Earticle

초록

영어

We propose a chapter mark addition method for surgery video application that adopts cubic higher-order local auto-correlation (CHLAC) features. In our method, normal motions, which frequently occur in a scene, are statistically learnt by using CHLAC in combination with the subspace method. An anomalous motion exists far from the subspace of the frequently-observed motions and such motion is detected based on the deviation from the subspace, and a chapter mark is placed just before the position of the detected anomalous motion. We conducted preliminary experiments using surgery video data to confirm effectiveness of the proposed method. The results show that the proposed method can detect the motions not frequently-observed in a surgery operation and the chapters are effectively constructed.

목차

Abstract
 1. Introduction
 2. Proposed method
  2.1. Scene analysis technique for proposed method
  2.2. Cubic higher local auto-correlation (CHLAC)
  2.3. Anomalousness detection
  2.4. Developed system for proposed method
 3. Experiment
  3.1. Detected anomalous motion values
  3.2. Detected anomalous motions
 4. Conclusion
 References

키워드

저자

• Fumio Sakabe [ Graduate School of Systems and Information Engineering, University of Tsukuba, Japan ]
• Masahiro Murakawa [ National Institute of Advanced Industrial Science and Technology (AIST), Japan ]
• Takumi Kobayashi [ National Institute of Advanced Industrial Science and Technology (AIST), Japan ]
• Tetsuya Higuchi [ National Institute of Advanced Industrial Science and Technology (AIST), Japan ]
• Nobuyuki Otsu [ National Institute of Advanced Industrial Science and Technology (AIST), Japan ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Advanced Science and Technology

• 간기

  월간

• pISSN

  2005-4238

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605