Augmented Reality with OpenCV using Python

• Place the image of the surface to be tracked inside the references folder.
• On line 221 of src/ra.py replace 'marley_source.jpg' with the name of the image you just copied inside the reference folder.
• On line 232 of src/ra.py replace 'fox.obj' with the name of the model you want to render. To change the size of the rendered model change the scale parameter (number 3) in line 189 of src/ra.py by a suitable number. This might require some trial and error.
• Open a terminal session inside the project folder and run:
• pip install opencv-python
• pip install opencv-contrib-python
• python3 src/ra.py

• --rectangle, -r: Draws the projection of the reference surface on the video frame as a blue rectangle.
• --matches, -ma: Draws matches between reference surface and video frame.

If you get the message:

Unable to capture video

printed to your terminal, the most likely cause is that your OpenCV installation has been compiled without FFMPEG support. Pre-built OpenCV packages such as the ones downloaded via pip are not compiled with FFMPEG support, which means that you have to build it manually.