Ask Your Question

Tetragramm's profile - activity

2017-10-21 12:25:53 -0500 commented answer Projecting points using OpenCV

Ah, I see. You are passing in an rvec and tvec into projectPoints, but you never modify the pointsTransformed3d. So if

2017-10-21 11:35:37 -0500 commented answer Projecting points using OpenCV

No, because I can't calibrate your camera for you. Re-calibrate the camera using the opencv functions like in THIS TUTO

2017-10-20 16:31:29 -0500 answered a question Projecting points using OpenCV

Ok, Obvious thing is you're doing something weird with the camera intrinsics. You've definitely done that wrong. The

2017-10-19 20:52:40 -0500 answered a question Matrix exponential

Nope. OpenCv has only basic support for matrix operations. Most of what it does support is actually implemented with E

2017-10-19 17:36:41 -0500 commented answer solvePnPRansac gave unstable results (has video)

Well, step 2 doesn't matter which two cameras, or whether they are tracked, so just use the ones you are using. The viv

2017-10-18 23:51:53 -0500 edited answer solvePnPRansac gave unstable results (has video)

This is an answer because it's so long. Those videos are listed as unavailable. Wait, so those are Vive tracking pucks

2017-10-18 23:45:30 -0500 commented answer solvePnPRansac gave unstable results (has video)

See the EDIT in the answer, it got long again.

2017-10-18 22:44:22 -0500 commented question Projecting points using OpenCV

Got some sample input that we can run through?

2017-10-18 22:40:38 -0500 answered a question solvePnPRansac gave unstable results (has video)

This is an answer because it's so long. Those videos are listed as unavailable. Wait, so those are Vive tracking pucks

2017-10-17 22:16:50 -0500 edited question How can I get the result described in the tutorial

How can I get the result described in the tutorial Hi ,dear, I want to calibrate omnidirectional camera,and rectify the

2017-10-17 22:15:50 -0500 edited question How can I get the result described in the tutorial

How can I get the result described in this tutorial,https://docs.opencv.org/trunk/dd/d12/tutorial_omnidir_calib_main.htm

2017-10-17 20:42:37 -0500 commented question solvePnPRansac gave unstable results (has video)

Can you try drawing the axes on the video? The ArUco module has a function for that HERE. It is possible for more than

2017-10-16 18:14:55 -0500 answered a question 0 running time in GPU methods

Make sure you're calling waitForCompletion between each method call. CUDA methods are asynchronous and can return immed

2017-10-16 17:56:10 -0500 commented question Why self compiled Opencv is slower than apt-get package?

Two things. I notice you have OpenCL disabled. That could do it. Secondly, they use the NVIDIA HAL called carotene.

2017-10-15 14:44:23 -0500 commented question Why self compiled Opencv is slower than apt-get package?

Actually, tomasth is correct. Can you edit your question with the getBuildInformation() from both versions? There shou

2017-10-14 16:58:37 -0500 commented question Why self compiled Opencv is slower than apt-get package?

What flags did you compile it with? Did you make sure to include all the optimizations your processor can use?

2017-10-14 13:31:02 -0500 commented answer Should the execution time change when I am running MOG2 extractor on image in GPU?

Yes. Now, for many algorithms, the GPU is faster than the CPU, so that's good. Also, there are many things that can sp

2017-10-14 13:20:36 -0500 answered a question Should the execution time change when I am running MOG2 extractor on image in GPU?

Ah, berak? https://docs.opencv.org/3.3.0/df/d23/classcv_1_1cuda_1_1BackgroundSubtractorMOG2.html As to your question,

2017-10-13 21:04:53 -0500 answered a question What does this specific matrix constructor does?

That constructor is the same as doing Mat roi = mask(rectant); Each iteration of that loop sets a new rectangle to C

2017-10-11 18:07:32 -0500 answered a question Feret diameter

You can indeed submit it as a pull-request, but make sure it does something more than already exists in functions like b

2017-10-11 18:02:09 -0500 commented answer Get coordinates of the projection point depending of the angles do the Camera

I do mean "make the camera the central point of the referencial", and yes tvec is the position of the camera. You don't

2017-10-10 20:51:31 -0500 commented answer Get coordinates of the projection point depending of the angles do the Camera

Ah hah. projectPoints apparently doesn't like such large numbers. If you subtract the tvec from both it, and all the w

2017-10-10 20:46:15 -0500 commented answer Hard to calibrate long focal length lens, result is very poor

Ah, but is that 40mm +/- 2mm, or is that 40mm +/- 0.1mm? A 2mm error is more than enough to cause the difference you ar

2017-10-10 17:56:19 -0500 answered a question How to calibrate two cameras whose field of View is 180 deg apart

The easiest way involves another camera. First calibrate the camera intrinsics for all three really well. Then get two

2017-10-10 17:37:30 -0500 commented answer Hard to calibrate long focal length lens, result is very poor

How precise are your measurements of the printed chessboard? The actual physical dimensions? If your board is printed

2017-10-08 23:02:28 -0500 answered a question Whats the equivalent of put(in java) for opencv c++?

