Skip to content
πŸ‘•πŸ“· Wearable camera to recognize familiar faces.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
deep-learning-face-detection
docs
imagezmq
.DS_Store
MobileNetSSD_deploy.caffemodel
MobileNetSSD_deploy.prototxt
README.md
client.py
server.py

README.md

Setup

$ workon <env_name> # my environment is named py3cv4
$ pip install opencv-contrib-python
$ pip install zmq
$ pip install imutils

Hardware

  • 1x Raspberry pi zero
  • 1x Pi camera v2
  • 1x Huawei e3372 usb modem
  • 1x USB phone battery charger

Setup

  1. Configure modem with SIM card
  2. Set up Raspberry pi with camera using Motion to run when active and stream endpoint
  3. Set up OpenCV machine for analyzing video for faces

Active process

  1. Run camera and stream video to server that analyzes stream
  2. Identified faces stored as images and embedded
  3. Embedded faces added to DB
  4. Faces tagged with "session"
  5. If photo fits category, trigger alert

Links

Reference

Inspiration

Code

You can’t perform that action at this time.