Comments on: Outdoor tracking using panoramic image http://www.visual-experiments.com/2010/12/22/outdoor-tracking-using-panoramic-image/ ASTRE Henri experiments with Ogre3D and web stuff Tue, 22 Aug 2017 10:32:15 +0000 hourly 1 http://wordpress.org/?v=3.1.2 By: Reena http://www.visual-experiments.com/2010/12/22/outdoor-tracking-using-panoramic-image/comment-page-1/#comment-65869 Reena Fri, 14 Mar 2014 06:34:09 +0000 http://www.visual-experiments.com/?p=1167#comment-65869 I wanted to know how you gave the input in sift->RunSift() as I wanted to know how you gave the input in
sift->RunSift() as

]]> By: Reena http://www.visual-experiments.com/2010/12/22/outdoor-tracking-using-panoramic-image/comment-page-1/#comment-65862 Reena Fri, 14 Mar 2014 05:41:03 +0000 http://www.visual-experiments.com/?p=1167#comment-65862 Hi I was wondering if I could refer your code cause I too am trying to extract videos from .avi file using SiftGPU but i have some problem with the arguments while processing Hi I was wondering if I could refer your code cause I too am trying to extract videos from .avi file using SiftGPU but i have some problem with the arguments while processing

]]> By: Alessandro http://www.visual-experiments.com/2010/12/22/outdoor-tracking-using-panoramic-image/comment-page-1/#comment-8340 Alessandro Wed, 16 Nov 2011 23:59:30 +0000 http://www.visual-experiments.com/?p=1167#comment-8340 Very impressive! I'm also playing with opencv but It took me a lot more to do a lot less =(. Very impressive! I’m also playing with opencv but It took me a lot more to do a lot less =(.

]]> By: 2010 visual experiments » Visual-Experiments.com http://www.visual-experiments.com/2010/12/22/outdoor-tracking-using-panoramic-image/comment-page-1/#comment-2003 2010 visual experiments » Visual-Experiments.com Fri, 07 Jan 2011 16:01:41 +0000 http://www.visual-experiments.com/?p=1167#comment-2003 [...] Outdoor 2D tracking using panorama image [...] [...] Outdoor 2D tracking using panorama image [...]

]]> By: admin http://www.visual-experiments.com/2010/12/22/outdoor-tracking-using-panoramic-image/comment-page-1/#comment-1825 admin Wed, 22 Dec 2010 14:48:02 +0000 http://www.visual-experiments.com/?p=1167#comment-1825 @Pierre: if you build the pyramid of the input frame and run Agast/Fast on each level you can be scale invariant. But this is not needed for this type of application. As you said the user need to be placed near the center of the reference panorama and the augmented object need to be far from the user (no parallax, otherwise the simple homography applied won't work). The rotation invariance however was more problematic, but as the mobile has accelerometer you can compensate the rotation of the input frame before BRIEF descriptor computation, thus you should be rotation invariant. The project I'm working on will use the GPS to select the reference panorama so I don't really need to have heavy BRIEF matching across different panorama. But BRIEF is indeed a very lightweight descriptor that is both very fast to compute and match! @Pierre: if you build the pyramid of the input frame and run Agast/Fast on each level you can be scale invariant. But this is not needed for this type of application. As you said the user need to be placed near the center of the reference panorama and the augmented object need to be far from the user (no parallax, otherwise the simple homography applied won’t work). The rotation invariance however was more problematic, but as the mobile has accelerometer you can compensate the rotation of the input frame before BRIEF descriptor computation, thus you should be rotation invariant. The project I’m working on will use the GPS to select the reference panorama so I don’t really need to have heavy BRIEF matching across different panorama. But BRIEF is indeed a very lightweight descriptor that is both very fast to compute and match!

]]> By: Pierre http://www.visual-experiments.com/2010/12/22/outdoor-tracking-using-panoramic-image/comment-page-1/#comment-1821 Pierre Wed, 22 Dec 2010 13:53:00 +0000 http://www.visual-experiments.com/?p=1167#comment-1821 If you use AGAST/FAST you will not be scale invariant anymore... So you must be near the place where the panorama was taken in order to make the things match. But it could be sufficient ! I'm curious to see what can BRIEF can give in such a application. And matching with many panorama for sure to see if the system could scale to large database ! If you use AGAST/FAST you will not be scale invariant anymore… So you must be near the place where the panorama was taken in order to make the things match. But it could be sufficient !

I’m curious to see what can BRIEF can give in such a application. And matching with many panorama for sure to see if the system could scale to large database !

]]>