SU‐E‐I‐92: Accuracy Evaluation of Depth Data in Microsoft Kinect

K. Kozono, M. Aoki, M. Ono, Y. Kamikawa, Hidetaka Arimura, F. Toyofuku

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Purpose: Microsoft Kinect has potential for use in real‐time patient position monitoring in diagnostic radiology and radiotherapy. We evaluated the accuracy of depth image data and the device‐to‐device variation in various conditions simulating clinical applications in a hospital. Methods: Kinect sensor consists of infrared‐ray depth camera and RGB camera. We developed a computer program using OpenNI and OpenCV for measuring quantitative distance data. The program displays depth image obtained from Kinect sensor on the screen, and the cartesian coordinates at an arbitrary point selected by mouse‐clicking can be measured. A rectangular box without luster (300 × 198 × 50 mm3) was used as a measuring object. The object was placed on the floor at various distances ranging from 0 to 400 cm in increments of 10 cm from the sensor, and depth data were measured for 10 points on the planar surface of the box. The measured distance data were calibrated by using the least square method. The device‐to‐device variations were evaluated using five Kinect sensors. Results: There was almost linear relationship between true and measured values. Kinect sensor was unable to measure at a distance of less than 50 cm from the sensor. It was found that distance data calibration was necessary for each sensor. The device‐to‐device variation error for five Kinect sensors was within 0.46% at the distance range from 50 cm to 2 m from the sensor. The maximum deviation of the distance data after calibration was 1.1 mm at a distance from 50 to 150 cm. The overall average error of five Kinect sensors was 0.18 mm at a distance range of 50 to 150 cm. Conclusions: Kinect sensor has distance accuracy of about 1 mm if each device is properly calibrated. This sensor will be useable for positioning of patients in diagnostic radiology and radiotherapy.

Original languageEnglish
Number of pages1
JournalMedical Physics
Volume39
Issue number6
DOIs
Publication statusPublished - Jan 1 2012

Fingerprint

Radiology
Calibration
Radiotherapy
Patient Positioning
Physiologic Monitoring
Least-Squares Analysis
Software
Equipment and Supplies

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

SU‐E‐I‐92 : Accuracy Evaluation of Depth Data in Microsoft Kinect. / Kozono, K.; Aoki, M.; Ono, M.; Kamikawa, Y.; Arimura, Hidetaka; Toyofuku, F.

In: Medical Physics, Vol. 39, No. 6, 01.01.2012.

Research output: Contribution to journalArticle

Kozono, K. ; Aoki, M. ; Ono, M. ; Kamikawa, Y. ; Arimura, Hidetaka ; Toyofuku, F. / SU‐E‐I‐92 : Accuracy Evaluation of Depth Data in Microsoft Kinect. In: Medical Physics. 2012 ; Vol. 39, No. 6.
@article{9813d26ae1be4e3abaf820c1e928ebea,
title = "SU‐E‐I‐92: Accuracy Evaluation of Depth Data in Microsoft Kinect",
abstract = "Purpose: Microsoft Kinect has potential for use in real‐time patient position monitoring in diagnostic radiology and radiotherapy. We evaluated the accuracy of depth image data and the device‐to‐device variation in various conditions simulating clinical applications in a hospital. Methods: Kinect sensor consists of infrared‐ray depth camera and RGB camera. We developed a computer program using OpenNI and OpenCV for measuring quantitative distance data. The program displays depth image obtained from Kinect sensor on the screen, and the cartesian coordinates at an arbitrary point selected by mouse‐clicking can be measured. A rectangular box without luster (300 × 198 × 50 mm3) was used as a measuring object. The object was placed on the floor at various distances ranging from 0 to 400 cm in increments of 10 cm from the sensor, and depth data were measured for 10 points on the planar surface of the box. The measured distance data were calibrated by using the least square method. The device‐to‐device variations were evaluated using five Kinect sensors. Results: There was almost linear relationship between true and measured values. Kinect sensor was unable to measure at a distance of less than 50 cm from the sensor. It was found that distance data calibration was necessary for each sensor. The device‐to‐device variation error for five Kinect sensors was within 0.46{\%} at the distance range from 50 cm to 2 m from the sensor. The maximum deviation of the distance data after calibration was 1.1 mm at a distance from 50 to 150 cm. The overall average error of five Kinect sensors was 0.18 mm at a distance range of 50 to 150 cm. Conclusions: Kinect sensor has distance accuracy of about 1 mm if each device is properly calibrated. This sensor will be useable for positioning of patients in diagnostic radiology and radiotherapy.",
author = "K. Kozono and M. Aoki and M. Ono and Y. Kamikawa and Hidetaka Arimura and F. Toyofuku",
year = "2012",
month = "1",
day = "1",
doi = "10.1118/1.4734809",
language = "English",
volume = "39",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "6",

