Optimising Concrete Crack Detection: A Study of Transfer Learning with Application on Nvidia Jetson Nano
C. Long Nguyen, Andy Nguyen, Jason Brown, Terry Byrne, Binh Thanh Ngo, Chieu Xuan Luong · 2024
Read Optimising Concrete Crack Detection: A Study of Transfer Learning with Application on Nvidia Jetson Nano by C. Long Nguyen, Andy Nguyen, Jason Brown, Terry Byrne, Binh Thanh Ngo, Chieu Xuan Luong (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11645055.txt.
Description
Long Nguyen and co-authors train crack spotting networks for concrete and squeeze the best onto a palm sized computer, in a study from 2024. Inspecting bridges and roads for cracks is slow, costly, and sometimes dangerous. A drone carrying a small smart camera could scan structures and call out damage on the spot.
Six known image networks were retrained by transfer learning on three thousand photos of concrete, half cracked and half sound. Extra training copies were roughened with noise and motion blur to harden the models. The study compared accuracy across the six and prepared the winner for a Jetson Nano board, the kind of cheap edge device a drone can lift. The work tests whether lab grade detection survives real deployment limits.
Catalog record
| CREATOR | C. Long Nguyen, Andy Nguyen, Jason Brown, Terry Byrne, Binh Thanh Ngo, Chieu Xuan Luong |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |