Tyson Foods Uses AWS Panorama and Amazon SageMaker for Industrial Automation and Predictive Maintenance
Tyson Foods implemented a computer vision solution to automate chicken tray counting on packaging lines using AWS Panorama and Amazon SageMaker. The solution captures real-time video streams processed locally on AWS Panorama appliances, reducing bandwidth costs and latency, and enables real-time production insights. Model training involved Amazon SageMaker Ground Truth for image labeling and Amazon SageMaker for model training and deployment at the edge. The solution enhances production efficiency by providing timely feedback on inventory levels and allows planned expansion into predictive maintenance using vision-based anomaly detection.
- Organization
- Tyson Foods, Inc.
- Industry
- Manufacturing
- Location
- United States
- Published
- January 2022
Reported outcomes
Strategic outcomes
Primary read
Use case focus
Showing 3 of 3
- 1Industrial Automation
- 2Computer Vision
- 3Edge AI
- Developed a vision-based object detection system using AWS Panorama Appliance to process video streams locally, minimizing latency and cost.
- Leveraged Amazon SageMaker for training object detection models with labeled data from Amazon SageMaker Ground Truth, deploying optimized models on edge devices.
- Implemented a real-time dashboard visualization of production throughput via integration with AWS IoT Core, Amazon S3, and AWS Lambda.
- Improved production line efficiency by enabling precise, real-time inventory monitoring.
- Reduced network bandwidth costs by processing video data locally at the edge.
- Laid groundwork for predictive maintenance with planned deployment of anomaly detection on industrial equipment.
Architecture
The architecture uses AWS Panorama Appliance to collect video frames at intervals and process them locally. Images are labeled with Amazon SageMaker Ground Truth, models are trained on Amazon SageMaker, and application deployment involves containerized assets including model and inference scripts. Results feed into AWS IoT Core and Amazon S3 for visualization and monitoring.
Implementation partners1
Sources & evidence1
The same organization appears in newer AI deployment evidence.
- Same organization re-documented as recently as 2025.
Measures whether this deployment's public evidence persists — not whether the system is still in production.
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Was this useful?