Characterization of Different Microsoft Kinect Sensor Models

被引:50
作者
DiFilippo, Nicholas M. [1 ]
Jouaneh, Musa K. [1 ]
机构
[1] Univ Rhode Isl, Dept Mech Engn, Kingston, RI 02881 USA
关键词
Kinect sensor; Kinect accuracy; 3-D image reconstruction; Kinect for Xbox; Kinect for windows; OpenNI; depth; DEPTH; VALIDITY;
D O I
10.1109/JSEN.2015.2422611
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This experimental study investigates the performance of three different models of the Microsoft Kinect sensor using the OpenNI driver from Primesense. The accuracy, repeatability, and resolution of the different Kinect models' abilities to determine the distance to a planar target was explored. An ANOVA analysis was performed to determine if the model of the Kinect, the operating temperature, or their interaction were significant factors in the Kinect's ability to determine the distance to the target. Different sized gauge blocks were also used to test how well a Kinect could reconstruct precise objects. Machinist blocks were used to examine how well the Kinect could reconstruct objects setup on an angle and determine the location of the center of a hole. All the Kinect models were able to determine the location of a target with a low standard deviation (<2 mm). At close distances, the resolutions of all the Kinect models were 1 mm. Through the ANOVA analysis, the best performing Kinect at close distances was the Kinect model 1414, and at farther distances was the Kinect model 1473. The internal temperature of the Kinect sensor had an effect on the distance reported by the sensor. Using different correction factors, the Kinect was able to determine the volume of a gauge block and the angles machinist blocks were setup at, with under a 10% error.
引用
收藏
页码:4554 / 4564
页数:11
相关论文
共 30 条
[1]  
Afthoni R, 2013, 2013 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS, BIOMIMETICS, AND INTELLIGENT COMPUTATIONAL SYSTEMS (ROBIONETICS), P24, DOI 10.1109/ROBIONETICS.2013.6743572
[2]  
Alexiadis D.S., 2011, P 19 ACM INT C MULT, P659, DOI [DOI 10.1145/2072298.2072412, 10.1145/2072298.2072412]
[3]  
Alnowami M., 2012, P SOC PHOTO-OPT INS, V8316
[4]  
Andersen M. R., 2012, ECETR6 AARH U DEP EN
[5]   Validity of the Microsoft Kinect for assessment of postural control [J].
Clark, Ross A. ;
Pua, Yong-Hao ;
Fortin, Karine ;
Ritchie, Callan ;
Webster, Kate E. ;
Denehy, Linda ;
Bryant, Adam L. .
GAIT & POSTURE, 2012, 36 (03) :372-377
[6]  
El-laithy RA, 2012, IEEE POSITION LOCAT, P1280, DOI 10.1109/PLANS.2012.6236985
[7]   Controller-free exploration of medical image data: experiencing the Kinect [J].
Gallo, Luigi ;
Placitell, Alessio Pierluigi ;
Ciampi, Mario .
2011 24TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), 2011,
[8]   Enhanced Computer Vision with Microsoft Kinect Sensor: A Review [J].
Han, Jungong ;
Shao, Ling ;
Xu, Dong ;
Shotton, Jamie .
IEEE TRANSACTIONS ON CYBERNETICS, 2013, 43 (05) :1318-1334
[9]   RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments [J].
Henry, Peter ;
Krainin, Michael ;
Herbst, Evan ;
Ren, Xiaofeng ;
Fox, Dieter .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2012, 31 (05) :647-663
[10]  
Kadambi A., 2014, Computer Vision and Machine Learning with RGB-D Sensor, P3, DOI [DOI 10.1007/978-3-319-08651-4_1, 10.1007/978-3-319-08651-4_1]