my use case is only concerned with locationing, in fact only 2-d locationing. so a lot of the cool capabilities in tango are probably not useful to me. so I'm trying to see if i could implement the location algorithm myself.
from teardown reports it seems the 9dof sensors are pretty commodity hardware. the basic integration-based location algorithm (even with magnetic field calibration) has been mature knowledge. what algorithm does tango use?
from the description it seems that tango tries to aid in navigation by using the images it sees as a reference, sort of like the "terrain-following" mode in cruise missiles, is this right? this would be too ccomplex for me to implemente
You may easily get 2D position using the TangoPoseData with the correct coordinate system:
Project Tango uses a right-handed, local-level frame for the START_OF_SERVICE and AREA_DESCRIPTION coordinate frames. This convention sets the Z-axis aligned with gravity, with Z+ pointed upwards, and the X-Y plane is perpendicular to gravity and locally level with the ground plane. This local-level convention is based on the local east-north-up (ENU) earth-based coordinate system. Instead of true north, Project Tango uses the direction the back of the device is pointed when the service started as the Y axis, and the X axis is pointed to the right. The START_OF_SERVICE and AREA_DESCRIPTION base coordinate frames of the API will use this local-level frame convention.
Said more simply, use the pose data y/x coordinates for your space as you would latitude/longitude for the earth.
Heading data is also derived from the TangoPoseData and can be converted from quaternion to euler angles. Euler angles may be easier for you to use in your 2D location app.
Tango uses 3D to increase the confidence of its position within the space...even if you don't need 3D. I would let Tango do the hard stuff and extract the 2D position so you can focus on your app.
Tango uses the camera images to detect any change in position. And uses the IMU for device rotation and acceleration. Try blocking the camera and using the Motion Tracking app, it will fail.
Related
I'm using Tango motion tracking and it is very easy to get the pose of the device relative to the TANGO_START_OF_SERVICE. For the translation that works fine for me, but I'd like my orientation to be aligned with gravity, so that the yaw and roll angles are aligned with gravity rather than with the arbitrary position at which the Tango service started. I'm fine with an arbitrary azimuth angle.
I can do this by using the accelerometer data to get the absolute orientation at one point in time and then use that going forward, but is there an easier way?
I think the Z axis of TANGO_COORDINATE_FRAME_CAMERA_DEPTH frame is always aligned with gravity.
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.
I have been working on a 3D scanner for a while now and I still have some questions about the projection matrix I want to clear out before I continue.
I understand the fact that this matrix describes the relation between the camera coordinate system and the world coordinate system. Yet I don't understand why all the calibration software packages give you this matrix? Does the software just picks a random world coordinate system in space and does it calculate the matrix afterwards?
I was thinking it would be way easier to choose the world coordinate system by yourself (if it is even possible). My plan is to create a scanner where the object stands still on a static surface and where the camera + laser moves around the object in a circular movement. If it would be possible to create your projection matrix this way so the world coordinate system is nicely placed in the middle of the static platform.
If I'm not very clear, let me know and I'll add an image.
Hopefully someone can clear things a little bit up for me so I can make some progress :).
Kind regards
Ruts
The matrix after camera calibration give you relation between two cameras (stereo vision) and it consist of intrinsic and extrinsic of camera. The matrix convert your image to 3D coordinate system and give you depth of objects.
The are number of video on youtube about 3D scanner.
http://www.youtube.com/watch?v=AYq5n7jwe40 or http://www.youtube.com/watch?v=H3WzY8EWM9s
I've managed to understand how to project 3d point to 2d screen.
Now, I would like to ask some guidelines on how to integrate phone rotation according to accelerometar data to change marker's screen coordinate.
You need the gyro data, not the accelerometer data.
The gyro mouse might work for your application, see between 37:00-38:25 in the Google Tech Talk.
If you need more than the gyro mouse then I highly recommend Direction Cosine Matrix IMU: Theory, it is basically a tutorial on how to implement orientation tracking.
Similar questions:
track small movements of iphone with no GPS
What is the real world accuracy of phone accelerometers when used for positioning?
how to calculate phone's movement in the vertical direction from rest?
iOS: Movement Precision in 3D Space
How to use Accelerometer to measure distance for Android Application Development
How can I find distance traveled with a gyroscope and accelerometer?
I'd like to implement a dragging feature where users can drag objects around the workspace. That of course is the easy bit. The hard bit is to try and make it a physically correct drag which incorporates rotation due to torque moments (imagine dragging a book around on a table using only one finger, how does it rotate as you drag?).
Does anyone know where I can find explanations on how to code this (2D only, rectangles only, no friction required)?
Much obliged,
David
EDIT:
I wrote a small app (with clearly erroneous behaviour) that I hope will convey what I'm looking for much better than words could. C# (VS 2008) source and compiled exe here
EDIT 2:
Adjusted the example project to give acceptable behaviour. New source (and compiled exe) is available here. Written in C# 2008. I provide this code free of any copyright, feel free to use/modify/whatever. No need to inform me or mention me.
Torque is just the applied force projected perpendicular to a vector between the point where the force is applied and the centroid of the object. So, if you pull perpendicular to the diameter, the torque is equal to the applied force. If you pull directly away from the centroid, the torque is zero.
You'd typically want to do this by modeling a spring connecting the original mouse-down point to the current position of the mouse (in object-local coordinates). Using a spring and some friction smooths out the motions of the mouse a bit.
I've heard good things about Chipmunk as a 2D physics package:
http://code.google.com/p/chipmunk-physics/
Okay, It's getting late, and I need to sleep. But here are some starting points. You can either do all the calculations in one coordinate space, or you can define a coordinate space per object. In most animation systems, people use coordinate spaces per object, and use transformation matrices to convert, because it makes the math easier.
The basic sequence of calculations is:
On mouse-down, you do your hit-test,
and store the coordinates of the
event (in the object coordinate
space).
When the mouse moves, you create a
vector representing the distance
moved.
The force exterted by the spring is k * M, where M is the amount of distance between that initial mouse-down point from step 1, and the current mouse position. k is the spring constant of the spring.
Project that vector onto two direction vectors, starting from the initial mouse-down point. One direction is towards the center of the object, the other is 90 degrees from that.
The force projected towards the center of the object will move it towards the mouse cursor, and the other force is the torque around the axis. How much the object accelerates is dependent on its mass, and the rotational acceleration is dependent on angular momentum.
The friction and viscosity of the medium the object is moving in causes drag, which simply reduces the motion of the object over time.
Or, maybe you just want to fake it. In that case, just store the (x,y) location of the rectangle, and its current rotation, phi. Then, do this:
Capture the mouse-down location in world coordinates
When the mouse moves, move the box according to the change in mouse position
Calculate the angle between the mouse and the center of the object (atan2 is useful here), and between the center of the object and the initial mouse-down point. Add the difference between the two angles to the rotation of the rectangle.
This would seem to be a basic physics problem.
You would need to know where the click, and that will tell you if they are pushing or pulling, so, though you are doing this in 2D, your calculations will need to be in 3D, and your awareness of where they clicked will be in 3D.
Each item will have properties, such as mass, and perhaps information for air resistance, since the air will help to provide the motion.
You will also need to react differently based on how fast the user is moving the mouse.
So, they may be able to move the 2 ton weight faster than is possible, and you will just need to adapt to that, as the user will not be happy if the object being dragged is slower than the mouse pointer.
Which language?
Here's a bunch of 2d transforms in C