Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  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

Externe Referenzen

einblenden:
ausblenden:
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Engel, D1, 2, 3, Autor           
Curio, C1, 2, 3, Autor           
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              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: 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

einblenden:
ausblenden:
Sprache(n):
 Datum: 2008-12
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: DOI: 10.1109/ICPR.2008.4761373
BibTex Citekey: 5257
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 19th International Conference on Pattern Recognition (ICPR 2008)
Veranstaltungsort: Tampa, FL, USA
Start-/Enddatum: 2008-12-08 - 2008-12-11

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: 2008 19th International Conference on Pattern Recognition
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Piscataway, NJ, USA : IEEE
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 1 - 4 Identifikator: ISBN: 978-1-424-42174-9