The Kinect Sensor returns 16-bit raw depth frame data in a row of stride in Figure 4.
The first three bits are used to represent the identified players and the remaining 13 bits give
you the measured depth distance in millimeters.
In the Figure 4, the upper 13 bits, which represent the actual distance of the pixel value from the sensor and lower 3 bits represent player index.
For depth distance calculation from the 13 bits, a bitwise shift operation (>>) need to be perform to move thebits to their correct position.