The point of this project is to demonstrate the advantages and disadvantages of 2D recognition and how it can be used to warn drivers about obstacles or other dangers. We created a prototype model to test this idea in the real world and identify areas for improvement. Since this is simply a proof of concept, we manually adjust the OpenCV thresholds to account for specific lighting conditions. We hope that this project will serve as a stepping stone to help us improve when testing other ideas. Projects like these also help educate the public about new safety concepts and encourage them to think about their thoughts on this project.
CollisionTech
The point of this project is to demonstrate the advantages and disadvantages of 2d vehicle localization with vison and how it can be used to operate robots or warn drivers.
Updates
Sorry about the Youtube video! Just realized I only screen recorded my Visual Studio Code. The code is available on github for those interested.
This project is originally designed to be a robotics system with 2d localization of a robot and cargo. Unfortunately, we can not get the communication pipeline to work in time. But we've created a working API in the process. At last, we switched to remote control and converted to an obstacle warning program under the view of a webcam.
Log in or sign up for Devpost to join the conversation.
Leave feedback in the comments!
Log in or sign up for Devpost to join the conversation.
Log in or sign up for Devpost to join the conversation.