How CattleEye Uses V7 to Develop AI Models 10x Faster

How CattleEye Uses V7 to Develop AI Models 10x Faster

Cow and calf in a field
Cattle Eye Logo

Monitoring the health of cattle through computer vision

Industry

Agriculture

Use Case

Livestock Health Monitoring

Company size

11-50 employees

Headquarters

Belfast, Northern Ireland

Data labelling
Discover our solutions

About

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.

Model Development Speed

10x

My favorite feature is the API because it automated everything for us. I like automation and being able to put things into Darwin without ever having to look at it and just review things later.

Man with crossed arms in from of panoramic sea coastal view

Ryan McMillan

Lead Data Engineer at CattleEye

Annotated data

Videos

Favorite Feature

API

Model Development Speed

10x

My favorite feature is the API because it automated everything for us. I like automation and being able to put things into Darwin without ever having to look at it and just review things later.

Man with crossed arms in from of panoramic sea coastal view

Ryan McMillan

Lead Data Engineer at CattleEye

Annotated data

Videos

Favorite Feature

API

Model Development Speed

10x

My favorite feature is the API because it automated everything for us. I like automation and being able to put things into Darwin without ever having to look at it and just review things later.

Man with crossed arms in from of panoramic sea coastal view

Ryan McMillan

Lead Data Engineer at CattleEye

Annotated data

Videos

Favorite Feature

API

The challenge

CattleEye monitors cows to give farmers insights on the herd’s overall health and detect behavioral anomalies or health issues of any individual cow.

The solution

CattleEye uses overhead security cameras to collect video data and annotate it using bounding boxes and V7’s keypoint skeleton tool. The goal is to monitor and understand cows’ behavior to build robust AI models that help farmers to act immediately when needed.

The results

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. This also saves 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. 

Furthermore, Darwin’s API has proven invaluable in helping CattleEye to automate their data upload process and save time.

Training data needs

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.

With the help of trained vets, the team focuses on annotating the extreme edge cases to improve the algorithms. Vets use V7 to label videos, add health scores and thus enrich the data to make algorithms more accurate.

Testimonial

Managing our data from one place is particularly important for us. Previously, our data was stored in many different formats and in different places. Having a single source makes our data more robust and also greatly reduces the development time for new algorithms, as the learning curve for developers is small.

Managing our data from one place is particularly important for us. Previously, our data was stored in many different formats and in different places. Having a single source makes our data more robust and also greatly reduces the development time for new algorithms, as the learning curve for developers is small.

Francesca Donadoni

Data Scientist at CattleEye

Why V7?

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 can now easily upload, store, organize, and manage their video data from one place.

Ryan added: “V7 is really easy to use, looks good, feels good. The other great thing is the customer support - bugs are fixed,  email support is very fast, and feature requests are delivered as promised.”