What is it about?
Aerial imagery derived from unmanned aerial vehicles (UAVs) is an invaluable resource for impact assessment and disaster management after natural disasters. The current disaster assessment process is highly human-dependent, resource-intensive, and very slow. This research proposes a technique to reduce human intervention by using deep convolutional networks for semantic segmentation of aerial imagery, focusing on disaster-affected areas.
Featured Image
Photo by Felipe Santana on Unsplash
Why is it important?
This research produces an accurate disaster assessment that can be used for disaster emergency response, disaster recovery efforts, and effective decision-making in natural disaster management systems.
Perspectives
This research provides benefits to the development of science in the fields of image processing, computer vision, and deep learning, especially in the context of aerial imagery segmentation of natural disaster-affected areas.
Deny Wiria Nugraha
Universitas Tadulako
Read the Original
This page is a summary of: Aerial imagery segmentation of natural disaster-affected areas using deep convolutional networks for disaster assessment, January 2024, American Institute of Physics,
DOI: 10.1063/5.0211995.
You can read the full text:
Contributors
The following have contributed to this page