Abstract
The classification of wetlands in the Yellow River Delta is important for the monitoring of vegetation dynamics, rational resource utilization, and ecosystem protection. In this paper, the multi-temporal Sentinel-1 and Sentinel-2 data from 2021 are used to extract 168 features about spectral, index, texture, and polarization scattering. And based on the multi-source features, a novel multi-branch hierarchical feature extraction network (MHFE) is designed to classify the wetlands in the Yellow River Delta. By virtue of the multi-branch characteristics, the proposed MHFE can target the processing data with different features. The network includes the attention convolution module and fuzzy information module designed according to the characteristics of the data. The results show that the overall accuracy of multi-source features can reach 87.55% when classifying collaboratively, which is significantly higher than that of single-source features, and the fusion of multi-source data helps to improve the accuracy of wetland classification. Comparing with a variety of advanced deep learning classifiers, the proposed MHFE has the highest overall accuracy, which verifies that the application of this model to classify the wetlands in the Yellow River Delta has validity.
This is a preview of subscription content, log in via an institution to check access.
References
Xie, S.Y., Fu, L.B., Li, Y., et al.: Classification method on marsh wetlands in Honghe national nature reserve based on multi-dimensional remote sensing images. Wetland Sci. 19(01), 1–16 (2021)
Ming, Y.S., Liu, Q.H., Bai, H., et al.: Classification and change detection of vegetation in the Ruoergai Wetland using optical and SAR remote sensing data. Nat. Remote Sens. Bull. 27(6), 1414–1425 (2023)
Li, P., Li, D.H., Li, Z.H., et al.: Wetland classification through integration of GF-3 SAR and Sentinel-2B multispectral data over the Yellow River Delta. Geomatics Inf. Sci. Wuhan Univ. 44(11), 1641–1649 (2019)
Zhang, C.Y., Chen, S.L., Li, P., et al.: Spatiotemporal dynamic remote sensing monitoring of typical wetland vegetation in the current Huanghe river estuary reserve. Haiyang Xuebao 44(1), 125–136 (2022)
Xing, H., Niu, J., Feng, Y., et al.: A coastal wetlands mapping approach of Yellow River Delta with a hierarchical classification and optimal feature selection framework. Catena 223, 106897 (2022)
Zhang, L., Luo, W.T., Zhang, H.H., et al.: Classification scheme for mapping wetland herbaceous plant communities using time series Sentinel-1 and Sentinel-2 data. Nat. Remote Sens. Bull. 27(06), 1362–1375 (2023)
Han, Z., Gao, Y., Jiang, X., et al.: Multisource remote sensing classification for coastal wetland using feature intersecting learning. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2022)
He, M., Li, B., Chen, H.: Multi-scale 3D deep convolutional neural network for hyperspectral image classification. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3904–3908. IEEE (2017)
Hamida, A.B., Benoit, A., Lambert, P., et al.: 3-D deep learning approach for remote sensing image classification. IEEE Trans. Geosci. Remote Sens. 56(8), 4420–4434 (2018)
Mei, S., Li, X., Liu, X., et al.: Hyperspectral image classification using attention-based bidirectional long short-term memory network. IEEE Trans. Geosci. Remote Sens. 60, 1–12 (2021)
Song, W., Li, S., Fang, L., et al.: Hyperspectral image classification with deep feature fusion network. IEEE Trans. Geosci. Remote Sens. 56(6), 3173–3184 (2018)
Hong, D., Han, Z., Yao, J., et al.: SpectralFormer: rethinking hyperspectral image classification with transformers. IEEE Trans. Geosci. Remote Sens. 60, 1–15 (2021)
Sun, L., Zhao, G., Zheng, Y., et al.: Spectral–spatial feature tokenization transformer for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 60, 1–14 (2022)
Mei, S., Song, C., Ma, M., et al.: Hyperspectral image classification using group-aware hierarchical transformer. IEEE Trans. Geosci. Remote Sens. 60, 1–14 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, X., Liu, M., Dou, Q., Xu, M., Liu, S., Sheng, H. (2024). A Multi-branch Hierarchical Feature Extraction Network Combining Sentinel-1 and Sentinel-2 for Yellow River Delta Wetlands Classification. In: Yu, Q. (eds) Space Information Networks. SINC 2023. Communications in Computer and Information Science, vol 2057. Springer, Singapore. https://doi.org/10.1007/978-981-97-1568-8_8
Download citation
DOI: https://doi.org/10.1007/978-981-97-1568-8_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-1567-1
Online ISBN: 978-981-97-1568-8
eBook Packages: Computer ScienceComputer Science (R0)