Automatic road area extraction from printed maps based on linear feature detection

Sebastien Callier, Hideo Saito

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Raster maps are widely available in the everyday life, and can contain a huge amount of information of any kind using labels, pictograms, or color code e.g. However, it is not an easy task to extract roads from those maps due to those overlapping features. In this paper, we focus on an automated method to extract roads by using linear features detection to search for seed points having a high probability to belong to roads. Those linear features are lines of pixels of homogenous color in each direction around each pixel. After that, the seeds are then expanded before choosing to keep or to discard the extracted element. Because this method is not mainly based on color segmentation, it is also suitable for handwritten maps for example. The experimental results demonstrate that in most cases our method gives results similar to usual methods without needing any previous data or user input, but do need some knowledge on the target maps; and does work with handwritten maps if drawn following some basic rules whereas usual methods fail.

Original languageEnglish
Pages (from-to)1758-1765
Number of pages8
JournalIEICE Transactions on Information and Systems
VolumeE95-D
Issue number7
DOIs
Publication statusPublished - 2012 Jul

Fingerprint

Seed
Color codes
Pixels
Color
Labels

Keywords

  • Image segmentation
  • Raster map
  • Road extraction

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

Automatic road area extraction from printed maps based on linear feature detection. / Callier, Sebastien; Saito, Hideo.

In: IEICE Transactions on Information and Systems, Vol. E95-D, No. 7, 07.2012, p. 1758-1765.

Research output: Contribution to journalArticle

@article{ddcb9aed177c4c4c977ded97ef49e95f,
title = "Automatic road area extraction from printed maps based on linear feature detection",
abstract = "Raster maps are widely available in the everyday life, and can contain a huge amount of information of any kind using labels, pictograms, or color code e.g. However, it is not an easy task to extract roads from those maps due to those overlapping features. In this paper, we focus on an automated method to extract roads by using linear features detection to search for seed points having a high probability to belong to roads. Those linear features are lines of pixels of homogenous color in each direction around each pixel. After that, the seeds are then expanded before choosing to keep or to discard the extracted element. Because this method is not mainly based on color segmentation, it is also suitable for handwritten maps for example. The experimental results demonstrate that in most cases our method gives results similar to usual methods without needing any previous data or user input, but do need some knowledge on the target maps; and does work with handwritten maps if drawn following some basic rules whereas usual methods fail.",
keywords = "Image segmentation, Raster map, Road extraction",
author = "Sebastien Callier and Hideo Saito",
year = "2012",
month = "7",
doi = "10.1587/transinf.E95.D.1758",
language = "English",
volume = "E95-D",
pages = "1758--1765",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "7",

}

TY - JOUR

T1 - Automatic road area extraction from printed maps based on linear feature detection

AU - Callier, Sebastien

AU - Saito, Hideo

PY - 2012/7

Y1 - 2012/7

N2 - Raster maps are widely available in the everyday life, and can contain a huge amount of information of any kind using labels, pictograms, or color code e.g. However, it is not an easy task to extract roads from those maps due to those overlapping features. In this paper, we focus on an automated method to extract roads by using linear features detection to search for seed points having a high probability to belong to roads. Those linear features are lines of pixels of homogenous color in each direction around each pixel. After that, the seeds are then expanded before choosing to keep or to discard the extracted element. Because this method is not mainly based on color segmentation, it is also suitable for handwritten maps for example. The experimental results demonstrate that in most cases our method gives results similar to usual methods without needing any previous data or user input, but do need some knowledge on the target maps; and does work with handwritten maps if drawn following some basic rules whereas usual methods fail.

AB - Raster maps are widely available in the everyday life, and can contain a huge amount of information of any kind using labels, pictograms, or color code e.g. However, it is not an easy task to extract roads from those maps due to those overlapping features. In this paper, we focus on an automated method to extract roads by using linear features detection to search for seed points having a high probability to belong to roads. Those linear features are lines of pixels of homogenous color in each direction around each pixel. After that, the seeds are then expanded before choosing to keep or to discard the extracted element. Because this method is not mainly based on color segmentation, it is also suitable for handwritten maps for example. The experimental results demonstrate that in most cases our method gives results similar to usual methods without needing any previous data or user input, but do need some knowledge on the target maps; and does work with handwritten maps if drawn following some basic rules whereas usual methods fail.

KW - Image segmentation

KW - Raster map

KW - Road extraction

UR - http://www.scopus.com/inward/record.url?scp=84863490109&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863490109&partnerID=8YFLogxK

U2 - 10.1587/transinf.E95.D.1758

DO - 10.1587/transinf.E95.D.1758

M3 - Article

AN - SCOPUS:84863490109

VL - E95-D

SP - 1758

EP - 1765

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 7

ER -