Automatic street graph construction in sketch maps

Authors:
Klaus Broelemann;Xiaoyi Jiang;Angela Schwering
Affiliations:
Department of Mathematics and Computer Science, University of Münster, Germany;Department of Mathematics and Computer Science, University of Münster, Germany;Institute for Geoinformatics, University of Münster, Germany
Venue:
GbRPR'11 Proceedings of the 8th international conference on Graph-based representations in pattern recognition
Year:
2011

Citing 8
Cited 0

Parallel thinning with two-subiteration algorithms

Communications of the ACM
Text/Graphics Separation Revisited

DAS '02 Proceedings of the 5th International Workshop on Document Analysis Systems V
A System for Constructing Boundary Representation Solid Models from a Two-Dimensional Sketch

GMP '00 Proceedings of the Geometric Modeling and Processing 2000
Supervised Evaluation Methodology for Curvilinear Structure Detection Algorithms

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
State of the art on automatic road extraction for GIS update: a novel classification

Pattern Recognition Letters
Magic Paper: Sketch-Understanding Research

Computer
LADDER, a sketching language for user interface developers

Computers and Graphics
Mobile Multimedia Processing: fundamentals, Methods, and Applications

Mobile Multimedia Processing: fundamentals, Methods, and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present an algorithm for automatic street graph construction of hand-drawn sketch maps. This detection is important for a subsequent graph matching in order to align the sketch map with another map. Our algorithm detects a number of street candidates and selects street lines by rating the candidates and their neighbors in the street candidate graph. To evaluate this approach, we manually generated a ground truth for some maps and conducted a preliminary quantitative performance study.