Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure

A novel stereo matching algorithm is proposed that utilizes color segmentation on the reference image and a self-adapting matching score that maximizes the number of reliable correspondences. The scene structure is modeled by a set of planar surface patches which are estimated using a new technique...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Klaus, A., Sormann, M., Karner, K.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Belief propagation Brightness Image segmentation Image sensors Labeling Layout Pixel Robustness Signal to noise ratio Testing
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!