대한전기학회:학술대회논문집 (Proceedings of the KIEE Conference)
- 대한전기학회 2001년도 합동 추계학술대회 논문집 정보 및 제어부문
- /
- Pages.438-441
- /
- 2001
Convex hull과 Robust Hausdorff Distance를 이용한 실시간 얼굴 트래킹
A New Face Tracking Algorithm Using Convex-hull and Hausdorff Distance
- Park, Min-Sik (ICS Lab. Dept. of Electrical and Electronic Engineering, Yonsei University) ;
- Park, Chang-U (ICS Lab. Dept. of Electrical and Electronic Engineering, Yonsei University) ;
- Park, Min-Yong (ICS Lab. Dept. of Electrical and Electronic Engineering, Yonsei University)
- 발행 : 2001.11.24
초록
This paper describes a system for tracking a face in a input video sequence using facial convex hull based facial segmentation and a robust hausdorff distance. The algorithm adapts YCbCr color model for classifying face region by [l]. Then, we obtain an initial face model with preprocessing and convex hull. For tracking, a Robust Hausdorff distance is computed and the best possible displacement is selected. Finally, the previous face model is updated using the displacement t. It is robust to some noises and outliers. We provide an example to illustrate the proposed tracking algorithm in video sequences obtained from CCD camera.