Proposal of co-design platform for processing remote sensing images

• Grant number: 14/24392-8
• Support Opportunities: Scholarships in Brazil - Doctorate
• Effective date (Start): March 01, 2015
• Effective date (End): August 31, 2019
• Field of knowledge: Physical Sciences and Mathematics - Geosciences - Geodesy
• Acordo de Cooperação: Coordination of Improvement of Higher Education Personnel (CAPES)
• Principal Investigator: Erivaldo Antonio da Silva
• Grantee: Guilherme Pina Cardim
• Host Institution: Faculdade de Ciências e Tecnologia (FCT). Universidade Estadual Paulista (UNESP). Campus de Presidente Prudente. Presidente Prudente , SP, Brazil
• Associated scholarship(s): 16/04553-2 - Co-designed platform proposal for remote sensing images processing, BE.EP.DR

Abstract

The digital image processing (DIP) consists in a study area with big interest in the scientific community, which needs a lot of information processing. In Cartographic, the remote sensing area use the DPI a lot to detect cartographic features of interest present in the images. Nowadays, with the great technological advances, the remote sensing images have high spatial resolution and so, a lot of information to be processed during the studies related with those images. This way, the processing of high-resolution images normally needs a high processing time. Therefore, several libraries of digital images processing appeared in literature to facilitate the use of DIP functions and improve the performance of them, such as the OpenCV, DipImage and CARTOMORPH. Among the libraries mentioned, it is important to highlight the importance of the CARTOMORPH library, since it was developed aimed the studies of cartographic features detection present in digital images and focused in the mathematical morphology techniques, which are excelling in related studies. However, sometimes the processing of cartographic images, with high resolution, is slow, even using those libraries. This sense, the current project intend to propose a methodology to analyze routines of cartographic features detection, developed with the CAROTMORPH library, to split it and control the operations flow. The proposal continues after splitting the routine, with the possibility of send part of the processing to be performed in a hardware platform. The hardware platform will be defined during the project developing and will be responsible for the processing of high computational cost. Thus, we propose a co-design system between hardware and software able to process images of high spatial resolution, from remote sensing images, to obtain the desired results in a shorter processing time. The project is justified by the necessity of studies to improve the performance of the PDI functions and decrease the waiting time of Cartographic researchers to develop computational routines to detect cartographic features of interest present in remote sensing images. (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)

PINA CARDIM, GUILHERME; DA SILVA, ERIVALDO ANTONIO; DIAS, MAURICIO ARAUJO; BRAVO, IGNACIO; GARDEL, ALFREDO. Statistical Evaluation and Analysis of Road Extraction Methodologies Using a Unique Dataset from Remote Sensing. REMOTE SENSING, v. 10, n. 4, APR 2018. (16/04553-2, 14/24392-8)

CARDIM, GUILHERME PINA; DA SILVA, ERIVALDO ANTONIO; DIAS, MAURICIO ARAUJO; BRAVO, IGNACIO; GARDEL, ALFREDO. A nonrecursive GR algorithm to extract road networks in high-resolution images from remote sensing. EARTH SCIENCE INFORMATICS, AUG 2020. (16/04553-2, 14/24392-8)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

CARDIM, Guilherme Pina. Co-designed platform proposal for remote sensing images processing. 2019. Doctoral Thesis - Universidade Estadual Paulista (Unesp). Faculdade de Ciências e Tecnologia. Presidente Prudente Presidente Prudente.