One of the key motivations in setting up this blog was so that I could document the work on my Individual Project (part of my 4th year degree program at the University of Bristol). For this I am making a low-power, autonomous litter bin. This will use a Kinect (or similar device) to identify groups of people who would potentially generate litter and move towards them; avoiding crowds or moving people. While implementing this I intend to investigate low-power machine vision solutions in general and how the Kinect might be usefully leveraged in such an application.
The fundamental aims for my project are as follows:
- A low-power, Kinect-based, computer-vision solution.
- Real-time, autonomous decision-making.
- Robust, unobtrusive behaviour.
- Human behavioural analysis to intelligently detect potential litter generation.
From a hardware point of view I intend to use a Roomba (a robotic vacuum cleaner that has an API available to control it) as the wheeled-base for the project and a PandaBoard to perform the processing.
I shall update with more detailed information in the coming weeks.