After stereo calibration, when I run the Matlab example for stereo depth estimation (SDE), the distances are wrong: at about 2 meters, it always reports distance as less than 1m.
And my 3D scene reconstruction looks cone-shaped instead of like the real scene.
Disparity map is very noisy (non-smooth), but resembles the scene.
If I 'feed' the SDE script the example file instead of webcam input, it runs okay, all looks great; when I feed it from two webcams ( 'Logitech HD Pro Webcam C920' ) that's when I get the above bad results, beginning with rough disparity map.
I've tried many different calibration attempts with just a few images up to about 60, with Matlab's checkerboard pattern at different angles (never > 45) and distance to cameras about 8 to 20'. Camera lenses are 3.8175" apart always, and are mounted to top edge of laptop. Followed Matlab's recommended workflow.
What am I doing wrong in calibration?
Matlab R2015a.
Laptop Windows 7 64-bit
Checkerboard pattern is 37" x 27"
............JUST DISCOVERED PROBLEM:
Was creating disparity map with this:
disparityMap = disparity(frameLeftGray, frameRightGray);
However, my camera #1 is on the right, and Matlab says default disparity range is [0 64] and for cam #1 right it should be [-128 0], but that changes the disparity map to all uniform blue.
I got it working. (1) left/right of calibration and images and detection data structures must match. (2) Use mm for checkboard square size. Inches causes malfunction, because all else is in mm.
Related
I'm trying to calibrate camera using MatLab.
Is reprojection error a distance between a pattern keypoint detected in a calibration image, and a corresponding world point projected into the same image?
It shows Overall Mean Error (for example 0.86 pixels) and that's what I want to understand.
Does 0 is the best result?
I'm trying to use to stereo camera measure distance from cameras to a dynamic object(a moving car for example). I used a checkerboard pattern with 7 by 8 squares with square size of 89 millimeters(~ 3.5 inches). distance from camera to pattern was 212 centimeters (~ 83.5 inches). I'm using Python and OpenCV
My questions are:
that does the distance from pattern to camera affect much at the calibration parameters? It is stated in One of Matlab examples that distance from camera to pattern in calibration process should be the same as object distance that it is desired to measure1.
Should I use bigger board size and increase the camera to pattern distance to get more accurate results for my application?
I think that the specific distance you use for the calibration shouldn't really matter. What does matter is, that you take as many possible different images of your checkerboard as possible. At least 15. Checkerboard should be moved so that you cover the whole camera field. Checkerboard should be also imaged at different out of plane orientations. Having a checkerboard with more squares should also be beneficial as this means more corner points per image. Size of the squares shouldn't make a difference.
On the other hand, camera calibration should be performed with fixed focus which also shouldn't change after the calibration. So, in practice, I guess that this forces you to perform calibration at similar distance that will be used later for the experiment.
first I will try to explane what I have to do and then I will ask my question to the problem.
My task is to detect small balls (2mm) in gelatine using two webcams.
The steps for detection are these:
Image taking using two webcams (position: 90 degree to each other)
Stereo calibration of each pair of images
Masking of the areas in the images which are not necessary to analyse
Rectification of each pair of images
Circle detection resulting in structure with the positions (x, y) of the center of each circle (in reality of each ball)
Association of the resulted position to get something like a 3D coordinate to know the position of the balls (this is my problem)
Now the problem (step 6.):
What possibilities are given to compute the 3D-coordinates of each center of the balls using the 2D-coordinates of the two images.
I'm searching here
http://de.mathworks.com/help/vision/stereo-vision.html
for ideas, but I hope you know some easy way and have some ideas.
I can not upload any images (because I'm new at stackoverflow)
Take a look at this example: Depth Estimation from Stereo Video. The example takes a pair images with a calibrated stereo camera, rectifies the images, detects a person, and gets the 3D coordinates of the centroid of the person. You can do the same thing to find the balls.
Calibrate the cameras using the Stereo Camera Calibrator app.
Take two images
Rectify the images using the rectifyStereoImages function
Compute stereo disparity using the disparity funciton
Get the 3D coordinates for every pixel using the reconstructScene funciton
Detect the balls in image 1
Look up the 3D coordinates of their centroids
Once you have the disparity and the dense reconstruction from reconstructScene there is no need to find correspondences between the images. disparity already did that for you.
I am using Camera Calibration Toolbox for Matlab. After calibration I have intrinsic and extrinsic parameters of stereo camera system. Next, I would like to determine the distance between the camera system and the object. To get this information, I used the function stereo_triangulation which is included in the Toolbox. Input are two matrixes including pixel coordinates of correspondences in the left and right image.
I tried to get coordinates of correspondences with using of Basic Block Matching method which is described in Matlab's help for Stereo Vision.
Resolution of my pictures is 1280x960 pixels. I know that the biggest disparity is around 520 pixels. I set the maximum of disparity range to 520. But then determine the coordinates takes ages. It is not possible use in practice. Calculating of disparity map is much faster with using of Matlab's function disparity(). But I want the step before - coordinates of correspondences.
Please can you suggest how can I effectively get the coordinates with Matlab?
Disparity and 3D are related by simple formulas (see below) so the time for calculating 3D data and disparity map should be the same. The notation is
f - focal length in pixels,
B - separation between cameras,
u, v - row and column in the system centered on the middle of the image,
d-disparity,
x, y, z - 3D coordinates.
z=f*B/d;
x=z*u/f;
y=z*v/f;
1280x960 is too large resolution for any correlation stereo to work in real time. Think about it: you have to loop over a 2d image, over 2d correlation window and over the range of disparities. This means 5 embedded loops! I don't work with Matlab anymore but I know that it is quite slow.
I have been trying to do a stereo calibration with the Matlab camera calibration toolbox. I have two cameras being triggered at the same time, and I'm grabbing corners from 25 pairs of images. The individual calibrations are working, though one camera calibration uses only 24 of the 25 images (when I reproject on images, only 24 images pop up. When I try to use the L and R calibration.mat files for a stereo calibration, it throws Disabling view XX - L and R views are found inconsistent for every single pair (and it says there are only 24 pairs of images, not 25). I've read the help file but I don't think that it addresses my problem. Please advise!
Please check out the CameraCalibrator App that is a part of the Computer Vision System Toolbox for MATLAB. It gives you a very easy way to calibrate a single camera, including automatic checkerboard detection. It does not let calibrate a stereo pair, but it gets you half-way there.