期刊
REMOTE SENSING
卷 15, 期 8, 页码 -出版社
MDPI
DOI: 10.3390/rs15081996
关键词
building extraction; Lite Swin transformer; swin transformer; deep learning; remote sensing image
Extracting building data from remote sensing images has become more accurate with the emergence of deep learning technology, especially with the use of CNNs and Transformers. A Lite Swin transformer is proposed to simplify the calculation number of transformers, while the LiteST-Net model combines the features extracted by the Lite Swin transformer and CNN to better integrate global and local features. Comparison experiments show that LiteST-Net outperforms other networks in terms of all metrics and predicted image accuracy.
Extracting building data from remote sensing images is an efficient way to obtain geographic information data, especially following the emergence of deep learning technology, which results in the automatic extraction of building data from remote sensing images becoming increasingly accurate. A CNN (convolution neural network) is a successful structure after a fully connected network. It has the characteristics of saving computation and translation invariance with improved local features, but it has difficulty obtaining global features. Transformers can compensate for the shortcomings of CNNs and more effectively obtain global features. However, the calculation number of transformers is excessive. To solve this problem, a Lite Swin transformer is proposed. The three matrices Q, K, and V of the transformer are simplified to only a V matrix, and the v of the pixel is then replaced by the v with the largest projection value on the pixel feature vector. In order to better integrate global features and local features, we propose the LiteST-Net model, in which the features extracted by the Lite Swin transformer and the CNN are added together and then sampled up step by step to fully utilize the global feature acquisition ability of the transformer and the local feature acquisition ability of the CNN. The comparison experiments on two open datasets are carried out using our proposed LiteST-Net and some classical image segmentation models. The results show that compared with other networks, all metrics of LiteST-Net are the best, and the predicted image is closer to the label.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据