Skip to content

Latest commit

 

History

History
61 lines (42 loc) · 1.43 KB

readme.md

File metadata and controls

61 lines (42 loc) · 1.43 KB
Raw

Repository for Car Plate Reader

The scripts contained herein are meant to process the videos and images from public cameras (or cameras in public transport) to find A-lane or other statically identifiable violators.

Process and components

cpr-flow
Edit this diagram

Server API

Install

Tested on Ubuntu 14.04

Using vagrant

vagrant up
vagrant ssh

# inside vagrant
cd /vagrant

Manual install

# install Ubuntu's ffmpeg fork - libav
sudo apt-get install libav-tools

# install openalpr (https://github.com/openalpr/openalpr#binaries)
wget -O - http://deb.openalpr.com/openalpr.gpg.key | sudo apt-key add -
echo "deb http://deb.openalpr.com/master/ openalpr main" | sudo tee /etc/apt/sources.list.d/openalpr.list
sudo apt-get update
sudo apt-get install openalpr openalpr-daemon openalpr-utils libopenalpr-dev

# install openalpr python2 bindings
sudo apt-get install -y python-openalpr

Test openalpr

wget http://plates.openalpr.com/ea7the.jpg
alpr -c us ea7the.jpg

wget http://plates.openalpr.com/h786poj.jpg
alpr -c eu h786poj.jpg

Helpers

Converting video stream to PNG images

# if you've installed libav-tools, ffmpeg == avconv
ffmpeg -i /path/to/video.avi -vf fps=1 out/%d.png