To expand the receptive field, various feature pyramid modules have been designed based on dilated convolution or large-scale convolutional kernels, such as the receptive field block and atrous spatial pyramid pooling module. When the receptive field is too small or the feature map contains irregularly shaped buildings, it is difficult to capture the complete shape feature of an entire building for identifying a round-shaped shed or irregularly shaped buildings, such as art museums. Moreover, the range of the receptive field is regular. In conventional CNNs, the size of the receptive field of the generated feature map is limited. (2) With the target, the shapes and features of buildings are not maintained adequately, making it difficult to distinguish buildings from their surrounding ground-based objects. Thus, the AFL-Net offers the prospect of application for successful extraction of buildings from remote sensing images. The proposed AFL-Net achieved 91.37, 82.10, 73.27, and 79.81% intersection over union (IoU) values on the WHU Building Aerial Imagery, Inria Aerial Image Labeling, Massachusetts Buildings, and Building Instances of Typical Cities in China datasets, respectively. An ablation study was conducted with both qualitative and quantitative analyses, verifying the effectiveness of the AMFF and SFR modules. The SFR module captures the shape features of the buildings, which enhances the network capability for identifying the area between building edges and surrounding nonbuilding objects and reduces the over-segmentation of buildings. The AMFF module adaptively adjusts the weights of multi-scale features through the attention mechanism, which enhances the global perception and ensures the integrity of building segmentation results. We designed an attentional multiscale feature fusion (AMFF) module and a shape feature refinement (SFR) module to improve building recognition accuracy in complex environments. To overcome this challenge, we propose an Attentional Feature Learning Network (AFL-Net) that can accurately extract buildings from remote sensing images. This leads to an inaccurate distinction between buildings and complex backgrounds. However, the intraclass heterogeneity of buildings is high in images, while the interclass homogeneity between buildings and other nonbuilding objects is low. Convolutional neural networks (CNNs) perform well in tasks of segmenting buildings from remote sensing images.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |