Semantic Structure from Motion for Railroad Bridges Using Deep Learning

Abstract

Current maintenance practices consume significant time, cost, and manpower. Thus, a new technique for maintenance is required. Construction information technologies, including building information modeling (BIM), have recently been applied to the field to carry out systematic and productive planning, design, construction, and maintenance. Although BIM is increasingly being applied to new structures, its application to existing structures has been limited. To apply BIM to an existing structure, a three-dimensional (3D) model of the structure that accurately represents the as-is status should be constructed and each structural component should be specified manually. This study proposes a method that constructs a 3D model and specifies the structural component automatically using photographic data with a camera installed on an unmanned aerial vehicle. This procedure is referred to as semantic structure from motion because it constructs a 3D point cloud model together with semantic information. A validation test was carried out on a railroad bridge to validate the performance of the proposed system. The average precision, intersection over union, and BF scores were 80.87%, 66.66%, and 56.33%, respectively. The proposed method could improve the current scan-to-BIM procedure by generating the as-is 3D point cloud model by specifying the structural component automatically.

3D Survey with Apple LiDAR Sensor—Test and Assessment for Architectural and Cultural Heritage

“…Via multi-image photogrammetry, it is possible to obtain complete and exhaustive 3D metric surveys with a rapid and intuitive approach [10,11]. Several examples of this are reported in the literature: ranging from architectural applications [12][13][14] to the control and monitoring of structures [15,16], or to environmental and forestry assessments [17][18][19]. In particular, Structure-from-Motion (SfM) algorithms, used in multi-image photogrammetry, produce accurate point clouds with good repeatability [20] and are well suited for the production of metric documentation.…”

Diretrizes para a digitalização de usinas hidrelétricas baseadas no estudo de caso da usina de Paulo Afonso IV, Bahia: do SCAN-TO-BIM à prática.

“…No contexto da construção civil e indústria, o escaneamento LIDAR aéreo, ou ALS, está predominantemente associado ao uso de drones equipados com escâneres LIDAR, ao invés do uso de aviões acoplados com módulos de escaneamento, algo inviável devido ao custo de combustível, aluguel e piloto (KLINC; JOTANOVI Ć; KRE-GAR, 2021). A aplicação do escâner LIDAR e uma câmera fotográfica acoplado a um drone torna-se vantajosa, em relação ao TLS, em projetos de grande escala, como mapeamento e monitoramento de canteiros de obras, mineração e grandes projetos de infraestrutura (PARK; LEE; YOON, 2021). No entanto, a precisão dos resultados do escaneamento aéreo ainda é bem menor, escala de centímetros (BANFI et al, 2022), e ainda pode variar dependendo da forma que o piloto do drone irá cobrir a área desejada, altitude e clima (JANG et al, 2021).…”