Leonardo Assumpção Moreira

Leonardo Assumpção Moreira

Auto-generated profile, based on publicly available information

Leonardo Assumpção Moreira

Programa de Pós Graduação em Ciências Geodésicas, Universidade Federal do Paraná

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2022 in Boletim de Ciências Geodésicas
Verified
Journal Article
Open access
LMLeonardo Assumpção Moreira
Leonardo Assumpção Moreira
LPLivia Moreira Poelking
Livia Moreira Poelking
HAHideo Araki
Hideo Araki

27 July 2023 in Anuário do Instituto de Geociências
Verified
Journal Article
Open access
PDF file
LMLeonardo Assumpção Moreira
Leonardo Assumpção Moreira
LPLivia Moreira Poelking
Livia Moreira Poelking
ASAlan Salomão
Alan Salomão
HAHideo Araki
Hideo Araki
Digital elevation models are responsible for providing altimetric information on a surface to be mapped. While global models of low and medium spatial resolution are available open source by several space agencies, the high- resolution ones, which are utilized in scales 1:25,000 and larger, are scarce and expensive. Here we address this limitation by the utilization of deep learning algorithms coupled with Single Image Super-Resolution techniques in digital elevation models to obtain better spatial quality versions from lower resolution inputs. The development of a GAN-based (Generative Adversarial Network-based) methodology enables the improvement of the initial spatial resolution of low-resolution images. In the geospatial data context, for example, these algorithms can be used with digital elevation models and satellite images. The methodological approach uses a dataset with digital elevation models SRTM (Shuttle Radar Topography Mission) (30 meters of spatial resolution) and ALOS PALSAR (12.5 meters of spatial resolution), created with the objective of allowing the study to be carried out, promoting the emergence of new research groups in the area as well as enabling the comparison between the results obtained. It has been found that by increasing the number of iterations the performance of the generated model was improved and the quality of the generated image increased. Furthermore, the visual analysis of the generated image against the high- and low-resolution ones showed a great similarity between the first two.

10 July 2020 in Revista Brasileira de Geomática
Verified
Journal Article
Open access
PDF file
LMLeonardo Assumpção Moreira
Leonardo Assumpção Moreira
CKClaudia Pereira Krueger
Claudia Pereira Krueger
O uso do GNSS (Global Navigation Satellite System) vem se difundindo nas mais distintas aplicações, e o método de posicionamento em tempo real tem sido uma forma de determinação de coordenadas de veemente importância em diversas áreas da engenharia. Com o progresso da ciência e da tecnologia, novos equipamentos vêm sendo desenvolvidos, proporcionando uma melhora na precisão e a acurácia destes levantamentos, permitindo sua aplicação em monitoramento de linhas de costa, execução de levantamentos hidrográficos e cadastrais, entre outros. O presente artigo avalia a acurácia e precisão de alguns destes métodos de posicionamento em tempo real, como: o o RTK via NTRIP (Network Transport of RTCM Via Internet Protocol) e o RTG (Real Time Gipsy). A área de pesquisa localizou-se na Diretoria de Hidrografia e Navegação (DHN), em Niterói/RJ, permitindo a realização de levantamentos simultâneos com 03 equipamentos. Como resultado dos desníveis realizados, os erros altimétricos médios apresentados foram de 0,0608m para o NTRIP e 0,4332m para o RTG. Em relação as precisões, os valores médios calculados foram de 0,0869m para o NTRIP e 0,4246m para o RTG. Dessa forma, o NTRIP obteve melhores resultados para o experimento realizado, tanto na precisão quanto na acurácia, considerando-se todas as variáveis impostas pela metodologia adotada. O rastreio NTRIP perdeu algumas correções diferenciais devido a problemas de conectividade do telefone celular com o rastreador. O rastreio RTG não apresentou problemas quanto ao recebimento das correções diferenciais em todo o experimento.

8 September 2025 in Anuário do Instituto de Geociências
Verified
Journal Article
Open access
LMLeonardo Assumpção Moreira
Leonardo Assumpção Moreira
LPLivia Moreira Poelking
Livia Moreira Poelking
HAHideo Araki
Hideo Araki
RMRodrigo Souto Maior
Rodrigo Souto Maior
Digital Surface Models (DSM) are responsible for providing altimetric information on a surface to be mapped. This work addressesthe viability of the utilization of deep learning algorithms coupled with Single Image Super Resolution (SISR) techniques in DSMto obtain better spatial quality versions from lower resolution inputs. The development of a Generative Adversarial Network (GAN)-based methodology enables this improvement of the initial spatial resolution of low resolution images. A dataset with different pairs ofDSM was created with the objective of allowing the study to be carried out, promoting the emergence of new research groups in thearea as well as enabling the comparison between the results obtained. It has been found that by increasing the number of iterations the performance of the generated model was improved and the quality of the generated image increased. Furthermore, the visual analysis of the generated image against the high and low resolution ones showed a great similarity between the first two.