UAV-Based Structural Damage Mapping: A Review

Abstract

Structural disaster damage detection and characterization is one of the oldest remote sensing challenges, and the utility of virtually every type of active and passive sensor deployed on various air- and spaceborne platforms has been assessed. The proliferation and growing sophistication of unmanned aerial vehicles (UAVs) in recent years has opened up many new opportunities for damage mapping, due to the high spatial resolution, the resulting stereo images and derivatives, and the flexibility of the platform. This study provides a comprehensive review of how UAV-based damage mapping has evolved from providing simple descriptive overviews of a disaster science, to more sophisticated texture and segmentation-based approaches, and finally to studies using advanced deep learning approaches, as well as multi-temporal and multi-perspective imagery to provide comprehensive damage descriptions. The paper further reviews studies on the utility of the developed mapping strategies and image processing pipelines for first responders, focusing especially on outcomes of two recent European research projects, RECONASS (Reconstruction and Recovery Planning: Rapid and Continuously Updated Construction Damage, and Related Needs Assessment) and INACHUS (Technological and Methodological Solutions for Integrated Wide Area Situation Awareness and Survivor Localization to Support Search and Rescue Teams). Finally, recent and emerging developments are reviewed, such as recent improvements in machine learning, increasing mapping autonomy, damage mapping in interior, GPS-denied environments, the utility of UAVs for infrastructure mapping and maintenance, as well as the emergence of UAVs with robotic abilities.

Multi-Hazard and Spatial Transferability of a CNN for Automated Building Damage Assessment

“…Automated building damage classification has received increased attention during the last several years both from practitioners [15][16][17] and from researchers [18,19]. Models have been developed that forecast the building damage before the disaster arrives or that predict the building damage after the disaster has struck.…”

“…The first studies on automatically predicting damage from remotely sensed data mainly explored the use of texture-and segmentation-based methods (e.g., [23,[29][30][31]) and showed that while it is possible to automatically detect damage, results in performance are not always satisfying [18]. Due to the complex nature of features indicating damage and with the increased popularity of machine learning, research started to be conducted on the use of machine learning techniques for automatic classification, especially focusing on CNNs.…”

“…Research on CNN-based models for damage classification has focused on improving speed and usability [39], alleviating the effects of imprecise building masks [40], and extending the classification to man-made building features connected to damage, such as blue tarp cover [41]. While the use of CNNs has shown the most promising results in previous research, no models using these novel technologies have yet been applied in real-time operations [18]. Table 1 shows an overview of the research done on automated damage classification with satellite imagery using CNNs on the spatial granularity scale of buildings.…”

Rail Track Detection and Projection-Based 3D Modeling from UAV Point Cloud

“…Today, the use of unmanned aerial vehicles (UAVs) is one of the techniques accepted by experts to achieve accurate, high-quality, and fast mapping data [ 16 ]. In recent years, photogrammetric point clouds and especially UAV point clouds have been used in different modeling and reconstruction applications [ 17 , 18 , 19 ], and UAV point clouds are used to obtain surveying data for analyzing, detecting and reconstructing railways. By using UAV technology, rail mapping projects can be controlled from outside the railway area, thus preventing the disruption of rail services as well as saving people from danger [ 20 ].…”

Grand Challenges in Earth Observation Using Unpiloted Airborne Systems

“…Advances intechnologyandavailabilityhaveboosted the number of applications in many sectors but especially in regions with local and regional dynamic features. Just a few innovative and successful examples of UAS-based monitoring are glacier monitoring for ice flow and mass wasting (Immerzeel et al, 2014;Kraaijenbrink et al, 2016), landslide dynamics monitoring and surface deformation (McKean, 2004;Niethammer et al, 2012;Lucieer et al, 2014;Giordan et al, 2020;Karantanellis et al, 2020), dune dynamics (Ruessink et al, 2018), flood risk mapping (Hashemi-Beni et al, 2018), night-time light monitoring as proxy for economic activity (Li et al, 2020), public health care and health-related services (Amukele et al, 2015;Scalea, 2020), and post-disaster damage assessment (Kerle et al, 2019;Liao et al, 2020).…”