Superpixels and Polygons Using Simple Non-iterative Clustering

We present an improved version of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Unlike SLIC, our algorithm is non-iterative, enforces connectivity from the start, requires lesser memory, and is faster. Relying on the superpixel boundaries obtained using our algorithm, we als...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) S. 4895 - 4904
Hauptverfasser: Achanta, Radhakrishna, Susstrunk, Sabine
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.07.2017
Schlagworte:
Clustering algorithms
Estimation
Image color analysis
Image segmentation
Iterative algorithms
Memory management
Partitioning algorithms
ISSN:1063-6919, 1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We present an improved version of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Unlike SLIC, our algorithm is non-iterative, enforces connectivity from the start, requires lesser memory, and is faster. Relying on the superpixel boundaries obtained using our algorithm, we also present a polygonal partitioning algorithm. We demonstrate that our superpixels as well as the polygonal partitioning are superior to the respective state-of-the-art algorithms on quantitative benchmarks.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2017.520