Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지

Motion Analysis Using Competitive Learning Neural Network and Fuzzy Reasoning

경쟁학습 신경망과 퍼지추론법을 이용한 움직임 분석

  • 이주한 (서강대학교 전자계산학과) ;
  • 오경환 (서강대학교 전자계산학과)
  • Published : 1995.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we suggest a motion analysis method using ART-I1 competitive learning neural network and fuzzy reasoning by matching the same objects through the consecutive image sequence. we use the size and mean intensity of the region obtained from image segmentation for the region matching by the region and use a ART-I1 competitive learning neural network wh~ch has a learning ability to reflect the topology of the input patterns in order to select characteristic points to describe the shape of a region. Motion vectors for each regions are obtained by matching selected characteristic points. However, the two dimensional image, the projection of the the three dimensional real world, produces fuzziness in motion analysis due to its incompleteness by nature and the error from image segmentation used for extracting information about objects. Therefore, the belief degrees for each regions are calculated using fuzzy reasoning to l-nanipulate uncertainty in motion estimation.

본 논문에서는 ART-II 경쟁학습 신경망과 퍼지추론을 이용하여 동일한 물체를 연속적인 영상열에서 정합 시킴으로서 움직임을 분석하는 방법을 제시한다. 영상분할을 통해 얻을 수 있는 영역의 크기가 평균광도를 이용하여 영역단위의 정합을 수행하고, 영역의 모양을 표현하기 위한 특징점을 선택하기 위하여 입력패턴들의 위상을 나타날 수 있는 ART-II 경쟁학습 신경망을 사용하였다. 선택된 특징점들의 정합을 통해 각 물체에 대한 움직임 벡터를 구한다. 그러나 3차원적 실제세계의 사영인 2차원 영상은 영상 자체의 불완전성과 물체에 대한 정보를 얻기 위하여 사용되는 영상분할의 잘목스오 인한 오류 때문에 움직임 추정 과정에서 모호성이 발생한다. 이러한 움직임 분석과정에서 나타나는 불확실성을 처리하기 위하여 퍼지추론을 사용하여 신뢰도를 표현함으로써 이동 물체와 음직임 벡터를 추출하였다.

Keywords

References

  1. IEEE Computer v.14 no.8 Computer analysis of time varying images Snyder,W.E.
  2. Computer Vision Dana H. Ballard;Christopher M. Brown
  3. IEEE International Joint Conference on Neural Networks v.I An Artificial Neural Network for Motion Detection and Speed Estimation S.H.Courellis;V.Z.Marmarelis
  4. IEEE International Joint Conference on Neural Networks v.III Velocity Estimators of Visual Motion in Two Spatial Dimensions S.H.Courellis;V.Z.Marmarelis
  5. Digital Image Processing William K. Pratt
  6. Digital Image Processing Algorithms Ioannis Pitas
  7. Image and Vision Computing v.2 no.2 Difference and accumulative difference pictures in dynamic scene analysis R.Jain
  8. Image Processing, Analysis and Machine Vision Milan Sonka;Vaclav Hlavac;Roger Boyle
  9. Pattern Recognition Letters v.23 no.11 Corner detection R.Mehrotra;S.Nichani
  10. Proceedings of 5th International Joint Conference on Artificial Intelligence Change detection and analysis in multi-spectral images Price,K.E.;Reddy
  11. Proceedings of IEEE Workshop on Pattern Recognition and Artificial Intelligence, Princeton, NJ On a motion analysis process for image sequences from real world scenes Jain,R.;H.H.Nagel
  12. Applied Optics v.26 no.23 ART-2 : Self-organizing of stable category recognition codes for analog input patterns Gail A. Carpenter;Stephen Grossberg
  13. Biological Cybernetics Self-organized formation of topologically correct feature maps T.Kohonen
  14. IEEE Transactions on Computer v.26 Applications of fuzzy logic to approximate reasoning Mamdani,E.H.