Traditional manual visual inspections have demonstrated certain shortcomings in post -earthquake assessment of urban buildings, such as being time-consuming and laborious. In contrast, computer vision (CV) and unmanne...
详细信息
Traditional manual visual inspections have demonstrated certain shortcomings in post -earthquake assessment of urban buildings, such as being time-consuming and laborious. In contrast, computer vision (CV) and unmanned aerial vehicle (UAV) approaches have revealed competitive potentials in the fields of automatic data acquisition, data processing, and autono-mous decision-making. In UAV images, structuralcomponents of post-earthquake buildings often present different scales, which are affected by different local damage. Therefore, acquiring the feature information of structuralcomponents has precisely been significant for refined damage assessment of post-earthquake buildings. This study proposes a geometry-informed deep learning -based structural component segmentation of post-earthquake buildings. An Enhanced UNet model is established with a new synthetical loss function containing the geometric consistency (GC) term. Given an edge closure of a connected domain for homogeneous structuralcomponents, the GC term comprises split line loss and area loss to adapt to the circumference and area con-straints of each component region. The Enhanced UNet network is designed to improve the extraction capability of high-level features, and it includes six encoder stages (superior to five in the original version), of which the bottom four stages have many convolution layers, and five corresponding decoders. The investigated synthetic QuakeCity dataset includes 4,809 images with a resolution of 1,920 x 1,080 pixels. Training and test results reveal that compared to the original UNet, the proposed method achieves a more stable training process and higher test ac-curacy for structural component segmentation. The proposed method can achieve a mIoU of 97.97 %, which is 1.29 % higher than that of the original UNet. In addition, misrecognition of inner voids inside structuralcomponents is addressed, which further validates the optimization efficiency of the proposed geometric cons
Recent studies for computer vision and deep learning-based,post-earthquake inspections on RC structures mainly perform well for specific tasks,while the trained models must be fine-tuned and re-trained when facing new...
详细信息
Recent studies for computer vision and deep learning-based,post-earthquake inspections on RC structures mainly perform well for specific tasks,while the trained models must be fine-tuned and re-trained when facing new tasks and datasets,which is inevitably *** study proposes a multi-task learning approach that simultaneously accomplishes the semantic segmentation of seven-type structuralcomponents,three-type seismic damage,and four-type deterioration *** proposed method contains a CNN-based encoder-decoder backbone subnetwork with skip-connection modules and a multi-head,task-specific recognition *** backbone subnetwork is designed to extract multi-level features of post-earthquake RC *** multi-head,task-specific recognition subnetwork consists of three individual self-attention pipelines,each of which utilizes extracted multi-level features from the backbone network as a mutual guidance for the individual segmentation task.A synthetical loss function is designed with real-time adaptive coefficients to balance multi-task losses and focus on the most unstably fluctuating *** experiments and comparative studies are further conducted to demonstrate their effectiveness and *** results show that the proposed method can simultaneously recognize different structuralcomponents,seismic damage,and deterioration states,and that the overall performance of the three-task learning models gains general improvement when compared to all single-task and dual-task models.
暂无评论