Deep Neural Networks for Forest Fire Detection from UAV

Technology Summary

• The technology is developed for disaster recognition and response by utilizing an UAV (Unmanned Aerial Vehicle) and an image analysis server.

• Deep convolutional neural networks(CNNs) were selected as a fire detection method for the image analysis system.
• The system is comprised of UAV control system, image analysis system, disaster forecasting system, Web-based visualization system, alert system, and disaster response scenario database.
• The procedure including the image capturing, transferring and analyzing is performed in real time in order to provide immediate recognition result to a decision support system for disaster management.
  

• The system can be extended to support other kinds of disasters like flood and earthquake.

Contact Info.: Su-Jin Youn, +82-42-860-5092, sjy@etri.re.kr