Monthly Archives: November 2012

Progress Update

Over the past week or so I have acquired a Pandaboard to run the project on, and organised a Microsoft Kinect and an iRobot Create (a Roomba without the vacuum cleaner compartment) for the main components.

I have spent some time setting up the Pandaboard and installing an Operating System. I have opted to use an ARM desktop build of Ubuntu 12.04 for buycbdproducts time being as it is relatively straight forward to use and people have previously got a Pandaboard running it and interfacing with a Kinect via the open source drivers. As such I figured that while it is a fairly heavy-weight Operating System for the task in hand – especially from a performance/power-consumption point of view – it is a known working configuration and is a great place to start and learn the process of getting it working.

I have tried to install and run the drivers, however while installing one of the libraries the system crashed and eventually had to be manually restarted. This left it in a partially upgraded state which did not find my somewhat heavy-handed restoration attempt pleasing. I am now back to square one and need to reinstall Ubuntu on the SD card and try again.

Individual Project Overview

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.

Blog Update

As I mentioned in my previous post, I wasn’t happy with my, then current, theme, Gridiculous. The browser compatibility issues were the main problem, but I also wasn’t 100% happy with the theme itself.

Since then I have learnt quite a bit more about how themes in WordPress are written and I have subsequently written my own in the form of a child theme built on top of the twentytwelve theme. This has the advantage of both being a relatively plain theme (so easy to customize) and, having been written by WordPress themselves, a pleasure to modify. Since it’s a child theme it will update as twentytwelve is updated so it should be fairly robust. I was surprised at just how painless the whole procedure was: the bulk of the rewrite took me just 6 hours with a small amount of planning before hand and a bit of messing around uploading it afterwards. I’m very happy with the end result and feel far more comfortable editing these themes now so I should be able to fix any problems as they arise; as I’m sure they will!