17 March 2017 Dense-HOG-based drift-reduced 3D face tracking for infant pain monitoring
Author Affiliations +
Proceedings Volume 10341, Ninth International Conference on Machine Vision (ICMV 2016); 103411U (2017) https://doi.org/10.1117/12.2268522
Event: Ninth International Conference on Machine Vision, 2016, Nice, France
Abstract
This paper presents a new algorithm for 3D face tracking intended for clinical infant pain monitoring. The algorithm uses a cylinder head model and 3D head pose recovery by alignment of dynamically extracted templates based on dense-HOG features. The algorithm includes extensions for drift reduction, using re-registration in combination with multi-pose state estimation by means of a square-root unscented Kalman filter. The paper reports experimental results on videos of moving infants in hospital who are relaxed or in pain. Results show good tracking behavior for poses up to 50 degrees from upright-frontal. In terms of eye location error relative to inter-ocular distance, the mean tracking error is below 9%.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ronald W.J.J. Saeijs, Ronald W.J.J. Saeijs, Walther E. Tjon A Ten, Walther E. Tjon A Ten, Peter H. N. de With, Peter H. N. de With, } "Dense-HOG-based drift-reduced 3D face tracking for infant pain monitoring", Proc. SPIE 10341, Ninth International Conference on Machine Vision (ICMV 2016), 103411U (17 March 2017); doi: 10.1117/12.2268522; https://doi.org/10.1117/12.2268522
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT

Image sequence coding using 3D scene models
Proceedings of SPIE (September 16 1994)
Three-dimensional motion tracking by Kalman filtering
Proceedings of SPIE (October 11 2000)
Tracking a rigid object in 3D from a single camera
Proceedings of SPIE (August 18 1997)
Three-dimensional semantic object tracking in video sequences
Proceedings of SPIE (December 27 2000)

Back to Top