Success case
Edge AI at the farm: precise livestock management helps farmers optimize livestock productivity.
The livestock industry is huge, however, several issues impede its productivity, such as the soaring
- Industry
- Livestock & Aquaculture
- Application
- Livestock growth and behavior monitoring
- Results
- 98% Per-animal management cost reduction
Project background and needs
Intflow in Korea uses on-site cameras and reComputer edge AI devices to help farms continuously track pigs' eating, movement, weight, and health status.
Manual management workload
- Precise breeding is constrained by human workload.
- Farms need to track eating, movement, fighting, and weight gain.
Needs to continuously obtain individual animal status.
Tracking in dense scenes
- Real-time tracking of many pigs requires substantial computation.
- Livestock farms commonly have densely packed animal scenes.
Needs animal-optimized detection and identity tracking.
Solution and architecture
On-site capture and inference
IP cameras connect to reComputer J1010, which performs on-site object detection, ID tracking, and behavior recognition.
Data and management
A TensorRT-optimized model runs on Jetson Nano, and biometric data is uploaded through the EdgeFarm database to the cloud dashboard and app.
Solution components
See the solution in action
On-site gallery (2)
Discuss your application with our team
Tell us about your requirements and deployment environment.