Applied photogrammetry for civil engineering
Lead Research Organisation:
University College London
Department Name: Civil Environmental and Geomatic Eng
Abstract
The project aims to enhance civil engineering industry capability in applied photogrammetry, particularly in the field of infrastructure asset management, inspection and appraisal. The project will help to explore, develop and deliver the next generation of digital photogrammetry tools. It is expected that this will provide significant benefits to automation and appraisal of infrastructure asset condition which will benefit whole life project and maintenance costs, and also the health, safety and welfare of civil engineers in this field. The research will focus on the development of a low-cost photogrammetric inspection system, image processing and data analytics.
The combination of computer vision and Deep Learning as accessible imaging technology has enabled significant quality, cost and safety improvements to be made to conventional routines of inspection and management of civil infrastructure assets.
The research will focus on underground rail tunnel inspection providing an end to end tool for high-accuracy inspections, providing the user with a full automated rapport with information about the actual conditions of the inspected structure.
The combination of computer vision and Deep Learning as accessible imaging technology has enabled significant quality, cost and safety improvements to be made to conventional routines of inspection and management of civil infrastructure assets.
The research will focus on underground rail tunnel inspection providing an end to end tool for high-accuracy inspections, providing the user with a full automated rapport with information about the actual conditions of the inspected structure.
People |
ORCID iD |
| Jan Boehm (Primary Supervisor) | |
| Fabio Panella (Student) |
Studentship Projects
| Project Reference | Relationship | Related To | Start | End | Student Name |
|---|---|---|---|---|---|
| EP/P510683/1 | 01/10/2016 | 30/09/2021 | |||
| 1835904 | Studentship | EP/P510683/1 | 20/03/2017 | 19/09/2021 | Fabio Panella |
| Description | The civil engineering and construction sector, including the railway industry, is seeking innovative approaches to reduce costs on repetitive and labour-intensive tasks and avoid the use of highly qualified engineers for simple manual duties. Such tasks can include the visual inspection of tunnels, where the process is still dominated by manual operations. the project analyses the benefits of substituting conventional visual inspections of tunnels with automated survey approaches and computer vision techniques. The project's outcomes suggest that photogrammetry is a valid alternative to laser scanning for tunnel visual inspection: from the geometric point of view it provides comparable global accuracy to the laser scanner technique but it also halves the time to generate the 3D model and provides the user with photo-realistic outputs, making it possible to perform defect recognition at a smaller scale. It is generally more versatile, and easier to inspect, visualise and navigate the data. This technique, in combination with deep learning algorithms for defect detection, can drastically improve asset management of underground infrastructure and H&S conditions of the operators speeding up the data acquisition. |
| Exploitation Route | The outcomes of this research have already partially put to use. An experimental project in collaboration with Network Rail have demonstrated the effectiveness of the project. Anyway inspection of tunnels is not the only possible application. A wider area of application could be the construction industry in general. |
| Sectors | Construction,Education,Transport |
| Description | The research project have been successfully applied for the inspection of a tunnel section for high speed traffic: the outcome showed how low-end imaging sensor (GoPros in the specific case) can produce a photogrammetric 3D model with comparable global accuracy with terrestrial laser scanner. The project's outcomes suggest that photogrammetry is a valid alternative to laser scanning for tunnel visual inspection: from the geometric point of view it provides comparable global accuracy to the laser scanner technique but it also halves the time to generate the 3D model and provides the user with photo-realistic outputs, making it possible to perform defect recognition at a smaller scale. It is generally more versatile, and easier to inspect, visualise and navigate the data. Moreover, the combination of photogrammetry with deep learning (hot topic of the research) will push visual inspections in the direction of automated approaches with direct benefits on surveying costs as well as Health \& Safety (H\&S). Utilising available technology supports risk-based asset management and thus ensures safe and better operational performance of a railway for passengers to use. |
| First Year Of Impact | 2018 |
| Sector | Construction,Environment,Transport |
| Impact Types | Societal,Economic,Policy & public services |