English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Scale-invariant medial features based on gradient vector flow fields

Engel, D., & Curio, C. (2008). Scale-invariant medial features based on gradient vector flow fields. In 2008 19th International Conference on Pattern Recognition (pp. 1-4). Piscataway, NJ, USA: IEEE.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-C63B-4 Version Permalink: http://hdl.handle.net/21.11116/0000-0003-3797-5
Genre: Conference Paper

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Engel, D1, 2, 3, Author              
Curio, C1, 2, 3, Author              
Affiliations:
1Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              
3Project group: Cognitive Engineering, Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_2528702              

Content

show
hide
Free keywords: -
 Abstract: We propose a novel set of medial feature interest points based on gradient vector flow (GVF) fields [18]. We exploit the long ranging GVF fields for symmetry estimation by calculating the flux flow on it. We propose interest points that are located on maxima of that flux flow and offer a straight forward way to estimate salient local scales. The features owe their robustness in clutter to the nature of the GVF which accomplishes two goals simultaneously - smoothing of orientation information and its preservation at salient edge boundaries. A learning framework based on them, in contrast to classical edge-based feature detectors, would unlikely be distracted by background clutter and spurious edges, as these new mid-level features are shape-centered. We evaluate our scale-invariant feature coding scheme against standard SIFT keypoints by demonstrating generalization over scale in a patch-based pedestrian detection task.

Details

show
hide
Language(s):
 Dates: 2008-12
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: DOI: 10.1109/ICPR.2008.4761373
BibTex Citekey: 5257
 Degree: -

Event

show
hide
Title: 19th International Conference on Pattern Recognition (ICPR 2008)
Place of Event: Tampa, FL, USA
Start-/End Date: 2008-12-08 - 2008-12-11

Legal Case

show

Project information

show

Source 1

show
hide
Title: 2008 19th International Conference on Pattern Recognition
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Piscataway, NJ, USA : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1 - 4 Identifier: ISBN: 978-1-424-42174-9