How to Use FindPlane() - google-project-tango

Could someone explain to me how FindPlane works? (I understand the inputs, and the outputs, but not the process.) I am getting random values for the output and therefore I do not understand how it actually functions: does it raycast a normal vector from my camera according to my touch position and gets the depth point that hit the raycast and gets a plane out of that?

Operation is similar to raycast, but other way round. When you click any point on screen, screen coordinates are recorded. All 3D points in Pointcloud are projected onto image plane using camera intrinsic. Points which are close to screen coordinates are taken. RANSAC method is used to extract plane information from those points. SVD can also be used to extract plane normal from inliers obtained from RANSAC. This method should be used only once per frame transformation operation is applied on all points in pointcloud.
This method gives random values in cases where Sparse Pointcloud, reflections in 3D point cloud, reflective surfaces, Cluttered 3D space, IR from outside etc.,

Related

Camera Geometry: Algorithm for "object area correction"

A project I've been working on for the past few months is calculating the top area of ​​an object taken with a 3D depth camera from top view.
workflow of my project:
capture a group of objects image(RGB,DEPTH data) from top-view
Instance Segmentation with RGB image
Calculate the real area of ​​the segmented mask with DEPTH data
Some problem on the project:
All given objects have different shapes
The side of the object, not the top, begins to be seen as it moves to the outside of the image.
Because of this, the mask area to be segmented gradually increases.
As a result, the actual area of ​​an object located outside the image is calculated to be larger than that of an object located in the center.
In the example image, object 1 is located in the middle of the angle, so only the top of the object is visible, but object 2 is located outside the angle, so part of the top is lost and the side is visible.
Because of this, the mask area to be segmented is larger for objects located on the periphery than for objects located in the center.
I only want to find the area of ​​the top of an object.
example what I want image:
Is there a way to geometrically correct the area of ​​an object located on outside of the image?
I tried to calibrate by multiplying the area calculated according to the angle formed by Vector 1 connecting the center point of the camera lens to the center point of the floor and Vector 2 connecting the center point of the lens to the center of gravity of the target object by a specific value.
However, I gave up because I couldn't logically explain how much correction was needed.
fig 3:
What I would do is convert your RGB and Depth image to 3D mesh (surface with bumps) using your camera settings (FOVs,focal length) something like this:
Align already captured rgb and depth images
and then project it onto ground plane (perpendicul to camera view direction in the middle of screen). To obtain ground plane simply take 3 3D positions of the ground p0,p1,p2 (forming triangle) and using cross product to compute the ground normal:
n = normalize(cross(p1-p0,p2-p1))
now you plane is defined by p0,n so just each 3D coordinate convert like this:
by simply adding normal vector (towards ground) multiplied by distance to ground, if I see it right something like this:
p' = p + n * dot(p-p0,n)
That should eliminate the problem with visible sides on edges of FOV however you should also take into account that by showing side some part of top is also hidden so to remedy that you might also find axis of symmetry, and use just half of top side (that is not hidden partially) and just multiply the measured half area by 2 ...
Accurate computation is virtually hopeless, because you don't see all sides.
Assuming your depth information is available as a range image, you can consider the points inside the segmentation mask of a single chicken, estimate the vertical direction at that point, rotate and project the points to obtain the silhouette.
But as a part of the surface is occluded, you may have to reconstruct it using symmetry.
There is no way to do this accurately for arbitrary objects, since there can be parts of the object that contribute to the "top area", but which the camera cannot see. Since the camera cannot see these parts, you can't tell how big they are.
Since all your objects are known to be chickens, though, you could get a pretty accurate estimate like this:
Use Principal Component Analysis to determine the orientation of each chicken.
Using many objects in many images, find a best-fit polynomial that estimates apparent chicken size by distance from the image center, and orientation relative to the distance vector.
For any given chicken, then, you can divide its apparent size by the estimated average apparent size for its distance and orientation, to get a normalized chicken size measurement.

How to determine camera location from view matrix?

for a personal project, I've created a simple 3D engine in python using as little libraries as possible. I did what I wanted - I am able to render simple polygons, and have a movable camera. However, there is a problem:
I implemented a simple flat shader, but in order for it to work, I need to know the camera location (the camera is my light source). However, the problem is that I have no way of knowing the camera's location in the world space. At any point, I am able to display my view matrix, but I am unsure about how to extract the camera's location from it, especially after I rotate the camera. Here is a screenshot of my engine with the view matrix. The camera has not been rotated yet and it is very simple to extract its location (0, 1, 4).
However, upon moving the camera to a point between the X and Z axes and pointing it upwards (and staying at the same height), the view matrix changes to this:
It is obvious now that the last column cannot be taken directly to determine the camera location (it should be something like (4,1,4) on the last picture).
I have tried a lot of math, but I can't figure out the way to determine the camera x,y,z location from the view matrix. I will appreciate any and all help in solving this, as it seems to be a simple problem, yet whose solution eludes me. Thank you.
EDIT:
I was advised to transform a vertex (0,0,0,1) by my view matrix. This, however, does not work. See the example (the vertex obviously is not located at the printed coordinates):
Just take the transform of the vector (0,0,0,1) with the modelview matrix: Which is simply the rightmost column of the modelview matrix.
EDIT: #ampersander: I wonder why you're trying to work with the camera location in the first place, if you assume the source of illumination to be located at the camera's position. In that case, just be aware, that in OpenGL there is no such thing as a camera, and in fact, what the "view" transform does, is move everything in the world around so that where you assume your camera to be ends up at the coordinate origin (0,0,0).
Or in other words: After the modelview transform, the transformed vertex position is in fact the vector from the camera to the vertex, in view space. Which means that for your assumed illumination calculation the direction toward the light source, is the negative vertex position. Take that, normalize it to unit length and stick it into the illumination term.

Find my camera's 3D position and orientation according to a 2D marker

I am currently building an Augmented Reality application and stuck on a problem that seem quite easy but is very hard to me ... The problem is as follow:
My device's camera is calibrated and detect a 2D marker (such as a QRCode). I know the focal length, the sensor's position, the distance between my camera and the center of the marker, the real size of the marker and the coordinates of the 4 corners of the marker and of it center on the 2D image I got from the camera. See the following image:
On the image, we know the a,b,c,d distances and the coordinates of the red dots.
What I need to know is the position and the orientation of the camera according to the marker (as represented on the image, the origin is the center of the marker).
Is there an easy and fast way to do so? I tried some method imagined by myself (using Al-Kashi's formulas), but this ended with too much errors :(. Could someone point out a way to get me out of this?
You can find some example code for the EPnP algorithm on this webpage. This code consists in one header file and one source file, plus one file for the usage example, so this shouldn't be too hard to include in your code.
Note that this code is released for research/evaluation purposes only, as mentioned on this page.
EDIT:
I just realized that this code needs OpenCV to work. By the way, although this would add a pretty big dependency to your project, the current version of OpenCV has a builtin function called solvePnP, which does what you want.
You can compute the homography between the image points and the corresponding world points. Then from the homography you can compute the rotation and translation mapping a point from the marker's coordinate system into the camera's coordinate system. The math is described in the paper on camera calibration by Zhang.
Here's an example in MATLAB using the Computer Vision System Toolbox, which does most of what you need. It is using the extrinsics function, which computes a 3D rotation and a translation from matching image and world points. The points need not come from a checkerboard.

3D space: following the direction that an object is pointing towards, using the mouse pointer

Given the 3D vector of the direction that the camera is facing and the orientation/direction vector of a 3D object in the 3D space, how can I calculate the 2-dimensional slope that the mouse pointer must follow on the screen in order to visually be moving along the direction of said object?
Basically I'd like to be able to click on an arrow and make it move back and forth by dragging it, but only if the mouse pointer drags (roughly) along the length of the arrow, i.e. in the direction that it's pointing to.
thank you
I'm not sure I 100% understand your question. Would you mind posting a diagram?
You might find these of interest. I answered previous questions to calculate a local X Y Z axis given a camera direction (look at) vector, and also a question to translate an object in a plane parallel to the camera.
Both of these examples use Vector dot product, Vector cross product to compute the required vectors. In your example the vector dot product can be also used to output the angle between two vectors once you have found them.
It depends to an extent on the transformation that you are using to convert your 3d real world coordinates to 2d screen coordinates, e.g. perspective, isometric, etc... You will typically have a forward (3d -> 2d) and backward (2d -> 3d) transformation in play, where the backward transformation loses information. (i.e. going forward each 3d point will map to a unique 2d point, but going back from the point may not yield the same 3d point). You can often project the mouse point onto the object to get the missing dimension.
For mouse dragging, you typically get the user to specify an operation (translation on the plane of projection, zooming in or out, or rotating about an anchor point). Your input is the mouse coordinate at the start and end of the drag, which you transform into your 3d coordinate system to get two 3d coordinates, which will give you dx, dy, dz for dragging / translation etc...

How to determine top most object in 2d projection of 3d object?

I have a surface to which a set of 3d objects is drawn. The task is to determine an object by the given coordinates on the surface.
For example: some objects are drawn on the desktop application, I need to determine on which object user clicked.
Could you please advise, how such task is usually resolved? Am I need to create remember a top-most object for each pixel? I don't think it is the best approach.
Any thoughts are welcome!
Thanks!
The name for this task is picking (which ought to help you Google for more help on it). There are two main approaches:
Ray-casting: find the line that starts at the camera position and passes through the surface point you are interested in. (The line "under the mouse", or "under your finger" for a touch screen.) Depending on which 3D system you are using, there may be an API call to generate this line: for example Camera.ViewportPointToRay in Unity3D, or you may have to generate it yourself by inverting the camera transform. Find all the points of intersection between this line and the objects in your scene. Which of these points is closest to the near plane of the camera? You can use space partitioning to speed this up.
Rendering: do an extra render pass, in which instead of writing textures to the frame buffer, you record which objects were drawn. You don't do the render pass for the whole screen, you just do it for the area (e.g. the pixel) you are interested in. (This is GL_SELECT mode in OpenGL: see the Picking Tutorial for details.)
If you've described the surface somehow in 3D space, then the ray, defined by your point of observation and a 3D point that is a solution for where you clicked, should intersect one or more objects in your world, if indeed you clicked on one of them.
Given the equations for the surfaces of the objects, you can determine where this ray intersects the objects, if at all, since you also know the equation for the ray in the same coordinate system.
The object that has the closest intersection point to your point of observation (assuming you're looking at the objects from above) is the winner.

Resources