Methodology for extraction and / or detection of cartographic features using mathematical morphology and digital image processing techniques

• Grant number: 19/06608-7
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): August 01, 2019
• Effective date (End): April 30, 2021
• Field of knowledge: Physical Sciences and Mathematics - Geosciences
• Principal Investigator: Erivaldo Antonio da Silva
• Grantee: Thamires Gil Godoy
• Host Institution: Faculdade de Ciências e Tecnologia (FCT). Universidade Estadual Paulista (UNESP). Campus de Presidente Prudente. Presidente Prudente , SP, Brazil

Abstract

Even today in Brazil, there are some regions with deficiency of cartographic coverage. In addition, the maps are constantly out of date due to the natural changes that have occurred in the environment over the years or those caused directly by the action of man. The Brazilian Cartography presents a great deficiency in relation to the updating of cartographic products. Products from Remote Sensing have been widely used to support the area of Cartography. Remote Sensing images are processed through Digital Image Processing (PDI) techniques that involve the manipulation and interpretation of digital images. Among the several PDI tools chosen for the extraction of the cartographic features was the Mathematical Morphology, initially elaborated by MATHERON (1975) and SERRA (1982). The purpose of Mathematical Morphology is to describe quantitatively the geometric structures and to work as a technique in the design of algorithms in the area of PDI, having basic tools such as edge detectors and morphological filters. Currently, Mathematical Morphology is a widely used and researched theory in Universities and Research Centers around the world, thus being an excellent basis for studying the geometry of the signal, since it allows quantifying shape and size. In this way, this project has as main objective to propose an integrated method for extraction and treatment of cartographic features using techniques of Mathematical Morphology and Digital Image Processing. The result of the extraction will be submitted to a quality control to verify the accuracy obtained with the application of the proposed method and to prove the potential of its use in the area of cartography.