Header logo is avg

High Resolution Surface Reconstruction from Multi-view Aerial Imagery

2012

Conference Paper

ps


This paper presents a novel framework for surface reconstruction from multi-view aerial imagery of large scale urban scenes, which combines probabilistic volumetric modeling with smooth signed distance surface estimation, to produce very detailed and accurate surfaces. Using a continuous probabilistic volumetric model which allows for explicit representation of ambiguities caused by moving objects, reflective surfaces, areas of constant appearance, and self-occlusions, the algorithm learns the geometry and appearance of a scene from a calibrated image sequence. An online implementation of Bayesian learning precess in GPUs significantly reduces the time required to process a large number of images. The probabilistic volumetric model of occupancy is subsequently used to estimate a smooth approximation of the signed distance function to the surface. This step, which reduces to the solution of a sparse linear system, is very efficient and scalable to large data sets. The proposed algorithm is shown to produce high quality surfaces in challenging aerial scenes where previous methods make large errors in surface localization. The general applicability of the algorithm beyond aerial imagery is confirmed against the Middlebury benchmark.

Author(s): Calakli, Fatih and Ulusoy, Ali O. and Restrepo, Maria I. and Taubin, Gabriel and Mundy, Joseph L.
Book Title: 3D Imaging Modeling Processing Visualization Transmission (3DIMPVT)
Pages: 25--32
Year: 2012
Publisher: IEEE

Department(s): Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: 10.1109/3DIMPVT.2012.54

URL: http://mesh.brown.edu/gssd/pdf/Calakli-3dimpvt2012.pdf

Links: Video
Attachments: pdf

BibTex

@inproceedings{Calakli2012,
  title = {{High Resolution Surface Reconstruction from Multi-view Aerial Imagery}},
  author = {Calakli, Fatih and Ulusoy, Ali O. and Restrepo, Maria I. and Taubin, Gabriel and Mundy, Joseph L.},
  booktitle = {3D Imaging Modeling Processing Visualization Transmission (3DIMPVT)},
  pages = {25--32},
  publisher = {IEEE},
  year = {2012},
  url = {http://mesh.brown.edu/gssd/pdf/Calakli-3dimpvt2012.pdf}
}