Camera Calibration Parameters for Kinect. How to get intrinsic and extrinsic parameters?
7 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Hi;
I am new to Kinect programming and Camera Calibration in general.
I have been told that to start collecting data from the Kinect, it is important to calibrate the Kinect to get its intrinsic and extrinsic camera parameters.
So a quick search on the matlab website about camera calibration showed me what I needed to do.
So my problem is:
(1) the Kinect has two cameras; an RGB camera and a depth camera. Those two together are considered as stereo vision correct?
(2) If I perform the calibration procedures using the checkered board, will I be obtaining the parameters for both the RGB camera and the depth camera?
Sorry for the confusing questions.
Appreciate your answer.
0 comentarios
Respuestas (1)
Zheng
el 15 de Jul. de 2014
It really depends on your application. Depth camera itself already gives you back the 3D information, so you probably don't use the pair as a conventional stereo system. In another word, you don't need to do stereo calibration. If you want to use the conventional checkerboard to do calibration for each camera (mainly for radial distortion correction), it is fine. But you cannot see the checkers clearly in depth camera. you should use the IR camera (if you are using the old version of kinect).
The calibration involved in kinect is mostly about the alignment between color and depth camera. Sometimes people also calibrate the depth camera to improve the depth accuracy. Both steps do not exactly follow the traditional checkerboard workflow. Also MS SDK already provides the alignment function. If you are able to use the latest computer vision system toolbox 14b from matlab, you can easily get the aligned frame, called alignColorToDepth. You can also get the point cloud from depth image, and start from there. For many applications, these are good enough to start post-process. For a customized calibration procedure, check the following research work: http://www.ee.oulu.fi/~dherrera/papers/2012-KinectJournal.pdf
1 comentario
jenny jenny
el 15 de Oct. de 2017
Good morning sir, I have a problem to get the point cloud from depth image because i have to be connected to the kinect but for mei have a existing dataset and if i want estract cloud point i have to seaurch for the parameters of kinect, i will be thankful if you give me some help.
Ver también
Categorías
Más información sobre Acquisition Using Kinect for Windows Hardware en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!