English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Learning Depth From Stereo

Sinz, F., Candela, J., BakIr, G., Rasmussen, C., & Franz, M. (2004). Learning Depth From Stereo. Pattern Recognition: 26th DAGM Symposium, 245-252.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Sinz, F1, Author           
Candela, JQ2, Author           
BakIr, G2, Author           
Rasmussen, CE2, Author           
Franz, M2, Author           
Rasmussen, Editor
E., C., Editor
Bülthoff, H. H., Editor
Schölkopf, B., Editor
Giese, M. A., Editor
Affiliations:
1Research Group Computational Vision and Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497805              
2Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              

Content

show
hide
Free keywords: -
 Abstract: We compare two approaches to the problem of estimating the depth of a point in space from observing its image position in two different cameras: 1.~The classical photogrammetric approach explicitly models the two cameras and estimates their intrinsic and extrinsic parameters using a tedious calibration procedure; 2.~A generic machine learning approach where the mapping from image to spatial coordinates is directly approximated by a Gaussian Process regression. Our results show that the generic learning approach, in addition to simplifying the procedure of calibration, can lead to higher depth accuracies than classical calibration although no specific domain knowledge is used.

Details

show
hide
Language(s):
 Dates: 2004-09
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: URI: http://dagm.tuebingen.mpg.de/
BibTex Citekey: 2644
 Degree: -

Event

show
hide
Title: 26th DAGM Symposium
Place of Event: Tübingen, Germany
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: Pattern Recognition: 26th DAGM Symposium
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 245 - 252 Identifier: -