High-Resolution Road Disaster Monitoring and Assessment System

This project was proposed by National Disaster Reduction Center of the Ministry of Emergency Management of People’s Republic of China and completed by Pattern Recognition and Intelligent Vision Laboratory of Beijing University of Posts and Telecommunications. It aimed to construct an artificial intelligent assisted system to monitor geological disasters and assess road damage through remote sensing images taken by satellites.

• Processed remote sensing images with ArcGIS API for Python.
• Surveyed on the deep learning algorithms for detecting damaged road in post-disaster remote sensing images.
• Implemented and validated the feasibility of damaged road detection algorithm D-LinkNet.
• Applied CoCosNet on generating simulated post-disaster remote sensing images.
• Published the paper “Damaged Road Extraction Based on Simulated Post-Disaster Remote Sensing Images” as the first author.