Context-Aware Deep Learning based Indian Footpath Damage Segmentation Dataset for Risk Assessment
Priti Chakurkar, Deepali Vora · 2025
Read Context-Aware Deep Learning based Indian Footpath Damage Segmentation Dataset for Risk Assessment by Priti Chakurkar, Deepali Vora (2025) 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-12686011.txt.
Description
Priti Chakurkar and Deepali Vora present a data set of footpath damage in Pune, India, for risk study in 2025. Cracked and uneven footpaths pose fall risks, and automated checks could help cities spot danger early.
Images were taken with a high-grade camera in varied light and weather and marked by hand at pixel level. Damage was graded as low, medium or high by crack width, with advice from civil engineers. The authors trained a segmentation model and an ensemble version to show the data work. Their best model reached solid overlap and accuracy scores, and the data set is open for research use.
Catalog record
| CREATOR | Priti Chakurkar, Deepali Vora |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |