Methods for Neural Network Detection of Farm Animals in Dense Dynamic Groups on Images
- 作者: Zhigalov А.A.1, Ivashchuk O.A.1, Biryukova T.K.2, Fedorov V.I.1
-
隶属关系:
- Belgorod State National Research University
- Federal Research Center “Computer Science and Control” of Russian Academy of Sciences
- 期: 编号 1 (2023)
- 页面: 55-66
- 栏目: Machine Learning, Neural Networks
- URL: https://journals.rcsi.science/2071-8594/article/view/269809
- DOI: https://doi.org/10.14357/20718594230106
- ID: 269809
如何引用文章
全文:
详细
The development of non-invasive methods for monitoring the condition of farm animals is now a burning problem. The world is developing technologies for video surveillance of animals with subsequent image processing using neural networks. The purpose of this study is to develop methods for the detection (selection of individuals) of farm animals in images using pigs as an example. The main task is to perform the detection of "faces" of pigs in dense groups. To solve the task, a set of photographs of pigs from open sources was created, promising neural network architectures Faster R-CNN and YOLOv5 were selected, fine-tuning and training of neural networks were performed. The use of the YOLOv5 network enabled the detection accuracy mAP = 94.05%, which is significantly higher than the accuracy shown in similar works. This work is the first in an upcoming series of studies aimed at creating a software and hardware complex for automatic animal health monitoring on farms.
全文:

作者简介
Аlexey Zhigalov
Belgorod State National Research University
编辑信件的主要联系方式.
Email: jigaloff@gmail.com
Postgraduate student
俄罗斯联邦, BelgorodOlga Ivashchuk
Belgorod State National Research University
Email: olga.ivashuk@mail.ru
Doctor of technical sciences, professor. Head of the Department of Information and Robotic Systems
俄罗斯联邦, BelgorodTatyana Biryukova
Federal Research Center “Computer Science and Control” of Russian Academy of Sciences
Email: yukonta@mail.ru
Candidate of physical and mathematical sciences. Senior Researcher
俄罗斯联邦, MoscowVyacheslav Fedorov
Belgorod State National Research University
Email: fedorov_v@bsu.edu.ru
Candidate of technical sciences. Аssociated Professor of the Department of Information and Robotic Systems
俄罗斯联邦, Belgorod参考
- Effektivnost' sel'skokhozyaystvennogo proizvodstva (metodicheskie rekomendatsii) [Efficiency of agricultural production (guidelines)]. Moscow: Vserossiyskiy nauch-no-issledovatel'skiy institut ekonomiki sel'skogo khozyaystva [Russian Research Institute of Agricultural Economics]. 2005. 156 p.
- Sel'skoe khozyaystvo v Rossii. 2021: Statisticheskiy sbornik [Agriculture in Russia. 2021: Statistical compendium]. 2021. Moscow: Federal State Statistics Service. 100 p.
- Neethirajan, S. 2020. The role of sensors, big data and machine learning in modern animal farming. J. Sensing and Bio-Sensing Research. V.29.
- Yang, Q., D. Xiao. 2020. A review of video-based pig behavior recognition. J. Applied Animal Behaviour Science. V.233.
- Available at: https://github.com/ultralytics/yolov5 (accessed June 21, 2022).
- Ren, S., K. He, R. Girshick, J. Sun. 2017. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39: Р.1137–1149.
- He, K., X. Zhang, S. Ren, J. Sun. 2016. Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition. P.770–778.
- Available at: https://pytorch.org/vision/stable/generated/torchvision.mo dels.resnet50.html (accessed June 20, 2022).
- Available at: https://pytorch.org/vision/0.12/_modules/torchvision/mode ls/mobilenetv3.html (accessed June 18, 2022).
- Padilla, R., W.L. Passos, T.L.B. Dias, S.L. Netto, E.A.B. da Silva. 2021. A Comparative Analysis of Object Detection Metrics with a Companion Open-Source Toolkit. J. Electronics. 10(3). doi: 10.3390/electronics10030279. Available at: https://github.com/rafaelpadilla/review_object_detection_ metrics (accessed June 10, 2022).
- Li, G., J. Jiao, G. Shi, H. Ma, L. Gu, L. Tao. 2022. Fast Recognition of Pig Faces Based on Improved Yolov3. Journal of Physics: Conference Series. V.2171.
- Hansen, M.F., M.L. Smith, L.N. Smith, M.G. Salter, E.M. Baxter, M. Farish, B. Grieve. 2018. Towards on-farm pig face recognition using convolutional neural networks. J. Computers in Industry. 98: Р.145–152.
