KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Touching Pigs Segmentation and Tracking Verification Using Motion Information

움직임 정보를 이용한 근접 돼지 분리와 추적 검증

  • 박창현 (고려대학교 컴퓨터정보학과) ;
  • 사재원 (고려대학교 컴퓨터정보학과) ;
  • 김희곤 (고려대학교 컴퓨터정보학과) ;
  • 정용화 (고려대학교 컴퓨터정보학과) ;
  • 박대희 (고려대학교 컴퓨터정보학과) ;
  • 김학재 ((주)클래스액트)
  • Received : 2017.12.15
  • Accepted : 2018.03.23
  • Published : 2018.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The domestic pigsty environment is highly vulnerable to the spread of respiratory diseases such as foot-and-mouth disease because of the small space. In order to manage this issue, a variety of studies have been conducted to automatically analyze behavior of individual pigs in a pig pen through a video surveillance system using a camera. Even though it is required to correctly segment touching pigs for tracking each pig in complex situations such as aggressive behavior, detecting the correct boundaries among touching pigs using Kinect's depth information of lower accuracy is a challenging issue. In this paper, we propose a segmentation method using motion information of the touching pigs. In addition, our proposed method can be applied for detecting tracking errors in case of tracking individual pigs in the complex environment. In the experimental results, we confirmed that the touching pigs in a pig farm were separated with the accuracy of 86%, and also confirmed that the tracking errors were detected accurately.

좁은 공간에 돼지들을 밀집 사육하는 구조가 대부분인 국내 돈사의 환경은 구제역과 같은 전염병 확산에 취약하다. 이러한 밀집 사육의 문제점을 해결하기 위한 방법으로 감시 카메라를 활용한 돈사 내 개별 돼지들의 행동을 자동으로 분석하는 연구가 진행 되고 있다. 그러나 공격행동 등 복잡한 상황에서 개별 돼지들을 추적하기 위해서는 근접한 돼지들에 대한 올바른 분리가 우선적으로 수행되어야 하지만, 정확도가 떨어지는 키넥트 카메라의 깊이 정보를 이용할 경우 돼지들 간의 경계선이 정확히 추출되지 않는다는 문제가 있다. 본 논문에서는 이러한 문제를 해결하기 위한 방법으로 움직임 정보를 활용하여 근접 돼지를 분리하는 방법을 제안한다. 또한, 제안된 방법은 혼잡한 돈방에서 개별 돼지를 추적하는 경우 추적 오류를 탐지하는 문제에도 적용될 수 있다. 실험 결과, 실제 돈사에서 획득한 두 개의 근접 돼지 시퀀스에 대하여 86%의 정확도로 분리 가능함을 확인하였고, 객체 추적에 대한 검증을 통하여 식별 번호가 잘못 부여된 객체를 정확히 탐지할 수 있음을 확인하였다.

