https://github.com/alvarowolfx/gcloud-iot-edge-tensorflow

Asset Tracking using Edge Computing and Computer Vision.
https://github.com/alvarowolfx/gcloud-iot-edge-tensorflow

computer-vision edge-computing google-cloud platformio tensorflow

Last synced: 15 days ago
JSON representation

Asset Tracking using Edge Computing and Computer Vision.

• Host: GitHub
• URL: https://github.com/alvarowolfx/gcloud-iot-edge-tensorflow
• Owner: alvarowolfx
• Created: 2018-12-27T21:33:21.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2022-12-15T22:12:18.000Z (about 2 years ago)
• Last Synced: 2024-04-14T15:19:43.313Z (10 months ago)
• Topics: computer-vision, edge-computing, google-cloud, platformio, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 27.9 MB
• Stars: 34
• Watchers: 7
• Forks: 14
• Open Issues: 4
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Asset Tracking using Edge Computing and Computer Vision.

A bunch of ESP32 with camera, a local server (probablye a raspberry pi ) running image classification and object detection using Tensorflow and sending the data to 

processed data to Google Cloud.

[Work in Progress]

### Upload firmware with PlatformIO

Open `esp32-camera-firmware` folder on PlatformIO. Now the firmware have support for two models of esp32 with camera:

* ESP32 Cam from M5 Stack 

* ESP32 Cam from SeedStudio

Depending on your model, change on the platformio.ini file the `env_default` configuration depending on your board (`m5cam` or `esp32cam`). Also you need to change the Wifi credentials on the `sdkconfig.h` file ( `CONFIG_WIFI_SSID` and `CONFIG_WIFI_PASSWORD`). 

Then click on upload to flash the firmware into the board.

### Run server edge node

The server was written using NodeJS, Tensorflow.js library and the CocoSSD model to detect objects on the image.

Run the following commands inside the `edge-server` folder to setup the server:

* Install dependencies:

    * `npm install`

* Run server:

    * `npm start`

* Open `localhost:3000` to see the UI

### Google Cloud Setup

[Work in Progress]