3D Face Modelling Based on Structured-light Assisted Stereo Sensor

Abstract : In this paper we present a 3D human face reconstruction framework based on stereo sensor coupled with a structured lighting source. Starting from two calibrated images, the active part (video projector) which project controlled lights, allows the operator to locate two sets of structured features with sub-pixel accuracy in both left and right images. Then, exploiting epipolar geome-try improves the matching process by reducing its complexity from a bidirec-tional to a unidirectional search problem. Finally, we perform an adapted dy-namic programming algorithm to obtain corresponding features in each conju-gated scanline separately. Final three dimensional face models are achieved by a pipeline of four steps: (a) stereo triangulation, (b) data interpolation based on cubic spline models, (c) Delaunay triangulation-based meshing, and (d) texture mapping process.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01589133
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Monday, September 18, 2017 - 11:50:22 AM
Last modification on : Thursday, November 21, 2019 - 2:26:07 AM

Links full text

Identifiers

Citation

Boulbaba Ben Amor, Mohsen Ardabilian, Liming Chen. 3D Face Modelling Based on Structured-light Assisted Stereo Sensor. Image Analysis and Processing ICIAP 2005, Sep 2005, Cagliari, Italy. pp.842-849, ⟨10.1007/11553595_103⟩. ⟨hal-01589133⟩

Share

Metrics

Record views

185