Combination of deep learning and vegetation index for coastal wetland mapping using GF-2 remote sensing images

被引：0
作者：
Cui B. [1 ]
Wu J. [1 ]
Li X. [1 ]
Ren G. [2 ]
Lu Y. [1 ]
机构：
[1] College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao
[2] First Institute of Oceanography, Ministry of Natural Resources, Qingdao
来源：
National Remote Sensing Bulletin | 2023年 / 27卷 / 06期
基金：
中国国家自然科学基金;
关键词：
coastal wetland information extraction; deep convolutional neural network; GF-2; MFVNet model; remote sensing; vegetation index;
D O I：
10.11834/jrs.20221658
中图分类号：
学科分类号：
摘要：
The biomass and growth of coastal wetland vegetation vary greatly due to different water and salt conditions in the growing area, and the spectral features of certain vegetation at the peak biomass are highly similar, making it easy for coastal wetland vegetation to be misclassified. In response to this problem, this study proposes a new semantic segmentation network called MFVNet to be combined with vegetation index for the fine mapping of coastal wetlands. In the proposed MFVNet, an Enhanced Multiscale Feature Extraction (E-MFE) module was first constructed on the basis of atrous convolution and attention mechanism to capture features of different scales adaptively. Then, the E-MFE module was used to replace the double convolution operations in traditional encoder-decoder network architecture, such as UNet. It was also used to merge the semantic features and detailed features of different resolutions to enhance feature representation. Finally, some typical vegetation indices were selected and input into the proposed MFVNet to improve the ability of coastal wetland fine mapping. The experiments of this study were conducted using GF-2 remote sensing images to study the coastal wetlands of the Yellow River Estuary. Experimental results indicated that the proposed MFVNet achieved good performance with an overall accuracy of 93.89% and a Kappa coefficient of 0.9072. On typical vegetation, such as reeds, spartina alterniflora, tamarix mixed area, and seagrass beds in the Yellow River Estuary, the F1 scores of MFVNet were 0.91, 0.87, 0.82, and 0.76, respectively, which were better than that of other methods. Moreover, ablation experiments showed that the combination of the E-MFE module and the vegetation index can increase the overall accuracy from 91.46% to 93.89%. (1) Compared with deep semantic segmentation networks, such as HRNet, MFVNet can more effectively extract vegetation information of coastal wetlands. (2) The proposed EMFE module can adaptively capture features of different scales and improve the overall accuracy, which justified its effectiveness in coastal wetland mapping. (3) The inclusion of vegetation index can enhance the spectral features of coastal wetland vegetation and improve the accuracy of vegetation information extraction, indicating the importance of vegetation index in coastal wetland mapping. (4) Simultaneously splicing modified soil adjusted vegetation index, difference vegetation index, and ratio vegetation index in remote sensing images contributed the most to the extraction of coastal wetland information. © 2023 National Remote Sensing Bulletin. All rights reserved.
引用
收藏
页码：6 / 16
页数：10
相关论文
共 29 条
  • [1] Chen L C, Zhu Y, Papandreou G, Schroff F, Adam H, Encoder-decoder with atrous separable convolution for semantic image segmentation, Proceedings of the 15th European Conference on Computer Vision (ECCV), (2018)
  • [2] Fan D Q, Zhao X S, Zhu W Q, Zheng Z T, Review of influencing factors of accuracy of plant phenology monitoring based on remote sensing data, Progress in Geography, 35, 3, pp. 304-319, (2016)
  • [3] Feng Q L, Yang J Y, Zhu D H, Liu J T, Guo H, Bayartungalag B, Li B G, Integrating multitemporal sentinel-1/2 data for coastal land cover classification using a Multibranch convolutional neural network: a case of the Yellow River delta, Remote Sensing, 11, 9, (2019)
  • [4] Han X S, Pan J Y, Devlin A T, Remote sensing study of wetlands in the Pearl River delta during 1995-2015 with the support vector machine method, Frontiers of Earth Science, 12, 3, pp. 521-531, (2018)
  • [5] Hu Y B, Zhang J, Ma Y, An J B, Ren G B, Li X M, Hyperspectral coastal wetland classification based on a multiobject convolutional neural network model and decision fusion, IEEE Geoscience and Remote Sensing Letters, 16, 7, pp. 1110-1114, (2019)
  • [6] Hu Y B, Zhang J, Ma Y, Li X M, Sun Q P, An J B, Deep learning classification of coastal wetland hyperspectral image combined spectra and texture features: a case study of Huanghe (Yellow) River Estuary wetland, Acta Oceanologica Sinica, 38, 5, pp. 142-150, (2019)
  • [7] Ibtehaz N, Rahman M S, MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation, Neural Networks, 121, pp. 74-87, (2020)
  • [8] Li X W, Ji G S, Yang J, Estimating cyanophyta biomass standing crops in Meiliang Gulf of Lake Taihu by satellite remote sensing, Remote Sensing for Land and Resources, 7, 2, pp. 23-28, (1995)
  • [9] Lin T Y, Dollar P, Girshick R, He K M, Hariharan B, Belongie S, Feature pyramid networks for object detection, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017)
  • [10] Liu C, Tao R, Li W, Zhang M M, Sun W W, Du Q, Joint classification of hyperspectral and multispectral images for mapping coastal wetlands, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, pp. 982-996, (2021)
123