English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  Three-Dimensional Shape Knowledge for Joint Image Segmentation and Pose Estimation.

Rosenhahn, B., Brox, T., & Weickert, J. (2005). Three-Dimensional Shape Knowledge for Joint Image Segmentation and Pose Estimation. In Pattern recognition: 27th DAGM Symposium (pp. 109-116). Berlin, Germany: Springer.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-000F-2806-F Version Permalink: https://hdl.handle.net/11858/00-001M-0000-000F-2808-B
Genre: Conference Paper

Files

show Files
hide Files
:
brox_dagm05.pdf (Any fulltext), 2MB
 
File Permalink:
-
Name:
brox_dagm05.pdf
Description:
-
OA-Status:
Visibility:
Private
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
Springer
License:
-

Locators

show

Creators

show
hide
 Creators:
Rosenhahn, Bodo1, Author           
Brox, Thomas, Author
Weickert, Joachim, Author
Kropatsch, Walter, Editor
Sablatnig, Robert, Editor
Hanbury, Allan, Editor
Affiliations:
1Computer Graphics, MPI for Informatics, Max Planck Society, ou_40047              

Content

show
hide
Free keywords: -
 Abstract: This paper presents the integration of 3D shape knowledge into a variational model for level set based image segmentation and tracking. Having a 3D surface model of an object that is visible in the image of a calibrated camera, the object contour stemming from the segmentation is applied to estimate the 3D pose parameters, whereas the object model projected to the image plane helps in a top-down manner to improve the extraction of the contour and the region statistics. The present approach clearly states all model assumptions in a single energy functional. This keeps the model manageable and allows further extensions for the future. While common alternative segmentation approaches that integrate 2D shape knowledge face the problem that an object can look very different from various viewpoints, a 3D free form model ensures that for each view the model can perfectly fit the data in the image. Moreover, one solves the higher level problem of determining the object pose including its distance to the camera. Experiments demonstrate the performance of the method.

Details

show
hide
Language(s): eng - English
 Dates: 2006-05-312005
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: eDoc: 278992
Other: Local-ID: C125675300671F7B-F46AAAE404815527C12570DF003295A9-RosenhahnDAGM2005b
 Degree: -

Event

show
hide
Title: Untitled Event
Place of Event: Vienna, Austria
Start-/End Date: 2005-08-31

Legal Case

show

Project information

show

Source 1

show
hide
Title: Pattern recognition : 27th DAGM Symposium
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 109 - 116 Identifier: ISBN: 3-540-28703-5

Source 2

show
hide
Title: Lecture Notes in Computer Science
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 3663 Sequence Number: - Start / End Page: - Identifier: -