Application of inpainting techniques for the reconstruction of partially detected cartographic features and removal of excessive segmentation

• Grant number: 21/12585-0
• Support Opportunities: Scholarships abroad - Research Internship - Scientific Initiation
• Start date: January 01, 2022
• End date: March 31, 2022
• Field of knowledge: Physical Sciences and Mathematics - Geosciences
• Principal Investigator: Erivaldo Antonio da Silva
• Grantee: Allan Alves Lopes Ferreira
• 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
• Institution abroad: Universidade de Coimbra (UC), Portugal
• Associated to the scholarship: 20/07709-9 - APPLICATION OF INPANTING TECHNIQUES AND SEGMENTATION REMOVAL IN DIGITAL IMAGES OF PARTIALLY DETECTED CARTOGRAPHIC FEATURES, BP.IC

Abstract

The present project consists in the implementation and application of an Inpainting technique of digital images for the reconstruction of partially detected cartographic features and the removal of excessive segmentation, resulting from the application of morphological routines. With this, an Inpainting technique was selected that will be used to reconstruct and remove the excessive segmentation contained in digital images of partially detected cartographic features resulting from the application of morphological routines based on the theory of Mathematical Morphology. Then, the selection of testing areas of cartographic features that were extracted with some damaged part or excessive segmentation, whose nature of these features are anthropic, such as streets, highways, airports, etc. Starting from this problem, the inpainting techniques of Kimura et al [1] will be studied and implemented, and then applied to the extractions of cartographic features. Therefore, this project is important due to the needs of creating and updating cartographic products at various scales, contributing to the mapping in the national territory. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

NASCIMENTO, EDUARDO SOARES; LOPES FERREIRA, ALLAN ALVES; GODOY, THAMIRES GIL; MARTINEZ FONTOURA JUNIOR, CAIO FLAVIO; CARDIM, GUILHERME PINA; BERARDO DUARTE PINA, PEDRO MIGUEL; DA SILVA, ERIVALDO ANTONIO. CARTOGRAPHIC FEATURES EXTRACTION METHODOLOGY IN REMOTE SENSING IMAGES AIMING AT THE CARTOGRAPHIC UPDATE OF ALLOTMENTS. GEOSPATIAL WEEK 2023, VOL. 10-1, v. N/A, p. 6-pg., 2023-01-01. (21/12585-0, 23/07543-1, 21/12584-3)