Advanced search
Start date
Betweenand

Methodology development of features reconstruction partially detected after extraction process of cartographic features from digital images

Grant number: 16/09993-0
Support type:Scholarships in Brazil - Scientific Initiation
Effective date (Start): July 01, 2016
Effective date (End): June 30, 2017
Field of knowledge:Physical Sciences and Mathematics - Geosciences
Principal Investigator:Erivaldo Antonio da Silva
Grantee:Raissa Cristina de Souza
Home Institution: Faculdade de Ciências e Tecnologia (FCT). Universidade Estadual Paulista (UNESP). Campus de Presidente Prudente. Presidente Prudente , SP, Brazil

Abstract

Process of cartographic feature from digital images have been widely used in the mapping area. Such processes are the main objectives the identification of targets present in the earth's surface, with for example highways and airport runways, as well as the update of cartographic products. The Earth's surface undergoes constant changes caused mainly by human activities and nature, and the identification of such changes is crucial for mapping of a country with the continental dimensions of Brazil. Several Digital Image Processing techniques can be used in the feature extraction process, such as the Mathematical Morphology (MM). The use of MM theory is due to the great potential of this tool to quantify shape and size of objects to be extracted. The MM was initially prepared by MATHERON (1975) and SAW (1982), and consists of quantitatively describing geometric structures present in the image by means of erosion and dilation operations. Most often, the results of the feature extraction process have partially detected features, resulting in loss of quality of the extraction process. So, based on what was passed, this project has the main objective to develop a methodology for the reconstruction of features partially detected through the use of techniques of active contours, regression and cubic splines in order to improve the results in the extraction process cartographic features in digital images.