Flooded Area Detection from Uav Images Based on Densely Connected Recurrent Neural Networks Conference Paper uri icon

abstract

  • 2018 IEEE The emergence of small unmanned aerial vehicles (UAV) along with inexpensive sensors presents the opportunity to collect thousands of images after each natural disaster with high flexibility and easy maneuverability for rapid response and recovery. Despite the ease of data collection, data analysis of the big datasets remains a significant barrier for scientists and analysts. Here we propose an integration of densely connected CNN and RNN networks, which is able to accurately segment out semantically meaningful object boundaries with end-to-end learning. The proposed network is applied on UAV aerial images of flooded areas in Houston, TX. We achieved 96% accuracy in detecting flooded areas on a large UAV dataset.

name of conference

  • IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium

published proceedings

  • IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium

author list (cited authors)

  • Rahnemoonfar, M., Murphy, R., Miquel, M. V., Dobbs, D., & Adams, A.

citation count

  • 35

complete list of authors

  • Rahnemoonfar, Maryam||Murphy, Robin||Miquel, Marina Vicens||Dobbs, Dugan||Adams, Ashton

publication date

  • July 2018