Never Lose Sight of an Animal.
Know What Is in Every Pen.
Continuous livestock intelligence for feedlots and researchers: reconcile pen counts, review cattle movement, and keep every animal closer to the people responsible for its care.
Installed and recording at Tuskegee University · Now enrolling commercial cattle feedlots
Our north star
Never lose an animal.
That promise is bigger than tracking. It is how we put our mission—grace, mercy, and stewardship over God's creation—into daily work: serve people well, help them see what needs care, and build technology worthy of the animals and land entrusted to them.
Grace
Serve producers, researchers, and partners with humility, honesty, and respect.
Mercy
Help caretakers notice what needs attention and bring useful evidence to the right person.
Stewardship
Treat animals, land, time, and data as things entrusted to our care—not resources to waste.
Built for Your Operation
The same platform, tuned to two very different jobs.
For FeedlotsRunning a feedyard?
Observed pen counts, movement exceptions, and visual identity evidence for feedlot operating teams.
Explore the feedlot platform
For ResearchersRunning a study?
Research-ready evidence exports, deployment planning, and collaborative study-design support.
Explore academic partnershipsCameras, pixels, observations, decisions
See how a camera view becomes something your team can act on.
Livestock Technologies uses computer vision, geometry, time, thermal values, and site rules to organize livestock observations. The person responsible for the cattle or the study stays in control of the decision.
- Documented field camera view01Capture
Cameras observe the operation
Fixed color and thermal cameras preserve time-stamped views of pens, gates, bunks, alleys, and the chute.
Computer-vision detection output02MeasureSoftware turns pixels into observations
Computer-vision models, geometry, time, and thermal values organize detections into count, presence, movement, and reference observations.
- Review requestedPen 4 · 6:20 AM
Observed count differs from the yard record
Expected
60
Observed
Review
Illustrative interface—not a reported field result.
03CompareSite rules surface what changed
Expected records and observed activity are compared so the team can focus on a pen mismatch, movement event, or identity review.
Source evidence ready
Review the moment, then choose the action.
- 1Open the source frame or clip
- 2Compare with the operating record
- 3Confirm, correct, or investigate
Illustrative workflow; deployment outputs are scoped to the site or study.
04DecideA person reviews the source evidence
The operator or researcher sees the relevant time, location, and source imagery before deciding what happens next.
Direct observations come from captured imagery and time. Counts, movement exceptions, identity associations, and study measures are produced through deployment-specific models, geometry, rules, and validation.
Designed for the field, not just the demo.
Livestock operations create changing light, weather, occlusion, limited bandwidth, and long stretches of video. Each part of the platform is designed around those operating conditions.
Lost in the dark. Standard color cameras lose useful detail when lighting changes.
Low-Visibility Coverage
Color and thermal capture extend evidence collection across day and night.
Weather outages. Poor camera placement and unprotected hardware create avoidable coverage gaps.
Livestock-Ready Deployment
Camera geometry, enclosures, and quality checks are designed for livestock environments.
Animals disappear. Animals hidden in crowded pens can create incomplete observations.
Occlusion-Aware Tracking
Quality controls surface obstructed views and coverage gaps for review.
Raw data dumps. Endless spreadsheets of numbers are difficult to evaluate in the moment.
Review-Ready Evidence
Plain-language review cues point people back to the observed behavior and source imagery.
Bandwidth throttling. Sparse snapshots can miss the context around a behavior change.
Edge Processing
Local processing reduces bandwidth needs while preserving higher-frequency evidence.
Cloud-only dependence. Connectivity limits can interrupt cloud-only evidence workflows.
Resilient Retention
Local storage and backups are designed to preserve reviewable evidence when connectivity is limited.
Identity Evidence at the Chute,
Measured Against Known Animals.
Nose ID is an active chute identity workflow: it captures face, muzzle, and ear-tag views, builds a reference gallery, and connects each passage to known animal records.
- Chute Identity ReferencesLink each chute passage to existing tags, manifests, and reference imagery.
- Research PartnershipsScope capture geometry, reference workflows, and evaluation with feedlots and research teams.
Adaptable Vision Research
The field platform is built around cattle, while multispecies and aquaculture projects are available to scope with research partners around the relevant data and operating workflow.
Which pen does not reconcile tonight?
Tell us your head count, pen layout, current inventory process, and the exception you need to catch. We'll define the right deployment footprint for your yard.
Grace in how we serve. Mercy in how we care. Stewardship over God's creation. Our mission.
Practical questions
How the monitoring approach works
- Does it work at night and in bad weather?
- Yes. Deployed nodes pair 4K color and thermal cameras and record day and night at Tuskegee, creating a field record for livestock operations.
- Do you track individual animals or just pens?
- The current platform provides pen inventory and movement evidence plus controlled-chute identity references. Passive open-pen re-identification is being evaluated.
- What about bandwidth constraints?
- Core processing and storage run on site, so the field platform can retain and review data without depending on continuous cloud transfer.
- How do you prevent data loss?
- The architecture centers on on-site compute and storage; deployment terms define access, retention, and backup for each installation.