+ Site Statistics
+ Search Articles
+ PDF Full Text Service
How our service works
Request PDF Full Text
+ Follow Us
Follow on Facebook
Follow on Twitter
Follow on LinkedIn
+ Subscribe to Site Feeds
Most Shared
PDF Full Text
+ Translate
+ Recently Requested

An evaluation of 3D head pose estimation using the Microsoft Kinect v2



An evaluation of 3D head pose estimation using the Microsoft Kinect v2



Gait and Posture 48: 83-88



The Kinect v2 sensor supports real-time non-invasive 3D head pose estimation. Because the sensor is small, widely available and relatively cheap it has great potential as a tool for groups interested in measuring head posture. In this paper we compare the Kinect's head pose estimates with a marker-based record of ground truth in order to establish its accuracy. During movement of the head and neck alone (with static torso), we find average errors in absolute yaw, pitch and roll angles of 2.0±1.2°, 7.3±3.2° and 2.6±0.7°, and in rotations relative to the rest pose of 1.4±0.5°, 2.1±0.4° and 2.0±0.8°. Larger head rotations where it becomes difficult to see facial features can cause estimation to fail (10.2±6.1% of all poses in our static torso range of motion tests) but we found no significant changes in performance with the participant standing further away from Kinect - additionally enabling full-body pose estimation - or without performing face shape calibration, something which is not always possible for younger or disabled participants. Where facial features remain visible, the sensor has applications in the non-invasive assessment of postural control, e.g. during a programme of physical therapy. In particular, a multi-Kinect setup covering the full range of head (and body) movement would appear to be a promising way forward.

Please choose payment method:






(PDF emailed within 0-6 h: $19.90)

Accession: 057180020

Download citation: RISBibTeXText

PMID: 27477714

DOI: 10.1016/j.gaitpost.2016.04.030


Related references

Head Pose Estimation on Top of Haar-Like Face Detection: A Study Using the Kinect Sensor. Sensors 15(9): 20945-20966, 2015

Pose estimation with a Kinect for ergonomic studies: evaluation of the accuracy using a virtual mannequin. Sensors 15(1): 1785-1803, 2015

Validity and reliability of head posture measurement using Microsoft Kinect. British Journal of Ophthalmology 98(11): 1560-1564, 2014

Estimation of pig weight using a Microsoft Kinect prototype imaging system. Computers and Electronics in Agriculture 109: 32-35, 2014

Repurposing the Microsoft Kinect for Windows v2 for external head motion tracking for brain PET. Physics in Medicine and Biology 60(22): 8753-8766, 2015

Evaluation of the Microsoft Kinect for screening ACL injury. Conference Proceedings 2013: 4152-4155, 2013

Evaluation of foot posture using the Microsoft Kinect. Journal of Science and Medicine in Sport 16: E24-E25, 2013

Microsoft Kinect based head tracking for Life Size Collaborative Surgical Simulation Environments (LS-CollaSSLE). Studies in Health Technology and Informatics 184: 109-113, 2013

SU-E-I-92: Accuracy Evaluation of Depth Data in Microsoft Kinect. Medical Physics 39(6part5): 3646, 2012

Using the Microsoft Kinect for patient size estimation and radiation dose normalization: proof of concept and initial validation. Journal of Digital Imaging 26(4): 657-662, 2013

A technological evaluation of the Microsoft Kinect for automated behavioural mapping at bed rest. Studies in Health Technology and Informatics 188: 39-45, 2013

Evaluation of the Microsoft Kinect as a clinical assessment tool of body sway. Gait and Posture 40(4): 532-538, 2014

Accuracy and robustness of Kinect pose estimation in the context of coaching of elderly population. Conference Proceedings 2012: 1188-1193, 2012

Head pose estimation method based on pose manifold and tensor decomposition. Journal of Systems Engineering and Electronics 21(5): 907-913, 2010

Model-free non-rigid head pose tracking by joint shape and pose estimation. Machine Vision and Applications 27(8): 1229-1242, 2016