Affiliation:
1. Key Laboratory for Information Science of Electromagnetic Waves (Ministry of Education), School of Information Science and Technology, Fudan University, Shanghai 200433, China
Abstract
Hyperspectral images possess a continuous and analogous spectral nature, enabling the classification of distinctive information by analyzing the subtle variations between adjacent spectra. Meanwhile, a hyperspectral dataset includes redundant and noisy information in addition to larger dimensions, which is the primary barrier preventing its use for land cover categorization. Despite the excellent feature extraction capability exhibited by convolutional neural networks, its efficacy is restricted by the constrained receptive field and the inability to acquire long-range features due to the limited size of the convolutional kernels. We construct a dual-stream self-attention fusion network (DSSFN) that combines spectral and spatial information in order to achieve the deep mining of global information via a self-attention mechanism. In addition, dimensionality reduction is required to reduce redundant data and eliminate noisy bands, hence enhancing the performance of hyperspectral classification. A unique band selection algorithm is proposed in this study. This algorithm, which is based on a sliding window grouped normalized matching filter for nearby bands (SWGMF), can minimize the dimensionality of the data while preserving the corresponding spectral information. Comprehensive experiments are carried out on four well-known hyperspectral datasets, where the proposed DSSFN achieves higher classification results in terms of overall accuracy (OA), average accuracy (AA), and kappa than previous approaches. A variety of trials verify the superiority and huge potential of DSSFN.
Funder
National Natural Science Foundation of China
Natural Science Foundation of Shanghai
China High-resolution Earth Observation System (CHEOS)–Aerial Observation System Project
Subject
General Earth and Planetary Sciences
Reference86 articles.
1. Diverse Region-Based CNN for Hyperspectral Image Classification;Zhang;IEEE Trans. Image Process.,2018
2. Hyperion, a space-based imaging spectrometer;Pearlman;IEEE Trans. Geosci. Remote Sens.,2003
3. Feature Mining for Hyperspectral Image Classification;Jia;Proc. IEEE,2013
4. Classification of hyperspectral data from urban areas based on extended morphological profiles;Benediktsson;IEEE Trans. Geosci. Remote Sens.,2005
5. Wan, Y., Hu, X., Zhong, Y., Ma, A., Wei, L., and Zhang, L. (August, January 28). Tailings Reservoir Disaster and Environmental Monitoring Using the UAV-ground Hyperspectral Joint Observation and Processing: A Case of Study in Xinjiang, the Belt and Road. Proceedings of the IGARSS 2019–2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan.
Cited by
2 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