Aerial Image Classification for Drone-based Emergency Monitoring (EmergencyNet)

Developed by: Christos Kyrkou

A small deep learning model based on atrous convolutional feature fusion for the application of emergency response.

This algorithm[1] tackles the problem of on-board aerial scene classification and assigns automatically a semantic label to characterize an aerial image captured by a UAV. These labels will correspond to the type of danger or hazard that has occurred. Such a system can be deployed on UAVs for automated monitoring and inspection to enhance preparedness and provide rapid situational awareness.

A detailed description of the algorithm can be found in the link where the software is available (provided below).

[1] C. Kyrkou and T. Theocharides, “EmergencyNet: Efficient Aerial Image Classification for Drone-Based Emergency Monitoring Using Atrous Convolutional Feature Fusion,” in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 1687-1699, 2020.


Code written in Python is available here:

Leave a comment

Your email address will not be published. Required fields are marked *