75. Do we improve any aspects of animal welfare by implementing Computer Vision in livestock farming?

Abstract

Computer Vision technology has been developed recently as a tool for measuring behaviour on the individual level in group housed livestock. This form of digital agriculture or precision livestock farming has the potential to answer to public concerns on farm animal welfare by using the data to reduce the risk of harmful social interactions such as tail biting in pig production and severe feather pecking in laying hen production. Computer Vision, however comes with changes to livestock farming and therefore can lead to new moral questions. Currently it has not resulted in much public debate. We argue that this is not to be understood as a sign that there are no societal and ethical challenges, but that -as part of responsible research and innovation -this is an important moment to explore and analyse the potential societal and ethical issues. In this paper we aim to explore the moral dimensions of the use of Computer Vision in livestock farming with a special focus on poultry. We analyse the moral dimensions from an animal welfare perspective. Although introduced to prevent welfare risks or improve the welfare status of animals, this innovation can lead to welfare questions depending on one's concept of animal welfare.

Review of Poultry Monitoring using Computer Vision

“…The system captures activities of the birds within a defined environment, ranging from movement, interaction within the flock, water consumption, and feeding patterns (Rushen et al, 2012), (Massari et al, 2022). Captured images are subjected to pre-processing steps, where noise is removed from the image, and the image is resized which will lead to enhancement of the image and extraction of all the key features, no matter how insignificant, such as nuanced behaviors and physiological features are recognized and interpreted for better outcome or result (Pereira et al, 2013), (Publishers, 2022). Implementation of deep learning models, which is the core of the system, is made possible through training of a vast dataset and validation of the model for better insights into the health (Neethirajan, 2022), (Eijk et al, 2022), (Fang et al, 2020).…”