Developing an algorithm for body condition scoring of dairy cows

Cow’s body condition scoring (BCS) based on neural network algorithms is necessary to monitor the health and productivity of the animals. To develop an algorithm for assessing the physiological fatness of dairy cows according to the parameters of the fermur heads, the sacrum and the hunger hollow, the authors studied eighty animals on a farm of the state unitary enterprise “Grigorievskoe”, which were divided into fatness groups (from 1 to 5). The studies were carried out in November 2021 during the morning milking. Data were collected using a 3D ToF camera O3D303. Previously, the installation of a three-dimensional camera on the farm was simulated, and an algorithm was developed that takes into account the cow height and the distance from the highest point of the spine to the three-dimensional camera. An algorithm for assessing the physiological fatness of dairy cows (BCS) has been developed to take into account the condition of the fermur heads, the sacrum, the hunger hollow, which determines the highest point of the withers, the proportions between the body length and width, as well as the depth of the hunger hollows and the severity of the caudal ligament. Software has been developed to register the unique number of a cow and determine the BCS, as well as show the dynamics of changes in the animal’s fatness. Data were processed in accordance with the developed algorithm. The image was processed using the regression method. Comparison results of the BCS of cows, obtained according to the developed algorithm, and the experts’ assessment showed that the algorithm error in the fatness range of 2…4 points averaged 10%. When determining the BCS of cows with borderline and limit fatness state (1 and 5 points), the measurement error by the proposed algorithm increased to 25%. Based on the results obtained, the authors recommend pre-setting a neural network for further research; determine the correction factor for fatness points 1 and 5; finalize the software, develop customized software and an automatic system for body condition scoring, and conduct tests.

1. Pavkin D.Yu., Dorokhov A.S., Vladimirov F.E., Dovlatov I.M., Lyalin K.S. Algorithms for detecting cattle diseases at early stages and for making diagnoses and related recommendations. Applied Sciences (Switzerland). 2021; 11 (23): 11148. https://doi.org/10.3390/app112311148

2. EDN: GWBZKJ. Kolotushkin A.N., Yurochka S.S., Vasina M.Yu., Dovlatov I.M. Device for the automatic control of air quality in livestock premises. Agrotekhnika i energoobespechenie. 2021; 3 (32): 17-23. (In Rus.)

3. Kirsanov V.V., Pavkin D.Yu., Nikitin E.A., Dovlatov I.M. Methods for optimizing the parameters of machine cattle feeding. Agricultural Engineering. 2021; 1: 10-14. https://doi.org/10.26897/2687-1149-2021-1-10-14 (In Rus.)

4. Vanholder T., Papen J., Bemers R., Vertenten G., Berge A.C.B. Risk factors for subclinical and clinical ketosis and association with production parameters in dairy cows in the Netherlands. Journal of dairy science. 2015; 98 (2): 880-888. https://doi.org/10.3168/jds.2014-8362

5. Chapel J.M., Muiño R., Pereira V., Castillo C., Hernández J., Benedito J.L. Relationship of BCS prepartum with reproductive performance and lipomobilization in Holstein dairy cows. Pakistan Veterinary Journal. 2017; 37 (2): 215-219.

6. Daros R.R., Hötzel M.J., Bran J.A., LeBlanc S.J., Keyserlingk M.A.G. Prevalence and risk factors for transition period diseases in grazing dairy cows in Brazil. Preventive veterinary medicine. 2017; 145: 16-22. https://doi.org/10.1016/j.prevetmed.2017.06.004

7. Barletta R.V. et al. Association of changes among body condition score during the transition period with NEFA and BHBA concentrations, milk production, fertility, and health of Holstein cows. Theriogenology. 2017; 104: 30-36. https://doi.org/10.1016/j.theriogenology.2017.07.030

8. Garzón A., Oliver-Espinosa O. Incidence and risk factors for ketosis in grazing dairy cattle in the Cundi-Boyacencian Andean plateau, Colombia. Tropical animal health and production. 2019; 51 (6): 1481-1487. https://doi.org/10.1007/s11250-019-01835-z

9. Berry D.P., Macdonald K.A., Penno J.W., Roche J.R. Association between body condition score and live weight in pasture-based Holstein-Friesian dairy cows. Journal of dairy research. 2006; 73 (4): 487-491. https://doi.org/10.1017/S0022029906002020

10. Paul A., Mondal S., Kumar S., Kumari T. Body condition scoring in dairy cows-a conceptual and systematic review. Indian journal of animal research. 2020; 54: 929-935. https://doi.org/10.18805/ijar.B-3859

11. Yukun S. et al. Automatic monitoring system for individual dairy cows based on a deep learning framework that provides identification via body parts and estimation of body condition score. Journal of dairy science. 2019; 102 (11): 10140-10151. https://doi.org/10.3168/jds.2018-16164