Academia.eduAcademia.edu

Figure from:The Use of Microsoft Kinect for Human Movement Analysis

See full PDFdownloadDownload figure
Figure 1. Peak Motus and Kinect Systems Set up A Microsoft Kinect camera was also used to capture th 3D human movement. The Microsoft Kinect system wa composed of a depth sensor, an accelerometer and RGI cameras (one VGA and one infrared camera) to produce ; real time 3D image. Proprietary skeleton software designe: for the Kinect camera was used to capture kinematic: movement of human joints. Both the Peak Motus an Microsoft Kinect systems were connected to separat computers and synchronized via a LED sensor to start botl systems simultaneously as depicted in Figure 1.

Figure 1 Peak Motus and Kinect Systems Set up A Microsoft Kinect camera was also used to capture th 3D human movement. The Microsoft Kinect system wa composed of a depth sensor, an accelerometer and RGI cameras (one VGA and one infrared camera) to produce ; real time 3D image. Proprietary skeleton software designe: for the Kinect camera was used to capture kinematic: movement of human joints. Both the Peak Motus an Microsoft Kinect systems were connected to separat computers and synchronized via a LED sensor to start botl systems simultaneously as depicted in Figure 1.

Related Figures (4)

Figure 3. Calibration Tree for Peak Motus Prior to any testing sessions, the equipment was set up as depicted in Figure 1. The Peak Motus set up involved assembling the calibration tree on a tripod as shown in Figure 3. The set up also entailed the use of two basler cameras, with two external lights mounted on the tripod of each camera and connected to the computer, as depicted in Figure 1.
Figure 3. Calibration Tree for Peak Motus Prior to any testing sessions, the equipment was set up as depicted in Figure 1. The Peak Motus set up involved assembling the calibration tree on a tripod as shown in Figure 3. The set up also entailed the use of two basler cameras, with two external lights mounted on the tripod of each camera and connected to the computer, as depicted in Figure 1.
Figure 2. Sitting Moveable platform Microsoft Kinect system, the LED light was activated. The light was activated again, when the left mouse button was used to stop the recording. This approach allowed the frames captured on the Peak Motus system to be cropped to the same frames the Microsoft Kinect system captured.
Figure 2. Sitting Moveable platform Microsoft Kinect system, the LED light was activated. The light was activated again, when the left mouse button was used to stop the recording. This approach allowed the frames captured on the Peak Motus system to be cropped to the same frames the Microsoft Kinect system captured.
The ICC values computed to provide concurrent related evidence of validity when comparing the Microsoft Kinect displacement measures to the traditional Peak Motus system were different for trials 1 and 2. As depicted in Figure 5, trial 1 had a higher concurrent validity mean value (M=0.461, SD= 0.264) than trial 2 (M=0.33, SD=0.211). There was also more variability for the correlation measures of trial | when compared to trial 2. However, the left and right knee joints provided the strongest evidence of concurrent validity measures for both trials; all four of these values were above r=0.7, p<0.05, n=26. Figure 5. Concurrent validity of displacement measures between the traditional and Microsoft Kinect system
The ICC values computed to provide concurrent related evidence of validity when comparing the Microsoft Kinect displacement measures to the traditional Peak Motus system were different for trials 1 and 2. As depicted in Figure 5, trial 1 had a higher concurrent validity mean value (M=0.461, SD= 0.264) than trial 2 (M=0.33, SD=0.211). There was also more variability for the correlation measures of trial | when compared to trial 2. However, the left and right knee joints provided the strongest evidence of concurrent validity measures for both trials; all four of these values were above r=0.7, p<0.05, n=26. Figure 5. Concurrent validity of displacement measures between the traditional and Microsoft Kinect system
the fifteen body joints, however, had a reliability value below r=0.4, p<0.05, n=26. Figure 4. Reliability of displacement measures from the traditional and Microsoft Kinect system
the fifteen body joints, however, had a reliability value below r=0.4, p<0.05, n=26. Figure 4. Reliability of displacement measures from the traditional and Microsoft Kinect system