Assessing Stereo Camera Applicability for Digital Monitoring of Cattle Exterior

The paper highlights the substantial potential for digitalization in animal husbandry. Current applications of digital technologies include replacing manual data collection on animal phenotypes, particularly linear measurements of physical traits. In creating a contactless digital monitoring system for cattle exterior traits, cameras play a crucial role, as they enable accurate distance measurement to the object. Digital reconstruction of animal body morphometry using a contactless measurement method and automated size determination can effectively address the issues with inaccuracy and subjectivity associated with traditional scoring methods. (Research purpose) The study aims to explore the feasibility of using stereo cameras to measure object distances with the required accuracy and to analyze the performance of the stereo vision system across different areas of the frame. (Materials and methods) The study used a stereo pair of two 1/3-Inch CMOS OV4689 4-megapixel lenses mounted on the board, spaced at 6.3 centimeters from each other. Accurate distance measurement was considered achieved when the error remained within 1-2 percent (1-2 centimeters) of the object's distance (0.5-1 meter). A marked sheet with 25 centimeter intervals served as a test stand, and the stereo cameras captured the stand from distances of 30 to 100 centimeters, with a 10 centimeter increments. (Results and discussion) The study employed two camera configurations over two stages: a single stereo camera and a block of three cameras. Filming results with the single stereo camera showed a measurement error of 5-10 centimeters at distances ranging from 0.3 to 1 meter from the object. For the three-camera block, the accuracy remained comparable. It was found that accuracy was higher at the center of the frame, with an average error of 3 centimeters at viewing angles near zero.(Conclusions) The study confirmed that the number of stereo pairs does not impact accuracy, and the observed error represents the accuracy limit for these stereo pairs in stereo vision applications.

1. Tsench Yu.S. Scientific and technological potential as the main factor for agricultural mechanization development. Agricultural Machinery and Technologies. 2022. Т. 16. N2. С. 4-13 (In Russian). DOI: 10.22314/2073-7599-2022-16-2-4-13.

2. Lobachevskiy Ya.P., Dorokhov A.S. Digital technologies and robotic devices in the agriculture. Agricultural Machinery and Technologies. 2021. Т. 15. N4. С. 6-10 (In Russian). DOI: 10.22314/2073-7599-2021-15-4-6-10.

3. Kirsanov V.V., Vladimirov F.E., Pavkin D. Yu. et al. The cattle health monitoring systems' comparative analysis and selection. Journal of VNIIMZH. 2019. N1(33). 27-31 (In Russian). EDN: ZAIQZN.

4. Anderson D.M., Estell R.E., Cibils A.F. Spatiotemporal cattle data — a plea for protocol standardization. Positioning. 2013. N4. 115-136. (In English). DOI: 10.4236/pos.2013.41012.

5. Dorokhov A.S., Kirsanov V.V., Vladimirov F.E. et al. Temperature and pH level of the rumen as indicators of the probability of reproductive success. Bulletin NGIEI. 2019. N6 (97). 117-126 (In Russian). EDN: IURGBX.

6. Alem H. The role of technical efficiency achieving sustainable development: A dynamican analysis of Norwegian dairy farms. Sustainability. 2021/ N13(4):1841 (In English). DOI: 10.3390/su13041841.

7. Batanov S., Baranova I., Starostina O. Prediction model for milk production of cows by their exterior features. Vestnik BSAU. 2019. N1. 55-62 (In Russian). DOI: 10.31563/1684-7628-2019-49-1-55-62.

8. Kharchenko A.V., Feyzullaev F.R., Lepekhina TV The exterior features of the Kazakh white-headed cattle. Innovation science. 2022. N6(1). 62-64 (In Russian). EDN: HCHSJB.

9. Chindaliev A.E., Kalimoldinova A.S., Alipov A.U., Baimukanov A.D. The use of linear evaluation of body conformation of cows. Head of Animal Breeding. 2019. N8. 32-38 (In Russian). EDN: HYCFXA.

10. Sitdikov F.F., Tsoy Yu.A., Ziganshin B.G. Main directions and problems of digitalization of agricultural complex. Vestnik of the Kazan State Agrarian University. 2019. Vol. 14. N3(54). 112-115 (In Russian). DOI: 10.12737/article5db97473887137.67106533.

11. Shi Ch., Zhang J., Teng G. Mobile measuring system based on LabVIEW for pig body components estimation in a large-scale farm. Computers and Electronics in Agriculture. 2019. N156. 399-405 (In English). DOI: 10.1016/j.compag.2018.11.042.

12. Korolev V A., Bashilov A.M. Video-digital system-metric management of agrotechnological processes. Don Agrarian Science Bulletin. 2019. N4(48). 68-75 (In Russian). EDN: VSYVCN.

13. Buller H., Blokhuis H., Lokhorst K. et al. Animal welfare management in a digital world. Animals. 2020. N10. 1779 (In English). DOI: 10.3390/ani10101779.

14. Xue T., Qiao Y., Kong H. et al. One-shot learning-based animal video segmentation. IEEE Transactions on Industrial Informatics. 2021. Vol. 18. N6. 3799-3807 (In English). DOI: 10.1109/TII.2021.3117020.

15. Vlasenkova T. A., Kozyreva Yu.Yu. Digitalization as a basis for efficient agriculture. Management in Agriculture. 2021. N2. 11-16. (In Russian). DOI: 10.35244/2782-3776-2021-1-2-11-16.

16. Zhengxia Z., Zhenwei S., Yuhong G., Jieping Y. Object detectionin 20 years: a survey. Computer Vision and Pattern Recognition. 2019. 1905.05055v2. (In English). DOI: 0.48550/arXiv.1905.05055.

17. Jones J.W., Antle J.M., Basso B. et al. Toward a new generation of agricultural system data, models, and knowledge products: State of agricultural systems science. Agricultural Systems. 2017. 155. 269-288 (In English). DOI: 10.1016/j.agsy.2016.09.021.

18. Qiao Y., Kong H., Clark C. et al. Intelligent perception-based cattle lameness detection and behaviour recognition: a review. Animals. 2021. N11. 3033 (In English). DOI: 10.3390/ani11113033.