Farm Progress is part of the Informa Markets Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Serving: NE
: UNL researchers Ty Schmidt (back left), Mateusz Mittek (back right), Eric Psota (front left) and Lance C. Pérez are working with NUtech Ventures to commercialize their livestock-monitoring technology and make it available to industry Alyssa Amen
MONITORING TECH: UNL researchers Ty Schmidt (back left), Mateusz Mittek (back right), Eric Psota (front left) and Lance C. Pérez are working with NUtech Ventures to commercialize their livestock-monitoring technology.

Nebraska researchers develop livestock monitoring system

Technology processes video and uses machine learning to ID pigs and analyze data surrounding daily activities.

By Alyssa Amen

Livestock producers face a recurring challenge: watching animal behavior for signs of illness or injury.

An interdisciplinary team from the University of Nebraska-Lincoln has developed precision technology to help producers continuously monitor animals and use the resulting data to improve animal well-being.

The team includes UNL electrical and computer engineers Lance C. Pérez, Eric Psota and Mateusz Mittek, and animal scientists Ty Schmidt and Benny Mote, who developed the technology system using video footage of pigs.

The system processes video footage from livestock facilities — day and night — and applies machine learning, which uses statistical algorithms to help computer systems improve without being explicitly programmed. It identifies individual pigs and provides data about their daily activities, such as eating, drinking and movement.

Based on this data, the system also can estimate how much each pig weighs and how fast it is growing.

"Our system provides a pattern of typical behavior," said Psota, UNL research assistant professor of electrical and computer engineering. "When an animal deviates from that pattern, then it may be an indicator that something's wrong. It makes it easier to spot problems before they get too big to fix."

The team created its system using deep learning networks, a form of machine learning with millions of coefficients and parameters. To identify pigs from all angles, the networks processed images large and small — rotated, skewed and otherwise transformed.

The team uses ear tags to help with identification but aims to rely on unique physical characteristics such as ear shape, saving producers the added work of tagging.

Although the system has been developed to identify pigs, its algorithms can be used for other livestock, such as cattle, horses, goats and sheep.

"We want to make a tool that is available to the livestock producers," said Schmidt, UNL associate professor of animal science. "In a competitive agricultural market with rising costs, producers are looking for solutions that streamline operations while enhancing the health and well-being of their animals."

The team is pursuing further development with the help of NUtech Ventures, UNL's technology commercialization affiliate. NUtech has patented the technology and is exploring industry investment.

"NUtech provides a valuable service and opens us up to conversations with people outside the university," Schmidt said. "We're now looking for industry collaboration to help us advance this system."

Detecting illness, deciphering traits

The team recently received $675,000 from the National Association of Pork Producers to fund two studies. In collaboration with Kansas State University, the first study will explore the technology's ability to predict illness.

The team plans to collect data from healthy and immune-compromised pigs, training the system to distinguish early symptoms.

The second study will explore the lifespan of sows and traits that may be associated with longevity. The UNL team's technology will track sows over time and identify changes in movement, gait patterns and physical activity data that may yield links between genetic background and longevity.

It's a connection that hasn't been measured because there hasn't previously been technology to do it, Schmidt said.

"Could we make more informed management decisions — identifying optimal genetic lines that are healthier, more efficient or less aggressive?" Schmidt asked. "Can we identify a sick pig, days ahead of when symptoms are visible to the producer? In both of these studies, we're looking to push the boundaries of what we've already created."

Amen is marketing and communications manager at NUtech Ventures.

Source: IANR News, which is solely responsible for the information provided and is wholly owned by the source. Informa Business Media and all its subsidiaries are not responsible for any of the content contained in this information asset.
Hide comments


  • Allowed HTML tags: <em> <strong> <blockquote> <br> <p>

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.