Journal of Veterinary Science

The Korean Society of Veterinary Science (대한수의학회)
권호 표지
DOI QR코드

DOI QR Code

Object detection and tracking using a high-performance artificial intelligence-based 3D depth camera: towards early detection of African swine fever

  • Ryu, Harry Wooseuk (Research Institute for Veterinary Science, College of Veterinary Medicine, Seoul National University) ;
  • Tai, Joo Ho (Research Institute for Veterinary Science, College of Veterinary Medicine, Seoul National University)
  • Received : 2021.09.17
  • Accepted : 2021.11.24
  • Published : 2022.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

Background: Inspection of livestock farms using surveillance cameras is emerging as a means of early detection of transboundary animal disease such as African swine fever (ASF). Object tracking, a developing technology derived from object detection aims to the consistent identification of individual objects in farms. Objectives: This study was conducted as a preliminary investigation for practical application to livestock farms. With the use of a high-performance artificial intelligence (AI)-based 3D depth camera, the aim is to establish a pathway for utilizing AI models to perform advanced object tracking. Methods: Multiple crossovers by two humans will be simulated to investigate the potential of object tracking. Inspection of consistent identification will be the evidence of object tracking after crossing over. Two AI models, a fast model and an accurate model, were tested and compared with regard to their object tracking performance in 3D. Finally, the recording of pig pen was also processed with aforementioned AI model to test the possibility of 3D object detection. Results: Both AI successfully processed and provided a 3D bounding box, identification number, and distance away from camera for each individual human. The accurate detection model had better evidence than the fast detection model on 3D object tracking and showed the potential application onto pigs as a livestock. Conclusions: Preparing a custom dataset to train AI models in an appropriate farm is required for proper 3D object detection to operate object tracking for pigs at an ideal level. This will allow the farm to smoothly transit traditional methods to ASF-preventing precision livestock farming.

Keywords

Acknowledgement

We would also like to thank our team members at the Research Institute for Veterinary Science in the College of Veterinary Medicine of Seoul National University and Foreign Animal Disease Division, Animal and Plant Quarantine Agency, Gimcheon, Korea for their helps for this study.

