Paper: | IMDSP-P4.2 | ||
Session: | Image and Multidimensional Signal Processing: Theory and Methods | ||
Time: | Tuesday, May 18, 15:30 - 17:30 | ||
Presentation: | Poster | ||
Topic: | Image and Multidimensional Signal Processing: Image and Video Analysis | ||
Title: | 3D MODEL REFINEMENT USING SURFACE-PARALLAX | ||
Authors: | Amit Agrawal; University of Maryland, College Park | ||
Rama Chellappa; University of Maryland, College Park | |||
Abstract: | We present an approach to update and refine coarse 3D models ofurban environments from a sequence of intensity images usingsurface parallax. This generalizes the plane-parallax recoverymethods to surface-parallax using arbitrary surfaces. A coarse and potentially incomplete depth map of the scene obtained from aDigital Elevation Map (DEM) is used as a reference surface whichis refined and updated using this approach. The reference depthmap is used to estimate the camera motion and the motion of the 3D points on the reference surface is compensated. The resultingparallax, which is an epipolar field, is estimated using anadaptive windowing technique and used to obtain the refined depthmap. | ||
Back |
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops