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

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

Automatic Extraction of Focused Video Object from Low Depth-of-Field Image Sequences

낮은 피사계 심도의 동영상에서 포커스 된 비디오 객체의 자동 검출

  • 박정우 (한국정보통신대학교 공학부) ;
  • 김창익 (한국정보통신대학교 공학부)
  • Published : 2006.10.15
Download PDF
⟨ Previous Next ⟩

Abstract

The paper proposes a novel unsupervised video object segmentation algorithm for image sequences with low depth-of-field (DOF), which is a popular photographic technique enabling to represent the intention of photographer by giving a clear focus only on an object-of-interest (OOI). The proposed algorithm largely consists of two modules. The first module automatically extracts OOIs from the first frame by separating sharply focused OOIs from other out-of-focused foreground or background objects. The second module tracks OOIs for the rest of the video sequence, aimed at running the system in real-time, or at least, semi-real-time. The experimental results indicate that the proposed algorithm provides an effective tool, which can be a basis of applications, such as video analysis for virtual reality, immersive video system, photo-realistic video scene generation and video indexing systems.

영상을 낮은 피사계 심도로 찍는 카메라 기법은 전통적으로 널리 이용되는 영상 취득 기술이다. 이 방법을 사용하면 사진사가 사진이나 동영상을 찍을 때 영상의 관심 영역에만 포커스를 두어 선명하게 표현하고 나머지는 흐릿하게 함으로써 자신의 의도를 보는 이에게의 분명하게 전달 할 수 있다. 본 논문은 이러한 피사계 심도가 낮은 동영상 입력에 대하여 사용자의 도움 없이 포커스 된 비디오 객체를 추출하는 새로운 방법을 제안한다. 본 연구에서 제안하는 방법은 크게 두 모듈로 나뉜다. 첫 번째 모듈에서는 동영상의 첫 번째 프레임에 대해서 포커스 된 영역과 그렇지 않은 흐릿한 부분을 자동으로 구분하여 관심 물체만을 추출한다. 두 번째 모듈에서는 첫 번째 모듈에서 구한 관심 물체의 모델을 바탕으로 동영상 프레임에서의 관심 물체만을 실시간이나 실시간에 가깝게 추출한다. 본 논문에서 제안하는 방법은 가상현실(VR)이나 실감 방송, 비디오 인덱싱 시스템과 같은 여러 응용 분야에 효과적으로 적용될 수 있고, 이러한 유용성은 실험 결과를 통해 보였다.

Keywords

References

  1. C. Kim, 'Segmenting a Low Depth-of-Field Image Using Morphological Filters and Region Merging,' IEEE Tr. on Image Processing, vol. 14, issue 10, pp. 1503-1511, Oct. 2005 https://doi.org/10.1109/TIP.2005.846030
  2. J.Z. Wang, J. Li, R.M. Gray, and G. Wiederhold, 'Unsupervised multiresolution segmentation for images with low depth of field,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no.1, pp. 85-90, Jan. 2001 https://doi.org/10.1109/34.899949
  3. J. Pan, S. Li, and Y. Zhang, 'Automatic extraction of moving object using multiple features and multiple frames,' in Proc. of IEEE International Symposium on Circuits and Systems, vol. 1, pp. 36-39, May. 2000 https://doi.org/10.1109/ISCAS.2000.857020
  4. C. Gu and M.C. Lee, 'Semiautomatic Segmentation and Tracking of Semantic Video Objects,' IEEE Trans. Circuits Syst. Video Technol. VOL 8, NO. 5, Sept. 1998 https://doi.org/10.1109/76.718504
  5. M. Kass, A. Witkin, and D. Terzopoulos, 'Snake: active contour model,' in Proc. of First International Conference on Computer Vision, pp. 259-269, 1987
  6. P.J. Besl and R.C. Jain, 'Segmentation through variable - order surface fitting,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 10, pp. 167-192, March 1988 https://doi.org/10.1109/34.3881
  7. L.M. Lifshitz and S.M. Pizer, 'A multiresolution hierarchical approach to image segmentation based on intensity extrema,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, pp. 529-540, June 1990 https://doi.org/10.1109/34.56189
  8. D. Comaniciu, P. Meer, 'Robust Analysis of Feature Spaces: Color Image Segmentation,' in Proc. IEEE Conf, Computer Vision and Pattern Recognition (CVPR'97), San Juan, Puerto Rico, 750-755, 1997 https://doi.org/10.1109/CVPR.1997.609410
  9. K. Aizawa, A. Kubota, K. Kodama, 'Implicit 3D Approach to Image Generation: Object-Based Visual Effects by Linear Processing of Multiple Differently Focused Images,' in Proc. 10th International Workshop on Theoretical Foundations of Computer Vision, Vol. 2032, pp. 226-237, Dagstuhl Castle, Germany, March 2000
  10. C. Kim and J.-N. Hwang, 'Video Object Extraction for Object-Oriented Applications,' Journal of VLSI Signal Processing - Systems for Signal, Image, and Video Technology, Special Issue on Multimedia Signal Processing, vol. 29, no.1/2, pp. 7-21, August 2001
  11. Ju Guo, J. Kim, and C.-C. Jaykuo, 'Fast and Accurate Moving Object Extraction Technique for MPEG-4 Object-Based Video Coding,' in Proc. SPIE, vol. 3653, pp. 1210-1221, 1999
  12. M. Kim, J.G. Choi, D. Kim, H. Lee, M.H. Lee, and Y. Ho, 'A VOP Generation Tool: Automatic Segmentation of Moving Objects in Image Sequences Based on Spatio-Temporal Information,' IEEE Trans. Circuits Syst. Video Technology, vol. 9, no. 8, 1999 https://doi.org/10.1109/76.809157
  13. G. Borgefors, 'Distance Transformations in Digital Images,' Computer Vision, Graphics, and Image Processing, vol. 34, pp. 344-371, 1986 https://doi.org/10.1016/S0734-189X(86)80047-0
  14. M. Bierling, 'Displacement estimation by hierarchical blockmatching,' in Proc. SPIE Visual Commun. Image Processing, VCIP'88, vol. 1001, pp. 942-951, Cambridge, MA, Nov. 1988
  15. M. Wollbom and R. Mech, 'Refined procedure for objective evaluation of video generation algorithms,' Doc. ISO/IEC JTC1/SC29/WG11 M3448, March 1998
  16. G. Gelle, M. Colas, G. Delaunay, 'Higher Order Statistics for Detection and Classification of Faulty Fanbelts Using Acoustical Analysis,' in Proc. IEEE Signal Processing Workshop on Higher-Order Statistics (SPW-HOS '97), pp. 43-46, Banff, Canada, July 21-23, 1997 https://doi.org/10.1109/HOST.1997.613484
  17. P. Salembier and M. Pardas, 'Hierarchical Morphological segmentation for Image sequence Coding,' IEEE Transactions on Image Processing, vol. 3, no. 5, pp. 639-651, Sept. 1994 https://doi.org/10.1109/83.334980