Looks like there’s a gap in the market – partially filled

Posted: August 7, 2011 in Dissertation, Kinect
Tags: , , , ,

It’s three days since I somehow managed to get my KinectDTW project onto the SlashDot front page, and I’m still trying to get my head around the response. 220 release downloads and 60 grabbed the source from the repo. Ok, so far from Earth-shattering figures, but I think it shows healthy enthusiasm for what I’m trying to achieve here. That is to say I wanted to give people a tool to get them started with making their own Kinect-based gesture control systems.

I’ve had lots of feedback to, almost universally positive. And any detractors just don’t like Microsoft or the Kinect, nothing bad about the KinectDTW project itself. So the next challenge must be to become established in the community, rather than just a novelty factor. I’ve no idea how to do this, but I’ll work something out. A few well-placed links will be a good start, but then I will need to follow this up with improving the system, perhaps making it open-standards, and definitely by responding to feedback.

So if you’re yet to see it, check out KinectDTW.codeplex.com. It’s far from perfect, but that’s kind of the point: I’d love the community to pick this up and roll with it.

  1. paul Macefield says:

    HI Steve,

    wow it is all happening for you.

    Perhaps twitter if you haven’t already

  2. paul Macefield says:

    and make sure you patent your idea, seriously or at least register it with patent office

  3. Caddy says:

    just leaving you some feedback. i’ve been looking for random code samples for kinect stuff, (i’m also fucking about with kinect for my masters dissertation :) ) thougt it might be better if you used an sqlite db to hold the gestures, that way you can easily seperate them, and you’ll also know what point of data relates to what point on the skeleton at a glance, rather than just a bunch of numbers.

    cheers for Open sourcing this, and i hope everything goes well.

    • rymixxx says:

      Hey, thanks for the feedback. Yeah, DB is a wise move. I haven’t done this yet as frankly I’ve run out of time. I need to get cracking on the data collection and write-up part of my project, but it would be easy to do. Also, I used the file output just for ease of circulation within the community. When it comes to working with the data in real time, I think in-memory is the way to go. Whilst the computations are very simple, there are a lot of them, and you don’t want IO/queries to get in the way. Having said that, you could have thousands of different gestures (or versions of the same gesture). Performance would take a hit pretty quickly. But yeah, holding them in a DB is a good step.

      Also, as I said in the documentation for this, there are a million things to do to improve this, not least having variable length gestures, 3D gestures, tweakable parameters on a per-something basis (i.e. per gesture, per skeletal shape, per time). You could also hook this up into some sort of lookup tree to improve processing time (random decision forest, maybe?). Or perhaps only assess every n frame on the first iteration, then get into more detail as you home in on the intended gesture.

      But my ideas are bigger than a Level 4 Dissertation :) I need to realise when to stop…

      Good luck with yours. Steve.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s