Accuracy and reliability of optimum distance for high performance Kinect Sensor

A depth/range camera is able to return images like an ordinary camera, however, instead of color, each pixel value represent a particular distance correspond to a point in a real world. Recently, the Microsoft Kinect Sensor is a popular measurement tool due to its ability to provide length measurement, volume measurement, and motion measurement in Biomedical Application. Every researcher wants to know accuracy, precision and reliability of Kinect sensor depth distance performance. This paper presents an investigation of the quality of depth data obtained by Kinect sensor. Based on Kinect Sensor's specification by Microsoft a theoretical accuracy, precision and reliability analysis is presented, which provides an insight into the factors influencing the accuracy of the data. Experimental results show that the absolute mean percentage error of depth measurement increases with increasing distance to the sensor, and ranges from a few millimeters up to about 40mm at the maximum range of sensor. The standard deviation at different distances of plane to the sensor is provided a similar quadratic curve in precision. The reliability of Kinect Sensor is evaluated by using Kuder-Richardson formula 20 shown that 0.76 in reliability. The accuracy, precision and reliability of depth distance is important and beneficial to biomedical application due to the depth perception is required to determine the 3D estimation pose in human motion application.

[1]  B Bonnechère,et al.  Validity and reliability of the Kinect within functional assessment activities: comparison with standard stereophotogrammetry. , 2014, Gait & posture.

[2]  Michael Riis Andersen,et al.  Kinect Depth Sensor Evaluation for Computer Vision Applications , 2012 .

[3]  K. D. Mankoff,et al.  The Kinect: a low‐cost, high‐resolution, short‐range 3D camera , 2013 .

[4]  Kitsunezaki Naofumi,et al.  KINECT applications for the physical rehabilitation , 2012 .

[5]  Janusz Konrad,et al.  A gesture-driven computer interface using Kinect , 2012, 2012 IEEE Southwest Symposium on Image Analysis and Interpretation.

[6]  Linda Denehy,et al.  Validity of the Microsoft Kinect for assessment of postural control. , 2012, Gait & posture.

[7]  Jaafar Gaber,et al.  Creation of 3D Human Avatar using Kinect , 2012 .

[8]  B. Mentiplay,et al.  Reliability and validity of the Microsoft Kinect for evaluating static foot posture , 2013, Journal of Foot and Ankle Research.

[9]  Alexander Verl,et al.  Grasping in Depth maps of time-of-flight cameras , 2008, 2008 International Workshop on Robotic and Sensors Environments.

[10]  Ling Shao,et al.  Enhanced Computer Vision With Microsoft Kinect Sensor: A Review , 2013, IEEE Transactions on Cybernetics.

[11]  Jana Abhijit Kinect for Windows SDK Programming Guide , 2012 .

[12]  Sander Oude Elberink,et al.  Accuracy and Resolution of Kinect Depth Data for Indoor Mapping Applications , 2012, Sensors.

[13]  Jidong Huang,et al.  Study on the use of Microsoft Kinect for robotics applications , 2012, Proceedings of the 2012 IEEE/ION Position, Location and Navigation Symposium.

[14]  Andrew W. Fitzgibbon,et al.  Efficient regression of general-activity human poses from depth images , 2011, 2011 International Conference on Computer Vision.

[15]  François Guimbretière,et al.  Bimanual marking menu for near surface interactions , 2012, CHI.

[16]  Hong Wei,et al.  A survey of human motion analysis using depth imagery , 2013, Pattern Recognit. Lett..