Smart Media Journal (스마트미디어저널)

THE KOREAN INSTITUTE OF SMART MEDIA (한국스마트미디어학회)
권호 표지
DOI QR코드

DOI QR Code

Multi-Cattle Tracking Algorithm with Enhanced Trajectory Estimation in Precision Livestock Farms

  • Shujie Han (Department of Electronics Engineering, Jeonbuk National University) ;
  • Alvaro Fuentes (Department of Electronics Engineering, Jeonbuk National University) ;
  • Sook Yoon (Department of Computer Engineering, Mokpo National University) ;
  • Jongbin Park (Department of Electronics Engineering, Jeonbuk National University) ;
  • Dong Sun Park (Department of Electronics Engineering, Jeonbuk National University)
  • Received : 2023.10.20
  • Accepted : 2023.12.13
  • Published : 2024.02.29
Download PDF
⟨ Previous Next ⟩

Abstract

In precision cattle farm, reliably tracking the identity of each cattle is necessary. Effective tracking of cattle within farm environments presents a unique challenge, particularly with the need to minimize the occurrence of excessive tracking trajectories. To address this, we introduce a trajectory playback decision tree algorithm that reevaluates and cleans tracking results based on spatio-temporal relationships among trajectories. This approach considers trajectory as metadata, resulting in more realistic and accurate tracking outcomes. This algorithm showcases its robustness and capability through extensive comparisons with popular tracking models, consistently demonstrating the promotion of performance across various evaluation metrics that is HOTA, AssA, and IDF1 achieve 68.81%, 79.31%, and 84.81%.

Keywords

Acknowledgement

This work was supported by Korea Institute of Planning and Evaluation for Technology in Food, Agriculture and Forestry(IPET) and Korea Smart Farm R&D Foundation(KosFarm) through Smart Farm Innovation Technology Development Program, funded by Ministry of Agriculture, Food and Rural Affairs(MAFRA) and Ministry of Science and ICT(MSIT), Rural Development Administration(RDA)(421044-04)

References

  1. N. Li, Z. Ren, D. Li, and L. Zeng, "Review: Automated techniques for monitoring the behaviour and welfare of broilers and laying hens: towards the goal of precision livestock farming," Animal, vol. 14, no. 3, pp. 617-625, Mar. 2020. https://doi.org/10.1017/S1751731119002155
  2. J. A. Hassan-Vasquez, F. Maroto-Molina, and J. E. GuerreroGinel, "GPS Tracking to Monitor the Spatiotemporal Dynamics of Cattle Behavior and Their Relationship with Feces Distribution," Animals, vol. 12, no. 18, Art. no. 18, Jan. 2022, doi:10.3390/ani12182383.
  3. H. Dogan, I. B. Basyigit, M. Yavuz, and S. Helhel, "Signal level performance variation of radio frequency identification tags used in cow body," International Journal of RF and Microwave Computer-Aided Engineering, vol. 29, no. 7, p. e21674, 2019, doi: 10.1002/mmce.21674.
  4. A. Pretto, G. Savio, F. Gottardo, F. Uccheddu, and G. Concheri, "A novel low-cost visual ear tag based identification system for precision beef cattle livestock farming," Information Processing in Agriculture, Oct. 2022, doi: 10.1016/j.inpa.2022.10.003.
  5. W. Andrew, C. Greatwood, and T. Burghardt, "Fusing Animal Biometrics with Autonomous Robotics: Dronebased Search and Individual ID of Friesian Cattle (Extended Abstract)," presented at the Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, 2020, pp. 38-43. Accessed: Apr. 28, 2022. [Online]. Available: https://openaccess.thecvf.com/content_WACVW_2020/html/w2/Andrew_Fusing_Animal_Biometrics_with_Autonomous_Robotics_Dronebased_Search_and_Individual_WACVW_ 2020_paper.html
  6. W. Shao, R. Kawakami, R. Yoshihashi, S. You, H. Kawase, and T. Naemura, "Cattle detection and counting in UAV images based on convolutional neural networks," International Journal of Remote Sensing, vol. 41, no. 1, pp. 31-52, Jan. 2020, doi: 10.1080/01431161.2019.1624858.
  7. A. Bewley, Z. Ge, L. Ott, F. Ramos, and B. Upcroft, "Simple Online and Realtime Tracking," in 2016 IEEE International Conference on Image Processing (ICIP), Sep. 2016, pp. 3464-3468. doi: 10.1109/ICIP.2016.7533003.
  8. N. Wojke, A. Bewley, and D. Paulus, "Simple Online and Realtime Tracking with a Deep Association Metric." arXiv, Mar. 21, 2017. doi: 10.48550/arXiv.1703.07402.
  9. J. Cao, J. Pang, X. Weng, R. Khirodkar, and K. Kitani, "ObservationCentric SORT: Rethinking SORT for Robust Multi-Object Tracking," presented at the Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 9686-9696. Accessed: Oct. 20, 2023. [Online]. Available: https://openaccess.thecvf.com/content/CVPR2023/html/Cao_ObservationCentric_SORT_Rethinking_SORT_for_Robust_MultiObject_Tracking_CVPR_2023_paper.html
  10. S. Han, A. Fuentes, S. Yoon, Y. Jeong, H. Kim, and D. Sun Park, "Deep learning-based multi-cattle tracking in crowded livestock farming using video," Computers and Electronics in Agriculture, vol. 212, p. 108044, Sep. 2023, doi: 10.1016/j.compag.2023.108044.
  11. A. Fuentes, S. Yoon, J. Park, and D. S. Park, "Deep learning-based hierarchical cattle behavior recognition with spatio-temporal information," Computers and Electronics in Agriculture, vol. 177, p. 105627, Oct. 2020, doi: 10.1016/j.compag.2020.105627.
  12. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection." arXiv, May 09, 2016. doi:10.48550/arXiv.1506.02640.
  13. Y. Zhang et al., "ByteTrack: Multi-object Tracking by Associating Every Detection Box," in Computer Vision - ECCV 2022, S. Avidan, G. Brostow, M. Cisse, G. M. Farinella, and T. Hassner, Eds., in Lecture Notes in Computer Science. Cham: Springer Nature Switzerland, 2022, pp. 1-21. doi: 10.1007/978-3-031-20047-2_1.