- Marsot, M., J. Mei, X. Shan, L. Ye, P. Feng, X. Yan, C. Li, Y. Zhao. 2020. An adaptive pig face recognition approach using Convolutional Neural Networks. J. Computers and Electronics in Agriculture. V.173.
- Wang, K., C. Chen, Y. He. 2020. Research on pig face recognition model based on keras convolutional neural network. J. IOP Conference Series: Earth and Environmental Science. V.474.
- Wang, R., Z. Shi, Q. Li, R. Gao, C. Zhao, L. Feng. 2021. Pig face recognition model based on a cascaded network. J. Applied Engineering in Agriculture. 37(5): Р.879-890.
- Shigang, W., W. Jian, C. Meimei, W. Jinyang. 2021. A pig face recognition method for distinguishing features. IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC).
- Wang, Z., T. Liu. 2022. Two-stage method based on triplet margin loss for pig face recognition. J. Computers and Electronics in Agriculture. V.194.
- Alameer, A., I. Kyriazakis, J. Bacardit. 2020. Automated recognition of postures and drinking behaviour for the detection of compromised health in pigs. J. Scientific Reports.
- Redmon, J., A. Farhadi. 2017. YOLO9000: Better, Faster, Stronger. IEEE Conference on Computer Vision and Pattern Recognition; Honolulu, HI, USA. P.7263–7271.
- Sa, J., Y. Choi, H. Lee, Y. Chung, D. Park, J. Cho. 2019. Fast Pig Detection with a Top-View Camera under Various Illumination Conditions. J. Symmetry. 11(266).
- Ju M., Choi Y., Seo J. A Kinect-Based Segmentation of Touching-Pigs for Real-Time Monitoring // Sensors. 2018. V.18(1746).
- Riekert, M., A. Klein, F. Adrion, C. Hoffmann, E. Gallmann. 2020. Automatically detecting pig position and posture by 2D camera imaging and deep learning. J. Computers and Electronics in Agriculture. V.174.
- Psota, E.T., M. Mittek, L.C. Perez, T. Schmidt, B. Mote. 2019. Multi-Pig Part Detection and Association with a Fully-Convolutional Network. J. Sensors (Basel). 19(4):852.
- Lee, S.K. 2020. Pig Pose Estimation Based on Extracted Data of Mask R-CNN with VGG Neural Network for Classifications. Open Public Research Access Institutional Repository and Information Exchange. Electronic Theses and Dissertations. Available at: https://openprairie.sdstate.edu/etd/4098 (accessed June 23, 2022).
- Badrinarayanan, V., A. Kendall, R. Cipolla. 2017. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39: Р.2481–2495.
- He, K., G. Gkioxari, P. Dollar, R. Girshick. 2018. Mask R-CNN. arXiv:1703.06870v3 [cs.CV].
- Wang, Z., T. Liu. 2022. Two-stage method based on triplet margin loss for pig face recognition. J. Computers and Electronics in Agriculture. V.194.
- Tan, M. R. Pang, Q.V. Le. 2020. EfficientDet: Scalable and efficient object detection. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. P.10778–10787.
- Dwivedi, P. 2020. YOLOv5 compared to Faster RCNN. Who wins? Available at: https://towardsdatascience.com/yolov5-compared-to-faster-rcnn-who-wins-a771cd6c9fb4#:~:text=The%20final%20comparison%20b%2 Fw,little%20to%20no%20overlapping%20boxes (accessed June 21, 2022).
- Lin, T.-Y., P. Dollar, R. Girshick, K. He, B. Hariharan, S. Belongie. 2017. Feature Pyramid Networks for Object Detection. Available at: https://arxiv.org/pdf/1612.03144.pdf (accessed June 19, 2022).
- Available at: https://pytorch.org/vision/stable/models.html (accessed June 20, 2022).
- Available at: https://pytorch.org/vision/0.12/_modules/torchvision/mode ls/detection/faster_rcnn.html (accessed June 23, 2022).
- Available at: https://pytorch.org/vision/stable/generated/torchvision.mo dels.detection.fasterrcnn_resnet50_fpn.html#torchvision.m odels.detection.fasterrcnn_resnet50_fpn (accessed June 15, 2022).
- Available at: https://pytorch.org/vision/stable/generated/torchvision.models.detection.fasterrcnn_mobilenet_v3_large_fpn.html#torchvisi on.models.detection.fasterrcnn_mobilenet_v3_large_fpn (accessed June 17, 2022).
- Available at: https://cocodataset.org/#detection-eval (accessed June 23, 2022).
- Everingham, M., van Gool L., C. K. Williams, J. Winn, Zisserman. The pascal visual object classes (VOC) challenge. Int. J. Comput. 2010. No 88. P. 303–338.
补充文件
