DOI QR코드

DOI QR Code

움직임 벡터와 SVDD를 이용한 영상 감시 시스템에서 한우의 특이 행동 탐지

Unusual Behavior Detection of Korean Cows using Motion Vector and SVDD in Video Surveillance System

  • 투고 : 2013.05.30
  • 심사 : 2013.07.30
  • 발행 : 2013.11.30

초록

한우 발정기의 조기 탐지는 축산 농가의 경제성을 향상시키는 매우 중요한 연구 과제 중 하나이다. 이를 위한 다양한 방법들이 제안되었으나, 현재까지도 시스템의 경제성 문제를 포함한 조기 발정 탐지 및 탐지 정확도 등에 여전히 취약한 점이 있는 것이 사실이다. 본 논문에서는 감시카메라 환경에서 축사내 승가 행동을 포함하는 한우의 특이 행동들을 탐지하는 다중 객체의 특이 행동 탐지 프로토타입 시스템을 제안한다. 다중 객체의 특이 행동 탐지란 감시카메라로부터 유입되는 영상에서 다중 객체가 위험에 처한 상황 혹은 비정상적인 행동들을 신속하고 정확하게 탐지하는 분야를 말한다. 제안된 시스템은 한우 축사에 고정 설치된 카메라의 입력 동영상으로 부터 움직임 벡터 정보를 이용하여 영상내의 움직임 정보를 추출 표현하였으며, 특이 행동의 판별 문제를 실용적 차원의 단일 클래스 분류 문제로 재해석하여 단일 클래스 SVM의 대표적 모델인 SVDD를 탐지기로 설계하였다. 실제로 진주에 위치한 한 축사에서 취득한 한우 암소의 영상 정보를 이용하여 본 논문에서 제안한 시스템의 성능을 실험적으로 검증한다.

Early detection of oestrus in Korean cows is one of the important issues in maximizing the economic benefit. Although various methods have been proposed, we still need to improve the performance of the oestrus detection system. In this paper, we propose a video surveillance system which can detect unusual behavior of multiple cows including the mounting activity. The unusual behavior detection is to detect the dangerous or abnormal situations of cows in video coming in real time from a surveillance camera promptly and correctly. The prototype system for unusual behavior detection gets an input video from a fixed location camera, and uses the motion vector to represent the motion information of cows in video, and finally selects a SVDD (one of the most well-known types of one-class SVM) as a detector by reinterpreting the unusual behavior into an one class decision problem from the practical points of view. The experimental results with the videos obtained from a farm located in Jinju illustrate the efficiency of the proposed method.

키워드

참고문헌

  1. M. Saint‐Dizier and S. Chastant‐Maillard, "Towards an automated detection of oestrus in dairy cattle," Reprod. Domes. Anim., Vol.47, No.6, pp.1056-1061, 2012. https://doi.org/10.1111/j.1439-0531.2011.01971.x
  2. A. Fisher, R. Morton,J. Dempsey, J. Henshall, and J. Hill, "Evaluation of a new approach for the estimation of the time of the LH surge in dairy cows using vaginal temperature and electrodeless conductivity measurements," Theriogenology, Vol.70, No.7, pp.1065-1074, 2008. https://doi.org/10.1016/j.theriogenology.2008.06.023
  3. Y. Ikeda and Y. Ishii, "Recognition of two psychological conditions of a single cow by her voice," Comput. Electron. Agric., Vol.62, No.1, pp.67-72, 2008. https://doi.org/10.1016/j.compag.2007.08.012
  4. G. Jahns, "Call recognition to identify cow conditions - a call-recogniser translating calls to text," Comput. Electron. Agric., Vol.62, No.1, pp.54-58, 2008. https://doi.org/10.1016/j.compag.2007.09.005
  5. S. C. Yeon, J. H. Jeon, K. A. Houpt, H. H. Chang, H. C. Lee, and H. J. Lee, "Acoustic features of vocalizations of Korean native cows in two different conditions," Appli. Anim. Behavi. Sci., Vol.1, No.1-2, pp.1-9, 2006.
  6. T. Zho, R. Nevatia, and B. Wu, "Segmentation and tracking of multiple human in crowded environments," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.30, No.7, pp.1198-1211, 2008. https://doi.org/10.1109/TPAMI.2007.70770
  7. J. Feng, C. Zhang, and P. Hao, "Online learning with self-organizing maps for anomaly detection in crowd scenes," in Proc. of ICPR, pp.3599-3602, 2010.
  8. W. Fei and S. Zhu, "Mean shift clustering-based moving object segmentation in the H.264 compressed domain," IET Image Processing, Vol.4, No.1, pp.11-18, 2010. https://doi.org/10.1049/iet-ipr.2009.0038
  9. S. K. Kapotas and A. N. Skodras, "Moving object detection in the H.264 compressed domain," in Proc. of Image System and Technique(IST), pp.325-328, 2010.
  10. N. Kiryati, T. Raviv, Y. Invanchenko, and S. Rochel, "Real-time abnormal motion detection in surveillance video," in Proc. of ICPR, pp.1-4, 2008.
  11. R. Mehran, A. Oyama, and M. Shah, "Abnormal crowd behavior detection using social force model," in Proc. of CVPR, pp.935-942, 2009.
  12. Y. Shi, Y. Gao, and R. Wang, "Real-time abnormal event detection in complicated scenes," in Proc. of ICPR, pp. 3653-3656, 2010.
  13. S. Pathan, A. Al-Hamadi, and B. Michaelis, "Incorporating social entropy for crowd behavior detection using SVM," in Proc. of ISVC, pp.153-162, 2010.
  14. JIMS Report [Internet], http://www.limc.co.kr/
  15. T. Cao, X. Wu, J. Guo, S. Yu, and Y. Xu, "Abnormal crowd motion analysis," in Proc. of International Conference on Robotics and Biomimetics, pp.1709-1714, 2009.
  16. X. Zhang, H. Liu, Y. Gao, and D. Hu, "Detecting abnormal events via hierarchical dirichlet process," in Proc. of PAKDD, pp.278-289, 2009.
  17. V. Mahadevan, W. Li, V. Bhalodia, and N. Vasconcelos, "Anomaly detection in crowded scenes," in Proc. of CVPR, pp.1975-1981, 2010.
  18. L. Kratz and K. Nishino, "Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models," in Proc. of CVPR, pp.1446-1453, 2009.
  19. J. Ramirez, J. Gorriz, J. Segura, C. Puntonet, and A. Rubio, "Speech/non-speech discrimination combining Advanced feature extraction and SVM learning," in Proc. of INTERSPEECH, pp.1662-1665, 2006.
  20. D. Tax and R. Duin, "Uniform object generation for optimizing one-class classifiers," Journal of Machine Learning Research, Vol.2, pp.155-173, 2001.
  21. Y. Chung, J. Lee, S. Oh, D. Park, H. H. Chang, and S. Kim, "Automatic Detection of Cow's Oestrus in Audio Surveillance System," AJAS(Asian-Australasian Journal of Animal Sciences), Vol.26, No.7, pp.1030-1037, 2013. https://doi.org/10.5713/ajas.2012.12628