Learning an Infant Body Model from RGB-D Data for Accurate Full Body Motion Analysis - Archive ouverte HAL Access content directly
Book Sections Year : 2018

Learning an Infant Body Model from RGB-D Data for Accurate Full Body Motion Analysis

Abstract

Infant motion analysis enables early detection of neurode-velopmental disorders like cerebral palsy (CP). Diagnosis, however, is challenging, requiring expert human judgement. An automated solution would be beneficial but requires the accurate capture of 3D full-body movements. To that end, we develop a non-intrusive, low-cost, lightweight acquisition system that captures the shape and motion of infants. Going beyond work on modeling adult body shape, we learn a 3D Skinned Multi-Infant Linear body model (SMIL †) from noisy, low-quality, and incomplete RGB-D data. We demonstrate the capture of shape and motion with 37 infants in a clinical environment. Quantitative experiments show that SMIL faithfully represents the data and properly factorizes the shape and pose of the infants. With a case study based on general movement assessment (GMA), we demonstrate that SMIL captures enough information to allow medical assessment. SMIL provides a new tool and a step towards a fully automatic system for GMA.
Fichier principal
Vignette du fichier
hesseMiccai18.pdf (4.61 Mo) Télécharger le fichier
Vignette du fichier
smil.png (169.24 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Loading...

Dates and versions

hal-02162177 , version 1 (21-06-2019)

Identifiers

  • HAL Id : hal-02162177 , version 1

Cite

Nikolas Hesse, Sergi Pujades, Javier Romero, Michael J Black, Christoph Bodensteiner, et al.. Learning an Infant Body Model from RGB-D Data for Accurate Full Body Motion Analysis. In A. Frangi, J. Schnabel, C. Davatzikos, C. Alberola-López, & G. Fichtinger (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI, pp.792-800, 2018. ⟨hal-02162177⟩
237 View
393 Download

Share

Gmail Facebook X LinkedIn More