Deep learning image recognition of cow behavior and an open data set acquired near an automatic milking robot

Authors

• Olli Koskela HAMK Smart research unit, Häme University of Applied Sciences, Hämeenlinna, Finland https://orcid.org/0000-0002-3424-9969
• Leonardo Santiago Benitez Pereira Federal Institute of Santa Catarina, Florianópolis, Brazil https://orcid.org/0000-0001-9429-7308
• Ilpo Pölönen HAMK Bio research unit, Häme University of Applied Sciences, Hämeenlinna, Finland
• Ilmo Aronen Lantmännen Feed Oy, Turku, Finland https://orcid.org/0000-0002-2524-0452
• Iivari Kunttu HAMK Smart research unit, Häme University of Applied Sciences, Hämeenlinna, Finland https://orcid.org/0000-0002-7460-6422

DOI: https://doi.org/10.23986/afsci.111665

Keywords:

animal well-being, video recording

Abstract

Production animals enjoying good health and well-being are more productive and have a higher output quality. Several technical solutions have been used to monitor the animals’ welfare: those based on computer vision provide cost-efficient and scalable options. In this work, we performed a continuous two-month image acquisition of cows in front of an automatic milking station and divided the data into ten different classes related to the most important activities appearing in the images. The data consisted of almost 19 hours of video, equivalent to more than 1.7 million still images. Based on these imaged, we then implemented a convolutional neural network classifier to recognize the cows' behavior. The network was tested using cross-validation methodology and achieved an 86% precision rate and 85% recall rate in the classification. The data and the Python program code used in this study are made available. An image data set that directly resembles the harsh conditions inside a barn and can be used for deep learning purposes has not been previously made available.