Automatic identification and analysis of multi-object cattle rumination based on computer vision
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Rumination in cattle is closely related to their health, which makes the automatic monitoring of rumination an important part of smart pasture operations. However, manual monitoring of cattle rumination is laborious and wearable sensors are often harmful to animals. Thus, we propose a computer vision-based method to automatically identify multi-object cattle rumination, and to calculate the rumination time and number of chews for each cow. The heads of the cattle in the video were initially tracked with a multi-object tracking algorithm, which combined the You Only Look Once (YOLO) algorithm with the kernelized correlation filter (KCF). Images of the head of each cow were saved at a fixed size, and numbered. Then, a rumination recognition algorithm was constructed with parameters obtained using the frame difference method, and rumination time and number of chews were calculated. The rumination recognition algorithm was used to analyze the head image of each cow to automatically detect multi-object cattle rumination. To verify the feasibility of this method, the algorithm was tested on multi-object cattle rumination videos, and the results were compared with the results produced by human observation. The experimental results showed that the average error in rumination time was 5.902% and the average error in the number of chews was 8.126%. The rumination identification and calculation of rumination information only need to be performed by computers automatically with no manual intervention. It could provide a new contactless rumination identification method for multi-cattle, which provided technical support for smart pasture.
Abstract
Rumination in cattle is closely related to their health, which makes the automatic monitoring of rumination an important part of smart pasture operations. However, manual monitoring of cattle rumination is laborious and wearable sensors are often harmful to animals. Thus, we propose a computer vision-based method to automatically identify multi-object cattle rumination, and to calculate the rumination time and number of chews for each cow. The heads of the cattle in the video were initially tracked with a multi-object tracking algorithm, which combined the You Only Look Once (YOLO) algorithm with the kernelized correlation filter (KCF). Images of the head of each cow were saved at a fixed size, and numbered. Then, a rumination recognition algorithm was constructed with parameters obtained using the frame difference method, and rumination time and number of chews were calculated. The rumination recognition algorithm was used to analyze the head image of each cow to automatically detect multi-object cattle rumination. To verify the feasibility of this method, the algorithm was tested on multi-object cattle rumination videos, and the results were compared with the results produced by human observation. The experimental results showed that the average error in rumination time was 5.902% and the average error in the number of chews was 8.126%. The rumination identification and calculation of rumination information only need to be performed by computers automatically with no manual intervention. It could provide a new contactless rumination identification method for multi-cattle, which provided technical support for smart pasture.
참고문헌 (34)
- Xie H, "Analysis on the competitiveness of Inner Mongolia animal husbandry industry", J Domest Anim Ecol, 40, pp.50~55 (2019)
- Wang L, "Connotation, development and problems of China’s animal husbandry industry system", Chin J Anim Sci, 53, pp.130~134 (2017)[DOI]
- Wolfert S, "Big data in smart farming : a review", Agric Syst, 153, pp.69~80 (2017)[DOI]
- Eastwood C, "Managing socio-ethical challenges in the development of smart farming : from a fragmented to a comprehensive approach for responsible research and innovation", J Agric Environ Ethics, 32, pp.741~768 (2019)[DOI]
- Chen C, "Study and application of early warning architecture of animal health culture", Trans Chin Soc Agric Eng, 26, pp.215~220 (2010)
