Dual-camera 3D head tracking for clinical infant monitoring

R.W.J.J. Saeijs, W.E. Tjon A Ten, P.H.N. de With

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)
1 Downloads (Pure)

Abstract

This paper presents a new algorithm for dual-camera 3D head tracking, intended for clinical infant monitoring. The paper includes a brief motivation with reference to the state-of-the-art in face-related image analysis. The proposed algorithm uses a clipped-ellipsoid head model and 3D head pose recovery by joint alignment of paired templates based on dense-HOG features. In the algorithm, template pairs are dynamically extracted and a limited number of template pairs are stored and re-used for drift reduction. We report experimental results on real-life videos of infants in bed in a hospital, captured in visual light as well as near-infrared light. Results show consistently good tracking behavior. For challenging video sequences, the mean tracking error in terms of endocanthion location error relative to the innercanthal distance remains below 30%. This error has proven to be sufficiently low for 3D head tracking to support infant face analysis. For this reason, the proposed algorithm is used successfully in an infant monitoring system under development.

Original languageEnglish
Title of host publication2018 International Conference on Intelligent Systems and Computer Vision, ISCV 2018
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages1-8
Number of pages8
ISBN (Electronic)978-1-5386-4396-9
ISBN (Print)978-1-5386-4397-6
DOIs
Publication statusPublished - 3 May 2018
Event2018 International Conference on Intelligent Systems and Computer Vision, ISCV 2018 - Fez, Morocco
Duration: 2 Apr 20184 Apr 2018

Conference

Conference2018 International Conference on Intelligent Systems and Computer Vision, ISCV 2018
CountryMorocco
CityFez
Period2/04/184/04/18

Keywords

  • 3D head tracking
  • dense HOG
  • dual camera
  • infant monitoring

Fingerprint Dive into the research topics of 'Dual-camera 3D head tracking for clinical infant monitoring'. Together they form a unique fingerprint.

Cite this