期刊
GISCIENCE & REMOTE SENSING
卷 59, 期 1, 页码 861-884出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/15481603.2022.2076382
关键词
Remote sensing imagery; urban building extraction; convolutional neural network (CNN); generative adversarial network (GAN); conditional information constraint
资金
- National Natural Science Foundation of China [62172338]
- Jiangsu Innovation and Entrepreneurship Program [184080H10827]
- Neural Science Foundation of Shanxi Province [2021JQ-879]
In this study, a practical method for building extraction based on convolution neural networks (CNNs) is proposed to accurately extract building regions from high-resolution remote sensing images by introducing multi-scale recurrent residual convolution and attention gates skip connection technologies.
Urban building extraction from high-resolution remote sensing imagery is important for urban planning, population statistics, and disaster assessment. However, the high density and slight boundary differences of urban building regions pose a great challenge for accurate building extraction. Although existing building extraction methods have achieved better results in urban building extraction, there are still some problems, such as boundary information loss, poor extraction effect for dense regions, and serious interference by building shadows. To accurately extract building regions from high-resolution remote sensing images, in this study, we propose a practical method for building extraction based on convolution neural networks (CNNs). Firstly, the multi-scale recurrent residual convolution is introduced into the generative network to extract the multi-scale and multi-resolution features of remote sensing images. Secondly, the attention gates skip connection (AGs) is used to enhance the information interaction between different scale features. Finally, the adversarial network with parallel architecture is used to decrease the difference between the extracted results and the ground truths. Moreover, the conditional information constraint is introduced in the training process to improve robustness and generalization ability of the proposed method. The qualitative and quantitative analyses are performed on IAILD and Massachusetts datasets. The experimental results show that the proposed method can accurately and effectively extract building regions from remote sensing images.
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