ParkingProctor | Devpost

## Inspiration We were inspired by how much we hate parking at UF!

What it does

It uses computer vision and ultrasonic sensor technology to check when a car enters a parking lot. The 2 factor authentication allows us to have an insanely high level of accuracy so students can have confidence in our data.

How we built it

We built it using a webcam, arduino R3 UNO and an ultrasonic sensor as far as physical tech goes. For languages, we used c++ for the arduino, Python + Flask for the backend and React with Tailwind for the frontend.

Challenges we ran into

We ran into a lot of theoretical and in the moment challenges while creating this project. Here is a list of the main obstacles we overcame: running arduino code in VSCode, filtering camera output to only sense cars, slowing down the camera capture rate to speed up the program, tweaking the ultrasonic sensor to increase accuracy, merging the camera and ultrasonic data in flask, checking that the time signatures match on the camera/ultrasonic data, pushing images from our backend to our frontend.

Accomplishments that we're proud of

Accomplishments that we are proud of include building a website from scratch using Next.js, React, Typescript, and Chart.js. Backend wise we're really proud that we were able to setup the yolov8 model with our camera via opencv and ultrasonic arduino sensor to detect cars. This project truly felt like each of us were combining our skills to make something great.

What we learned

We learned about effectively managing and splitting up roles for a project in order to meet expectations and deadlines. Being able to fully execute an idea is something that was very fulfilling for all of us as a team. Increasing our proficiency in a pseudo-working environment gives us great experience for working on new projects and the development involved.

What's next for ParkingProctor

In the future we hope to actually set this project up in actual parking lots. We know it would work (it worked on every random car that drove by), the issue is that we don't have multiple webcams and arduino ultrasonic sensors to be able to do this on a large scale. If this project gains traction, maybe we'll expand it :).