openCV 3D reconstruction using 2 stereo camera pairs - opencv

I'm experimenting with 2 pairs of stereo cameras (4 pairs), and I'm wondering how to combine the 3d point clouds I get from the 2 pairs of cameras. Basically, I'm successfully getting 2 sets of 3d points from the 2 different pairs of cameras. But, I'm not sure which coordinate frame (the world coordinates) the 3d points are in relative to.
Is it relative to the left camera (the 1st set of image points when calibrating)?
My idea is, if I get the rotation and transform between the two left cameras (let's say it's L_1 and L_2, where L_1 is the left camera for this pair), and then try to transform the 3d points from the R_2 and L_2 pair to the new frame, it would work? But, I'm not sure.

Normally it refers to the left camera, indeed there are some exceptions but in most cases you use the left image as the reference image for disparity calculation. Meaning that the Point cloud is the 3D representation of the left 2D Image. In order to align the Point Clouds you could use the ICP algorithm with the knowledge that the images overlap in some areas.
Take a look here http://pointclouds.org/documentation/tutorials/iterative_closest_point.php
Hope this helps, even if its too late

Related

view mapping between two images taken from same cameras of same scene using homography in open CV, except the camera positions are not parallel

I am trying to understand mapping points between two images of same scene except the camera positions are different. say like this apologies for the rough sketch and the hand-writing. Sample image taken from cam1 and Sample image taken from cam2 . Trying to map between these two images. since the two cameras used are same(logitech camera). I assume camera calibration isn't required. So with the help of SIFT descriptors and feature matching, using the good matches from the images as inputs to Homography with RANSAC. I get 3*3 matrix. To verify the view mapping. I select few objects(say bins in the image) in cam1 image and try to map the same object in cam2 image using 3 * 3 matrix by using warp_perspective, but the outputs aren't good. say something like this had selected top left and bottom right of the objects in cam1 image(i.e. bins) and trying to draw a bounding box for the desired object in cam2 image.
But as visible in the view map output image the bounding boxes aren't proper to the bins.
Wanted to understand, where am i going wrong. Is it the camera positions affecting, and this shouldn't be used for homography or have to use multiple homographies or have to get to know the translation between the camera positions. very confused. Thank you.
Homography transforms plane into a plane. It can only be used if all of the matches lay on a plane in real world (e.g. on the planar wall) or the feature points are located far from both cameras so the transformation between the cameras might be expressed as pure rotation. See this link for further explanation.
In your case the objects are located at different depths so you need to perform stereo calibration of cameras and then compute the depth map to be able to map pixels from one camera into another.

Multiple camera view triangulation

Given a scene, multiple camera views of that scene and their corresponding projection matrices, we wish to triangulate 2D matching points into 3D.
What i've been doing so far is solve the system PX = alphax where P is the projection matrix, X is the 3D point in camera coordinates, alpha is a scalar and x is the vector corresponding to the point in 2D. X and x are in homogeneous coords.
See https://tspace.library.utoronto.ca/handle/1807/10437 page 102 for more detail.
Solving this with an SVD yields proper results when the 2D points are accurately selected or when i only use two views. Introducing more views adds a lot of error.
Any advice on what techniques are best to improve/refine this solution and make it support more views?
If I understand correctly, we can view this as finding a point in 3D space that minimizes the sum of orthogonal distances between the point and lines (one line per camera view) ? I guess with a gradient descent in 3d space, it's possible to find a local minimum of this.
Did I understand the problem correctly?

