The introduction of low-cost, relatively high-resolution 3-D sensing systems, like the Microsoft Kinect, has considerable potential in autonomous system applications. One of the impediments to wider Kinect application development is that the available Kinect drivers define C language interfaces. To help fully realize the Kinect's potential, the aims of this paper are 1) to develop a ``VU-Kinect" block which provides easy access to the sensor's camera and depth image streams, and which enables them to be incorporated seamlessly within a higher level, Simulink-based, image-processing and real-time control strategy; 2) to address implementation issues associated with the Kinect, such as sensor calibration; and 3) to show the utility of both the VU-Kinect block and the Kinect itself through a simple 3-D object tracking example.
Published in:
Mechatronics, IEEE/ASME Transactions on
(Volume:PP
,
Issue:
99
)