Ask Your Question

Der Luftmensch's profile - activity

2020-03-23 18:16:56 -0500 commented answer HarrisCorner Detection in OpenCV C++

My bad, I know see GFTTDetector.

2020-03-23 13:24:01 -0500 commented question Type issues

You are pointing a cv::Mat header at 32-bit data and inpterpreting it as 16-bit. How is that going to produce sensible o

2020-03-23 13:23:17 -0500 commented question Type issues

You are pointing a cv::Mat header at 32-bit data and inpterpreting it as 16-bit. How is that going to produce sensible o

2020-03-23 10:25:02 -0500 commented question Type issues

A float is 32-bits. JPEG most likely cannot handle floating point images.

2020-03-22 19:51:01 -0500 commented answer HarrisCorner Detection in OpenCV C++

That function unfortunately does not return the response value of the features.

2020-03-22 09:06:55 -0500 commented answer HarrisCorner Detection in OpenCV C++

I see, then on the user to sort and perform non-max suppression. Interesting how there isn’t a Harris Features2D interfa

2020-03-21 10:17:30 -0500 commented answer HarrisCorner Detection in OpenCV C++

Do you know if OpenCV offers a function to return the response/score of Harris corners? This would be better than a list

2020-03-20 10:19:18 -0500 commented answer ORB keypoints distribution over an image

I've tried this method and it works great and is super fast. Highly recommended.

2020-03-06 09:38:49 -0500 commented question How to remove multiple hits on detection?

Look into non-maxima suppression or weighted fusion. You'll want to sort your results by response or score and then iter

2020-03-04 16:09:55 -0500 commented question Broadcast single channel to N-channels

cv::mixChannels()?

2020-03-04 16:03:48 -0500 asked a question Broadcast single channel to N-channels

Broadcast single channel to N-channels Is there an OpenCV function to take a single channel image and extend it to N-cha

2020-02-05 07:17:50 -0500 commented question How to run a for loop with vector<Point2f> type variable in GPU

Using a cv::cuda::GpuMat with thrust. You could also give ArrayFire a look.

2020-02-01 11:43:51 -0500 commented question OpenCV Exposure Compensation Without The Need To Stitch Images

The other option is to process overlapping tiles and then blend/merge/average the overlapping regions.

2020-01-31 14:40:35 -0500 commented question OpenCV Exposure Compensation Without The Need To Stitch Images

Also, please link to the StackOverflow post.

2020-01-31 14:39:25 -0500 commented question OpenCV Exposure Compensation Without The Need To Stitch Images

cv::hconcat? Those appear to be range images, why do you want to change the range values?

2020-01-08 08:37:58 -0500 commented question Jitter using ArUco marker

It depends on how small the markers are in your image and the viewing angle. Your measurements are noisy which is to be

2020-01-05 09:00:39 -0500 commented question Request: joint aka cross option for bilateralFilter

Are you asking for cv::jointBilateralFilter?

2019-12-12 11:41:52 -0500 commented question Calculating depth with Ptr<StereoSGBM>, black bar on image

The black bar is equivalent to your disparity search range. Those pixels cannot be searched for the entire range and so

2019-11-18 08:37:58 -0500 commented question How to apply a gaussian filter only to the borders of regions

Smoothing with a mask

2019-11-16 09:28:36 -0500 asked a question cv::Mat and cv::cuda::GpuMat containers

cv::Mat and cv::cuda::GpuMat containers I am writing a class that uses PLK optical flow and I want it to be able to use

2019-11-14 16:38:22 -0500 asked a question How to use cv::OutputArrayOfArrays with std::vector<cv::cuda::GpuMat>?

How to use cv::OutputArrayOfArrays with std::vector<cv::cuda::gpumat>? I am trying to write a build_pyramid routin

2019-10-24 06:40:41 -0500 commented question StereoBM CPU and StereoBM GPU versions on OpenCV give very different output.

Look at the source code and you'll see that many of those parameters are ignored. There is no L/R check on the CUDA vers

2019-08-30 16:44:07 -0500 edited question Brigthtness detecction

Brigthtness detecction I am working on a project to detect the brightness of an ID card. I am using OpenCV and C# to per

2019-08-08 19:42:51 -0500 commented question Parallel READ Access on Mats

cv::parallel_for_()

2019-07-11 11:01:03 -0500 commented question How to automatically find pattern size for Opencv Camera Calibration?

Why not loop? Start big and reduce until it works.

