Connected Components Labeling on the GPU with Generalization to Voronoi Diagrams and Signed Distance Fields

被引：0

作者：

Rasmusson, A. ^{[1
,2
]}

Sorensen, T. S. ^{[1
]}

Ziegler, G. ^{[3
]}

机构：

[1] Aarhus Univ, DK-8000 Aarhus C, Denmark

[2] Aarhus Univ, Stereology & EM Lab, DK-8000Y Aarhus C, Denmark

[3] Nvidia Corp, Santa Clara, CA USA

来源：

ADVANCES IN VISUAL COMPUTING, ISVC 2013, PT I | 2013年 / 8033卷

关键词：

Computer vision; connected components labeling; GPU; Voronoi diagrams;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Many image processing problems benefit from a complete solution to connected components labeling. This paper introduces a new data parallel labeling method based on calculation of label propagation sizes from the connectivity between pixels extracted in a pre-processing step and re-usal of established label propagation routes. The method achieves real-time performance for 2D images and it also generalizes to Voronoi diagrams and signed distance fields.

引用

页码：206 / 215

页数：10

共 6 条

[1] Voronoi diagrams of algebraic distance fields
Emiris, Ioannis Z.
Mantzaflaris, Angelos
Mourrain, Bernard
COMPUTER-AIDED DESIGN, 2013, 45 (02) : 511 - 516
[2] Generating signed distance fields on the GPU with ray maps
Bastian Krayer
Stefan Müller
The Visual Computer, 2019, 35 : 961 - 971
[3] Generating signed distance fields on the GPU with ray maps
Krayer, Bastian
Mueller, Stefan
VISUAL COMPUTER, 2019, 35 (6-8): : 961 - 971
[4] Optimizing GPU-Based Connected Components Labeling Algorithms
Allegretti, Stefano
Bolelli, Federico
Cancilla, Michele
Grana, Costantino
2018 IEEE THIRD INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, APPLICATIONS AND SYSTEMS (IPAS), 2018, : 175 - 180
[5] GaussMR: Interactive Gaussian Splatting Sandbox with GPU Particles and Signed Distance Fields
Taniguchi, Daiki
PROCEEDINGS OF THE SIGGRAPH 2024 IMMERSIVE PAVILION, 2024,
[6] On GPU Connected Components and Properties: A Systematic Evaluation of Connected Component Labeling Algorithms and Their Extension for Property Extraction
Asad, Pedro
Marroquim, Ricardo
Souza, Andrea L. e L.
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (01) : 17 - 31

← 1 →