Python, YOLO and Kubernetes: Super-Vision for an Industrial Plant
summary
A Python-based computer vision system built with YOLO models and deployed on Kubernetes monitors a critical industrial machine at a Tenaris plant to prevent catastrophic incidents. The system is designed for real-world reliability, continuing to operate even during network outages, and the talk presents this production case study of AI applied to industrial safety.
AI-written summary · about
chapters (10)
- 0:00Project introduction
- 2:56Industrial context Tenaris
- 7:10Vision system requirements
- 10:20YOLO model development
- 13:08REST service and Kubernetes deployment
- 16:00Integration with real plant
- 19:11Latency optimization
- 24:09Defect detection at tip
- 26:03Lessons learned
- 27:54Q&A
related talks
22mBuild and Monitor Machine Learning Services in Kubernetes
42mAcross the Pond
21mAI, Embedded System and Robotics
04mYOLO in R
01h 14mFoundations of Object Detection from an Expert's Overview
26mMachine Learning Meets K8s
29mTeam Teardown: MLOps in the Cloud for IoT
29mOwned By Statistics: How Kubeflow & MLOps Can Help Secure...