Search

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. [ABSTRACT FROM AUTHOR]

Considering the challenges associated with accurately identifying building shape features and distinguishing between building and non-building features during the extraction of buildings from remote sensing images using deep learning, we propose a novel method for building extraction based on U-Net, incorporating a recurrent residual deformable convolution unit (RDCU) module and augmented multi-head self-attention (AMSA). By replacing conventional convolution modules with an RDCU, which adopts a deformable convolutional neural network within a residual network structure, the proposed method enhances the module's capacity to learn intricate details such as building shapes. Furthermore, AMSA is introduced into the skip connection function to enhance feature expression and positions through content–position enhancement operations and content–content enhancement operations. Moreover, AMSA integrates an additional fusion channel attention mechanism to aid in identifying cross-channel feature expression Intersection over Union (IoU) score differences. For the Massachusetts dataset, the proposed method achieves an Intersection over Union (IoU) score of 89.99%, PA (Pixel Accuracy) score of 93.62%, and Recall score of 89.22%. For the WHU Satellite dataset I, the proposed method achieves an IoU score of 86.47%, PA score of 92.45%, and Recall score of 91.62%, For the INRIA dataset, the proposed method achieves an IoU score of 80.47%, PA score of 90.15%, and Recall score of 85.42%. [ABSTRACT FROM AUTHOR]

In this study, we address the limitations of current deep learning models in road extraction tasks from remote sensing imagery. We introduce MixerNet-SAGA, a novel deep learning model that incorporates the strengths of U-Net, integrates a ConvMixer block for enhanced feature extraction, and includes a Scaled Attention Gate (SAG) for augmented spatial attention. Experimental validation on the Massachusetts road dataset and the DeepGlobe road dataset demonstrates that MixerNet-SAGA achieves a 10% improvement in precision, 8% in recall, and 12% in IoU compared to leading models such as U-Net, ResNet, and SDUNet. Furthermore, our model excels in computational efficiency, being 20% faster, and has a smaller model size. Notably, MixerNet-SAGA shows exceptional robustness against challenges such as same-spectrum–different-object and different-spectrum–same-object phenomena. Ablation studies further reveal the critical roles of the ConvMixer block and SAG. Despite its strengths, the model's scalability to extremely large datasets remains an area for future investigation. Collectively, MixerNet-SAGA offers an efficient and accurate solution for road extraction in remote sensing imagery and presents significant potential for broader applications. [ABSTRACT FROM AUTHOR]

In order to effectively utilize acquired remote sensing imagery and improve the completeness of information extraction, we propose a new road extraction model called C2S-RoadNet. C2S-RoadNet was designed to enhance the feature extraction capability by combining depth-wise separable convolution with lightweight asymmetric self-attention based on encoder and decoder structures. C2S-RoadNet is able to establish long-distance dependencies and fully utilize global information, and it better extracts road information. Based on the lightweight asymmetric self-attention network, a multi-scale adaptive weight module was designed to aggregate information at different scales. The use of adaptive weights can fully harness features at different scales to improve the model's extraction performance. The strengthening of backbone information plays an important role in the extraction of road main branch information, which can effectively improve the integrity of road information. Compared with existing deep learning algorithms based on encoder–decoder, experimental results on various public road datasets show that the C2S-RoadNet model can produce more complete road extraction, especially when faced with scenarios involving occluded roads or complex lighting conditions. On the Massachusetts road dataset, the PA, F1 score, and IoU reached 98%, 77%, and 72%, respectively. Furthermore, on the DeepGlobe dataset, the PA, F1 score, and IoU reached 98%, 78%, and 64%, respectively. The objective performance evaluation indicators also significantly improved on the LSRV dataset, and the PA, F1 score, and IoU reached 96%, 82%, and 71%, respectively. [ABSTRACT FROM AUTHOR]