Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Anchor Frame Detection Using Anchor Object Extraction

앵커 객체 추출을 이용한 앵커 프레임 검출

  • Park Ki-Tae (Department of Computer Science and Engineering, Hanyang University) ;
  • Hwang Doo-Sun (Samsung Advanced Institute of Technology) ;
  • Moon Young-Shik (Department of Computer Science and Engineering, Hanyang University)
  • Published : 2006.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, an algorithm for anchor frame detection in news video is proposed, which consists of four steps. In the first step, the cumulative histogram method is used to detect shot boundaries in order to segment a news video into video shots. In the second step, skin color information is used to detect face regions in each shot boundary. In the third step, color information of upper body regions is used to extract anchor object, which produces candidate anchor frames. Then, from the candidate anchor frames, a graph-theoretic cluster analysis algorithm is utilized to classify the news video into anchor-person frames and non-anchor frames. Experiment results have shown the effectiveness of the proposed algorithm.

본 논문에서는 뉴스 비디오에서 앵커 프레임 검출을 위한 알고리즘을 제안한다. 제안된 알고리즘은 다음과 같이 4단계로 구성된다. 첫 번째 단계에서, 뉴스 비디오를 비디오 샷들로 분할하기 위해 누적 히스토그램(cumulative histogram) 기법을 이용하여 샷 경계(shot boundary)를 검출한다. 두 번째 단계에서는 각 비디오 샷 경계에서 얼굴 영역들을 찾기 위해서 피부 컬러(skin color) 정보를 이용하고, 세 번째 단계에서는, 앵커 객체를 추출하기 위해서 사람의 상체 부분의 컬러 정보를 이용하여 앵커 후보 프레임을 검출하며, 마지막 단계에서, 후보 프레임들에 대해서 앵커 프레임과 비앵커 프레임을 분류하기 위해서 그래프 이론을 이용한 클러스터 분석 알고리즘을 적용한다. 실험 결과를 통해서 제안한 알고리즘이 효과적으로 앵커 프레임을 검출하는 것을 보여준다.

Keywords

References

  1. A Hanjalic, R. L. Lagendijk, and J. Biemond, 'Template-based detection of anchorperson shots in news programs,' IEEE Image Processing, ICIP Vol. 3, pp. 148-152, 1998 https://doi.org/10.1109/ICIP.1998.727156
  2. W. Wang and W. Gao, 'A fast anchor shot detection algorithm on compressed video,' Advanced in Multimedia Information Processing - PCM, pp. 873-878, October 2001
  3. A. Albiol, L. Torres, and E. J. Delp, 'The indexing of persons in news sequences using audio-visual data,' in Proc. of IEEE ICASSP 2003, vol. 3, pp. 137-140, April 2003 https://doi.org/10.1109/ICASSP.2003.1199126
  4. D.J. Lan, Y. F Ma, and H. J. Zhang, 'Multi-level anchorperson detection using multimodal association,' in Proc. of IEEE ICIP 2004, vol. 3, pp. 890-893, August 2004 https://doi.org/10.1109/ICPR.2004.1334671
  5. X. Gao and X. Tang, 'Unsupervised video shot segmentation and model free anchorperson detection for news video story parsing,' IEEE Trans. Circuits and Systems for Video Tech., pp. 765-776, September 2002 https://doi.org/10.1109/TCSVT.2002.800510
  6. 황두선, 이종설, 조위덕, 문영식, '누적히스토그램과 에지 정보를 이용한 장면 전환 검출,' 대한전자공학회 하계종합학술대회 논문집 1호, pp. 211-214, 2002
  7. K T. Park, D. S. Hwang and Y. S. Moon, 'Anchor frame detection in news video using anchor . object extraction,' IEICE Tans. Fumdametal, vol. E88- A, pp. 1525-1528, June 2005 https://doi.org/10.1093/ietfec/e88-a.6.1525
  8. H. Ishii, M. Fukumi, and Akamatsu, 'Face detection based on skin color informagion in visual scenes by neural networks,' in Proc. of IEEE SMC '99 Conf. on Systems, Man, and Cybermetics, 1999
  9. J. Brand, J. S. Mason, M. Roach, and M. Pawlewski, 'Enhancing face detection in colour images using a skin probability map,' in Proc. of 2001 International Symposium Conf, on Intelligent Multimedia, Video and Speech Processing, pp. 344-347, 2001 https://doi.org/10.1109/ISIMP.2001.925404
  10. K. K. Sung and T. Poggio, 'Example based learning for view based human face detection,' IEEE Trans. on Pattern Analysis and Machine Intelligence, pp. 39-51, January 1998 https://doi.org/10.1109/34.655648
  11. J. B. Oh and Y. S. Moon, 'Content based image retrieval based on scale space theory,' IEICE Tans, June 1999