The Car Catcher project hunts down missing cars or cars involved in a criminal investigation. It is designed to track down any car based on a description of it and its license plate.
Inspiration: Amber Alerts seem to happen once every two weeks and every time I see one, I wonder why police have the description of a car but were still somehow unable to track down a suspect.
What it does: This app is going to be integrated with a drone to identify wanted cars based on their description and license plate.
How I built it: I built it by utilizing the many Google Cloud Vision API tools. This API has pretrained image recognition models that can identify anything with a scary level of accuracy.
Challenges I ran into: Google Vision API's documentation is made for beginners and it is difficult to break down all the features and attributes of every function in the API. Furthermore, it recognizes very abstract details and it was up to me to piece them all together.
Accomplishments that I'm proud of: I'm proud of being able to figure out how to use Google API for the first time and understand and use it pretty well. I'm also proud of coming up with what I believe to be a decent idea on my own.
What I learned: 2 hours of sleep go a long way to helping your thinking.
What's next for Car Catcher: The next step is to program it to parse real time data from maybe a phone camera. Then it will be time to make it actually work with a camera mounted on a drone and create a user friendly interface to make it easy to use.
Log in or sign up for Devpost to join the conversation.