- Pahl C, "Feeding characteristics and rumination time of dairy cows around estrus", J Dairy Sci, 98, pp.148~154 (2015)[DOI]
- Moretti R, "Heritability and genetic correlations between rumination time and production traits in Holstein dairy cows during different lactation phases", J Anim Breed Genet, 135, pp.293~299 (2018)[DOI]
- Andreen DM, "Relationships between milk fat and rumination time recorded by commercial rumination sensing systems", J Dairy Sci, 103, pp.8094~8104 (2020)[DOI]
- Meng R, "The development status and prospects of livestock and poultry precise feeding management technologies", J Domest Anim Ecol, 42, pp.1~7 (2021)[DOI]
- Xiong B, "Studies on key thing Internet technology for precise livestock feeding", J Agric Sci Technol, 13, pp.19~25 (2011)
- Hamilton AW, "Identification of the rumination in cattle using support vector machines with motion-sensitive bolus sensors", Sensors, 19, pp.1165~ (2019)[DOI]
- Campos DP, "Surface electromyography segmentation and feature extraction for ingestive behavior recognition in ruminants", Comput Electron Agric, 153, pp.325~333 (2018)[DOI]
- Ren XH, "Dairy cattle’s behavior recognition method based on support vector machine classification model", Trans Chin Soc Agric Mach, 50, pp.290~296 (2019)
- Rombach M, "Evaluation and validation of an automatic jaw movement recorder(RumiWatch)for ingestive and rumination behaviors of dairy cows during grazing and supplementation", J Dairy Sci, 101, pp.2463~2475 (2018)[DOI]
- Shen W, "Rumination recognition method of dairy cows based on the change of noseband pressure", Inf Process Agric, 7, pp.479~490 (2020)[DOI]
- Chen Y, "Intelligent monitoring method of cow ruminant behavior based on video analysis technology", Int J Agric Biol Eng, 10, pp.194~202 (2017)[DOI]
- Chen Y, "Automatic monitoring method of cow ruminant behavior based on spatio-temporal context learning", Int J Agric Biol Eng, 11, pp.179~185 (2018)[DOI]
- Song H, "Monitoring of multi-target cow ruminant behavior based on video analysis technology", Trans Chin Soc Agric Eng, 34, pp.211~218 (2018)[DOI]
- Mao Y, "Automatic detection of ruminant cows’ mouth area during rumination based on machine vision and video analysis technology", Int J Agric Biol Eng, 12, pp.186~191 (2019)[DOI]
- Wu D, "Using a CNN-LSTM for basic behaviors detection of a single dairy cow in a complex environment", Comput Electron Agric, 182, pp.106016~ (2021)[DOI]
- Babenko B, "Robust object tracking with online multiple instance learning", IEEE Trans Pattern Anal Mach Intell, 33, pp.1619~1632 (2011)[DOI]
- Kalal Z, "Tracking-learning-detection", IEEE Trans Pattern Anal Mach Intell, 34, pp.1409~1422 (2012)[DOI]
- Danelljan M, "Discriminative scale space tracking", IEEE Trans Pattern Anal Mach Intell, 39, pp.1561~1575 (2017)[DOI]
- Ma C, "Hierarchical convolutional features for visual tracking", Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), pp.3074~3082 (2015)
- Danelljan M, "ATOM: accurate tracking by overlap maximization", Proceedings of the 2019 IEEE, 2019, 4655~4664
- Wojke N, "Simple online and realtime tracking with a deep association metric", Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP), pp.3645~3649 (2017)
- Zhou X, "Tracking objects as points", Computer vision – ECCV 2020 16th European Conference, pp.474~490 (2020)
- Sun L, "Multi target pigs tracking loss correction algorithm based on faster R-CNN", Int J Agric Biol Eng, 11, pp.192~197 (2018)[DOI]
- Zhang L, "Automatic individual pig detection and tracking in pig farms", Sensors, 19, pp.1188~ (2019)[DOI]
- Zhang H, "Beef cattle multi-target tracking based on DeepSORT algorithm", Trans Chin Soc Agric Mach, 52, pp.248~256 (2021)[DOI]
- Xu B, "Evaluation of deep learning for automatic multi-view face detection in cattle", Agriculture, 11, pp.1062~ (2021)[DOI]
- Yuan Z, "Human body tracking method based on deep learning object detection", CSSE 2019: Proceedings of the 2nd International Conference on Computer Science and Software Engineering (CSSE), pp.114~118 (2019)
- "LabelImg. Git code" (2015)[URL]
- Henriques JF, "High-speed tracking with kernelized correlation filters", IEEE Trans Pattern Anal Mach Intell, 37, pp.583~596 (2015)[DOI]