Abstract
O objetivo deste trabalho foi aplicar uma metodologia para geração automática de mapas de danos em ortoimagens de fachadas de edifícios, utilizando-se VANT para a captura das fotografias. A geração de mapas de danos visa auxiliar na inspeção visual, método empregado nas atividades de recuperação manutenção ou intervenção em edifícios. Utilizando a técnica de dense stereo matching (DSM), modelos geométricos de edifícios foram gerados por nuvem de pontos no programa PhotoScan para a obtenção de ortoimagens. Após esta etapa, as ortoimagens foram submetidas à etapa de geração de mapas de danos de manchas escuras no Programa Tyche, que mapeou e quantificou percentualmente estas manifestações patológicas. Os resultados dos mapas de danos foram classificados também qualitativamente. A aplicação de VANT demonstrou ser uma ferramenta eficiente para a atividade de inspeção de fachadas e para a captura de imagens a serem utilizadas por meio da DSM. A geração de mapas de danos pelo Tyche demonstrou ser também eficaz, no entanto a interação do usuário mostrou-se importante para alcançar os resultados esperados.
Highlights
Do you need to create dense 3D point clouds and detailed surface models of physical objects, and do you want to do it in a cost-effective and efficient manner? A new class of 3D scanning technologies, called photo-based scanning, may be the solution you are looking for
We want to capture a high density of 3D points in a regular grid on the surface in an efficient manner - this is 3D scanning
The top part was 3D scanned, and bottom part was manually marked with lines, points and simple surfaces, all from one set of photos and all within PhotoModeler Scanner - resulting in a consistent model with no difficult merging or coordinate alignment processes required
Summary
A new class of 3D scanning technologies, called photo-based scanning, may be the solution you are looking for. Do you need to create dense 3D point clouds and detailed surface models of physical objects, and do you want to do it in a cost-effective and efficient manner? If the object or scene is complex and a high level of surface detail is required, creating the digital 3D model using point-based measurement methods (such as CMMs, touch-probe digitizers, or point photogrammetry) may not work or may not be efficient. We want to capture a high density of 3D points in a regular grid on the surface in an efficient manner - this is 3D scanning. If the intervals are small we get a dense and accurate representation of the surface in our digital 3D model
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
