2006 | OriginalPaper | Buchkapitel
Use of Nested K-Means for Robust Head Location in Visual Surveillance System
verfasst von : Hyun Jea Joo, Bong Won Jang, Sedai Suman, Phill Kyu Rhee
Erschienen in: PRICAI 2006: Trends in Artificial Intelligence
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
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 K-means 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.