Skip to content

I'm taking part in the EPFL Robotics Competition. We must build an autonomous robot from scratch that recognizes all types of bottles, catches them, and then bring them to a recycling bin. One of my responsibilities is the bottles recognition.

License

Notifications You must be signed in to change notification settings

Apiquet/Visual_recognition

Repository files navigation

Visual recognition

Project: https://apiquet.com/2019/06/02/visual-recognition/

DESCRIPTION:

You can find here the code I used for the EPFL (Ecole Polytechnique Fédérale de Lausanne) Robotics Competition. I had to build a standalone robot from scratch which recognizes any kind of bottles, catch it, then bring it to a recycling bin. It must overcome obstacles like rocks, take ramps, run over grass, etc.

I'm in charge of the collector (front of the robot to catch and store bottles), the bottle storage, the bottle recognition and the triangularization of the robot's position and orientation through a beacon. This repository is for the bottle recognition and the position triangularization. You can find them under bottle_recognition folder and beacon folder.

For the bottle recognition part, I tried several techniques such as the Python lib ImageAI, OpenCV filtering and ML approaches with an Haar Cascade. You can find it in the Jupyter notebook called main under the bottle_recognition folder.

Some results for the visual recognition part:

Set up of the homemade beacon on the robot:

About

I'm taking part in the EPFL Robotics Competition. We must build an autonomous robot from scratch that recognizes all types of bottles, catches them, and then bring them to a recycling bin. One of my responsibilities is the bottles recognition.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published