Efficient Keypoint Matching in Image Streams <3ms computer vision

i just want to present some additional videos showing our realtime image correspondence algorithm.
the GPU time for ~2000 correspondences on a 752x480 image is 2.7ms with a tesla c1060.
note it’s not KLT tracking.

http://www.youtube.com/watch?v=OFfynOWVkwg

http://www.youtube.com/watch?v=rhg9KsogWWU

http://www.youtube.com/watch?v=McpZmuJbg-k

Nice! Do we get to see the source code for this? What algo was mapped onto the GPUs?

This is the vehicle they use for testing. The VW Touareg, not the Wolf leading it ;)

http://www.deutschesheer.de/portal/a/heer/…E%2Fcontent.jsp

By the way, this research is done at the university of the German defense forces in Munich.

My take is: No, you won’t get to see the source code. ;)

Christian

Do we atleast get to know the algo? Have they published this anywhere? :mellow:

of course it’s published:
[Efficient Keypoint Matching for Robot Vision Using GPUs, ICCV09/ECVW]
see computervisioncentral.com

source code is going to get provided, but currently unclear in which form and licence.

greets,
moik

direct link for the lazy http://computervisioncentral.com/sites/all…09/AW-9-007.pdf

About the source code: Great news!

@cbuchner1: thanks for the link :)

@mikemoik: thanks a lot for the great news about the source code. Eagerly waiting for the moment!! :rolleyes: