google-project-tango

Ptoject Tango provides a point cloud, how can you get the position in pixels of a 3D point in the point cloud in meters? I tried using the projection matrix but I get very small values (0.5,1.3 etc) instead of say 1234,324 (in pixels). I include the code I have tried //Get the current rotation matrix Matrix4 projMatrix = mRenderer.getCurrentCamera().getProjectionMatrix(); //Get all the points in the pointcloud and store them as 3D points FloatBuffer pointsBuffer = mPointCloudManager.updateAndGetLatestPointCloudRenderBuffer().floatBuffer; Vector3[] points3D = new Vector3[pointsBuffer.capacity()

I'm using the camera intrinsic (fx, fy, cx, cy, width, hight) to store a depth image of TangoXyzIjData.xyz buffer. Therefore I calculate for each point of xyz the corresponding image point and store its z value x' = (fx * x) / z + cx y' = (fy * y) / z + cy depthImage[x'][y'] = z Now I would like to store the corresponding pose data as well. I'm using the timestamp of TangoXyzIjData.timestamp and the following function getPoseAtTime(double timestamp, TangoCoordinateFramePair framePair) with framepair new TangoCoordinateFramePair(TangoPoseData.COORDINATE_FRAME_START_OF_SERVICE, TangoPoseData

How take picture using project tango ? I read this answer: Using the onFrameAvailable() in Jacobi Google Tango API which works for grabbing a frame but picture quality is not great. Is there any takePicture equivalent ? Note that java API public void onFrameAvailable(int cameraId) { if (cameraId == TangoCameraIntrinsics.TANGO_CAMERA_COLOR) { mTangoCameraPreview.onFrameAvailable(); } } does not provide rgb data. If I use android camera to take picture, tango can not sense depth. There I will have to use TangoCameraPreview. Thanks You don't have to use TangoCameraPreview to get frames in Java.

I bought the lenovo phab 2 pro supporting the tango project from google. Using this setup, it it possible to obtain depth data in form of a pointcloud. But this is not what I need. I would prefer to obtain data in a more raw format like possible to be obtained by the Kinect, where each pixel of the imageplane is assigned a depth value. My question therefore: Is the depth data of the phab2 (or any tango device) possible to be obtained in such a raw format where each pixel is assigned a depth value? My research lead me to countless unsolved cases (typing tango raw data or similar in google,

with the marker detection example ( https://github.com/googlesamples/tango-examples-c/tree/master/cpp_marker_detection_example ) I tried to detect AR Tags with id's higher than 16. For that, I generated Alvar markers using http://wiki.ros.org/ar_track_alvar . (I have read these tags are Alvar in a comment in the google example source code). Is the SDK fixed to detect maximum only 16 ids (4bits)? If yes Does someone know if this will change in the future? I am not interested in QR codes, since they don't seem to be robustly detected from perspective angles. 来源： https://stackoverflow.com

I am trying to convert point clouds sampled and stored in XYZij data (which, according to the document , stores data in camera space) into a world coordinate system so that they can be merged. The frame pair I use for the Tango listener has COORDINATE_FRAME_START_OF_SERVICE as the base frame and COORDINATE_FRAME_DEVICE as the target frame. This is the way I implement the transformation: Retrieve the rotation quaternion from TangoPoseData.getRotationAsFloats() as q_r , and the point position from XYZij as p . Apply the following rotation, where q_mult is a helper method computing the Hamilton