Automated 3D Computer Vision Model Offers a New Tool to Measure and Understand Dairy Cow Behavior and Welfare

Dairy cows typically rest for 10 or more hours a day, so a dry, clean, and comfortable place—such as a freestall—to lie down and rest is essential for their health, well-being, and production performance. One key factor in whether stalls are comfortable for cows is the ease with which they can get up and down, so it is common on farms for staff to watch for abnormal rising behaviors as part of standard welfare management. In a new study 打開新的分頁／視窗 in the Journal of Dairy Science 打開新的分頁／視窗, published by Elsevier, a Swedish team, in collaboration with Sony Nordic, introduced a new automated model that accurately detects posture transitions in dairy cows. This innovative approach using 3-dimensional (3D) pose estimation offers valuable, unbiased insights into animal welfare and could offer a less time-consuming and more consistent assessment tool for researchers and farmers alike.

Led by Niclas Högberg, DVM, and Adrien Kroese, Eng, Department of Clinical Sciences, Faculty of Veterinary Medicine and Animal Science, Swedish University of Agricultural Sciences, Uppsala, Sweden, the study aimed to develop a reliable method for monitoring the ease with which cows can get up and down in their cubicles, a crucial indicator of overall comfort and well-being.

Adrien Kroese explained, “Evidence points to a clear link between restricted movement for cows and signs of reduced welfare, so it is common to have some kind of observation practice in place to catch signs of movement struggles.”

Traditional methods—which often rely on human observation—can be subjective, sporadic, and time-consuming.

Considering the need for more consistent methods, the study team proposed a novel framework for detecting cow movements, specifically to understand how to measure lying-to-standing transitions from 3D pose estimation data compared with the human eye.

The team employed a 24-hour setup of seven cameras recording a herd of Swedish Holstein and Swedish Red cows. This footage was then used with 3D pose estimation software, which tracks and records movements via a 2D object detector and pose estimator. These datapoints are then fed into convolutional neural networks to detect cow movements in comparison to specific anatomical landmarks on static images from the footage. The result is a 3D map of cows’ movement in their stalls and a selection of which movements indicate the transition to standing.

Dr. Kroese explained, “We then compared the standing data gathered by the software against timestamps in the video annotated by three human observers, which is considered the gold standard for behavioral observations.”

How did the 3D data model hold up in comparison to the human eye? Dr. Kroese said, “The framework was able to detect when a cow was transitioning from lying to standing with the same accuracy as humans. The sensitivity of the detection was over 88%.”

Notably, the results also indicate that the model introduced no more bias compared with human observers.

Although not without limitations, the study’s findings demonstrate the potential of 3D pose estimation to provide objective and reliable data on cow behavior. Dr. Kroese noted, “This technology represents an exciting advancement in our ability to study and monitor animal behavior and welfare. By automatically and accurately detecting posture transitions, we can gain valuable insights into the comfort and well-being of dairy cows.”

The model offers potential to help researchers scale up the study of dairy cow behavior and motion patterns and opens the door to the development of new assessment tools for farmers to make informed decisions about their herds.

Notes for editors

The article is “3-Dimensional pose estimation to detect posture transition in freestall-housed dairy cows,” by Adrien Kroese, Moudud Alam, Elin Hernlund, David Berthet, Lena-Mari Tamminen, Nils Fall, and Niclas Högberg (https://doi.org/10.3168/jds.2023-24427 打開新的分頁／視窗). It appears in the Journal of Dairy Science, volume 107, issue 9 (September 2024), published by the American Dairy Science Association 打開新的分頁／視窗 and Elsevier 打開新的分頁／視窗.

The article is openly available at https://www.journalofdairyscience.org/article/S0022-0302(24)00755-0/fulltext 打開新的分頁／視窗 and the PDF version is available at https://www.journalofdairyscience.org/action/showPdf?pii=S0022-0302%2824%2900755-0 打開新的分頁／視窗.

Full text of this article is also available to credentialed journalists upon request; contact Eileen Leahy at +1 732 406 1313 or [email protected] 打開新的分頁／視窗. Journalists wishing to interview the author should contact Adrien Kroese, Eng, Department of Clinical Sciences, Faculty of Veterinary Medicine and Animal Science, Swedish University of Agricultural Sciences, Uppsala, Sweden, at [email protected] 打開新的分頁／視窗.

About the Journal of Dairy Science

The Journal of Dairy Science® (JDS), an official journal of the American Dairy Science Association® (ADSA), is co-published by Elsevier and ADSA. It is the leading general dairy research journal in the world. JDS readers represent education, industry, and government agencies in more than 70 countries, with interests in biochemistry, breeding, economics, engineering, environment, food science, genetics, microbiology, nutrition, pathology, physiology, processing, public health, quality assurance, and sanitation. JDS has a 2023 Journal Impact Factor of 3.7 and five-year Journal Impact Factor of 4.1 according to Journal Citation Reports™ (Source: Clarivate™ 2024). www.journalofdairyscience.org 打開新的分頁／視窗

About the American Dairy Science Association (ADSA®)

The American Dairy Science Association (ADSA) is an international organization of educators, scientists, and industry representatives who are committed to advancing the dairy industry and keenly aware of the vital role the dairy sciences play in fulfilling the economic, nutritive, and health requirements of the world’s population. It provides leadership in scientific and technical support to sustain and grow the global dairy industry through generation, dissemination, and exchange of information and services. Together, ADSA members have discovered new methods and technologies that have revolutionized the dairy industry. www.adsa.org 打開新的分頁／視窗

關於 Elsevier

身為科學資訊與分析的全球領導者，Elsevier 協助研究人員與醫療照護專業人員推動科學發展，改善醫療成果，造福社會。我們以可信賴、以實證為基礎的內容和先進的 AI 數位技術為基礎，透過創新的解決方案促進洞察力和關鍵決策。

140 多年來，我們一直為研究和醫療保健界的工作提供支援。我們全球 9,500 名員工，包括 2,500 名技術人員，致力於支援研究人員、圖書館館長、學術領袖、資金提供者、政府、研發密集型公司、醫生、護士、未來醫療保健專業人員和教育工作者的重要工作。我們的 2,900 種科學期刊和經典參考工具書包括其領域中最重要的書籍，包括 Cell Press、The Lancet 和 Gray's Anatomy。 我們與愛思唯爾基金會 (Elsevier Foundation 打開新的分頁／視窗) 合作，與我們服務的社群攜手合作，在發展中國家和世界各地的科學、研究和醫療保健領域推動包容性和多樣性。 Elsevier 是 RELX 打開新的分頁／視窗 的一部分，RELX 打開新的分頁／視窗 是一家為專業和商業客戶提供以資訊為基礎的分析和決策工具的全球供應商。有關我們的工作、數位解決方案和內容的更多資訊，請造訪 www.elsevier.com 。