2020-09-24 22:33:23 -0600 | received badge | ● Notable Question (source) |
2018-11-29 23:15:06 -0600 | received badge | ● Popular Question (source) |
2018-11-20 02:17:47 -0600 | received badge | ● Notable Question (source) |
2017-09-12 13:02:45 -0600 | received badge | ● Popular Question (source) |
2017-04-10 09:05:08 -0600 | received badge | ● Nice Answer (source) |
2017-04-10 03:17:43 -0600 | received badge | ● Teacher (source) |
2017-04-09 17:04:27 -0600 | answered a question | Stereo Match of equirectangular panorama images Matching feature points directly won't work, as you've already discovered. There are two issues that you want to solve. 1) Use a narrower field of view. You can reproject pixels from the spherical map onto an image plane with a narrower fov. This would produce regular looking images on which you can use the standard feature matching techniques, computing the fundamental matrix, etc. You're looking for the inverse spherical projection equations for this. 2) Register the two panoramas. It is likely that the two panoramas are relatively shifted. Is the object at the left-most edge of the first panorama the same as in the second one? Hopefully this helps! |
2017-04-09 16:56:16 -0600 | asked a question | Going from homography to an image plane in 3D world coordinates I'm trying to recreate something like the Flash demo on this page. Computing homographies between image pairs is straightforward. I want to use the computed homographies to create a display like this using Viz. Any suggestions on how to go about doing this? Thanks! |
2017-04-09 16:14:09 -0600 | received badge | ● Scholar (source) |
2016-03-02 08:02:30 -0600 | received badge | ● Enthusiast |
2016-03-01 22:53:48 -0600 | received badge | ● Editor (source) |
2016-03-01 22:41:15 -0600 | asked a question | Passing an array of cv::GpuMat to a cuda kernel? I'm trying to write my own cuda kernel but I can't find a way to pass an array of Here is what I have until now: The compile error that the above snippet produces is: What's the correct way to pass an array of images to a cuda kernel? |
2016-02-21 09:28:09 -0600 | asked a question | Running into memory issues when using cv::cuda::sum I want calculate run https://gist.github.com/liquidmetal/9... Any help on how to fix this would be appreciated. I suspect I may be doing something wrong. |
2016-02-17 20:26:00 -0600 | commented question | Using cmake to find OpenCV version
|
2016-02-17 05:54:39 -0600 | received badge | ● Student (source) |
2016-02-17 00:43:48 -0600 | asked a question | Using cmake to find OpenCV version I'm trying to update the cmakefile for another project that depends on OpenCV. What's a good way to identify the correct OpenCV version across multiple platforms? I just need to figure out if OpenCV 3 is available on the current machine or not. Any hints or ideas on how to do this would be useful! Here's a summary of what I'm trying to accomplish:
I don't feel too good about running the shell command (locate, etc).. is there a better way to do this? |
2015-12-29 13:25:37 -0600 | commented question | Got Error Use of undeclared identifier 'ERStat' in XCode. This file seems to be missing from Github now. Was it removed from the project? |
2015-12-13 04:02:32 -0600 | asked a question | How do I find out if kmeans terminated because of iteration count or precision? Let's say I'm running kmeans on a dataset with a termination criteria on 100 iterations and epsilon of 0.01. Once the function returns, how do I find out which termination criteria was used to terminate the algorithm? |
2015-12-13 02:21:58 -0600 | received badge | ● Supporter (source) |
2014-11-17 08:50:22 -0600 | commented question | Has anyone tried doing mesh based image warping with OpenCV? If yes, how to do it? Did anyone find a way to do this yet? |