Active Wildfires Detection and Dynamic Escape Routes Planning for Humans through Information Fusion between Drones and Satellites

This talk presents a method for wilderness rescue using UAVs and satellite imagery. The approach integrates UAV vision technology and satellite image analysis for:

1. Detecting active wildfires and segmenting smoke and flames using Sentinel-2 satellite imagery.
2. Performing road segmentation and condition assessment in the fire-affected areas using D-LinkNet and NDVI values from UAV imagery.
3. Planning dynamic optimal escape routes in real time for humans using a weighted A* algorithm combined with a dynamic fire spread model.

A case study of the Chongqing wildfire on August 24, 2022, demonstrates the effectiveness of the proposed method for providing safe and efficient escape routes.

Authors: Chang Liu, Tamás Szirányi

Citations: C Liu, T Szirányi - 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC 2023).