2019-07-09 10:50:47 -0500 commented question Speckle in disparity map

I meant it in the sense that it is a connected component that is small because it does not agree with neighboring pixels

2019-07-09 09:30:09 -0500 commented question Speckle in disparity map

cv::filterSpeckles()

2019-07-09 09:10:08 -0500 commented question Speckle in disparity map

The matching solutions are not perfect and the speckles likely represent bad matches. The algorithm is available to you

2019-07-02 06:47:59 -0500 commented answer GTK or QT when build OpenCV

You also avoid protobuf version issues when opting for Qt over gtk.

2019-06-20 06:40:49 -0500 commented question XYZ coordinates with stereo vision

And I see you added a new question. Next time consider editing/adding info to your original question.

2019-06-20 06:39:33 -0500 commented question XYZ coordinates with stereo vision

Fixing the principle point allows you to force cx and cy to be W/2 and H/2. This leads to more intuitive 3D coords. They

2019-06-17 06:58:34 -0500 commented question XYZ coordinates with stereo vision

As far as I know, the (x,y) pixel coords should be in the undistorted and rectified frame.

2019-06-15 08:37:07 -0500 commented question XYZ coordinates with stereo vision

Do cx and cy correspond to the center of your image or are they off-center? If substantially off-center, try calibrating

2019-06-14 10:21:24 -0500 commented question WLS filtering

See this example and consider reading the relevant papers: Fast Global Image Smoothing Based on Weighted Least Squares a

2019-06-13 09:04:05 -0500 commented question WLS filtering

The exposure/gain/wb looks different. If you have a static scene and a static camera, you can temporally filter your res

2019-05-08 17:18:03 -0500 commented question Camera calibration without Z component?

The chessboard is flat and the 3D coordinate system is relative to the chessboard, not the camera. So just imagine that

2019-04-29 13:06:11 -0500 commented question Fit ellipse with most points on contour (instead of least squares)

Try repeatedly calling the function after rejecting outliers? What you want is iteratively reweighted least-squares. cv:

2019-04-29 13:04:12 -0500 commented question Fit ellipse with most points on contour (instead of least squares)

Try repeatedly calling the function after rejecting outliers? What you want is iteratively reweighted least-squares.

2019-04-17 08:54:45 -0500 commented question Inverse Flow - Forward Warping or Bilinear "Splatting"

I now see that "frame interpolation" is a worthwhile search string. Estimating an intermediate frame given an optical fl

2019-04-16 12:45:19 -0500 asked a question Inverse Flow - Forward Warping or Bilinear "Splatting"

Inverse Flow - Forward Warping or Bilinear "Splatting" I am interested in the inverse or backward flow given the forward

2019-04-08 07:19:36 -0500 commented answer ORB keypoints distribution over an image

I've already copied, modified and ran the SSC code, just go ahead and use it, no waiting for OpenCV, or do a pull reques

2019-04-05 14:39:55 -0500 commented answer ORB keypoints distribution over an image

The algorithm in the answer above should be similar to the paper also listed in the answer (from 2016). The SSC method y

2019-04-05 14:10:17 -0500 commented answer ORB keypoints distribution over an image

The algorithm in the answer above should be similar to the Paper also listed in the answer (from 2016). The SSC method y

2019-04-04 08:55:28 -0500 edited question Error using calculLut and/or getMinMaxHistogram

Error using calculLut and/or getMinMaxHistogram int main(int argc, char** argv){ if(argc!=1){ usage();

2019-04-04 08:50:25 -0500 commented question i am working on django project for face recognition in which i use opencv library for face recognition.bt video frame is not showing into browser .it is showing in separate window frame .for that i used opencv.js..help me if anyone can.

Please read FAQ.

2019-04-04 08:48:21 -0500 commented question Error using calculLut and/or getMinMaxHistogram

You need to reduce this to the smallest possible code that throws the exception. What does reading 14 images have to do

2019-04-04 08:46:37 -0500 edited question Error using calculLut and/or getMinMaxHistogram

Hi evry body, I'm traying to read all images from a forlder by using this int main(int argc, char** argv){ if(argc!

2019-04-04 08:46:26 -0500 edited question Error using calculLut and/or getMinMaxHistogram

Hi evry body, I'm traying to read all images from a forlder by using this int main(int argc, char** argv){ if(argc!

2019-03-30 14:27:14 -0500 commented answer How to draw line with alpha transparency?

Use cv::addWeighted() to mimic an alpha channel. Draw on a copy of the original image and then do weighted addition of t

2019-03-28 10:37:13 -0500 commented question How to detect an object in an image using HOG Descriptors?

Just flip the rectangle image each direction and you're done!