Abstract
Computational intelligence techniques have been widely used for automatic building detection from high-resolution remote sensing imagery and especially the methods based on neural networks. However, existing methods do not pay attention to the value of high-frequency and low-frequency information in the frequency domain for feature extraction of buildings in remote sensing images. To overcome these limitations, this paper proposes a frequency spectrum intensity attention network (FSIANet) with an encoder–decoder structure for automatic building detection. The proposed FSIANet mainly involves two innovations. One, a novel and plug-and-play frequency spectrum intensity attention (FSIA) mechanism is devised to enhance feature representation by evaluating the informative abundance of the feature maps. The FSIA is deployed after each convolutional block in the proposed FSIANet. Two, an atrous frequency spectrum attention pyramid (AFSAP) is constructed by introducing FSIA in widely used atrous spatial pyramid pooling. The AFSAP is able to select the features with high response to building semantic features at each scale and weaken the features with low response, thus enhancing the feature representation of buildings. The proposed FSIANet is evaluated on two large public datasets (East Asia and Inria Aerial Image Dataset), which demonstrates that the proposed method can achieve the state-of-the-art performance in terms of F1-score and intersection-over-union.
Funder
National Natural Science Foundation of China
Natural Science Basic Research Plan in Shaanxi Province of China
Special Scientific Research Projects of Shaanxi Provincial Department of Education
Subject
General Earth and Planetary Sciences
Reference67 articles.
1. A novel point-matching algorithm based on fast sample consensus for image registration;Wu;IEEE Geosci. Remote Sens. Lett.,2014
2. Wu, Y., Li, J., Yuan, Y., Qin, A., Miao, Q.G., and Gong, M.G. Commonality autoencoder: Learning common features for change detection from heterogeneous images. IEEE Trans. Neural Netw. Learn. Syst., 2021.
3. Multi-fidelity evolutionary multitasking optimization for hyperspectral endmember extraction;Li;Appl. Soft Comput.,2021
4. Iterative training sample expansion to increase and balance the accuracy of land classification from VHR imagery;Lv;IEEE Trans. Geosci. Remote Sens.,2020
5. Unsupervised feature extraction in hyperspectral images based on wasserstein generative adversarial network;Zhang;IEEE Trans. Geosci. Remote Sens.,2018
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献