Ask Your Question

adrians's profile - activity

2017-12-05 05:26:44 -0500 received badge  Famous Question (source)
2016-03-16 09:17:17 -0500 received badge  Notable Question (source)
2015-07-21 10:56:01 -0500 received badge  Nice Question (source)
2015-07-21 10:55:56 -0500 received badge  Popular Question (source)
2014-04-30 03:21:19 -0500 answered a question problem with light reflection

If the area is not completely white or black, converting the image from RGB to HSV or HSL and then ignoring the Saturation or Lightness channels might be a solution, because now the image is invariant to "whitening".

2014-04-30 03:14:41 -0500 commented answer Calculating motion/movement energy/difference

After reading a bit more about kinect integration, I see that you can get a matrix which contains depths (one channel) instead of colors.

You can try to apply an optical flow algorithm on a depth-matrix instead of a colour-matrix. (and maybe add some image filtering - smoothing, eroding, to remove the noise/background elements)

2014-04-29 17:26:54 -0500 answered a question OpenCV Shape Module - How to Install

AFAIK the shape module will be released with OpenCV in the 3.0 version.

Until then you could try to compile and install the development version available in the "master" branch of the github repository, because there's the "shape" module. Be aware that the repository contains development versions, and these may or may not be stable enough.

To compile from sources there's some documentation. For linux I can assure you it's a simple process (cmake . && make && sudo make install), but for windows I don't know.

2014-04-29 16:58:36 -0500 answered a question Calculating motion/movement energy/difference


It seems that you want to compute the optical flow on an image.

I don't know if the depth data from the kinect can be integrated in the computation, but the 2d color images should be enough.

Have some references

2013-07-31 06:46:28 -0500 received badge  Scholar (source)
2013-07-31 06:46:10 -0500 received badge  Supporter (source)
2013-07-31 01:10:25 -0500 received badge  Student (source)
2013-07-30 14:52:40 -0500 asked a question open-source NEON optimizations

Hello !

I saw in the ICVS materials that there would be an open-source code for the NEON optimizations for the OpenCV library (maybe in the 3.0 release), but at the moment it's uncertain.

I want to know more about that because I'd like to present what effect does the optimization level (prefetching, vectorizations, etc.) have on the runtime performance of computer vision algorithms on embedded platforms, and if the optimized versions are not available I'll have to write them myself (but that would contain only a few operations so that a working demo could be done and the statistics be gathered).

I'd like to mention that I'll be using an dev board with an ARM Cortex A8 core (with Mali400 GPU but I'm not aiming for using GPU).

Thanks a lot!