metermaid-monitor

Avoidance, Awareness, and Prevention. Tensorflow, PiCamera, and Metermaids. A Citizen's lovestory.

The purpose of this project was to provide a cheap alternative to worry about parking. People who park in residential areas, especially in 2 hour limited parking will know the desire to park for as long as available. Normally what ruins that availability is the dreadful driveby of a metermaid Interceptor. With this set of tools, one can park their car, knowing that a notification will arrive via text message notifying them of a passing metermaid. This should mark their 'official' 2 hour parking time limit. As the metermaid should only be able to assume the car had just parked there.

We combined Tensorflow image classification with a raspberry pi motion detection and speed measuring program. The raspberry pi and PiCamera would be installed in the car. The camera would point towards the street and be configured to capture vehicles driving by. Cars are then classified using TensorFlow. Upon positive verification of a parking enforcement Interceptor, an SMS will be sent to the vehicle owner.

When Image is captured (moving car is in field of view), the image is sent for analysis to an instance running Tensorflow, with trained data. If image is a match, a message is sent via twilio with a link to the image for human verification.

PiCamera Car Monitor --> TensorFlow Classification --> SMS Message

  • Requires Installation of OpenCV 3.0.0 and Python3 and wifi-hotspot (for raspberry pi)
  • Tensorflow was ran in docker following this tutorial
  • Pictures were shamelessly downloadedfrom Google Images.

**This is a free, open-source project and the developers are in no_way accountable for parking tickets because of rebellious, citation-breaking citizens.

Special Thanks

Built With

Share this project:
×

Updates