Labeled Street View Images for Detecting Flammable Scaffolding Systems in Urban Environments
Abstract
This study develops FireWrapNet, a deep learning–based instance segmentation framework for the automated detection and mapping of flammable scaffolding systems using street view imagery. A manually curated dataset of 3,500 labeled images from Hong Kong, stored and open-access here, was constructed to train an encoder–decoder segmentation model.
Fields of Study & Subjects
Advanced Neural Network Applications
Infrastructure Maintenance and Monitoring
Fire Detection and Safety Systems
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 26 February 2026
- Language
- EN
- Document type
- Dataset