Keywords

References

  1. Y. Chung, S. Oh, J. Lee, D. Park, H. -H. Chang, and S. Kim, "Automatic Detection and Recognition of Pig Wasting Diseases Using Sound Data in Audio Surveillance Systems," Sensors, Vol.13, No.10, pp.12929-12942, 2013. https://doi.org/10.3390/s131012929
  2. I. Camerlink, S. P. Turner, W. W. Ursinus, I. Reimert, and J. E. Bolhuis, "Aggression and Affiliation during Social Conflict in Pigs," PLoS ONE, Vol.9, No.11, pp.e113502, 2014. https://doi.org/10.1371/journal.pone.0113502
  3. L. Jin, S. Zuo, J. Lee, D. Park, and Y. Chung, "Aggressive Behavior Detection of Weaning Pigs," in Proc. of the KSII Fall Conference, pp.325-326, 2014.
  4. J. Lee, L. Jin, D. Park, and Y. Chung, "Automatic Recognition of Aggressive Behavior in Pigs by using a Kinect Depth Sensor," Sensors, Vol.16, No.5, p.631, 2016. https://doi.org/10.3390/s16050631
  5. S. Zuo, L. Jin, Y. Chung, and D. Park, "An Index Algorithm for Tracking Pigs in Pigsty," in Proc. of ICITMS, pp.797-803, 2014.
  6. J. Sa, S. Han, S. Lee, H. Kim, S. Lee, Y. Chung, and D. Park, "Image Segmentation of Adjoining Pigs Using Spatio-Temporal Information," KIPS Tr. Software and Data Eng., Vol.4, No.10, pp.473-478, 2015. https://doi.org/10.3745/KTSDE.2015.4.10.473
  7. M. Ju, H. Baek, J. Sa, H. Kim, Y. Chung, and D. Park, "Real-Time Pig Segmentation for Individual Pig Monitoring in a Weaning Pig Room," J. of Korea Multimedia Society, Vol.19, No.2, pp.215-223, 2016. https://doi.org/10.9717/kmms.2016.19.2.215
  8. H. Baek, Y. Chung, M. Ju, Y. Chung, D. Park, and H. Kim, "Pig Segmentation using Concave Points and Edge Information," J. of Korea Multimedia Society, Vol.19, No.8, pp.1361-1370, 2016. https://doi.org/10.9717/kmms.2016.19.8.1361
  9. J. Choi, J. Lee, Y. Chung, and D. Park, "Individual Pig Detection Using Kinect Depth Information," KIPS Tr. Comp. and Comm. Sys., Vol.5, No.10, pp.319-326, 2016. https://doi.org/10.3745/KTCCS.2016.5.10.319
  10. J. Choi, J. Lee, Y. Chung, and D. Park, "Individual Pig Detection using Fast Region-based Convolution Neural Network," J. of Korea Multimedia Society, Vol.20, No.2, pp.216-224, 2017. https://doi.org/10.9717/kmms.2017.20.2.216
  11. J. Kim, Y. Chung, Y. Choi, J. Sa, H. Kim, Y. Chung, D. Park, and H. Kim, "Depth-based Detection of Standing-Pigs in Moving Noise Environments," Sensors, Vol.17, pp.2757, 2017. https://doi.org/10.3390/s17122757
  12. S. Lee, K. Kim, and T. Yoon, "Individual Tooth Image Segmentation by Watershed Algorithm," Trans. Korean Inst. Elect. Eng., Vol.59, No.1, pp.210-216, 2010.
  13. C. Koyuncu, S. Arslan, I. Durmaz, R. Cetin-Atalay, and C. Gunduz-Demir, "Smart Markers for Watershed-Based Cell Segmentation," PLoS one, Vol.7, No.11, pp.e48664, 2012. https://doi.org/10.1371/journal.pone.0048664
  14. G. Kim, G. Lee, and S. Lee, "An Edge Extraction Method Using K-means Clustering In Image," Journal of Digital Convergence, Vol.12, No.11, pp.281-288, 2014. https://doi.org/10.14400/JDC.2014.12.11.281
  15. J. Peng, Y. Chen, M. Green, S. Sabatinos, S. Forsburg, and C. Hsu, "PombeX: Robust Cell Segmentation for Fission Yeast Transillumination Images," PLoS one, Vol.8, No.12, pp.e81434, 2013. https://doi.org/10.1371/journal.pone.0081434
  16. G. Bradski and A. Kaehler, Learning OpenCV: Computer Vision with the OpenCV Library, O'Reilly Media, Sebastopol, California, 2008.
  17. R. Ghosh and W. Webb, "Automated Detection and Tracking of Individual and Clustered Cell Surface Low Density Lipoprotein Receptor Molecules," Biophysical Journal, Vol. 66, No.5, pp.1301-1318, 1994. https://doi.org/10.1016/S0006-3495(94)80939-7
  18. K. Bernardin and R. Stiefelhagen, "Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics," EURASIP Journal on Image and Video Processing, Vol. 2008, No.1, pp.1-10, 2008.
  19. J. Kim, Y. Choi, J. Kim, Y. Chung, Y. Chung, and D. Park, "Efficient Task Distribution for Pig Monitoring Applications using OpenCL," KIPS Tr. Comp. and Comm. Sys., Vol.6, No.10, pp.407-414, 2017. https://doi.org/10.3745/KTCCS.2017.6.10.407