Recover plane from homography

I have used openCV to calculate the homography relating to views of the same plane by using features and matching them. Is there any way to recover the plane itsself or the plane normal from this homography? (I am looking for an equation where H is the input and the normal n is the output.)
If you have the calibration of the cameras, you can extract the normal of the plane, but not the distance to the plane (i.e. the transformation that you obtain is up to scale), as Wikipedia explains. I don't know any implementation to do it, but here you are a couple of papers that deal with that problem (I warn you it is not straightforward): Faugeras & Lustman 1988, Vargas & Malis 2005.
You can recover the real translation of the transformation (i.e. the distance to the plane) if you have at least a real distance between two points on the plane. If that is the case, the easiest way to go with OpenCV is to first calculate the homography, then obtain four points on the plane with their 2D coordinates and the real 3D ones (you should be able to obtain them if you have a real measurement on the plane), and using PnP finally. PnP will give you a real transformation.
Rectifying an image is defined as making epipolar lines horizontal and lying in the same row in both images. From your description I get that you simply want to warp the plane such that it is parallel to the camera sensor or the image plane. This has nothing to do with rectification - I’d rather call it an obtaining a bird’s-eye view or a top view.
I see the source of confusion though. Rectification of images usually involves multiplication of each image with a homography matrix. In your case though each point in sensor plane b:
Xb = Hab * Xa = (Hb * Ha^-1) * Xa, where Ha is homography from the plane in the world to the sensor a; Ha and intrinsic camera matrix will give you a plane orientation but I don’t see an easy way to decompose Hab into Ha and Hb.
A classic (and hard) way is to find a Fundamental matrix, restore the Essential matrix from it, decompose the Essential matrix into camera rotation and translation (up to scale), rectify both images, perform a dense stereo, then fit a plane equation into 3d points you reconstruct.
If you interested in the ground plane and you operate an embedded device though, you don’t even need two frames - a top view can be easily recovered from a single photo, camera elevation from the ground (H) and a gyroscope (or orientation vector) readings. A simple diagram below explains the process in 2D case: first picture shows how to restore Z (depth) coordinate to every point on the ground plane; the second picture shows a plot of the top view with vertical axis being z and horizontal axis x = (img.col-w/2)*Z/focal; Here is img.col is image column, w - image width, and focal is camera focal length. Note that a camera frustum looks like a trapezoid in a birds eye view.

Project 2d points in camera 1 image to camera 2 image after a stereo calibration

I am doing stereo calibration of two cameras (let's name them L and R) with opencv. I use 20 pairs of checkerboard images and compute the transformation of R with respect to L. What I want to do is use a new pair of images, compute the 2d checkerboard corners in image L, transform those points according to my calibration and draw the corresponding transformed points on image R with the hope that they will match the corners of the checkerboard in that image.
I tried the naive way of transforming the 2d points from [x,y] to [x,y,1], multiply by the 3x3 rotation matrix, add the rotation vector and then divide by z, but the result is wrong, so I guess it's not that simple (?)
Edit (to clarify some things):
The reason I want to do this is basically because I want to validate the stereo calibration on a new pair of images. So, I don't actually want to get a new 2d transformation between the two images, I want to check if the 3d transformation I have found is correct.
This is my setup:
I have the rotation and translation relating the two cameras (E), but I don't have rotations and translations of the object in relation to each camera (E_R, E_L).
Ideally what I would like to do:
Choose the 2d corners in image from camera L (in pixels e.g. [100,200] etc).
Do some kind of transformation on the 2d points based on matrix E that I have found.
Get the corresponding 2d points in image from camera R, draw them, and hopefully they match the actual corners!
The more I think about it though, the more I am convinced that this is wrong/can't be done.
What I am probably trying now:
Using the intrinsic parameters of the cameras (let's say I_R and I_L), solve 2 least squares systems to find E_R and E_L
Choose 2d corners in image from camera L.
Project those corners to their corresponding 3d points (3d_points_L).
Do: 3d_points_R = (E_L).inverse * E * E_R * 3d_points_L
Get the 2d_points_R from 3d_points_R and draw them.
I will update when I have something new
It is actually easy to do that but what you're making several mistakes. Remember after stereo calibration R and L relate the position and orientation of the second camera to the first camera in the first camera's 3D coordinate system. And also remember to find the 3D position of a point by a pair of cameras you need to triangulate the position. By setting the z component to 1 you're making two mistakes. First, most likely you have used the common OpenCV stereo calibration code and have given the distance between the corners of the checker board in cm. Hence, z=1 means 1 cm away from the center of camera, that's super close to the camera. Second, by setting the same z for all the points you are saying the checker board is perpendicular to the principal axis (aka optical axis, or principal ray), while most likely in your image that's not the case. So you're transforming some virtual 3D points first to the second camera's coordinate system and then projecting them onto the image plane.
If you want to transform just planar points then you can find the homography between the two cameras (OpenCV has the function) and use that.

