Smartphone-based accurate pothole depth estimation using monocular RGB and LiDAR-guided deep learning

Waqar Rauf Butt, Muhammad Farooq, Sohail Jabbar, Muhammad Munwar Iqbal, Umar Raza, Alaa E S Ahmed · 2026

Read Smartphone-based accurate pothole depth estimation using monocular RGB and LiDAR-guided deep learning by Waqar Rauf Butt, Muhammad Farooq, Sohail Jabbar, Muhammad Munwar Iqbal, Umar Raza, Alaa E S Ahmed (2026) 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/plos-pone-0344604.txt.

Description

Waqar Rauf Butt and co-workers turn an ordinary smartphone into a pothole measuring tool. Councils struggle to survey road damage because pro gear is costly and manual checks are slow. Their 2026 study pairs phone photos with the depth sensor built into newer phones, guided by a deep learning pipeline that outlines each pothole and refines its depth.

Training used twenty-five thousand photo and depth pairs gathered under mixed road and light conditions. The system beat existing methods on both depth accuracy and outline quality. Cleaner edges after extra processing helped too. A phone in a vehicle could feed cities a live damage map, letting repair crews start with the deepest, riskiest holes.

Catalog record

CREATORWaqar Rauf Butt, Muhammad Farooq, Sohail Jabbar, Muhammad Munwar Iqbal, Umar Raza, Alaa E S Ahmed
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE42512
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0344604

Browse the full library · About the Tower of Babel