Geometric consistency enhanced deep convolutional encoder-decoder for urban seismic damage assessment by UAV images

•A deep QuakeCityNet is established for seismic assessment of urban dense buildings.•Flexible configurations of encoder stages and embedding convolutions are designed.•Geometric consistency loss suppresses non-smooth boundaries and small-region noise.•Ablation studies and actual applications are per...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Engineering structures Ročník 286; s. 116132
Hlavní autori:	Wang, Yu, Jing, Xin, Cui, Liangyi, Zhang, Chenzong, Xu, Yang, Yuan, Jian, Zhang, Qiangqiang
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier Ltd 01.07.2023
Predmet:	City-scale seismic damage assessment Complex weather robustness Deep convolutional encoder-decoder Geometric consistency loss UAV images Geometric consistency loss City-scale seismic damage assessment Complex weather robustness Deep convolutional encoder-decoder UAV images
ISSN:	0141-0296, 1873-7323
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	•A deep QuakeCityNet is established for seismic assessment of urban dense buildings.•Flexible configurations of encoder stages and embedding convolutions are designed.•Geometric consistency loss suppresses non-smooth boundaries and small-region noise.•Ablation studies and actual applications are performed for effectiveness validation.•Accurate and robust model performance is obtained under complex weather conditions. Precise and rapid assessment of seismic damage to buildings is critical for urban regions. To address this challenge, this study proposes QuakeCityNet (QCNet-M-N)- a model with flexible configurations of M encoding stages and N embedding convolution operations for exact pixel-level recognition of earthquake-damaged buildings using unmanned aerial vehicle (UAV) images. A novel loss function, geometric consistency enhanced (GCE) loss, is designed to focus on the building regions and local boundaries, taking into account the geometrical constraints of split line length, curvature, and area. Test results indicate that the proposed QCNet model can achieve robust and stable segmentation accuracy under diverse weather conditions, such as abnormal illumination, rain, and fog. Moreover, the utilization of GCE loss significantly reduces the false-positive small-region noise while preserving overall geometrical shapes. Finally, an application of seismic assessment is conducted in Beichuan county to demonstrate the effectiveness of the proposed method.
ISSN:	0141-0296 1873-7323
DOI:	10.1016/j.engstruct.2023.116132