal face detection. We use motion segmentation algorithm that makes use of differencing to detect moving people's head. The novelty of this paper comes from adaptive frame differencing, detecting edge lines and restoration, finding the head area and cutting the head candidate. Moreover, we adopt nested Kmeans algorithm for finding head regions. Our system applies the statistical modeling of face and non - face classes and classifies multiple frontal face images with the Bayesian Discriminating Features (BDF) method to verify. Finally experimental results (using capture diverse image sources for 13 frames per second during 20 seconds and having 260 images per person) shows the feasibility of the differencing based head and Nested K-means Detection method.