AGRICULTURE
Livestock Monitoring
Livestock Monitoring. What it takes to run it.
Health and activity tracking for herd management.
// 01 · The question
“Which animals are off their normal pattern today?”
// 02 · Why it is hard
Animals crowd, and they look alike. Holding an identity across a pen for long enough to say this one is off its pattern is a tracking problem before it is a detection one.
// 03 · What the labels have to be
Bounding box + keypoints
Decided before the first frame
Health flags come from posture and gait, not from presence. Keypoints on the spine and legs make lameness and abnormal standing measurable, which a box around an animal cannot express.
This is the decision that is expensive to reverse. The geometry has to match what the answer contains, and finding out it does not means labelling the set a second time.
// 04 · How we run it
Three parts of one loop, on this job.
LexAnnotate
Field Precision
Annotate crops, equipment, obstacles, and pathways with polygons, polylines, and semantic segmentation. Tag environmental factors like dust, shadows, and occlusions. 80k+ image annotations in production deployments.
LexInsight
Yield Intelligence
Transform plant-level detections into field-level intelligence. Map disease patterns across zones, track crop health progression over time, estimate yield from visual data.
LexAlert
Navigation Alerts
Monitor autonomous navigation models against seasonal drift. Retrain as fields change to keep navigation reliable through the seasons.
// 05 · What breaks it after launch
Barn cameras get knocked by equipment and by the animals themselves. The pen and the pattern are unchanged, but the geometry the behaviour baseline was learned in is not.
It is not the only one that can get this use case, it is the one that usually gets it first. All ten conditions.
// 06 · In agriculture
GPS-Denied Autonomy
The Challenge
Unreliable GPS under tree canopies and low visibility. Models failed in unstructured, obstacle-heavy terrains.
Our Execution
Annotated thousands of images with polygons and polylines. Tagged diverse environmental factors like dust, shadows, and occlusions.
The Result
Enhanced autonomy in GPS-denied environments. Faster deployment of AI-powered navigation.
80k+
Image annotations in production