Benchmark Dataset for Automatic Damaged Building Detection from Post-Hurricane Remotely Sensed Imagery

TL;DR

This paper introduces benchmark datasets and a scalable framework for automatic detection of hurricane-damaged buildings using post-hurricane remote sensing imagery, facilitating improved emergency response and research.

Contribution

It presents a novel scalable framework for creating benchmark datasets and publicly shares datasets for hurricane-damaged buildings, enabling better model training and evaluation.

Findings

Benchmark datasets for hurricane-damaged buildings are publicly available.

The framework supports creating datasets from airborne and satellite imagery.

Facilitates comparison and development of automatic damage detection methods.

Abstract

Rapid damage assessment is of crucial importance to emergency responders during hurricane events, however, the evaluation process is often slow, labor-intensive, costly, and error-prone. New advances in computer vision and remote sensing open possibilities to observe the Earth at a different scale. However, substantial pre-processing work is still required in order to apply state-of-the-art methodology for emergency response. To enable the comparison of methods for automatic detection of damaged buildings from post-hurricane remote sensing imagery taken from both airborne and satellite sensors, this paper presents the development of benchmark datasets from publicly available data. The major contributions of this work include (1) a scalable framework for creating benchmark datasets of hurricane-damaged buildings and (2) public sharing of the resulting benchmark datasets for Greater Houston area after Hurricane Harvey in 2017. The proposed approach can be used to build other hurricane-damaged building datasets on which researchers can train and test object detection models to automatically identify damaged buildings.