UFL/IFAS to use artificial intelligence to assess livestock mobility

University of Florida scientists want to assess livestock mobility faster and more accurately, ultimately helping farm animals’ health and production. To do this, they will use artificial intelligence to analyze high-resolution videos of the animals as they move.

Samantha Brooks, a geneticist at the University of Florida’s Institute of Food and Agricultural Sciences and associate professor of equine physiology—along with other UF researchers—received a $49,713 grant from the Agricultural Genomics Initiative to Phenome for this research.

The team will combine machine learning and gait analytics to speed up their assessment of livestock movement. Brooks cites an example of how this technology can help: In horses, a vet can perform a basic lameness test in about 15 minutes.

“Our long-term goal is to build an automated pipeline that can deliver results in near real time, just seconds after the animal has passed the camera,” Brooks says. “This pilot project is the first step toward that goal.”

Brooks and her colleagues primarily work with horses because they are an excellent model of locomotion and because scientists can gather a lot of data quickly.

She and her lab are already working with about 2,000 videos of moving horses. Brooks credits the video for the hard work of graduate student Madeline Smith and the generosity of hundreds of horse owners in Central Florida.

“The large video library will allow the creation of accurate models to track the movement of animals in the video frame,” says Brooks. “Although we started with the horse, what we learn here will translate into similar models for other four-legged farm animals.”

For this project, they will also build artificial intelligence models to analyze video of cattle, pigs, and small ruminants.

While reviewing the data, the researchers will look at the horse’s traits such as standing time, stride length, and limb extension. In cows and pigs, scientists are more concerned with asymmetry and postures that indicate pain due to abnormal function of one or more limbs.

Brooks says she wants to help other scientists and owners of farm animals because AI, while useful, is not always self-evident.

“The AI ​​approach could accelerate our ability to measure complex kinetic features in cattle, with better accuracy than the human eye,” Brooks says. “However, AI tools are often not biology friendly, nor are they ready for challenging on-farm applications. To deal with these issues, we hope to adapt existing AI methodologies and compile them into an analysis package accessible to scientists from diverse backgrounds and publishable in Variety of Livestock Management Settings”.

For example, technology can detect lameness in cattle as they pass the camera each day. Imagine dairy cattle entering the salon, for example – alerting the farmer to potentially serious health problems early, with less effort from farm staff.

Funded by the US Department of Agriculture’s National Institute of Food and Agriculture, AG2PI is a three-year project ending in 2023. The goal of the AG2PI is to connect crop and livestock scientists to each other and those working in data science, statistics, engineering, and the social sciences to identify common problems and collaborate on solutions.

Source: University of Florida Institute of Food and Agricultural Sciences, is solely responsible for the information provided, and owns the information in its entirety. Informa Business Media and all its affiliates are not responsible for any of the content included in this information asset.