Edge Impulse Experts / AI-Based Mechanical Anomaly Detector (Camera) Public

AI-Based Mechanical Anomaly Detector (Camera)

Object detection
DFRobot FireBeetle 2 ESP32-S3 mechanical anomaly PCB industrial Twilio SMS

About this project

This object detection (FOMO) model detects specialized components (color-coded) representing defective parts causing mechanical deviations in a production line:

  • Red
  • Green
  • Blue

After building my object detection model, I deployed my model as a fully optimized and customizable Arduino library and uploaded it to FireBeetle 2 ESP32-S3. Also, I developed a web application from scratch to inform the user of the diagnosed root cause of the inflicted anomaly via SMS through Twilio.

home_9.jpg

home_10.jpg

Red_6
Green_14
Red_17
Blue_8
Blue_4
Blue_9
Green_13
Red_7

Run this model

Scan QR code or launch in browser

Dataset summary

Data collected
45 items
Labels
blue, green, red

Project info

Project ID 338236
Project version 1
License Apache 2.0
No. of views 7,149
No. of clones 0