ROSpioneer's profile - activity

Distortion correction I've some unknown distortion like in the picture below, is there any solution to solve those disto

Usually I don't add opencv_highgui and opencv_imgcodecs manually but this time it has to be added I don't know why but i

Opencv in ubuntu 20.04 undefined reference I upgraded my PC to Ubuntu 20.04 and I installed OpenCV 4.2.0 which compiles

@Eduardo Because that package could get compiled with version3 it does exist before V4.. how can I solve that issue of h

cannot find -lopencv_gapi I'm struggling to compile marker_mapper which uses aruco lib. This is my settings: GCC 5.5.0

I want to estimate the pose of the camera using solvepnp function and for object_points and image_points I have all in millimeters, is that correct? what I do have to change in solvepnp to get it to work with mm units?

SolvePnp in millimeters instead of pixels I want to estimate the pose of the camera using solvepnp function and for obje

SolvePnp doesn't give the same result with four points and more points I'm computing the pose of the camera using SolveP

solvePnP object pose for Omnidirectional model I'm interested in pose estimation using slightly different sensors called

Opencv function runs on GPU or CPU It has been said in that document: Any OpenCV function that accepts Input/Outpu

I didn't notice anything really.. I do have a good internet connection so I don't think that the issue.. The only thing

Sorry! I hit Ask Your Question button and it didn't work at first and at second time.. and after a couple of tries it wo

What's new in opencv 3.4.1 I've 3.4.0 installed and I discovered that there"s a new version released. I want to know wha

What's new in opencv 3.4.1 I've 3.4.0 installed and I discovered that there"s a new version released. I want to know wha

What's new in opencv 3.4.1 I've 3.4.0 installed and I discovered that there"s a new version released. I want to know wha

@berak I just edited my post with an example code

Access/Create/Modify pixels in UMat I want to create a vector of type cv::UMat but I didn't find any method to do that.

Access/Create/Modify pixels in UMat I want to create a vector of type cv::UMat but I didn't find any method to do that.

What do you mean by all focals?

Working with a camera with variable focal length I'm using a camera for tracking and pose estimation.. I know that we ne

Well I don't agree with you on that point.. It is always good to post your solution and for people to take advantages fr

You didn't show how did you solve them. There's more details here https://stackoverflow.com/questions/46584000/cmake-er

Yes you're right CUDA9 doesn''t support Fermi anymore

@Amaro @mfisher could you please share the solution i'm having the sale issue with nvcc fatal "compute_20"?

Okay I confused DOF and Focal length! thanks However, when you say large depth, it means we can see farthest objects better? how about nearest objects? That was my question. I want to see both of them like there is no depth!

I don't know where to ask this question but as I'm working with OpenCV I'll do it here.

I'm working with this camera: Blackfly 0.9 MP Color GigE PoE (Sony ICX692) with focal length 2.8-8 mm.

My question is how to set the focal to infinity so as I can see objects near the camera as well as far ones simultaneously without blurring. I don't know if that is possible! When I want to detect a chessboard for example, it works well when the board is on the focal plan but otherwise it appears little bit blurred so it's not detectable!

If it is not possible how you deal with that issue?

The one that I'm familiar with is Jetson TX1 or TX2 of Nvidia. It's not very expensive, however I don't know what kind of processing you'll do with 15 caméras because 15 FullHD is quite big number!

The graphic cards used in research or in industry are different from those for games because they don't have the same interfaces. For research we use a GPU that has a CPU and graphic cards but also a camera and many other inputs outputs.. Those cards work independently from the computer and they have their own OS.. so easy to work with when developing your application.

I believe that If you rotate the image you need to permute the c_x and c_y For other intrinsic parameters if your pixel size is square then you don't need change them

I'll write an answer to the issue after doing some experiments. I corrected my distance as follow:

Distance_corrected = distNorme+distNorme*correction

distNorme is the distance to the chessboard which is the norm of the translation vector given by solvePnP OpenCV function.

correction is

correction=pixel_size/focal_mm/2 = 2/focal_pixel

The results are better, still have an error increasing linearly though but not very strong as distNorme (distance not corrected).

I'm still seeking for references or documentation of that correction error. I need more details about it.

OK got it! I'll write an answer.. thanks both of you

@LBerger I mean that error d*pixel_size/focal/2, how did you get it ? it's not linear!

@LBerger @Tetragramm Do you have any references about that? I'm interested more in that error so I can correct it with respect to my camera parameters :)

@LBerger So what do you think that error is due to? is it normal as I'm using a single camera?

I compute the distance from an object (Chessboard) using OpenCV and my camera parameters following those steps:

1- findChessboardCorners

2- solvePnP

3- ->Distance from the translation vector given by solvePnP

The issue is that the error is increasing linearly when I get far from the camera.

The error is simply the difference between the real distance and the one given by my program.

The camera is calibrated (focal length 2.8mm, wide angle + distortion)

I want to know why the error is increasing? Is that normal?

I compute the distance from an object (Chessboard) using OpenCv and my camera parameters using those steps:

findChessboardCorners

solvePnP

->Distance

The distance I get is between two points: the chessboard and the camera. My question is where is the origine of my camera?

I know perfectly about my Chessboard but not my camera in terms of reference.

I have some classifiers file.xml, is there a way to know from which images are trained?

The name of the file is usually not clear!

Those are the classifiers:

https://github.com/JaouadROS/head_dep...

Many thanks