Finding Street Parking in Downtown is now easier
Everyday so many people in Detroit or in fact any major city struggle with finding cheap street parking in downtown area. Now street parking is much better than parking garages as it is cheaper and in fact even free after certain hours in the evening. I wanted to make the openly available data of street parallel parking spots available to the masses
What it does
So the idea is to hookup a camera on the side of a bus. The reason I chose a bus is that they frequent a lot in the downtown area and cover most of the hotspot commercial area streets where people end up looking for parking. So my camera on the bus clicks an image of the curbside and processes it my algorithm written using Microsoft Computer Vision API under Microsoft Cognitive Services, to detect which spot has a car and which is empty. This data is transmitted to an iOS app which has a layout of the street. Based on the data, the parking spots on the screen turn red or green.
How I built it
I built the backend using Microsoft Computer Vision API under Microsoft Cognitive Services using python and Flask. I wrote the fronted using swift and made an iOS app that fetches the data from the Flask REST API to present information about parking to the user
Challenges I ran into
So a few hours into hacking, my team members decided to leave my team as they were called by their friends to join their team. So I was left alone with this idea which was challenging to execute. Instead of freaking out as I didn't know frontend iOS development, I challenged myself to learn iOS and make the interface for the app
Accomplishments that I'm proud of
I overcame the challenge of not knowing iOS development and made my first iOS app today, that actually even fetches data from a REST API and updates on the fly. Being able to single handedly finish all of this under time is something I am extremely proud of
What I learned
I learned how to use Microsoft Computer Vision API and learned iOS development and made my first ever iOS app
What's next for Park With Me
Gathering data from the parking spots and after a significant amount of data has been collected, predict availability of parking spots based on time of the day and the day of the week.