Application of technical vision systems for diagnosing the quality of cattle feed

Russian and foreign literature on the development of diagnostic systems and scanning of objects using a vision system with deep machine learning programs has been analyzed during the study. The features of the technological process of feeding cattle have been studied. A system of non-contact assessment of the dry matter content/humidity of the components of the feed mixture of natural cultivation on the example of a corn silo using technical vision systems was proposed. A database of images of corn silage was collected and the dependences on the intensity of the reflecting light flux of the silage were revealed taking into account changes in humidity. The research was conducted in 2020 on the basis of the Federal Scientific Agroengineering Center VIM (FNAC VIM), using experimental equipment of the Institute of General Physics of the Russian Academy of Sciences named after A. M. Prokhorov and FNAC VIM. A stand with a technical vision system has been developed that allows to classify the components of a cattle feed mixture by color characteristics. The obtained dependences of the reflecting intensity of corn silage allow us to assert the prospect of using a vision system for express-evaluation of the quality indicators of feed mixture components. Taking into account the level of robotization of technological processes of feeding cattle, the problem of assessing the quality indicators (in particular, the dry matter/moisture content) of the components of a feed mixture is relevant.

1. Nikitin E. A., Dorokhov A. S., Pavkin D. Yu. Sovershenstvovanie tekhnologii prigotovleniya kormovoy smesi pri rekonstruktsii kormovykh ploshchadok. [Improving a process for the preparation of feed mixture during the reconstruction of feed sites]. Tekhnika i oborudovanie dlya sela = Machinery and Equipment for Rural Area. 2019;(11):32-34. (In Russ.). DOI: https://doi.org/10.33267/2072-9642-2019-11-32-34

2. Pavkin D. Yu., Nikitin E. A., Zobov V. A. Sistema robotizirovannogo obsluzhivaniya kormovogo stola na zhivotnovodcheskikh kompleksakh. [Robotic system for maintenance of feed table for livestock complexes]. Sel'skokhozyaystvennye mashiny i tekhnologii = Agricultural Machinery and Technologies. 2020;14(3):33-38. (In Russ.). DOI: https://doi.org/10.22314/2073-7599-2020-14-3-33-38

3. Neethirajan S. The role of sensors, big data and machine learning in modern animal farming. Sensing and Bio-Sensing Research. 2020;29:100367. DOI: https://doi.org/10.1016/j.sbsr.2020.100367

4. Nasirahmadi A., Edwards S., Sturm B. Implementation of machine vision for detecting behaviour of cattle and pigs. Livestock Science. 2017;202:25-38. DOI: https://doi.org/10.1016/j.livsci.2017.05.014

5. Regoa G., Ferreroa F., Valledora M., Campoa Ju. C., Forcadab S., Royob L. J., Soldadob A. A portable IoT NIR spectroscopic system to analyze the quality of dairy farm forage. Computers and Electronics in Agriculture. 2020;175:105578. DOI: https://doi.org/10.1016/j.compag.2020.105578

6. Wajizaha S. S., Munawarb A. A. Rapid and Simultaneous Determination of Feed Nutritive Values by Means of Near Infrared Spectroscopy. Tropical Animal Science Journal, August 2018;41(2):121-127. DOI: https://doi.org/10.5398/tasj.2018.4L2.121

7. Rodionova O. Ye., Fernandez Pierna J. A., Baeten V., Pomerantsev A. L. Chemometric non-targeted analysis for detection of soybean meal adulteration by near infrared spectroscopy. Food Control. 2021;119:107459. DOI: https://doi.org/10.1016/j.foodcont.2020.107459

8. Piccioli-Cappelli F., Calegari F., Calamari L., Bani P., Minuti A. Application of a NIR device for precision feeding in dairy farms: effect on metabolic conditions and milk production. Italian Journal of Animal Science. 2019;18(1): 754-765. DOI: https://doi.org/10.1080/1828051X.2019.1570829

9. Oetzel G. R., Villalba F. P., Goodger W. J., Nordlund K. V. A Comparison of On-Farm Methods for Estimating the Dry Matter Content of Feed Ingredients. Journal of Dairy Science. 1993;76(1):293-299. DOI: https://doi.org/10.3168/jds.S0022-0302(93)77349-X

10. Crofcheck C., Wade J., Swamy J. N., Aslan M. M., MenguQ M. P. Effect of Fat and Casein Particles in Milk on the Scattering of Elliptically Polarized Light. Biosystems and Agricultural Engineering Faculty Publications. 2005;48(3):1147-1155. DOI: https://doi.org/10.13031/2013.18488

11. Taneja P., Vasava H. K., Daggupati P., Biswas A. Multi-algorithm comparison to predict soil organic matter and soil moisture content from cell phone images. Geoderma. 2021;385:114863. DOI: https://doi.org/10.1016/j.geoderma.2020.114863

12. Kim W.-S., Lee D.-H., Kim Y.-J., Kim Y.-S., Kim T., Park S.-U., Kim S.-S., Hong D.-H.g. Crop height measurement system based on 3D image and tilt sensor fusion. 2020;10(11):1670. DOI: https://doi.org/10.3390/agronomy10111670

13. Dorokhov A. S., Sibirev A. V., Aksenov A. G. Dynamic systems modeling using artificial neural networks for agricultural machines. INMATEH-AGRICULTURAL ENGINEERING. 2019;58(2):63-74. URL: https://inmateh.eu/INMATEH_2_2019/58-07%20Dorokhov.pdf

14. Dorokhov A. S., Shepovalova O. V. Solar PV systems integrated into hardscape and sculptures. Technologies and materials for renewable energy, environment and sustainability: TMREES19GR. 2019;2190:020094. DOI: https://doi.org/10.1063/1.5138580