Machines are looking for Michael Jackson

Today passes my 5th year of living and working in the UK... feeling in sort of a nostalgic/festive mood, did some cool VJing last nite and decided to spend semi-hangovery afternoon doing some (softcore) flashcoding. I got some good feedback and suggestions (thanks you know who) to my recent Terminator Salvation "machine vision" experiment and decided to explore that area a bit further.

This time I've managed to add "the real face tracking" ported from OpenCV by Masakazu "Mash" Ohtsuka (with some great optimizations by Quasimondo) to my video processing framework (codename HiSlope) which should be hopefully released within a couple of weeks (still need to do some important/major refactoring). Follow me on twitter.com/blog2t for updates.

So I was looking for some perfect video to use for testing... couldn't think of anything really. Then suddenly the spirit of Michael Jackson (RIP) came to me and whispered into my ear: "Black or white?" – and it was all clear then :)

Enough words, click the image to sing along.

Terminator Machine Vision plus Michael Jackson's Black or White mashup by Og2t

I found this video particularly challenging – with loads of head banging and different races (skin tones, facial hair etc.) – which actually makes a perfect source material for testing.

And again, I am really surprised by the final result – it's still not the fastest (I am getting 20 FPS in browser and about 35 FPS in standalone projector) but the main task is achieved.

The filters' settings were optimized for the video, so if you switch to the webcam mode you probably won't get your eyes detected (there's still a bit of work for me to do on it – that's why I am not releasing the sources yet), but do try to play with sliders, especially with HSBC (no, not the bank, it's Hue, Saturation, Brightness, Contrast) – enable it by clicking the checkbox on the left) and Eye Finder – enable debug and adjust blur and fuziness.

So, where's Michael? He's wandering somewhere in that black puma's outfit, fighting with racism. Watch out!

05:05 PM | | 13 Comments | Tags: , , , ,

Comments

  1. Very impressive Tomek - well done!

    Tom on

  2. nice work, although the webcam version doesnt work out very good for me. have you heard of the camshift algorithm? it's great: http://www.alexmil.de/face-tracking/

    alex on

  3. indeed impressive :) how do you catch the nose and the mouth corners ? very nice anyway, keep up !

    nicoptere on

  4. This looks pretty sweet and the swf file is only 142k. Congrats on your advancements!

    Jonathan on

  5. Fantastic work my friend, the most impressive use of the Open CV port yet in my opinion. Respect :)

    Rob McCardle on

  6. what ever happened to the idea of tracking chickens? g

    Good job!

    flashgordon on

  7. Hello, is this yours? http://www.flickr.com/photos/govan/134109327/sizes/o/ I'd love it as a desktop - any help? Ta

    Monty on

  8. Wow, that's amazing! I'm getting a pretty solid 47-50 FPS on a 3.0 Ghz Intel Core 2 Duo with 4GB of RAM on Windows XP. I wonder what kind of performance you'd get if you disabled all the visuals but still did the computations.

    Jackson Dunstan on

  9. Hey Tomek,

    You're almost impossible to contact. No email or contact form to be found on either your blog or portfolio.

    Can you please email me? I have some questions about one of your videos related to eye tracking.

    Thanks, Andrew

    Andrew McCloud on

  10. Hi Tomek, very impressive! I Am interested in using the HiSlope framework in my psychology research. Found your GITHub repo, are you planning on making the framework available there?

    Robin on

  11. Hi... im a Graphic Designer from Brazil.. and i´m starting a research to develop one interface for disabled people. Is there any chance to you share your eye tracking code? You´ll make it open source... my goals is to make a very cheap system for poor disabled people interact with the world. Thanx in advance. Cheers from Brazil, and keep up the good work!

    Gabriel himself on

  12. Simply awesome tech there!

    +1 to all of the above questions about the release? Any chance? Pretty please? =)

    Jussi Laakkonen on

  13. Great peace of work. When are you going to put it on google code? I'd love to play with the code

    Jeetu on