한국정보과학회논문지:소프트웨어및응용 (Journal of KIISE:Software and Applications)

한국정보과학회 (Korean Institute of Information Scientists and Engineers)
권호 표지

두 단계 합성 기울기 맵을 이용한 활성 외곽선 모델 기반 자동 얼굴 추적

Automatic Face Tracking based on Active Contour Model using Two-Level Composite Gradient Map

  • 김수경 (서울여자대학교 미디어학부) ;
  • 장유진 (서울여자대학교 미디어학부) ;
  • 홍헬렌 (서울여자대학교 미디어학부)
  • 발행 : 2009.11.15
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 연속 프레임에서 움직임이 큰 얼굴을 자동으로 추적하기 위해 두 단계 합성 기울기 지형 생성 방법을 제안한다. 본 제안 방법은 다음과 같은 세 가지 단계로 이루어진다. 첫째, 활성 외곽선이 빠르게 수렴하기 위한 두 단계 해상도 기울기 맵을 생성한다. 둘째, 연속하는 프레임 간의 변위를 파악하고 주변 배경을 제거하기 위하여 이전 프레임과 현재 프레임의 합성 기울기 맵과 차별 마스크를 산정하여 가중 합성 기울기 맵을 구성한다. 셋째, 활성 외곽선이 지역적 최소값에 수렴하는 것을 막기 위해 닫기 연산을 사용하여 에너지 비탈면을 생성한다. 이 때, 닫기 연산의 계산 비용 문제는 빠른 닫기 연산을 통해 해결한다. 제안방법의 정확성을 평가하기 위해 기존 활성 외곽선 모델 기반 방법들과 제안방법의 수행 결과를 통한 육안 평가와 활성 외곽선의 평균 에너지 변화를 통한 견고성 평가를 수행하고, 수행 시간을 분석한다. 실험 결과 제안방법의 경우 배경의 영향을 받지 않으면서 얼굴의 움직임이 큰 경우에도 빠르고 정확하게 추적할 수 있었다.

In this paper, we propose a construction technique of two-level composite gradient map to automatically track a face with large movement in successive frames. Our method is composed of three main steps. First, the gradient maps with two-level resolution are generated for fast convergence of active contour. Second, to recognize the variations of face between successive frames and remove the neighbor background, weighted composite gradient map is generated by combining the composite gradient map and difference mask of previous and current frames. Third, to prevent active contour from converging local minima, the energy slope is generated by using closing operation. In addition, the fast closing operation is proposed to accelerate the processing time of closing operation. For performance evaluation, we compare our method with previous active contour model-based face tracking methods using a visual inspection, robustness test and processing time. Experimental results show that our method can effectively track the face with large movement and robustly converge to the optimal position even in frames with complicated background.

키워드

참고문헌

  1. M. Kass, A. Witkin, D. Terzopoulos, 'Snakes: active contour models,' Int. J. Computer Vision, vol.1, pp.321-331, 1988 https://doi.org/10.1007/BF00133570
  2. Won K., SunGi H., Jujang L., 'An Active Contour Model using Image Flow for Tracking a Moving Object,' Proceedings of the IEEE/RSJ International Conference on, vol.1, pp.216-221, 1999
  3. M. Pardas, E. Sayrol, 'Motion Estimation based Tracking of Active Contours,' Pattern Recognition Letters 22, pp.1447-1456, 2001 https://doi.org/10.1016/S0167-8655(01)00084-8
  4. Bing, X. Wei, Y. Charoensak, C., 'Face Contour Tracking in Video using Active Contour Model,' Image Processing, International Conference on Image Processing(ICIP), vol.2, pp.1024-1024, 2004
  5. J.H. Lee, H.G. Oh, H.Hong, 'Active Contour Model for Object Tracking with Large Motion Displacement,' Korea Computer Congress, vol.33, pp.464-469, 2006
  6. Leymarie, F.; Levine, M.D., 'Tracking Deformable Object in the Plane Using an Active Contour Model,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.15, no.6, pp.617-634, 1993 https://doi.org/10.1109/34.216733
  7. J.M. Ogden, E.H.Adelson, J R. Bergen, P.J Burt, 'Pyramid-based Computer Graphics,' RCA Engineer, vol.30(5), pp.4-15, 1985
  8. Peter j. Burt, Edward H. Andelson, 'The Laplacian Pyramid as a Compact Image Code,' IEEE Transactions on Communications, vol. Com-31, no. 4, 1983
  9. Chenyang Xu, Prince, J.L., 'Gradient Vector Flow: A New External Force for Snakes,' Computer Vision and Pattern Recognition, Proceedings, IEEE Computer Society Conference on, pp. 66-71, 1997 https://doi.org/10.1109/CVPR.1997.609299
  10. P.K.Biswas, Madhukar Pandit, 'Opti-GVF Snake Model For Face Segmentation from Video Sequences,' Proceedings of the Third Indian Conference on Computer Vision, Graphics Image Processing (ICVGIP), 2002
  11. M.Vatsa, R.Singh, P.Gupta, 'Face Detection Using Gradient Vector Flow,' Proceedings of the Second International Conference on Machine Learning and Cybernetics, 2005
  12. Xia Siyu, Li Jiuxian, Xia Liagzheng, 'Robust Face Tracking Using Self-Skin Color Segmentation,' International Conference on Signal Processing Proceedings (ICSP), 2006 https://doi.org/10.1109/ICOSP.2006.345704
  13. Iraji, R. Manzuri-Shalmani, M.T. Jamalian, A.H. Sefidpour, A.R., 'A Real Time Color Independent Method for Multiple Face Tracking,' Cognitive Informatics, 6th IEEE International Conference on, pp.99-105, 2007 https://doi.org/10.1109/COGINF.2007.4341878
  14. Yanjiang Wang, Baodi Liu, Wuli Wang, 'Human Face Tracking with Adaptive Facial Orientation Template by Mean Shift Alogorithm,' Signal Processing, 2006 8th International Conference on, vol.3, 2007
  15. R.C.Gonzalez, R.E. Woods, Digital Image Processing, Prentice Hall(2002) pp.136, 578-584
  16. Petrovic, V.S. Xydeas, C.S., 'Gradient-based multiresolution image fusion,' Image Processing, IEEE Transactions on, vol.13, issue.2, pp.228-237, 2004 https://doi.org/10.1109/TIP.2004.823821
  17. Patton, Ron, Brzakovic, Dragana, 'Rule based composite gradient edge operator,' Proceedings of the Meeting, Orlando, 1987(A88-44528 18-35). Society of Photo-Optical Instrumentation Engineers, pp.122-129, 1987
  18. Bernd Girod, Charles A. Bouman, Eckehard G. Steinbach, 'Video object extraction based on adaptive background and statistical change detection,' Proceeding of Society of Photographic Instrumentation Engineers (SPIE), vol.4310, 2003
  19. R.C.Gonzalez, R.E. Woods, Digital Image Processing, Prentice Hall (2002), 550-551
  20. R.C.Gonzalez, R.E. Woods, Digital Image Processing, Prentice Hall (2002), 119, 231, 581
  21. Morse, P. M. and Feshbach, H. 'The Variational Integral and the Euler Equations,' Methods of Theoretical Physics, pp.276-280, 1953