Few automated video systems are described in the open literature that enable hands-free cataloging and identification (ID) of cows in a dairy herd. In this work, we describe our system, composed of an AutoCattloger, which builds a Cattlog of dairy cows in a herd with a single input video clip per cow, an eidetic cow recognizer which uses no deep learning to ID cows, and a CowFinder, which IDs cows in a continuous stream of video. We demonstrate its value in finding individuals in unlabeled, unsegmented videos of cows walking unconstrained through the holding area of a milking parlor.
@article{arxiv.2508.15945,
title = {Automatic Retrieval of Specific Cows from Unlabeled Videos},
author = {Jiawen Lyu and Manu Ramesh and Madison Simonds and Jacquelyn P. Boerman and Amy R. Reibman},
journal= {arXiv preprint arXiv:2508.15945},
year = {2025}
}
Comments
Extended abstract. Presented at the 3rd US Conference on Precision Livestock Farming (USPLF), 2025, Lincoln NE