eprintid: 10051437 rev_number: 24 eprint_status: archive userid: 608 dir: disk0/10/05/14/37 datestamp: 2018-07-03 14:59:41 lastmod: 2021-09-26 22:59:45 status_changed: 2018-07-03 14:59:41 type: proceedings_section metadata_visibility: show creators_name: Panella, F creators_name: Boehm, J creators_name: Loo, Y creators_name: Kaushik, A creators_name: Gonzalez, D title: Deep learning and image processing for automated crack detection and defect measurement in underground structures ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F44 keywords: Deep Learning, Automated Crack Detection, Photographic Tunnelling Surveys note: © Author(s) 2018. This work is distributed under the Creative Commons Attribution 4.0 License. abstract: This work presents the combination of Deep-Learning (DL) and image processing to produce an automated cracks recognition and defect measurement tool for civil structures. The authors focus on tunnel civil structures and survey and have developed an end to end tool for asset management of underground structures. In order to maintain the serviceability of tunnels, regular inspection is needed to assess their structural status. The traditional method of carrying out the survey is the visual inspection: simple, but slow and relatively expensive and the quality of the output depends on the ability and experience of the engineer as well as on the total workload (stress and tiredness may influence the ability to observe and record information). As a result of these issues, in the last decade there is the desire to automate the monitoring using new methods of inspection. The present paper has the goal of combining DL with traditional image processing to create a tool able to detect, locate and measure the structural defect. date: 2018-05-30 date_type: published publisher: ISPRS SC official_url: https://doi.org/10.5194/isprs-archives-XLII-2-829-2018, 2018 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1563531 doi: 10.5194/isprs-archives-XLII-2-829-2018 lyricists_name: Boehm, Jan lyricists_name: Panella, Fabio lyricists_id: JOBOE65 lyricists_id: FPANE86 actors_name: Bracey, Alan actors_id: ABBRA90 actors_role: owner full_text_status: public publication: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives volume: XLII-2 number: 2 place_of_pub: Riva del Garda, Italy pagerange: 829-835 event_title: ISPRS TC II Mid-term Symposium “Towards Photogrammetry 2020” issn: 1682-1750 book_title: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences citation: Panella, F; Boehm, J; Loo, Y; Kaushik, A; Gonzalez, D; (2018) Deep learning and image processing for automated crack detection and defect measurement in underground structures. In: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. (pp. pp. 829-835). ISPRS SC: Riva del Garda, Italy. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10051437/1/isprs-archives-XLII-2-829-2018.pdf