Development of methodology for features partially detected reconstruction after cartographic features extraction in digital images: case study: curved features

• Grant number: 17/13029-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: September 01, 2017
• End date: July 31, 2020
• Field of knowledge: Physical Sciences and Mathematics - Geosciences
• Principal Investigator: Erivaldo Antonio da Silva
• Grantee: Ana Luisa Chaves Figueira
• Host Institution: Faculdade de Ciências e Tecnologia (FCT). Universidade Estadual Paulista (UNESP). Campus de Presidente Prudente. Presidente Prudente , SP, Brazil
• Associated scholarship(s): 18/21965-8 - Interfacement of the methodology developed to reconstruct features partially detected in digital images to cartomorph and development of methodology for minimizing noise around the rebuilded features, BE.EP.IC

Abstract

The process of cartographic features extraction from digital images have been of great importance in the area of Cartography. These processes has as main objective the identification of targets on the terrestrial surface, such as highways, drainage, airport runways, and the updating of cartographic products. The terrestrial surfaces changes constantly and these changes are mainly caused by anthropic and nature actions. The identification of such changes is essential for the cartography of a country like Brazil, which has continental dimensions. A number of techniques concerning Digital Images Processing can be used in the process of features extraction and, almost every time, the results obtained from these techniques present partially detected features, which represent significant loss in terms of quality of the extraction process. Although there are studies that involve the reconstruction of these features, their applications in curvilinear features generates low-quality effects. Therefore, based on what have been said, the main goal of this project was the development of a reconstruction methodology for partially detected curvilinear features. This was achieved through applying inpainting techniques proposed by Marcelo Bertalmio and Guillermo Sapiro [1], Andrea L. Bertozzi, Selim Esedoglu, and Alan Gillette[2], aiming the improvement of the results concerning the extraction process of partially detected curvilinear features. (AU)