Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences

TL;DR

This paper introduces SMIL, a statistical 3D infant body model learned from low-quality RGB-D data, enabling detailed shape and movement analysis for early neurodevelopmental disorder detection.

Contribution

The paper presents a novel method to learn a 3D infant body model from incomplete RGB-D sequences, overcoming data quality and cooperation limitations.

Findings

SMIL accurately models infant shape and pose from RGB-D data.

The model captures sufficient motion detail for clinical assessment.

Demonstrated potential for early neurodevelopmental disorder detection.

Abstract

Statistical models of the human body surface are generally learned from thousands of high-quality 3D scans in predefined poses to cover the wide variety of human body shapes and articulations. Acquisition of such data requires expensive equipment, calibration procedures, and is limited to cooperative subjects who can understand and follow instructions, such as adults. We present a method for learning a statistical 3D Skinned Multi-Infant Linear body model (SMIL) from incomplete, low-quality RGB-D sequences of freely moving infants. Quantitative experiments show that SMIL faithfully represents the RGB-D data and properly factorizes the shape and pose of the infants. To demonstrate the applicability of SMIL, we fit the model to RGB-D sequences of freely moving infants and show, with a case study, that our method captures enough motion detail for General Movements Assessment (GMA), a method used in clinical practice for early detection of neurodevelopmental disorders in infants. SMIL provides a new tool for analyzing infant shape and movement and is a step towards an automated system for GMA.