To answer all your basic questions, check out the tutorials HERE. Both .get and .put are, in c++, .at< type >().

2017-10-08 17:42:23 -0500 commented question Image subtraction weird effect

Ok, things to check. You're doing absdiff into the Mat foregrounds, and the threshold on a Mat called foreground. Is t

2017-10-08 15:15:32 -0500 commented question Image subtraction weird effect

That... might be correct. It looks like that's a transition between two scenes in a video. Look at the grid on the flo

2017-10-08 15:13:43 -0500 commented question stereocalibration Qs

I think the problem is probably with getOptimalNewCameraMatrix. The distortion near the edge is enough to make it "fold

2017-10-06 23:02:04 -0500 commented question VideoCapture returns black image, when linked with tensorflow lib

Can you make a really simple program that does the same thing? That we could test? Try to make it as small as possible

2017-10-06 19:06:43 -0500 commented answer Get coordinates of the projection point depending of the angles do the Camera

Ah, I see the problem. Your eulerAnglesToRotationMatrix is going into the wrong coordinate system. OpenCV uses a syste

2017-10-04 19:13:56 -0500 answered a question 'Mapping' Aruco markers?

So you find the rvec and tvec to each marker. Let's say A and B. So you know where the camera is relative to each marke

2017-10-03 17:35:51 -0500 commented answer Get coordinates of the projection point depending of the angles do the Camera

I think I need a picture to understand what you mean by "all in the same place". One thought though, your get_camera_m

2017-10-02 18:04:31 -0500 answered a question Get coordinates of the projection point depending of the angles do the Camera

You want to use the function projectPoints as it does everything you want. You pass in the 3d world points you want pro

2017-10-02 17:54:07 -0500 answered a question opencv triangulatePoints() giving NaN values

So I didn't have an problems, using the latest version. Only very small errors, e-5, and e-6. Are you sure you are pas

2017-09-30 10:38:06 -0500 edited answer Hard to calibrate long focal length lens, result is very poor

I suggest using an ARUCO chessboard (ChARUCO). That gives you a bit of tolerance if you slide out of the field of view,

2017-09-30 10:34:40 -0500 answered a question Hard to calibrate long focal length lens, result is very poor

I suggest using an ARUCO chessboard (ChARUCO). That gives you a bit of tolerance if you slide out of the field of view,

2017-09-29 17:37:45 -0500 commented answer Feature extraction for dynamic gesture recognition classification

Ah, well that's not what your question was, was it? Start a new question, with details about what you're doing, why you

2017-09-28 19:23:31 -0500 answered a question Feature extraction for dynamic gesture recognition classification

OpenCV has no facilities for training a neural network. I suggest taking a look at one of these pieces of software. Go

2017-09-28 18:02:00 -0500 answered a question What is solvePnP() exactly for? (while i already have the projection matrices P)

You don't. You would use solvePnP to get the location of a camera relative to a set of points already known by some oth

2017-09-27 17:59:37 -0500 commented question Multiple imshow windows without needing waitkey in same function

Make what general enough? OpenCV allows you to access the data, which means you can interface with just about every GUI

2017-09-26 21:45:04 -0500 commented question Multiple imshow windows without needing waitkey in same function

Whatever the appropriate GUI framework is. I don't actually ever use one, for pretty much the same reasons as berak. Y

2017-09-26 18:30:15 -0500 commented question opencv triangulatePoints() giving NaN values

I'm not sure what's wrong with triangulate, but you can try using THIS module, which can handle more than two cameras.

2017-09-26 18:25:21 -0500 commented question Multiple imshow windows without needing waitkey in same function

I will also point out that imshow is not a particularly efficient display method. If you really need to display things

2017-09-25 20:53:54 -0500 answered a question Remove small objects from binary image

You want the morphology operations. Much faster than connectedComponents.

2017-09-25 19:59:31 -0500 answered a question Multi-camera calibration for tracking objects

Without a known size object or calibration target within the videos, you'll have to use a Structure From Motion (SfM) al

2017-09-24 17:36:50 -0500 commented question Multi-camera calibration for tracking objects

So do you control the cameras? Could you carry a chessboard into the scene and calibrate them? Can you measure the sce

2017-09-23 11:35:18 -0500 answered a question Background subtraction from single static image

Berak's suggestions are good, but one other idea is kmeans clustering. The large cluster is the background, and everyth

2017-09-23 11:30:38 -0500 answered a question Aruco markers with openCv, get the 3d corner coordinates?

So the way that function works, you pass in the location of the four corners in the image, and the marker length. It as

2017-09-21 19:08:39 -0500 answered a question Can I measure suface of an object which can have any shape with this library.

You can indeed find the surface area of leather pieces like that, assuming they lie flat. You need to calibrate the cam