}

TY - JOUR

T1 - SU‐E‐I‐92

T2 - Accuracy Evaluation of Depth Data in Microsoft Kinect

AU - Kozono, K.

AU - Aoki, M.

AU - Ono, M.

AU - Kamikawa, Y.

AU - Arimura, Hidetaka

AU - Toyofuku, F.

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Purpose: Microsoft Kinect has potential for use in real‐time patient position monitoring in diagnostic radiology and radiotherapy. We evaluated the accuracy of depth image data and the device‐to‐device variation in various conditions simulating clinical applications in a hospital. Methods: Kinect sensor consists of infrared‐ray depth camera and RGB camera. We developed a computer program using OpenNI and OpenCV for measuring quantitative distance data. The program displays depth image obtained from Kinect sensor on the screen, and the cartesian coordinates at an arbitrary point selected by mouse‐clicking can be measured. A rectangular box without luster (300 × 198 × 50 mm3) was used as a measuring object. The object was placed on the floor at various distances ranging from 0 to 400 cm in increments of 10 cm from the sensor, and depth data were measured for 10 points on the planar surface of the box. The measured distance data were calibrated by using the least square method. The device‐to‐device variations were evaluated using five Kinect sensors. Results: There was almost linear relationship between true and measured values. Kinect sensor was unable to measure at a distance of less than 50 cm from the sensor. It was found that distance data calibration was necessary for each sensor. The device‐to‐device variation error for five Kinect sensors was within 0.46% at the distance range from 50 cm to 2 m from the sensor. The maximum deviation of the distance data after calibration was 1.1 mm at a distance from 50 to 150 cm. The overall average error of five Kinect sensors was 0.18 mm at a distance range of 50 to 150 cm. Conclusions: Kinect sensor has distance accuracy of about 1 mm if each device is properly calibrated. This sensor will be useable for positioning of patients in diagnostic radiology and radiotherapy.

AB - Purpose: Microsoft Kinect has potential for use in real‐time patient position monitoring in diagnostic radiology and radiotherapy. We evaluated the accuracy of depth image data and the device‐to‐device variation in various conditions simulating clinical applications in a hospital. Methods: Kinect sensor consists of infrared‐ray depth camera and RGB camera. We developed a computer program using OpenNI and OpenCV for measuring quantitative distance data. The program displays depth image obtained from Kinect sensor on the screen, and the cartesian coordinates at an arbitrary point selected by mouse‐clicking can be measured. A rectangular box without luster (300 × 198 × 50 mm3) was used as a measuring object. The object was placed on the floor at various distances ranging from 0 to 400 cm in increments of 10 cm from the sensor, and depth data were measured for 10 points on the planar surface of the box. The measured distance data were calibrated by using the least square method. The device‐to‐device variations were evaluated using five Kinect sensors. Results: There was almost linear relationship between true and measured values. Kinect sensor was unable to measure at a distance of less than 50 cm from the sensor. It was found that distance data calibration was necessary for each sensor. The device‐to‐device variation error for five Kinect sensors was within 0.46% at the distance range from 50 cm to 2 m from the sensor. The maximum deviation of the distance data after calibration was 1.1 mm at a distance from 50 to 150 cm. The overall average error of five Kinect sensors was 0.18 mm at a distance range of 50 to 150 cm. Conclusions: Kinect sensor has distance accuracy of about 1 mm if each device is properly calibrated. This sensor will be useable for positioning of patients in diagnostic radiology and radiotherapy.

UR - http://www.scopus.com/inward/record.url?scp=84903577586&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903577586&partnerID=8YFLogxK

U2 - 10.1118/1.4734809

DO - 10.1118/1.4734809

M3 - Article

AN - SCOPUS:84903577586

VL - 39

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 6

ER -