Ask Your Question

Tetragramm's profile - activity

2017-12-15 10:25:18 -0600 answered a question Skeletonization of the image

In addition to the link provided by berak, there is also the thinning operation in the OpenCV contrib ximgproc.

2017-12-15 10:24:04 -0600 answered a question Dynamic Thresholding

OpenCV has two different types of dynamic thresholding. niBlackThreshold and adaptiveThreshold Be sure to check the do

2017-12-13 10:46:43 -0600 commented question Overhead camera's pose estimation with OpenCV SolvePnP results in a few centimeter off height

So my suggestion is to check at several different heights, and see if there is a constant offset between measured and ca

2017-12-13 10:26:18 -0600 commented question Overhead camera's pose estimation with OpenCV SolvePnP results in a few centimeter off height

Umm, 1400 mm is an incredibly long focal length. That's like those pods you see under helicopters for watching things m

2017-12-12 16:14:36 -0600 commented question Extract google map embedded from an image

Well, it's not white or black. That's probably a pretty good sign.

2017-12-12 12:23:26 -0600 commented question Overhead camera's pose estimation with OpenCV SolvePnP results in a few centimeter off height

Remember, OpenCV uses a pinhole camera model. This is not actually a representation of how the lenses actually work. S

2017-12-10 21:04:54 -0600 commented answer why is CV_32FC1 not normalized to 0-1?

the .convertTo function is what you want. for example: cv::Mat intMat = whatever; cv::Mat floatMat; intMat.convertTo(fl

2017-12-10 18:11:30 -0600 commented question ImportError: dlopen <ipython-input-2-c8ec22b3e787> in <module>()

Merged duplicate questions.

2017-12-10 18:11:16 -0600 edited question ImportError: dlopen <ipython-input-2-c8ec22b3e787> in <module>()

ImportError: dlopen <ipython-input-2-c8ec22b3e787> in <module>() when i try to import cv2 with ipython, i ge

2017-12-10 18:10:40 -0600 edited question ImportError: dlopen <ipython-input-2-c8ec22b3e787> in <module>()

ImportError: dlopen <ipython-input-2-c8ec22b3e787> in <module>() when i try to import cv2 with ipython, i ge

2017-12-10 16:10:10 -0600 commented question Output from solvePnP doesn't match projectPoints

Is that a crop of the image you used, or did you use the crop? If you used the crop, then your camera matrix and distor

2017-12-10 16:07:31 -0600 commented answer why is CV_32FC1 not normalized to 0-1?

cvtColor doesn't change the min/max values, other than the normal color space conversion. If you put in a float image o

2017-12-08 14:26:36 -0600 received badge  Good Answer (source)
2017-12-07 20:34:11 -0600 received badge  Nice Answer (source)
2017-12-06 21:33:26 -0600 answered a question why is CV_32FC1 not normalized to 0-1?

OpenCV is Row-major, not column-major Stored Row1: BGRABGRA... Row2 BGRABGRA.... I don't see anything obviously wrong

2017-12-06 15:50:54 -0600 commented question Strange Memory Leak (cvResize, cvCreateImage) [C]

You really shouldn't use the C interface. That's been obsolete for a very long time. I recommend replacing those with

2017-12-06 14:41:35 -0600 commented answer Camera Pose Estimation With OpenCV and Python

I knew where to find the tutorial, but I don't actually understand it as well as I should. I think that's correct, beca

2017-12-05 18:15:32 -0600 commented question Human Detection and tracking opencv c++

Usually a good test is if the mouse moves or the keyboard is pressed. Typically that means you have detected a human on

2017-12-05 17:20:31 -0600 answered a question Camera Pose Estimation With OpenCV and Python

That is not a method of finding the pose. You give all the points a value of z = 1, which is not accurate, and will not

2017-12-03 20:45:58 -0600 commented question Moving Window With Mouse Using Imshow

Is your waitkey still running? Once it lets go, you can't move it any more. Try using waitKey(0).

2017-12-03 20:45:37 -0600 commented question Moving Window With Mouse Using Imshow

Is your waitkey still running? Once it lets go, you can't move it any more.

2017-12-03 20:01:21 -0600 edited question Moving Window With Mouse Using Imshow

Moving Window With Mouse Using Imshow I am using OpenCV 3.3 on a Win10 platform with C++. Is there a way to enable the

2017-12-03 20:01:06 -0600 commented question Moving Window With Mouse Using Imshow

You can simply drag the titlebar, or use the standard right click on the icon and then click move. EDIT: Merged duplica

2017-12-03 20:00:49 -0600 edited question Moving Window With Mouse Using Imshow

Moving Window With Mouse Using Imshow I am using OpenCV 3.3 on a Win10 platform with C++. Is there a way to enable the

2017-12-03 19:27:37 -0600 commented question Moving Window With Mouse Using Imshow

You can simply drag the titlebar, or use the standard right click on the icon and then click move.

