Abstract:ABSTRACT:The extraction of information from image and range data is one of the main research topics. In literature, several papers dealing with this topic has been already presented. In particular, several authors have suggested an integrated use of both range and image information in order to increase the reliability and the completeness of the results exploiting their complementary nature. In this paper, an integration between range and image data for the geometric reconstruction of man-made object is presen… Show more
“…Based on the results of previous studies [62,[69][70][71], this combination is advantageous, especially in the area of orthorectification and texturing 3D models. The combination is valuable in texture mapping of point clouds to obtain 3D photorealistic models, e.g., [72,73]; extraction of reference objects for registration and calibration, e.g., [74]; adoption of images for registration of multiple scans, e.g., [75]; using images to reconstruct the main shape of the object and employing TLS data to reconstruct the detailed areas, e.g., [76,77]; and filling holes and gaps in point clouds caused by occlusions, e.g., [73].…”
Section: Multi-sensor Integration For Developing the 3d Modelmentioning
As the most comprehensive document types for the recording and display of real-world information regarding construction projects, 3D realistic models are capable of recording and displaying simultaneously textures and geometric shapes in the same 3D scene. However, at present, the documentation for much of construction infrastructure faces significant challenges. Based on TLS, GNSS/IMU, mature photogrammetry, a UAV platform, computer vision technologies, and AI algorithms, this study proposes a workflow for 3D modeling of complex structures with multiple-source data. A deep learning LoFTR network was used first for image matching, which can improve matching accuracy. Then, a NeuralRecon network was employed to generate a 3D point cloud with global consistency. GNSS information was used to reduce search space in image matching and produce an accurate transformation matrix between the image scene and the global reference system. In addition, to enhance the effectiveness and efficiency of the co-registration of the two-source point clouds, an RPM-net was used. The proposed workflow processed the 3D laser point cloud and UAV low-altitude multi-view image data to generate a complete, accurate, high-resolution, and detailed 3D model. Experimental validation on a real high formwork project was carried out, and the result indicates that the generated 3D model has satisfactory accuracy with a registration error value of 5 cm. Model comparison between the TLS, image-based, data fusion 1 (using the common method), and data fusion 2 (using the proposed method) models were conducted in terms of completeness, geometrical accuracy, texture appearance, and appeal to professionals. The results denote that the generated 3D model has similar accuracy to the TLS model yet also provides a complete model with a photorealistic appearance that most professionals chose as their favorite.
“…Based on the results of previous studies [62,[69][70][71], this combination is advantageous, especially in the area of orthorectification and texturing 3D models. The combination is valuable in texture mapping of point clouds to obtain 3D photorealistic models, e.g., [72,73]; extraction of reference objects for registration and calibration, e.g., [74]; adoption of images for registration of multiple scans, e.g., [75]; using images to reconstruct the main shape of the object and employing TLS data to reconstruct the detailed areas, e.g., [76,77]; and filling holes and gaps in point clouds caused by occlusions, e.g., [73].…”
Section: Multi-sensor Integration For Developing the 3d Modelmentioning
As the most comprehensive document types for the recording and display of real-world information regarding construction projects, 3D realistic models are capable of recording and displaying simultaneously textures and geometric shapes in the same 3D scene. However, at present, the documentation for much of construction infrastructure faces significant challenges. Based on TLS, GNSS/IMU, mature photogrammetry, a UAV platform, computer vision technologies, and AI algorithms, this study proposes a workflow for 3D modeling of complex structures with multiple-source data. A deep learning LoFTR network was used first for image matching, which can improve matching accuracy. Then, a NeuralRecon network was employed to generate a 3D point cloud with global consistency. GNSS information was used to reduce search space in image matching and produce an accurate transformation matrix between the image scene and the global reference system. In addition, to enhance the effectiveness and efficiency of the co-registration of the two-source point clouds, an RPM-net was used. The proposed workflow processed the 3D laser point cloud and UAV low-altitude multi-view image data to generate a complete, accurate, high-resolution, and detailed 3D model. Experimental validation on a real high formwork project was carried out, and the result indicates that the generated 3D model has satisfactory accuracy with a registration error value of 5 cm. Model comparison between the TLS, image-based, data fusion 1 (using the common method), and data fusion 2 (using the proposed method) models were conducted in terms of completeness, geometrical accuracy, texture appearance, and appeal to professionals. The results denote that the generated 3D model has similar accuracy to the TLS model yet also provides a complete model with a photorealistic appearance that most professionals chose as their favorite.
“…Conversely, the point cloud acquired by laser scanner technique allowed to develop a 3D model very detailed on the facades but with a lack of information on the roofs and ledges. For these reasons, a data fusion of the two point clouds was tested, in order to define the complexities of its generation and to show the potentialities offered by a final unique 3D model Nex and Remondino, 2011). This test took place within the software 3D Reshaper and it was focused on a portion of the Santa Maria Church.…”
Section: Different Sensors Clouds Fusion and New Modelsmentioning
ABSTRACT:Recognizing the various advantages offered by 3D new metric survey technologies in the Cultural Heritage documentation phase, this paper presents some tests of 3D model generation, using different methods, and their possible fusion. With the aim to define potentialities and problems deriving from integration or fusion of metric data acquired with different survey techniques, the elected test case is an outstanding Cultural Heritage item, presenting both widespread and specific complexities connected to the conservation of historical buildings. The site is the Staffarda Abbey, the most relevant evidence of medieval architecture in Piedmont. This application faced one of the most topical architectural issues consisting in the opportunity to study and analyze an object as a whole, from twice location of acquisition sensors, both the terrestrial and the aerial one. In particular, the work consists in the evaluation of chances deriving from a simple union or from the fusion of different 3D cloudmodels of the abbey, achieved by multi-sensor techniques. The aerial survey is based on a photogrammetric RPAS (Remotely piloted aircraft system) flight while the terrestrial acquisition have been fulfilled by laser scanning survey. Both techniques allowed to extract and process different point clouds and to generate consequent 3D continuous models which are characterized by different scale, that is to say different resolutions and diverse contents of details and precisions. Starting from these models, the proposed process, applied to a sample area of the building, aimed to test the generation of a unique 3Dmodel thorough a fusion of different sensor point clouds. Surely, the describing potential and the metric and thematic gains feasible by the final model exceeded those offered by the two detached models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.