References

  1. Clemmons EA, Alfson KJ, Dutton JW 3rd. Transboundary animal diseases, an overview of 17 diseases with potential for global spread and serious consequences. Animals (Basel). 2021;11(7):2039. https://doi.org/10.3390/ani11072039
  2. Dixon LK, Sun H, Roberts H. African swine fever. Antiviral Res. 2019;165:34-41. https://doi.org/10.1016/j.antiviral.2019.02.018
  3. Faverjon C, Meyer A, Howden K, Long K, Peters L, Cameron A. Risk-based early detection system of African swine fever using mortality thresholds. Transbound Emerg Dis. 2021;68(3):1151-1161. https://doi.org/10.1111/tbed.13765
  4. Chenais E, Stahl K, Guberti V, Depner K. Identification of wild boar-habitat epidemiologic cycle in African swine fever epizootic. Emerg Infect Dis. 2018;24(4):810-812. https://doi.org/10.3201/eid2404.172127
  5. Cho KH, Kim HJ, Kim DY, Yoo D, Nah JJ, Kim YJ, et al. Surveillance of ASF-infected pig farms from September to October 2019 in South Korea. J Vet Sci. 2021;22(2):e26. https://doi.org/10.4142/jvs.2021.22.e26
  6. Yoon H, Hong SK, Lee I, Yoo DS, Jung CS, Lee E, et al. Clinical symptoms of African swine fever in domestic pig farms in the Republic of Korea, 2019. Transbound Emerg Dis. 2020;67:2245-2248. https://doi.org/10.1111/tbed.13552
  7. Kim J, Chung Y, Choi Y, Sa J, Kim H, Chung Y, et al. Depth-based detection of standing-pigs in moving noise environments. Sensors (Basel). 2017;17(12):2757. https://doi.org/10.3390/s17122757
  8. Carr J, Chen SP, Conner JF, Kirkwood R, Segales J. Pig Health. Boca Raton: CRC Press; 2018.
  9. Vranken E, Berckmans D. Precision livestock farming for pigs. Anim Front. 2017;7(1):32-37. https://doi.org/10.2527/af.2017.0106
  10. Queen C. Artificial Intelligence in Veterinary Medicine [Internet]. Horsham: AI Med; https://ai-med.io/ai-med-news/artificial-intelligence-veterinary/. Updated 2018.
  11. Cihan P, Gokce E, Kalipsiz O. A review of machine learning applications in veterinary field. Kafkas Univ Vet Fak Derg. 2017;23(4):673-680.
  12. Aiello SE, Moses MA, Allen DG. The Merck Veterinary Manual. 11th ed. Kenilworth, NJ: Merck Sharp & Dohme Corp; 2016.
  13. Soleimanitaleb Z, Keyvanrad MA, Jafari A. Proceedings of 2019 9th International Conference on Computer and Knowledge Engineering (ICCKE); 2019 Oct 24-25; Mashhad, Iran. Mashhad: Ferdowsi University of Mashhad; 2019.
  14. Bi F, Ma X, Chen W, Fang W, Chen H, Li J, et al. Review on video object tracking based on deep learning. J New Media. 2019;1(2):63-74. https://doi.org/10.32604/jnm.2019.06253
  15. Zhao ZQ, Zheng P, Xu ST, Wu X. Object detection with deep learning: a review. IEEE Trans Neural Netw Learn Syst. 2019;30(11):3212-3232. https://doi.org/10.1109/tnnls.2018.2876865
  16. McFarlane NJ, Schofield CP. Segmentation and tracking of piglets in images. Mach Vis Appl. 1995;8(3):187-193. https://doi.org/10.1007/BF01215814
  17. Cho KH, Kim HJ, Kim DY, Yoo D, Nah JJ, Kim YJ, et al. Surveillance of ASF-infected pig farms from September to October 2019 in South Korea. J Vet Sci. 2021;22(2):e26. https://doi.org/10.4142/jvs.2021.22.e26
  18. Torres-Velez F, Havas KA, Spiegel K, Brown C. Transboundary animal diseases as re-emerging threats - impact on one health. Semin Diagn Pathol. 2019;36(3):193-196. https://doi.org/10.1053/j.semdp.2019.04.013
  19. Chen I, Chi C, Hsu S, Chen L. Proceedings of the 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2014 May 4-9; Florence, Italy. Piscataway: IEEE; 2014.
  20. Gutev A, Debono CJ. Proceeding of the IEEE EUROCON 2019 - 18th International Conference on Smart Technologies; 2019 Jul 1-4; Novi Sad, Serbia. Piscataway: IEEE; 2019.
  21. Mithun NC, Munir S, Guo K, Shelton C. Proceedings of the 2018 17th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN); 2018 Apr 11-13; Porto, Portugal. Piscataway: IEEE; 2018.
  22. Naeem H, Ahmad J, Tayyab M. Proceedings of the INMIC; 2013 Dec 19-20; Lahore, Pakistan. Piscataway: IEEE; 2013.
  23. Luo W, Xing J, Milan A, Zhang X, Liu W, Zhao X, et al. Multiple object tracking: a literature review. Artif Intell. 2021;293:103448. https://doi.org/10.1016/j.artint.2020.103448
  24. Dixon LK, Stahl K, Jori F, Vial L, Pfeiffer DU. African swine fever epidemiology and control. Annu Rev Anim Biosci. 2020;8(1):221-246. https://doi.org/10.1146/annurev-animal-021419-083741
  25. Lim JS, Kim E, Ryu PD, Pak SI. Basic reproduction number of African swine fever in wild boars (Sus scrofa) and its spatiotemporal heterogeneity in South Korea. J Vet Sci. 2021;22(5):e71. https://doi.org/10.4142/jvs.2021.22.e71
  26. Tack J. Wild Boar (Sus scrofa) Populations in Europe: A Scientific Review of Population Trends and Implications for Management. Brussels: ELO; 2018, 56.
  27. Mondal A. Camouflaged object detection and tracking. arXiv. 2020 Dec 25. https://arxiv.org/abs/2012.13581.