Document Detail


Video Normals from Colored Lights.
MedLine Citation:
PMID:  21339525     Owner:  NLM     Status:  Publisher    
Abstract/OtherAbstract:
We present an algorithm and the associated single-view capture methodology to acquire the detailed 3D shape, bends, and wrinkles of deforming surfaces. Moving 3D data has been difficult to obtain by methods that rely on known surface features, structured light, or silhouettes. Multispectral photometric stereo is an attractive alternative because it can recover a dense normal field from an untextured surface. We show how to capture such data, which in turn allows us to demonstrate the strengths and limitations of our simple frame-to-frame registration over time. Experiments were performed on monocular video sequences of un-textured cloth, and faces with and without white makeup. Subjects were filmed under spatially separated red, green, and blue lights. Our first finding is that the color photometric stereo setup is able to produce smoothly varying per-frame reconstructions with high detail. Second, when these 3D reconstructions are augmented with 2D tracking results, one can both register the surfaces and relax the homogenous-color restriction of the single-hue subject. Quantitative and qualitative experiments explore both the practicality and limitations of this simple multispectral capture system.
Authors:
Gabriel J Brostow; Carlos Hernandez; George Vogiatzis; Bjorn Stenger; Roberto Cipolla
Related Documents :
16292315 - Force production by disassembling microtubules.
21184495 - Adaptive patterns of movement during arm elevation test in patients with shoulder impin...
15897455 - Quantitating intracellular transport of polyplexes by spatio-temporal image correlation...
22353535 - Shrinking neighbors: a quantitative examination of the 'shrinking building illusion'.
8184285 - Acoustic impedance in the human ear canal.
15129175 - Glides in speech fundamental frequency are reflected in the auditory n1m response.
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2011-2-17
Journal Detail:
Title:  IEEE transactions on pattern analysis and machine intelligence     Volume:  -     ISSN:  1939-3539     ISO Abbreviation:  -     Publication Date:  2011 Feb 
Date Detail:
Created Date:  2011-2-22     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9885960     Medline TA:  IEEE Trans Pattern Anal Mach Intell     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Affiliation:
University College London, London.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Pulmonary embolism in a teenage girl.
Next Document:  Weakly Supervised Recognition of Daily Life Activities with Wearable Sensors.