Computer Vision based inspection on post-earthquake with UAV synthetic dataset

TL;DR

This paper introduces a deep learning pipeline trained on synthetic data for UAV-based post-earthquake damage inspection, enabling accurate detection and assessment of building defects in real-world scenarios.

Contribution

It presents a novel, adaptable deep learning pipeline trained on synthetic datasets for UAV-based damage detection after earthquakes, facilitating real-time assessment.

Findings

High accuracy in building defect detection

Effective segmentation of construction components

Reliable condition estimation from a single drone flight

Abstract

The area affected by the earthquake is vast and often difficult to entirely cover, and the earthquake itself is a sudden event that causes multiple defects simultaneously, that cannot be effectively traced using traditional, manual methods. This article presents an innovative approach to the problem of detecting damage after sudden events by using an interconnected set of deep machine learning models organized in a single pipeline and allowing for easy modification and swapping models seamlessly. Models in the pipeline were trained with a synthetic dataset and were adapted to be further evaluated and used with unmanned aerial vehicles (UAVs) in real-world conditions. Thanks to the methods presented in the article, it is possible to obtain high accuracy in detecting buildings defects, segmenting constructions into their components and estimating their technical condition based on a single drone flight.