opencv/doc/user_guide/user_highgui.tex
2011-01-27 10:53:13 +00:00

89 lines
3.2 KiB
TeX

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% %
% C++ %
% %
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\ifCpp
\section{Using Kinect sensor.}
To get Kinect data there is support in VideoCapture class. So the user can retrieve depth map,
rgb image and some other formats of Kinect output by using familiar interface of \texttt{VideoCapture}.\par
To use existing support of Kinect sensor the user should do the following preliminary steps:\newline
1.) Install OpenNI library and PrimeSensor Module for OpenNI from here \url{http://www.openni.
org/downloadfiles}. The installation should be made in default folders listed in install instrac-
tions of these products:
\begin{lstlisting}
OpenNI:
Linux & MacOSX:
Libs into: /usr/lib
Includes into: /usr/include/ni
Windows:
Libs into: c:/Program Files/OpenNI/Lib
Includes into: c:/Program Files/OpenNI/Include
PrimeSensor Module:
Linux & MacOSX:
Libs into: /usr/lib
Bins into: /usr/bin
Windows:
Libs into: c:/Program Files/Prime Sense/Sensor/Lib
Bins into: c:/Program Files/Prime Sense/Sensor/Bin
\end{lstlisting}
2.) Configure OpenCV with OpenNI support by setting \texttt{WITH\_OPENNI} flag in CMake. If OpenNI
is found in default install folders OpenCV will be built with OpenNI library regardless of whether
PrimeSensor Module is found or not. If PrimeSensor Module was not found the user get warning
about this in CMake log. OpenCV is compiled with OpenNI library even though PrimeSensor
Module was not detected, but \texttt{VideoCapture} object can not grab the data from Kinect sensor in
such case. Build OpenCV.\par
VideoCapture provides retrieving the following Kinect data:
\begin{lstlisting}
a.) data given from depth generator:
OPENNI_DEPTH_MAP - depth values in mm (CV_16UC1)
OPENNI_POINT_CLOUD_MAP - XYZ in meters (CV_32FC3)
OPENNI_DISPARITY_MAP - disparity in pixels (CV_8UC1)
OPENNI_DISPARITY_MAP_32F - disparity in pixels (CV_32FC1)
OPENNI_VALID_DEPTH_MASK - mask of valid pixels (not ocluded,
not shaded etc.) (CV_8UC1)
b.) data given from RGB image generator:
OPENNI_BGR_IMAGE - color image (CV_8UC3)
OPENNI_GRAY_IMAGE - gray image (CV_8UC1)
\end{lstlisting}
To get depth map from Kinect the user can use \texttt{VideoCapture::operator >>}, e. g.
\begin{lstlisting}
VideoCapture capture(0); // or CV_CAP_OPENNI
for(;;)
{
Mat depthMap;
capture >> depthMap;
if( waitKey( 30 ) >= 0 )
break;
}
\end{lstlisting}
To get several Kinect maps the user should use \texttt{VideoCapture::grab + VideoCapture::retrieve},
e. g.
\begin{lstlisting}
VideoCapture capture(0); // or CV_CAP_OPENNI
for(;;)
{
Mat depthMap;
Mat rgbImage
capture.grab();
capture.retrieve( depthMap, OPENNI_DEPTH_MAP );
capture.retrieve( bgrImage, OPENNI_BGR_IMAGE );
if( waitKey( 30 ) >= 0 )
break;
}
\end{lstlisting}
For more information see example kinect maps.cpp in sample folder.
\fi