TY - JOUR
T1 - Influence of a marker-based motion capture system on the performance of Microsoft Kinect v2 skeleton algorithm
AU - Naeemabadi, Mohammadreza
AU - Dinesen, Birthe
AU - Andersen, Ole Kæseler
AU - Hansen, John
PY - 2019/1/1
Y1 - 2019/1/1
N2 - Microsoft Kinect sensors are being widely used as low-cost marker-less motion capture systems in various kinematic studies. Previous studies investigated the reliability and validity of Microsoft Kinect sensors by employing marker-based motion capture systems. Both systems employ IR emitters and detectors to track human posture and physical activities. This paper hypothesizes that the motion capture systems may interfere with Microsoft Kinect One sensor and influence the sensor’s performance in tracking the skeleton. Hence, this study investigated the impact of a motion capture system on the Microsoft Kinect v2 skeleton algorithm using a mannequin in the presence of eight Qualisys Oqus 300/310 cameras and retroreflective markers. It was found that the motion capture system introduced a destructive impact on the Microsoft Kinect v2 skeleton tracking algorithm. In addition, it was observed that retroreflective markers placed near the joints caused the Microsoft Kinect v2 to give an incorrect reading of estimate the joint position. The motion capture cameras thus caused a timevarying distortion of the Microsoft Kinect estimate of the joint position. It is believed that the inference can be reduced by decreasing the number of markers and avoiding facing the motion capture cameras in sight of Microsoft Kinect v2.
AB - Microsoft Kinect sensors are being widely used as low-cost marker-less motion capture systems in various kinematic studies. Previous studies investigated the reliability and validity of Microsoft Kinect sensors by employing marker-based motion capture systems. Both systems employ IR emitters and detectors to track human posture and physical activities. This paper hypothesizes that the motion capture systems may interfere with Microsoft Kinect One sensor and influence the sensor’s performance in tracking the skeleton. Hence, this study investigated the impact of a motion capture system on the Microsoft Kinect v2 skeleton algorithm using a mannequin in the presence of eight Qualisys Oqus 300/310 cameras and retroreflective markers. It was found that the motion capture system introduced a destructive impact on the Microsoft Kinect v2 skeleton tracking algorithm. In addition, it was observed that retroreflective markers placed near the joints caused the Microsoft Kinect v2 to give an incorrect reading of estimate the joint position. The motion capture cameras thus caused a timevarying distortion of the Microsoft Kinect estimate of the joint position. It is believed that the inference can be reduced by decreasing the number of markers and avoiding facing the motion capture cameras in sight of Microsoft Kinect v2.
KW - Bones
KW - Cameras
KW - experimental noise analysis
KW - Joints
KW - Microsoft Kinect sensor
KW - mutual interference
KW - Qualisys motion capture system
KW - RGB-D sensor
KW - Sensor systems
KW - Tracking
UR - http://www.scopus.com/inward/record.url?scp=85055018211&partnerID=8YFLogxK
U2 - 10.1109/JSEN.2018.2876624
DO - 10.1109/JSEN.2018.2876624
M3 - Journal article
AN - SCOPUS:85055018211
SN - 1530-437X
VL - 19
SP - 171
EP - 179
JO - IEEE Sensors Journal
JF - IEEE Sensors Journal
IS - 1
M1 - 8494823
ER -