Estimation of human body shape and posture under clothing

•We present a representation that models human body shape and posture independently.•We estimate body shape and posture under clothing from single or multiple frames.•For multiple frames, the fitting approach is stable.•Higher fitting accuracy is achieved than when using a common variant of SCAPE. E...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer vision and image understanding Jg. 127; S. 31 - 42
Hauptverfasser: Wuhrer, Stefanie, Pishchulin, Leonid, Brunton, Alan, Shu, Chang, Lang, Jochen
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Amsterdam Elsevier Inc 01.10.2014
Elsevier
Schlagworte:
Algorithmics. Computability. Computer arithmetics
Applied sciences
Artificial intelligence
Biological and medical sciences
Computer science; control theory; systems
Digital human shape and posture modeling
Exact sciences and technology
Fitting accuracy
Fundamental and applied biological sciences. Psychology
Geometry processing
Hosiery manufacture
Human subjects
Motion sequences
Pattern recognition. Digital image processing. Computational geometry
Perception
Posture modeling
Psychology. Psychoanalysis. Psychiatry
Psychology. Psychophysiology
Psychophysics
Search spaces
Statistical modeling
Statistical shape space
Statistical shapes
Theoretical computing
Virtual reality
Statistical shape space
Digital human shape and posture modeling
Geometry processing
Invariant
Statistical analysis
Probabilistic approach
Clothing
Form defect
Psychophysics
Modeling
Posture
Computational geometry
Visual cue
Body movement
Skeleton
Body
ISSN:1077-3142, 1090-235X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•We present a representation that models human body shape and posture independently.•We estimate body shape and posture under clothing from single or multiple frames.•For multiple frames, the fitting approach is stable.•Higher fitting accuracy is achieved than when using a common variant of SCAPE. Estimating the body shape and posture of a dressed human subject in motion represented as a sequence of (possibly incomplete) 3D meshes is important for virtual change rooms and security. To solve this problem, statistical shape spaces encoding human body shape and posture variations are commonly used to constrain the search space for the shape estimate. In this work, we propose a novel method that uses a posture-invariant shape space to model body shape variation combined with a skeleton-based deformation to model posture variation. Our method can estimate the body shape and posture of both static scans and motion sequences of human body scans with clothing that fits relatively closely to the body. In case of motion sequences, our method takes advantage of motion cues to solve for a single body shape estimate along with a sequence of posture estimates. We apply our approach to both static scans and motion sequences and demonstrate that using our method, higher fitting accuracy is achieved than when using a variant of the popular SCAPE model [2,18] as statistical model.
ISSN:1077-3142
1090-235X
DOI:10.1016/j.cviu.2014.06.012