Road segment extraction from varied resolution images using the parallel edges principle

• Grant number: 05/03184-9
• Support Opportunities: Scholarships in Brazil - Master
• Start date: October 01, 2006
• End date: July 31, 2008
• Field of knowledge: Physical Sciences and Mathematics - Geosciences - Geodesy
• Principal Investigator: Aluir Porfírio Dal Poz
• Grantee: Regina Ishibashi
• Host Institution: Faculdade de Ciências e Tecnologia (FCT). Universidade Estadual Paulista (UNESP). Campus de Presidente Prudente. Presidente Prudente , SP, Brazil

Abstract

In this research is proposed two methodologies for road segment extraction from low-, medium-, and high-resolution images. Both methodologies are based on the generalized concept of lines in digital images, by which lines can be described as symmetry features between two parallel edges. In specific case of low-resolution images, where roads manifest as features of 1 or 2 pixels wide, line representations coincide with the own roads. In this case, it is proposed a methodology based on the following sequential steps: 1- road network enhancement using the DRO (Duda Road Operator) road operator; 2- Road detection using the concept of parallel edges; and 3- Polygon extraction representing road segments by vectorization and polygonization algorithms. In medium- and high-resolution images roads manifest as narrow and elongated strips and, consequently, the extraction goal becomes the symmetry axis of each road. In this case, it is necessary only the two last steps of the proposed methodology for low-resolution images. Both methodology will be evaluated with real images of varied resolutions.

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

ISHIBASHI, Regina. Extração de segmentos de rodovias em imagens de resoluções variadas usando o princípio de bordas paralelas. 2008. Master's Dissertation - Universidade Estadual Paulista (Unesp). Faculdade de Ciências e Tecnologia. Presidente Prudente Presidente Prudente.