Mission
Parking can be an absolute nightmare. We all have spent 45 minutes circling a lot struggling to find that one free spot, or finally realizing that there was no free spot to begin with. This wastes time and gas, further polluting the atmosphere and hurting the wellbeing of our ecosystems. Our goal is save time and prevent pollution by letting drivers know where available parking spots are.
Building the system
Mechanical:
A custom harness is created so a camera setup could be successfully mounted to an above ground object (such as a lamp post) in order to get a live feed of the parking lot. The harness was designed in SolidWorks and 3D printed.
​
Server:
The server takes in images sent by the Raspberry Pi via post requests. From there, it saves the image, reprojects it to have an even view of every spot in the parking lot, and classifies each parking space individually. Each parking space has an ID, so it can mark it as taken or free. It uses a Tensorflow model trained from Google Colab for predictions, OpenCV for image processing, and Flask to run the server.
​
Raspbery Pi:
The Raspbery Pi has a simple job: take pictures and send them. The pictures are taken using Motion (a terminal application) and sent to the server using Python. It uses a USB webcam to take the pictures.