2017-12-03 18:57:57 -0600 commented question Deskew Image using FitElipse angle

That looks like it matches the ellipse, if not the letter. You should probably now focus on a better fit. Whether usin

2017-12-02 15:01:14 -0600 commented question Deskew Image using FitElipse angle

It looks like it's just more rotated. Try removing the WARP_INVERSE flag.

2017-11-30 18:30:46 -0600 commented answer Any plan for constant time computing ?

Yeah, it's not pretty. If someone has a paper on a more effective way to do it, or just figures it out, let me know and

2017-11-29 21:48:38 -0600 edited answer Any plan for constant time computing ?

I had not heard of them, but I am certainly interested. It looks like they plan to charge, so we couldn't integrate it

2017-11-29 17:57:06 -0600 answered a question Image registration: transformation matrix

It is an affine transformation. Wikipedia does a good job of describing it HERE.

2017-11-28 18:25:13 -0600 commented question Detecting Light Colored Objects on Black Background

Edited the post to put the question in the question and created a suitable title.

2017-11-28 18:24:46 -0600 edited question Detecting Light Colored Objects on Black Background

So I am trying to detect any lighter colored object on a surface that is primarily black (solar panel surface). Can anyo

2017-11-28 18:24:26 -0600 edited question Detecting Light Colored Objects on Black Background

So I am trying to detect any lighter colored object on a surface that is primarily black (solar panel surface). Can anyo

2017-11-28 17:43:33 -0600 commented answer I have a question regarding the imagepoints output of the projectPoints() funtion in open CV. I am getting image points which have negative coordinates and I understand that they are outside the screen area definitely.

If you subtract the camera coordinates from your object point, you also need to subtract the same value from your tvec.

2017-11-28 17:42:23 -0600 commented answer Getting to grips with video stabilisation in python

Good! Now, of course, for longer videos or videos with differing motion, the simple average may not work, so you would

2017-11-27 22:03:14 -0600 commented question I am trying to create a program that will compare a video image to a library of images. Is this possible?

If you have a specific problem using a particular function or set of functions, we can definitely help. If you are tryi

2017-11-27 19:02:55 -0600 commented answer Getting to grips with video stabilisation in python

You're still missing a step. Your final shift is relative to the previous image. But you've shifted that image. So fo

2017-11-27 17:38:49 -0600 commented answer Getting to grips with video stabilisation in python

The code at the link looks reasonable. What kind of odd behavior?

2017-11-26 21:57:34 -0600 answered a question Center of Charuco Board

You want to use the projectPoints function. You know the size of the squares of the board. So project the point (x,y,0

2017-11-26 21:54:21 -0600 commented question Object Tracking At Night

Can you show an example image of a train coming towards and one going away from the camera?

2017-11-26 21:30:29 -0600 commented answer Getting to grips with video stabilisation in python

That's correct. That is not a valid way to combine matrices. Try limiting it to just translation to start, to make su

2017-11-25 20:41:03 -0600 commented question how to make bounding box on surf features ?

As berak said, you can't put a bounding box around the points, it means nothing. You can match the points to the model,

2017-11-25 20:37:13 -0600 answered a question Getting to grips with video stabilisation in python

So I believe I see your problem. You are applying the average motion to each new frame. Simplifying to one dimension

2017-11-25 20:32:50 -0600 edited answer Find distance between two eyes

import cv2 import math import numpy as np from scipy.spatial import distance as dist

2017-11-25 20:32:49 -0600 edited answer Find distance between two eyes

import cv2 import math import numpy as np from scipy.spatial import distance as dist

2017-11-25 20:32:47 -0600 edited question Find distance between two eyes

Find distance between two eyes I have worked on harcascade face detection and eye detection. it works well now i am stuc

2017-11-25 20:16:37 -0600 edited question install opencv3 to codeblocks "missing libintl-8.dll"

hi im trying to install opencv3 to codeblocks but get "missing libintl-8.dll" i spent all day yesterday searching for a

2017-11-25 20:16:15 -0600 edited question install opencv3 to codeblocks "missing libintl-8.dll"

hi im trying to install opencv3 to codeblocks but get "missing libintl-8.dll" i spent all day yesterday searching for a

2017-11-25 14:04:59 -0600 commented question Multiple Laser Detection : OPENCV + Qt

Youtube or a filesharing site is more useful. Just put a link in your post, and anyone can help.

2017-11-24 11:51:32 -0600 answered a question I have a question regarding the imagepoints output of the projectPoints() funtion in open CV. I am getting image points which have negative coordinates and I understand that they are outside the screen area definitely.

Project points will, if your inputs are correct, provide the locations on the FPA that would see those 3d points. To be