Development of methodology for the extraction of cartographic features aiming at updating urban areas using remote sensing images from medium and high spatial resolutions

• Grant number: 21/12584-3
• Support Opportunities: Scholarships abroad - Research Internship - Scientific Initiation
• Effective date (Start): January 01, 2022
• Effective date (End): March 31, 2022
• Field of knowledge: Physical Sciences and Mathematics - Geosciences
• Principal Investigator: Erivaldo Antonio da Silva
• Grantee: Eduardo Soares Nascimento
• Supervisor: Pedro Miguel Berardo Duarte Pina
• Host Institution: Faculdade de Ciências e Tecnologia (FCT). Universidade Estadual Paulista (UNESP). Campus de Presidente Prudente. Presidente Prudente , SP, Brazil
• Research place: Universidade de Coimbra (UC), Portugal
• Associated to the scholarship: 20/07357-5 - Proposition of methodology for the extraction of cartographic features in digital media and high spatial resolutions aiming at updating cartographic products from urban areas (condominiums and lots), BP.IC

Abstract

Nowadays, even with the advance of technologies, monitoring the changes of the earth's surface is one of the biggest problems facing the Brazilian cartography. Being aware of these changes is extremely important for planning, in which it is necessary updated and quality cartographic products, which help and serve as a basis for project implementation. Therefore, with the use of orbital images obtained by Remote Sensing submitted to processes and manipulations, it becomes possible to generate updated and quality cartographic products aiming at solving the problem in question. Thus, combining hybrid techniques of Digital Image Processing (PDI) and Mathematical Morphology (MM) made it possible to detect and extract features of interest, resulting in a cartographic document. Using the Matlab software, through image processing tooboxes, applying PDI techniques together with MM and also with post processing techniques, such as Inpainting, it is possible to detect and extract features of interest. From the Cartomorph software analyze the quality of the results with statistical metrics, so that later can aim to analyze the changes of these areas tests and perform the update of cartographic products. The present project consists of developing an improved methodology for extracting cartographic features aiming at updating urban areas using remote sensing images of medium and high spatial resolutions. (AU)