Maintenancedemo-0015

Computer Vision Quality Inspection

Camera inspects products for defects in real time. YOLO detection plus a vision language model provides pass/fail verdicts with natural language defect descriptions.

gpucomputenvidiahpaihpzgxn001in-progress

Not available to book

This demo is under maintenance and cannot be booked. It will reopen once its owner marks it ready.

Watch lab overview (21 sec)
Run Count0
Student MaterialsPublic Repo
Admin / CI-CDPrivate Repo

Lab overview

No walkthrough is recorded for this demo yet, so this is a 21 sec tour of the lab and how to use it.

Trouble playing? Download the file.

Overview

A two-stage inspection pipeline: YOLO runs at frame rate for fast object detection, while a vision language model (LLaVA) provides detailed defect analysis every 2 seconds with natural language descriptions of what's wrong.

What You'll Learn

  • Computer vision for manufacturing quality control
  • YOLO object detection + vision language model pipeline
  • Reference image comparison for defect detection
  • Real-time inspection statistics and pass rate tracking

Key Capabilities

  • Real-time PASS/FAIL/REVIEW verdicts with confidence scores
  • Natural language defect descriptions (not just labels)
  • Reference image upload for comparison-based inspection
  • Inspection statistics dashboard with pass rate tracking
  • Image upload mode for offline inspection