Distance to the object using stereo camera

Is there a way to calculate the distance to specific object using stereo camera?
Is there an equation or something to get distance using disparity or angle?
NOTE: Everything described here can be found in the Learning OpenCV book in the chapters on camera calibration and stereo vision. You should read these chapters to get a better understanding of the steps below.
One approach that do not require you to measure all the camera intrinsics and extrinsics yourself is to use openCVs calibration functions. Camera intrinsics (lens distortion/skew etc) can be calculated with cv::calibrateCamera, while the extrinsics (relation between left and right camera) can be calculated with cv::stereoCalibrate. These functions take a number of points in pixel coordinates and tries to map them to real world object coordinates. CV has a neat way to get such points, print out a black-and-white chessboard and use the cv::findChessboardCorners/cv::cornerSubPix functions to extract them. Around 10-15 image pairs of chessboards should do.
The matrices calculated by the calibration functions can be saved to disc so you don't have to repeat this process every time you start your application. You get some neat matrices here that allow you to create a rectification map (cv::stereoRectify/cv::initUndistortRectifyMap) that can later be applied to your images using cv::remap. You also get a neat matrix called Q, which is a disparity-to-depth matrix.
The reason to rectify your images is that once the process is complete for a pair of images (assuming your calibration is correct), every pixel/object in one image can be found on the same row in the other image.
There are a few ways you can go from here, depending on what kind of features you are looking for in the image. One way is to use CVs stereo correspondence functions, such as Stereo Block Matching or Semi Global Block Matching. This will give you a disparity map for the entire image which can be transformed to 3D points using the Q matrix (cv::reprojectImageTo3D).
The downfall of this is that unless there is much texture information in the image, CV isn't really very good at building a dense disparity map (you will get gaps in it where it couldn't find the correct disparity for a given pixel), so another approach is to find the points you want to match yourself. Say you find the feature/object in x=40,y=110 in the left image and x=22 in the right image (since the images are rectified, they should have the same y-value). The disparity is calculated as d = 40 - 22 = 18.
Construct a cv::Point3f(x,y,d), in our case (40,110,18). Find other interesting points the same way, then send all of the points to cv::perspectiveTransform (with the Q matrix as the transformation matrix, essentially this function is cv::reprojectImageTo3D but for sparse disparity maps) and the output will be points in an XYZ-coordinate system with the left camera at the center.
I am still working on it, so I will not post entire source code yet. But I will give you a conceptual solution.
You will need the following data as input (for both cameras):
camera position
camera point of interest (point at which camera is looking)
camera resolution (horizontal and vertical)
camera field of view angles (horizontal and vertical)
You can measure the last one yourself, by placing the camera on a piece of paper and drawing two lines and measuring an angle between these lines.
Cameras do not have to be aligned in any way, you only need to be able to see your object in both cameras.
Now calculate a vector from each camera to your object. You have (X,Y) pixel coordinates of the object from each camera, and you need to calculate a vector (X,Y,Z). Note that in the simple case, where the object is seen right in the middle of the camera, the solution would simply be (camera.PointOfInterest - camera.Position).
Once you have both vectors pointing at your target, lines defined by these vectors should cross in one point in ideal world. In real world they would not because of small measurement errors and limited resolution of cameras. So use the link below to calculate the distance vector between two lines.
Distance between two lines
In that link: P0 is your first cam position, Q0 is your second cam position and u and v are vectors starting at camera position and pointing at your target.
You are not interested in the actual distance, they want to calculate. You need the vector Wc - we can assume that the object is in the middle of Wc. Once you have the position of your object in 3D space you also get whatever distance you like.
I will post the entire source code soon.
I have the source code for detecting human face and returns not only depth but also real world coordinates with left camera (or right camera, I couldn't remember) being origin. It is adapted from source code from "Learning OpenCV" and refer to some websites to get it working. The result is generally quite accurate.

Resources