Vision Docs
Here you will find documentation and tutorials relating to the vision subteam, which is responsible for computer vision related tasks.
What is Computer Vision?
The goal of the Computer Vision subteam is to create algorithms that detect obstacles and identify objects. We take image data from the camera and turn it into data that the flight team can use. The flight team uses the data we give them to make decisions.
What technologies do we use?
The computer vision subteam uses two main Python libraries: NumPy and OpenCV. NumPy provides contiguous memory arrays that are much faster than Python’s List type. OpenCV provides computer vision functions that are built in C++ (faster than Python).
The computer vision subteam uses additional libraries and technologies, such as Pytesseract (text detection) for more specific use cases.
Where should I start?
To start, check out the documentation and tutorials on NumPy. Then, move on to OpenCV. You can also check out other libraries we use and vision code from past competitions below.
In the categories below, you will find documentation, tutorials, and practice projects to help you learn computer vision.
You should also make sure you have the following packages installed: numpy, opencv-python, scipy, matplotlib, pytesseract.
Reminder that packages can be installed with the following command:
Linux:
pip3 install <package_name>
Windows:
pip install <package_name>