This was a project implemented by Ian Stähli and Miro Voellmy as a semesterthesis at Prof. Otmar Hilliges Advanced Interactive Technologies Lab at ETH Zurich from 03/17 - 07/17.
The goal of the project was to implement a pipeline which can estimate the state of the stove top and its objects such as the operator, the pans, the tools, the plates and the food.
The project contains a 'gesture_recognizer.py' and 'food_recognizer.py' class which make up the main part of the pipeline. They are used to identify the actions of the cook as well as the pan and the food within the pans.
Results of running the main pipeline can be found here:
Implemented with Python 3 and OpenCV 3.