A novel convolutional neural network for enhancing the continuity of pavement crack detection
Jinhe Zhang, Shangyu Sun, Weidong Song, Yuxuan Li, Qiaoshuang Teng · 2024
Read A novel convolutional neural network for enhancing the continuity of pavement crack detection by Jinhe Zhang, Shangyu Sun, Weidong Song, Yuxuan Li, Qiaoshuang Teng (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-11621684.txt.
Description
Jinhe Zhang, Shangyu Sun, Weidong Song, Yuxuan Li, and Qiaoshuang Teng present a neural network that finds cracks in road surfaces. Their 2024 paper notes that cracks weaken roads and threaten safety, but standard networks often miss parts of a crack or flag false ones. A broken outline makes damage hard to judge.
Their network, called CPCDNet, adds a module that lines up crack parts and a loss rule that weights crack edges. Tests on four public image sets gave strong scores for overlap between found and true cracks. The method improved both the completeness and the correctness of crack outlines in hard scenes. Road crews could use such a tool to survey long stretches faster and plan repairs with better maps.
Catalog record
| CREATOR | Jinhe Zhang, Shangyu Sun, Weidong Song, Yuxuan Li, Qiaoshuang Teng |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 70 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |