The Kinect V2 is composed of a time-of-flight continues-wave camera with a resolution of 512*424 pixels (width*height), an RGB camera with a resolution of 1920*1080 pixels (width*height), an array of 4 microphones and some electronics for signal elaboration. The camera is able to acquire images at a maximum frequency of 30 Hz. Sending out invisible structures pulses into the scene whilst measuring the individual traveling time of each point in the pulse (See figure 3.1, page 16). The operating field is defined by a depth range of 0.5m-4.5m and a 70- degrees horizontal and 60-degrees vertical view angle (Corti, Giancola, Mainetti, and Sala, 2016).
A Software Development Kit (SDK), provided by Microsoft, gives the possibility to write software to control the device and in particular, to acquire and save the depth stream, the IR stream, the colour stream and the audio stream values through USB3.0. The SDK also contains a function, based on the pinhole camera model, called coordinate mapper, which transforms acquired depth map data from the camera reference frame to the world refer- ence frame, …show more content…
Optical depth-finding motion-sensing prototype Figure 3.1: Microsoft Kinect for Windows v2 sensor. (a) Appearance of Kinect v2 (front view). (b) Camera config- uration (isometric view). (c) Camera configuration (front view). Image and caption source: Yang, Zhang, Dong, Alelaiwi, and El Saddik, 2015
3.1.1. Single tracker accuracy distribution
Depth accuracy means the difference between the true depth value and the average value of the measured depth values corresponding with a planar surface located in front of a Kinect v2. As shown in part A in the figure blow (See figure 3.2, page 17), the depth values inside the light blue circle are captured by a Kinect v2 representing a planar surface and a average depth value is calculated as the center of the circle. The difference between the mentioned average depth value and the true depth value is defined as depth
A Software Development Kit (SDK), provided by Microsoft, gives the possibility to write software to control the device and in particular, to acquire and save the depth stream, the IR stream, the colour stream and the audio stream values through USB3.0. The SDK also contains a function, based on the pinhole camera model, called coordinate mapper, which transforms acquired depth map data from the camera reference frame to the world refer- ence frame, …show more content…
Optical depth-finding motion-sensing prototype Figure 3.1: Microsoft Kinect for Windows v2 sensor. (a) Appearance of Kinect v2 (front view). (b) Camera config- uration (isometric view). (c) Camera configuration (front view). Image and caption source: Yang, Zhang, Dong, Alelaiwi, and El Saddik, 2015
3.1.1. Single tracker accuracy distribution
Depth accuracy means the difference between the true depth value and the average value of the measured depth values corresponding with a planar surface located in front of a Kinect v2. As shown in part A in the figure blow (See figure 3.2, page 17), the depth values inside the light blue circle are captured by a Kinect v2 representing a planar surface and a average depth value is calculated as the center of the circle. The difference between the mentioned average depth value and the true depth value is defined as depth