предыдущий|следующий

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

  • role： First author第一作者
  • Affiliation：

    College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China

  • Email：cuibinge@sdust.edu.cn
  • Introduction：崔宾阁，研究方向为高光谱遥感、海洋和海岸带遥感监测技术。E-mail：cuibinge@sdust.edu.cn
CUI Binge1,  
  • Affiliation：

    College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China

WU Jing1,  
  • Affiliation：

    College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China

LI Xinhui1,  
  • Affiliation：

    First Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, China

REN Guangbo2,  
  • role： Corresponding author通信作者
  • Affiliation：

    College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China

  • Email：luyan@sdust.edu.cn
  • Introduction：路燕，研究方向为智能信息处理、遥感图像分类和目标检测。E-mail：luyan@sdust.edu.cn
LU Yan1*

реферат

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.

ключеви́че слова́

remote sensing;Coastal Wetland Information Extraction;GF-2;Deep Convolutional Neural Network;MFVNet Model;vegetation index

References

  1. 1.
    Chen L C, Zhu Y, Papandreou G, Schroff F and Adam H. 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation//Proceedings of the 15th European Conference on Computer Vision (ECCV). Munich: Springer
  2. 2.
    Fan D Q, Zhao X S, Zhu W Q and Zheng Z T. 2016. Review of influencing factors of accuracy of plant phenology monitoring based on remote sensing data. Progress in Geography, 35(3): 304-319
  3. 3.
    Feng Q L, Yang J Y, Zhu D H, Liu J T, Guo H, Bayartungalag B and Li B G. 2019. 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): 1006
  4. 4.
    Han X S, Pan J Y and Devlin A T. 2018. 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): 521-531
  5. 5.
    Hu Y B, Zhang J, Ma Y, An J B, Ren G B and Li X M. 2019b. Hyperspectral coastal wetland classification based on a multiobject convolutional neural network model and decision fusion. IEEE Geoscience and Remote Sensing Letters, 16(7): 1110-1114
  6. 6.
    Hu Y B, Zhang J, Ma Y, Li X M, Sun Q P and An J B. 2019a. 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): 142-150
  7. 7.
    Ibtehaz N and Rahman M S. 2020. MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation. Neural Networks, 121: 74-87
  8. 8.
    Li X W, Ji G S and Yang J. 1995. Estimating cyanophyta biomass standing crops in Meiliang Gulf of Lake Taihu by satellite remote sensing. Remote Sensing for Land and Resources, 1995, 7(2): 23-28 (李旭文,季耿善,杨静.太湖梅梁湖湾蓝藻生物量遥感估算.国土资源遥感,1995(02):23-28)
  9. 9.
    Lin T Y, Dollár P, Girshick R, He K M, Hariharan B and Belongie S. 2017. Feature pyramid networks for object detection//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE
  10. 10.
    Liu C, Tao R, Li W, Zhang M M, Sun W W and Du Q. 2021. Joint classification of hyperspectral and multispectral images for mapping coastal wetlands. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 982-996
  11. 11.
    Liu J F, Li L F, Ren C Y, Mao D H and Zhang B. 2018. Information extraction of coastal wetlands in Yellow River estuary by optimal feature-based random forest model. Wetland Science, 16(2): 97-105
  12. 12.
    Liu Y B, Han M, Pan B and Liu Y R. 2017. The spatial distribution of vegetation biomass and soil salinity in new-born wetlands of the Yellow River delta. Wetland Science, 15(3): 364-368
  13. 13.
    Lu H T and Zhang Q C. 2016. Applications of deep convolutional neural network in computer vision. Journal of Data Acquisition and Processing, 31(1): 1-17
  14. 14.
    Luo W J, Li Y J, Urtasun R and Zemel R. 2016. Understanding the effective receptive field in deep convolutional neural networks//Proceedings of the 30th International Conference on Neural Information Processing Systems. Barcelona: Curran Associates Inc.
  15. 15.
    Meng X R. 2019. Study on Remote Sensing Finer Classification of Freshwater Wetland Based on Deep Learning. Harbin: Harbin Normal University
  16. 16.
    Pearson R L and Miller L D. 1972. Remote mapping of standing crop biomass for estimation of the productivity of the short-grass prairie//Proceedings of the Eighth International Symposium on Remote Sensing of Environment. Ann Arbor: [s.n.]: 7-12
  17. 17.
    Qi J G, Chehbouni A, Huete A R, Kerr Y H and Sorooshian S. 1994. A modified soil adjusted vegetation index. Remote Sensing of Environment, 48(2): 119-126
  18. 18.
    Ronneberger O, Fischer P and Brox T. 2015. U-Net: convolutional networks for biomedical image segmentation//18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer: 234-241
  19. 19.
    Rouse J W, Haas R H, Schell J A and Deering D W. 1974. Monitoring vegetation systems in the great plains with ERTS//Third Earth Resources Technology Satellite-1 Symposium. Washington: NASA: 309-317
  20. 20.
    Sun K, Xiao B, Liu D and Wang J D. 2019. Deep high-resolution representation learning for human pose estimation//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach: IEEE
  21. 21.
    Wang J, Song J W, Chen M Q and Yang Z. 2015. Road network extraction: a neural-dynamic framework based on deep learning and a finite state machine. International Journal of Remote Sensing, 36(12): 3144-3169
  22. 22.
    Wang J B, Zhang J, Ma Y and Ren G B. 2014. Classification method of hyperspectral image in typical surface feature of Huanghe River estuary wetland. Journal of Marine Sciences, 32(3): 36-41
  23. 23.
    Xu D X and Zhang G X. 2007. Impact of Human activities on coastal wetlands in China. Wetland Science, 5(3): 282-288
  24. 24.
    Yang J F, Ren G B, Ma Y and Fan Y G. 2016. Coastal wetland classification based on high resolution SAR and optical image fusion//2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Beijing: IEEE
  25. 25.
    Zhang C J, Zhu L, Yu L. 2021. Review of Attention Mechanism in Convolutional Neural NetWorks. Computer Engineering and Applications, 2021, 57(20):64-72
  26. 26.
    Zhang L, Gong Z N, Wang Q W, Jin D D and Wang X. 2019. Wetland mapping of Yellow River Delta wetlands based on multi-feature optimization of Sentinel-2 images. Journal of Remote Sensing, 23(2): 313-326
  27. 27.
    Zhao H S, Shi J P, Qi X J, Wang X G and Jia J Y. 2017. Pyramid scene parsing network//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE: 6230-6239
  28. 28.
    Zhou F Y, Jin L P and Dong J. 2017. Review of convolutional neural network. Chinese Journal of Computers, 40(6): 1229-1251
  29. 29.
    Zhu Y L. 2020. Remote-Sensed Monitoring and Analysis of Invasive Alien Species Spartina Alterniflora in Shandong Province Based on Deep Learning Classification Method. Qingdao: First Institute of Oceanography, Ministry of Natural Resources. (朱玉玲. 2020. 基于深度学习分类方法的山东省外来入侵物种互花米草遥感监测与分析. 青岛: 自然资源部第一海洋研究所)

Читать полностью

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website