Development of Tracking Equipment for Real­Time Multiple Face Detection

실시간 복합 얼굴 검출을 위한 추적 장치 개발

  • 나상동 (조선대학교 컴퓨터공학부) ;
  • 송선희 (조선대학교 컴퓨터공학부) ;
  • 나하선 (Univ. Colorado at Boulder 전자, 컴퓨터공학과) ;
  • 김천석 (여수대학교 전자통신공학과) ;
  • 배철수 (관동대학교 정보통신공학부)
  • Published : 2003.12.01

Abstract

This paper presents a multiple face detector based on a robust pupil detection technique. The pupil detector uses active illumination that exploits the retro­reflectivity property of eyes to facilitate detection. The detection range of this method is appropriate for interactive desktop and kiosk applications. Once the location of the pupil candidates are computed, the candidates are filtered and grouped into pairs that correspond to faces using heuristic rules. To demonstrate the robustness of the face detection technique, a dual mode face tracker was developed, which is initialized with the most salient detected face. Recursive estimators are used to guarantee the stability of the process and combine the measurements from the multi­face detector and a feature correlation tracker. The estimated position of the face is used to control a pan­tilt servo mechanism in real­time, that moves the camera to keep the tracked face always centered in the image.

본 논문에서는 동공 검출 기술을 이용한 얼굴 검출 방법을 제안하고자 한다. 동공 검출기는 눈의 역 반사 특성을 이용한 능동적 조명을 사용하여 검출을 용이하도록 하였고. 제안된 방법의 검출 범위는 소형 컴퓨터나 무인 정보 단말기 등의 활용에 적합하도록 하였다. 동공 후보 영역을 계산하여 검출한 후, 학습 규칙을 사용하여 얼굴에 대응하는 두 개의 지점을 선택하도록 하였다. 얼굴 검출 성능을 증명하기 위하여, 얼굴의 최대 돌출 부위를 지정 할 수 있는 이중 모드의 얼굴 추적 장치를 개발하였다. 추정치 와 복합 얼굴 검출기의 측정치를 결합하여 특징 관계를 추적함으로 처리의 안정성을 높이었다. 또한, 실시간으로 서보의 제어장치를 원격 조정하여 항상 카메라가 이미지의 중앙을 추적하도록 함으로서 얼굴의 위치를 추정할 수 있도록 하였다.

Keywords

References

  1. S. Birchfield. Elliptical head tracking using intensity gra-dients and color histograms. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 232?37,Santa Barbara, CA, June 1998
  2. G. Bradski. Computer vision face tracking for use in a per-ceptual user interface. Technical Report Q2, Intel Corpora-tion, Microcomputer Research Lab, Santa Clara, CA, 1998
  3. M. L. Cascia and S. Sclaroff. Fast, reliable head tracking under varying illumination. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, CO, June 1999
  4. A. Christian and B. Avery. Digital smart kiosk project. In Proc. ACM SIGCHI - Human Factors in Computing Systems Conference, pages 155?62, Los Angeles, CA, April 1998
  5. J. Crowley and F. Berard. Multi-modal tracking of faces for video communications. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 640?45, Puerto Rico,PR, June 1997
  6. T. Darrell, G. Gordon, J. Woodfil, and M. Harville. A vir-tual mirror interface using real-time robust face tracking. In Proc. of the 3rd Int. Conf. on Automatic Face and Gesture ognition, pages 616?21, Nara, Japan, April 1998
  7. T. Darrell, B. Moghaddam, and A. Pentland. Active face racking and pose esti-mation in an interactive room. Techni-cal Report 356, M.I.T. Media Laboratory Perceptual Com-puting Section, Cambridge, MA, 1996
  8. Y. Ebisawa and S. Satoh. Effectiveness of pupil area detec-tion technique using two light sources and image difference method. In A. Szeto and R. Rangayan, editors, Proceedings of the 15th Annual Int. Conf. of the IEEE Eng. in Medicine and Biology Society, pages 1268?269, San Diego, CA, 1993