"V7 is really easy to use and has great customer support—bugs are fixed, email support is very fast, and feature requests are delivered as promised."
CattleEye is an AI-first cattle monitoring company founded by Terry Canning and Adam Askew in 2019.
Their mission is to provide farmers with insights on cows’ welfare and performance using autonomous video monitoring.
With the help of trained vets, the team focuses on annotating the extreme edge cases to improve the AI algorithms they are building.
CattleEye collects video data from the CCTV cameras installed on various farms.
They work with two types of videos – long clips (20 minutes) for cattle object detection and tracking, and short (20 seconds) videos corresponding to a single, particular cow.
Vets use V7 to label videos, add health scores and thus enrich the data to make algorithms more accurate.
CattleEye’s goal is to annotate 100,000 cows by the end of 2021.
CattleEye handles large volumes of video data, and they needed a tool that could help them organize and manage their datasets more efficiently.
V7’s dataset management solution was the answer the team was looking for.
CattleEye's team could finally upload, store, organize, and manage their video data from one place, hassle-free.
Thanks to V7’s advanced video annotation solution, CattleEye managed to significantly speed up their annotation process.
Going from on-farm visits with vets manually recording data to fully remote scoring of videos in V7, the team has been able to greatly enrich the variety of training data from farms across the world.
Managing data from a single place allowed for the collaboration between engineers & vets and faster model iteration.
This also saved the busy vet travel time in addition to reducing the potential impact on the herd as cows do not need to be disturbed with on-farm visits.