Active contours for visual tracking: a geometric gradient based approach - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 1995

Active contours for visual tracking: a geometric gradient based approach

Arun Kumar
  • Fonction : Auteur
Allen Tannenbaum
  • Fonction : Auteur
Anthony Yezzi
  • Fonction : Auteur
Satyanad Kichenassamy

Résumé

In this paper, we analyze the geometric active contour models discussed previously from a curve evolution point of view and propose some modifications based on gradient flows relative to certain new feature-based Riemannian metrics. This leads to a novel snake paradigm in which the feature of interest may be considered to lie at the bottom of a potential well. Thus the snake is attracted very naturally and efficiently to the desired feature. Moreover, we consider some 3-D active surface models based on these ideas.

Dates et versions

hal-03673059 , version 1 (19-05-2022)

Identifiants

Citer

Arun Kumar, Peter Olver, Allen Tannenbaum, Anthony Yezzi, Satyanad Kichenassamy. Active contours for visual tracking: a geometric gradient based approach. 34th IEEE Conference on Decision and Control, Dec 1995, New Orleans, LA, United States. pp.810-815, ⟨10.1109/CDC.1995.479238⟩. ⟨hal-03673059⟩
16 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More