Unmanned aerial vehicle (UAV) remote sensing plays a crucial role in the rapid assessment of post-earthquake damaged buildings. Existing methods for automatic identification of damaged buildings based on UAV remote sensing imagery primarily focus on assessment accuracy. However, during earthquake emergency response, both speed and accuracy of assessment are equally important. Therefore, we propose a high-precision and real-time damaged building instance segmentation model, DBA-RTMDet, based on the RTMDet framework. Three key modules are designed to enhance the network's feature extraction capability for damaged buildings. First, we develop a Depthwise Separable Atrous Spatial Pyramid Pooling Module to improve the model's ability to detect damaged buildings of varying sizes. Second, an Adjacent Level Feature Enhancement and Fusion Module is introduced to enhance the network's ability to localize the irregular boundaries of collapsed buildings. Finally, to mitigate the interference caused by intact buildings that exhibit features like partially damaged roofs, we incorporated a Cross Atrous Attention Module. We conduct experiments on post-disaster UAV imagery collected during the 2021 Yangbi earthquake with surface wave magnitude scale (Ms) of 6.4 in Yunnan, China. The results demonstrate that our model achieves a segmentation mean Average Precision (mAP^seg) of 80.4% and a bounding box mean Average Precision (mAP^box) of 81.2%, significantly outperforming methods such as YOLACT, FCOS, PolarMask, TensorMask, YOLOv5, YOLOX, YOLOv6, and YOLOv8. We observed that, compared to the widely used model YOLOv5, DBA-RTMDet not only improves mAP^seg and mAP^box by 10.3% and 9.7%, respectively, but also the Frames Per Second (FPS) is increased significantly by 26. Our approach can quickly and accurately identify damaged buildings, with its high application value verified through the generalization validation experiment. The code and datasets will be available at https://github.com/Kangsan-Y/UAV-based-Damaged-Buildings-Instance-Segmentation-model-DBA-RTMDet.

Automatic extraction of building contours from high-resolution images is of great significance in the fields of urban planning, demographics, and disaster assessment. Network models based on convolutional neural network (CNN) and transformer technology have been widely used for semantic segmentation of buildings from high resolution remote sensing images (HRSI). However, the fixed geometric structure and the local receptive field of the convolutional kernel are not good at global feature extraction, and the transformer technique with self-attention mechanism introduces computational redundancies and extracts local feature details poorly in the process of modeling the global contextual information. In this paper, a dual-branch fused reconstructive transformer network, DFRTNet, is proposed for efficient and accurate building extraction. In the encoder, the traditional transformer is reconfigured by designing the local and global feature extraction module (LGFE); the branch of global feature extraction (GFE) performs dynamic range attention (DRA) based on the idea of top-k attention for extracting global features; furthermore, the branch of local feature extraction (LFE) is used to obtain fine-grained features. The multilayer perceptron (MLP) is employed to efficiently fuse the local and global features. In the decoder, a simple channel attention module (CAM) is used in the up-sampling part to enhance channel dimension features. Our network achieved the best segmentation accuracy on both the WHU and Massachusetts building datasets when compared to other mainstream and state-of-the-art methods.

As important disaster-bearing bodies, buildings are the focus of attention in seismic disaster risk assessment and emergency rescue. It is of great practical significance to extract buildings quickly and accurately with complex textures and variable scales and shapes from high-resolution remote sensing images. We proposed an improved TransUnet model based on multiscale grouped convolution and attention named MATUnet to retain more local detail features and enhance the representation ability of global features, while reducing the network parameters. We designed the multiscale grouped convolutional feature extraction module with attention (GAM) to enhance the representation of detailed features. The convolutional positional encoding module (PEG) was added to redetermine the number of transformer, it solved the problem of local feature information loss and the difficulty of convergence of the network. The channel attention module (CAM) of the decoder enhanced the salient information of the features and solved the problem of information redundancy after feature fusion. We experimented through MATUnet on the WHU building dataset and Massachusetts dataset. MATUnet achieved the best IOU results of 92.14% and 83.22%, respectively, and achieved better than the other generalized and state-of-the-art networks under the same conditions. We also have achieved good segmentation results on the GF2 Xichang building dataset.

Unmanned aerial systems (UASs) are increasingly playing a crucial role in earthquake emergency response and disaster assessment due to their ease of operation, mobility, and low cost. However, post-earthquake scenes are complex, with many forms of damaged buildings. UAS imagery has a high spatial resolution, but the resolution is inconsistent between different flight missions. These factors make it challenging for existing methods to accurately identify individual damaged buildings in UAS images from different scenes, resulting in coarse segmentation masks that are insufficient for practical application needs. To address these issues, this paper proposed DB-Transfiner, a building damage instance segmentation method for post-earthquake UAS imagery based on the Mask Transfiner network. This method primarily employed deformable convolution in the backbone network to enhance adaptability to collapsed buildings of arbitrary shapes. Additionally, it used an enhanced bidirectional feature pyramid network (BiFPN) to integrate multi-scale features, improving the representation of targets of various sizes. Furthermore, a lightweight Transformer encoder has been used to process edge pixels, enhancing the efficiency of global feature extraction and the refinement of target edges. We conducted experiments on post-disaster UAS images collected from the 2022 Luding earthquake with a surface wave magnitude (Ms) of 6.8 in the Sichuan Province of China. The results demonstrated that the average precisions (AP) of DB-Transfiner, ${AP}_{box}$ and ${AP}_{seg}$, are 56.42% and 54.85%, respectively, outperforming all other comparative methods. Our model improved the original model by 5.00% and 4.07% in ${AP}_{box}$ and ${AP}_{seg}$, respectively. Importantly, the ${AP}_{seg}$ of our model was significantly higher than the state-of-the-art instance segmentation model Mask R-CNN, with an increase of 9.07%. In addition, we conducted applicability testing, and the model achieved an average correctness rate of 84.28% for identifying images from different scenes of the same earthquake. We also applied the model to the Yangbi earthquake scene and found that the model maintained good performance, demonstrating a certain level of generalization capability. This method has high accuracy in identifying and assessing damaged buildings after earthquakes and can provide critical data support for disaster loss assessment.