Harnessing the power of computer vision systems to improve animal health and welfare in transition dairy cows

PI: João Dorea


Dorea is an assistant professor of animal and dairy sciences at UW–Madison who specializes in precision agriculture and data analytics. He has been working extensively on the development of top-notch applications of artificial intelligence to optimize farm management decisions and improve animal nutrition and health.

Postdoc: Dário Oliveira (pictured above), an electrical engineer by training, was most recently a research staff member with IBM Research in Sao Paulo, Brazil in the area of computer vision and visual understanding. He is now a postdoctoral researcher in animal and dairy sciences.

Nearly all cows will experience negative energy balance in order to support the high energy demands of lactation during the transition period. This can lead to a variety of metabolic disorders. Body condition score is a commonly used tool to monitor and manage these disorders in lactating cows. However, body condition is a periodic, subjective measurement that cannot detect small changes in body shape or composition. Consequently, the development of a computer vision system to assess body condition scores in real-time will play a crucial role to precisely detect changes in body condition. The objective of this project is to develop a platform that uses sensors for real-time detection of body shape and animal behavior. Results will be used for precise and early detection of metabolic disorders and associated health problems. This research will be conducted with guidance from João Dorea, assistant professor of animal and dairy sciences.

Brian Bockelman