Aruco MarkerDetector undistorts image? - opencv

I am currently using the aruco library to track fiducial markers, and I use the detect() method of the MarkerDetector class. The detect() method takes as input the camera parameters (camera matrix, distortion coefs), the length of the marker and the image. I actually use the function cv::undistort() to undistort the image before giving it as input to detect(). But i was asking myself if the detect() method already undistorts the image ? Which means that i should give the raw image as input to detect(), instead of the undistorted one. I read the doc of the function, but no information is given about that.
Thank you for your answers :-)

edit: I don't know the standalone library and can only talk about the aruco module of OpenCV
If you pass an undistorted picture to the aruco API, do not pass any distortion coefficients to the aruco API. You should however pass the "raw" image instead (and distortion coefficients in the following call), because that spares you from having to undistort the entire picture, which costs more than doing it to a few points.
The aruco module API was recently changed to clarify this... if I remember correctly. The detectMarkers() method is not supposed to do the undistorting, and does not do that. The undistorting, of points, is supposed to happen in the pose estimation call, estimatePoseSingleMarkers() or related ones, which comes after.
Yes, some parts of the docs are bad, and I wouldn't put all my trust in the implementation either.

Related

Advantage of fish-eyes lens and Camera Calibration

The purpose of calibration is to calibrated distortion the image.
What's main source of this distortion in the image when the lens is used, for example fish-eyes lens?
Q1-You think we are going to identify some of the objects and using fish-eyes lenses in order to cover a wide view of the environment, Do we need to calibrate the camera? That is, we must correct the image distortions and then identify the objects? Does the corrected image still cover the same amount of objects? If it's not cover all objects of distorted image, then what is the point of taking a wide-angle lens? Wouldn't it be better to use the same flat lens without having to calibrate the camera?
Q2-For calculating the distortion param like intrinsic and extrinsic param and etc, Is need to calculate parameters for all of camera with same specifics independently? That's, the finding parameters of distortion for one camera can be correctly work with other camera with same specifics?
Q1 Answer : You need to dewarp the image/video that comes out of the camera. There are some libraries that do it for you. You can also calibrate the dewarping according to your needs.
When dewarping the fisheye input, the corners of the video feed are a little lost. This won't be a huge loss.
Q2 Answer : Usually you don't have to do a different dewarping configuration based on your camera. But if you want to finetune it, there are parameters for it.
FFmpeg has lens correction filter, the parameters to finetune are also present in the link.

Finding depth of an object in an image given coordinates of object in image frame

I have images of an object and it has been recognised in the image using Neural network, with open cv, I was able to find coordinates of object in the image, How can I find it's depth i.e distance from the point where camera is, assuming I use two lenses to help in finding the depth.
Your problem is comonly known as "camera calibration".
Have for instance a look here to get the basic idea:
Camera calibration With OpenCV
Good luck

opencv: Correcting these distorted images

What will be the procedure to correct the following distorted images ? It looks like the images are bulging out from center. These are of the same QR code, and so a combination of such images can be used to arrive at a single correct and straight image.
Please advice.
The distortion you are experiencing is called "barrel distortion". A technical name is "combination of radial distortion and tangential distortions"
The solution for your problem is openCV camera calibration module. Just google it and you will find documentations in openCV wiki. More over, openCV already has built in source code examples of how to calibrate the camera.
Basically, You need to print an image of a chess board, take a few pictures of it, run the calibration module (built in method) and get as output transformation matrix. For each video frame you apply this matrix (I think the method called cvUndistort()) and it will straighten the curved lines in the image.
Note: It will not work if you change the zoom or focal length of the camera.
If camera details are not available and uncontrollable - then your problem is very serious. There is a way to solve the distortion, but I don't know if openCV has built in modules for that. I am afraid that you will need to write a lot of code.
Basically - you need to detect as much as possible long lines. Then from those lines (vertical and horizontal) you build a grid of intersection points. Finally you fit the grid of those points to openCV calibration module.
If you have enough intersection points (say 20 or more) you will be able to calculate the distortion matrix and un-distort the image.
You will not be able to fully calibrate the camera. In other words, you will not be able to run a one time process that calculates the expected distortion. Rather - in each and every video frame, you will calculate the distortion matrix directly - reverse it and un-distort the image.
If you are not familiar with image processing techniques or unable to find a reliable open source code which directly solves your problem - then I am afraid that you will not be able to remove the distortion. sorry

Change value of the camera focal in pixels

I am currently looking for a proper solution to the following problem, which is not directly programming oriented, but I am guessing that the users of opencv might have an idea:
My stereo camera has a sensor of 1/3.2" 752x480 resolution. I am using the two stereo images of this very camera in order to create a point cloud, thanks to the point cloud library (PCL).
The problem is that I would like to reduce the number of points contained by the point cloud, by directly lowering the resolution of the input images (passing from 752x480 to 376x240).
As it is indicated in the title, I have to adapt the focal of the camera in pixels to this need:
I calculate this very parameter thanks to the following formula:
float focal_pixel = (FOCAL_METERS / SENSOR_WIDTH_METERS)*InputImg.cols;
However the SENSOR_WIDTH_METERS is currently constant and corresponds to the 1/3.2" data converted to meters AND I would like to adapt this to the resolution that I would like to have: 376x240.
I am absolutly not sure if I turned my problem clearly enough to be answered, which would mean that I am going in the wrong direction.
Thank you in advance
edit: the function used to process the stereo image (after computing):
getPointCloud(hori_c_pp, vert_c_pp, focal_pixel, BASELINE_METERS, out_stereo_cloud, ref_texture);
where the two first parameters are just the coordinates of the center of the image, BASELINE_METERS the baseline of my camera out_stereo_cloud my output cloud and eventually ref_texture the color information. This function is taken from the sub library stereo_matching.
For some reason, if I just resize the stereo images, it seems to enter in conflict with the focal_pixel parameters, since the dimension are not the same anymore.
Im very lost on this issue.
As I don't really follow the formulas and method calls you're posting I advise you to use another approach.
OpenCV already gives you the possibility to create voxels using stereo images with the method cv::reprojectImageTo3D. Another question also already discusses the conversion to the according PCL datatype.
If you only want to reproject a certain ROI of your image you should opt for cv::perspectiveTransform as is explained in the documentation I pointed out in the first link.

Find the position of a pattern/marker inside a photograph

i need to find a marker like the ones used in Augmented Reality.
Like this:
I have a solid background on algebra and calculus, but no experience whatsoever on image processing. My thing is Php, sql and stuff.
I just want this to work, i've read the theory behind this and it's extremely hard to see in code for me.
The main idea is to do this as a batch process, so no interactivity is needed. What do you suggest?
Input : The sample image.
Output: Coordinates and normal vector in 3D of the marker.
The use for this will be linking images that have the same marker to spatialize them, a primitive version of photosync we could say. Just a caroussel of pinned images, the marker acting like the pin.
The reps given allowed me to post images, thanks.
You can always look at the open source libraries such as ARToolkit and see how it works but generally in order to get the 3D coordinates of marker you would need to:
Do the camera calibration.
Find marker in image using local features for example.
Using calibrated camera parameters and 2D coordinates of marker do the approximation the 3D coordinates.
I've never implemented sth similar by myself but I think this is a general concept you should apply on your method.
Your problem can be solved by perspective n point camera pose estimation. When you can reasonably assume that all correspondences are correct, a linear algorithm should do.
Since the marker is planar, you can also recover the displacement from the homography between the model plane and the image plane (link). As usual, best results are obtained by iterative algorithms (link).

Resources