Segmenting Motions of Different Types by Unsupervised Manifold Clustering

We propose a novel algorithm for segmenting multiple motions of different types from point correspondences in multiple affine or perspective views. Since point trajectories associated with different motions live in different manifolds, traditional approaches deal with only one manifold type: linear...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Goh, A., Vidal, R.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Algorithm design and analysis Analysis of variance Clustering algorithms Computer vision Data analysis Functional analysis Motion segmentation Null space Testing Vectors
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!