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

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

A Constrained Learning Method based on Ontology of Bayesian Networks for Effective Recognition of Uncertain Scenes

불확실한 장면의 효과적인 인식을 위한 베이지안 네트워크의 온톨로지 기반 제한 학습방법

  • 황금성 (연세대학교 컴퓨터과학과) ;
  • 조성배 (연세대학교 컴퓨터과학과)
  • Published : 2007.06.15
Download PDF
⟨ Previous Next ⟩

Abstract

Vision-based scene understanding is to infer and interpret the context of a scene based on the evidences by analyzing the images. A probabilistic approach using Bayesian networks is actively researched, which is favorable for modeling and inferencing cause-and-effects. However, it is difficult to gather meaningful evidences sufficiently and design the model by human because the real situations are dynamic and uncertain. In this paper, we propose a learning method of Bayesian network that reduces the computational complexity and enhances the accuracy by searching an efficient BN structure in spite of insufficient evidences and training data. This method represents the domain knowledge as ontology and builds an efficient hierarchical BN structure under constraint rules that come from the ontology. To evaluate the proposed method, we have collected 90 images in nine types of circumstances. The result of experiments indicates that the proposed method shows good performance in the uncertain environment in spite of few evidences and it takes less time to learn.

영상을 분석하여 얻은 증거를 바탕으로 장면의 의미를 추론하고 해석하는 것을 시각 기반 장면 이해라고 하며, 최근 인과적인 판단 및 추론 과정을 모델링하기에 유리한 베이지안 네트워크(BN)를 이용한 확률적인 접근 방법이 활발히 연구되고 있다. 하지만 실제 환경은 변화가 많고 불확실하기 때문에 의미 있는 증거를 충분히 확보하기 어려울 뿐만 아니라 전문가에 의한 설계로 유지하기 어렵다. 본 논문에서는 증거 및 학습 데이타가 부족한 장면인식 문제에서 효율적인BN 구조로 계산 복잡도가 줄어들고 정확도는 향상될 수 있는 BN 학습방법을 제안한다. 이 방법은 추론 대상 환경의 도메인 지식을 온톨로지로 표현하고 이를 제한적으로 사용하여 효율적인 계층구조의 BN을 구성한다. 제안하는 방법의 평가를 위하여 9종류의 환경에서 90장의 영상을 수집하고 레이블링하여 실험하였다. 실험 결과, 제안하는 방법은 증거의 수가 적은 불확실한 환경에서도 좋은 성능을 내고 학습의 복잡도가 줄어듦을 확인할 수 있었다.

Keywords

References

  1. K. B. Korb and A. E. Nicholson, Bayesian Artificial Intelligence, Chapman & Hall/CRC, 2003
  2. B. Neumann, A Conceptual Framework for High-Level Vision, Bericht, FB Informatik, FBI-HHB245/03, 2003
  3. J. Fernyhough et al., 'Building qualitative event models automatically from visual input,' In Proc. ICCV-98, IEEE Computer Society, pp.350-355, 1998 https://doi.org/10.1109/ICCV.1998.710742
  4. L. R. Biswas, et al., 'A probabilistic approach to inference with limited information in sensor networks,' In Proc. of the 3rd Int. Symposium on Information Processing in Sensor Networks, pp.269-276, 2004 https://doi.org/10.1145/984622.984662
  5. P. Spirtes, et al., Causation, Prediction, and Search (2nd edition), MIT Press, Cambridge, 2000
  6. N. Friedman and M. Goldszmidt, 'Learning Bayesian networks with local structure,' M.I. Jordan (eds.), Learning in Graphical Models, MIT Press, Cambridge, pp. 421-459, 1999
  7. D.M. Chickering, 'Learning Bayesian networks is NP-complete,' D. Fisher, H.-J. Lenz (eds.), Learning from Data: Artificial Intelligence and Statistics V, Springer-Verlag, Berlin Heidelberg New York, pp. 121-130, 1996
  8. G. F. Cooper and E. Herskovits, 'A Bayesian method for the induction of probabilistic networks from data,' Machine Learning, vol. 9, pp. 309-347, 1992 https://doi.org/10.1007/BF00994110
  9. M. L. Wong and K. S. Leung, 'An efficient data mining method for learning Bayesian networks using an evolutionary algorithm-based hybrid approach,' IEEE Transactions on Evolutionary Computation, vol. 8, no. 6, pp. 532-545, Aug. 2004 https://doi.org/10.1109/TEVC.2004.830334
  10. A. Torralba, et al., 'Context-based vision system for place and object recognition,' In Proc. of Int. Conf. Computer Vision, pp.273-280, 2003
  11. M. Marengoni, et al., 'Decision making and uncertainty management in a 3D reconstruction system,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no.7, pp.852-858, July 2003 https://doi.org/10.1109/TPAMI.2003.1206514
  12. J. Rissanen, 'Modeling by shortest data description,' Automatica, vol. 14, pp. 465-471, 1978 https://doi.org/10.1016/0005-1098(78)90005-5
  13. R. R. Bouckaert, 'Bayesian belief networks: From inference to construction,' Ph.D.Dissertation, Utrecht Univ., Utrecht, The Netherlands, 1995
  14. B. G. Buchanan and E. H. Shortliffe, Rule-based Expert Systems: The MYCIN Experiments of The Stanford Heuristic Programming Project, Addison-Wesley, Reading, MA, 1984
  15. J. Pearl, Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference, Morgan Kaufmann, San Mateo, CA, 1988
  16. T. Choudhury et al., 'Boosting and structure learning in dynamic Bayesian networks for audiovisual speaker detection,' Proc. of Int. Conf. on Pattern Recognition, vol. 3, pp. 789-794, Aug. 2002 https://doi.org/10.1109/ICPR.2002.1048137
  17. H. Schneiderman, 'Learning a restricted Bayesian network for object detection,' In Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 639-646, June 2004 https://doi.org/10.1109/CVPR.2004.1315224
  18. P. Lucas, 'Restricted Bayesian network structure learning,' In Proc. of 14th Belgian-Dutch Conf. on Artificial Intelligence, pp. 211-218, 2002
  19. B. Smith, 'Basic concepts of formal ontology,' Formal Ontology in Information Systems, IOS Press, pp. 19-28, 1998
  20. 황금성, 조성배, '효율적인 컨텍스트 분류를 위한 베이 지안 네트워크 구조의 제한 학습', 한국정보과학회 가을학술발표논문집, vol. 31, no. 2, pp. 112-114, 2004