kinect

I am working with my Kinect on some 2D 3D image processing. Here is my problem: I have points in 3D (x,y,z) which lie on a plane. I also know the coordinates of the points on the RGB image (x,y). Now I want to estimate a 2D-3D homography matrix to estimate the (x1,y1,z1) coordinates to a random (x1,y1) point. I think that is possible, but I don't know where to start. Thanks! What you're looking for is a camera projection matrix , not a homography . A homography maps a plane seen from a camera to the same plane seen from another. For estimating the camera matrix, look up solutions to solving

I have made a Kinect Application in Microsoft Visual Studio 2010. I need to make an exe of the application which can run on any windows based system. If I need to do that than is there any requirements that the system should fulfil? and If yes, then how do I do that? I tried to use the exe in application/bin/debug/application.exe by copying it in another folder but it shows an error but if I run the exe from the bin/debug/application.exe it works. Am I missing something here or is it the only way to do that? "Any Windows based system" isn't going to work. Assuming you're using the Kinect SDK,

I´m trying to make a dynamic point cloud visualizer. The points are updated every frame with Kinect Sensor. To grab the frames I´m using OpenCV and GLUT to display. The OpenCV API returns a 640 x 480 (float *), for the points xyz position , and a 640 x 480 (int *) for the rgb color data. To get the maximum performance, I´m trying to use Vertex Buffer Object in stream mode instead of a simple Vertex Array. I´m being able to render it with Vertex Array, but nothing is being rendered with my VBO implementation. I tryied a bunch of different orders in the declarations, but i can't find what I'm

I'm working with Kinect and OpenCV. I already search in this forum but I didn't find anything like my problem. I keep the raw depth data from Kinect (16 bit), I store it in a CvMat* and then I pass it to the cvGetImage to create an IplImage* from it: CvMat* depthMetersMat = cvCreateMat( 480, 640, CV_16UC1 ); [...] cvGetImage(depthMetersMat,temp); But now I need to work on this image in order to do cvThreshdold and find contours. These 2 functions need an 8-bit-depth-image in input. How can I convert the CvMat* depthMetersMat in an 8-bit-depth-CvMat* ? The answer that @SSteve gave almost did

I am looking for way to (as quick as possible) get the corresponding depth to a color pixel from the Kinect camera. I have found the MapDepthFrameToColorFrame function. But that only gives me the color at a certain depth position, I want the opposite. The reason I want this is that I will be able to click on a position at the RGB image and get the position to that pixel. Is there a way to do this faster than looping through all results from MapDepthFrameToColorFrame? The problem here is that not every color pixel will have a depth assigned to it because of the way the cameras and IR emitter

I have a Kinect program in Processing 2 that I would like to test or simulate by passing it saved skeletons from an .oni file rather than taking input from the Kinect. Is it possible to do this, i.e. to get Processing 2 instead of using the Kinect it should read values from the .oni file and produce an output? I recommend using the SimpleOpenNI library: import SimpleOpenNI.*; SimpleOpenNI ni; void setup(){ size(640,480); ni = new SimpleOpenNI(this); if(SimpleOpenNI.deviceCount() == 0) ni.openFileRecording("/path/to/yourRecording.oni"); ni.enableDepth(); } void draw(){ ni.update(); image(ni