Wageningen University and QAL improve automated cow tracking
The collaboration project between Wageningen University & Research and parties from the former QAL cooperation agreement focused on advancing tracking technology, can help farmers look after their animals more efficiently and effectively. By following each cow individually on video, the system can spot early signs of stress, illness, or injury, long before they might be noticeable to farmers. It also supports breeding programs by providing more accurate information about how each animal behaves, all while reducing manual work.
However, real barns are busy places. Cows often walk behind one another, move in and out of camera view, or group together. These situations make it hard for software to keep track of “who is who,” sometimes mixing up identities when animals cross paths. Fixing these mix ups becomes harder as herd size grows. To tackle this, the project team developed a new identity correction module that helps the tracking system recover when it gets confused. They tested it on video footage of 16 Holstein cows and saw strong improvements: the number of identity mistakes dropped from 11 to 5, and overall tracking accuracy increased from 89.38% to 90.81%.
Alongside optimizing the traditional method, the team also explored an approach by reformulating the problem so it could run on a quantum computer. While today’s classical systems are still faster and more dependable, the experiment showed that these kinds of tracking challenges can indeed be mapped onto a quantum annealer. This opens the door to future applications where quantum hardware could help handle extremely large herds or very crowded scenes, where traditional methods start to struggle.
This work marks an important step toward more automated, precise, and welfare focused livestock farming, bringing cutting edge technology directly into the barn.
