Semantic Structure from Motion for Railroad Bridges Using Deep Learning

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.

[1]  Hyungchul Yoon,et al.  Automatic Bridge Design Parameter Extraction for Scan-to-BIM , 2020, Applied Sciences.

[2]  Oral Büyüköztürk,et al.  Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks , 2017, Comput. Aided Civ. Infrastructure Eng..

[3]  J. Kwiatkowski,et al.  Comparison of Non-Destructive Techniques for Technological Bridge Deflection Testing , 2020, Materials.

[4]  Francesco Abbondati,et al.  I-BIM for existing airport infrastructures , 2020 .

[5]  Esin Ergen,et al.  BIM for building refurbishment and maintenance: current status and research directions , 2015 .

[6]  Francesco Abbondati,et al.  BIM Approach for Modeling Airports Terminal Expansion , 2020 .

[7]  Kenneth R. White,et al.  Close-range photogrammetry applications in bridge measurement: Literature review , 2008 .

[8]  S. Ullman.  The interpretation of structure from motion , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[9]  Ki-Nam Hong,et al.  Vision-Based Structural FE Model Updating Using Genetic Algorithm , 2021, Applied Sciences.

[10]  Qian Wang,et al.  An Application Oriented Scan-to-BIM Framework , 2019, Remote. Sens..

[11]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[12]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[13]  Billie F. Spencer,et al.  Vision‐based automated bridge component recognition with high‐level scene consistency , 2019, Comput. Aided Civ. Infrastructure Eng..

[14]  Sung-Han Sim,et al.  Automated bridge component recognition from point clouds using deep learning , 2020, Structural Control and Health Monitoring.

[15]  Paola Villoria Sáez,et al.  Terrestial laser scanning digitalization in underground constructions , 2019, Journal of Cultural Heritage.

[16]  Mani Golparvar-Fard,et al.  Target‐free approach for vision‐based structural system identification using consumer‐grade cameras , 2016 .

[17]  Xiao Liang,et al.  Image‐based post‐disaster inspection of reinforced concrete bridge systems using deep learning with Bayesian optimization , 2018, Comput. Aided Civ. Infrastructure Eng..

[18]  Pelagia Gawronek,et al.  Measurements of the Vertical Displacements of a Railway Bridge Using TLS Technology in the Context of the Upgrade of the Polish Railway Transport , 2019, Sensors.

[19]  Frédéric Bosché,et al.  The value of integrating Scan-to-BIM and Scan-vs-BIM techniques for construction monitoring using laser scanning and BIM: The case of cylindrical MEP components , 2015 .

[20]  Damian Beben,et al.  A Case Study on the Noncontact Inventory of the Oldest European Cast-iron Bridge Using Terrestrial Laser Scanning and Photogrammetric Techniques , 2020, Remote. Sens..