Combination of deep learning and vegetation index for coastal wetland mapping using GF-2 remote sensing images
- Vol. 27, Issue 6, Pages: 1376-1386(2023)
Published: 07 June 2023
DOI: 10.11834/jrs.20221658
扫 描 看 全 文
浏览全部资源
扫码关注微信
Published: 07 June 2023 ,
扫 描 看 全 文
崔宾阁,吴景,李心慧,任广波,路燕.2023.结合深度学习和植被指数的滨海湿地高分二号遥感影像信息提取.遥感学报,27(6): 1376-1386
Cui B G,Wu J,Li X H,Ren G B and Lu Y. 2023. Combination of deep learning and vegetation index for coastal wetland mapping using GF-2 remote sensing images. National Remote Sensing Bulletin, 27(6):1376-1386
针对滨海湿地植被光谱特征相似而易被混淆分类的问题,本文提出了结合深度学习和植被指数的滨海湿地信息提取网络MFVNet。该网络以高分辨率遥感影像和典型植被指数为输入,将UNet中的双卷积操作替换为本文提出的增强多尺度特征提取模块,用于捕获不同尺度的上下文特征,并在解码器中融合不同感受野的语义特征图,增强了滨海湿地地物的特征表示。在黄河口滨海湿地高分二号遥感影像上进行了实验,结果表明:(1)深度学习方法的信息提取精度普遍优于传统的机器学习分类方法SVM;相比HRNet等深度语义分割网络,MFVNet在滨海湿地植被类型上取得了更好的信息提取结果;(2)将修正土壤调节植被指数MSAVI、差值植被指数DVI和比值植被指数RVI与高分二号影像拼接对滨海湿地信息提取贡献较大。
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.
遥感滨海湿地信息提取高分二号深度卷积神经网络MFVNet模型植被指数
remote sensingcoastal wetland information extractionGF-2deep convolutional neural networkMFVNet modelvegetation index
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 [DOI: 10.1007/978-3-030-01234-2_49http://dx.doi.org/10.1007/978-3-030-01234-2_49]
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
范德芹, 赵学胜, 朱文泉, 郑周涛. 2016. 植物物候遥感监测精度影响因素研究综述. 地理科学进展, 35(3): 304-319 [DOI: 10.18306/dlkxjz.2016.03.005http://dx.doi.org/10.18306/dlkxjz.2016.03.005]
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 [DOI: 10.3390/rs11091006http://dx.doi.org/10.3390/rs11091006]
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 [DOI: 10.1007/s11707-017-0672-xhttp://dx.doi.org/10.1007/s11707-017-0672-x]
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 [DOI: 10.1109/LGRS.2018.2890421http://dx.doi.org/10.1109/LGRS.2018.2890421]
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 [DOI: 10.1007/s13131-019-1445-zhttp://dx.doi.org/10.1007/s13131-019-1445-z]
Ibtehaz N and Rahman M S. 2020. MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation. Neural Networks, 121: 74-87 [DOI: 10.1016/j.neunet.2019.08.025http://dx.doi.org/10.1016/j.neunet.2019.08.025]
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)
DOI 10.6046/gtzyyg.1995.02.04http://dx.doi.org/10.6046/gtzyyg.1995.02.04
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 [DOI: 10.1109/CVPR.2017.106http://dx.doi.org/10.1109/CVPR.2017.106]
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 [DOI: 10.1109/JSTARS.2020.3040305http://dx.doi.org/10.1109/JSTARS.2020.3040305]
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
刘家福, 李林峰, 任春颖, 毛德华, 张柏. 2018. 基于特征优选的随机森林模型的黄河口滨海湿地信息提取研究. 湿地科学, 16(2): 97-105 [DOI: 10.13248/j.cnki.wetlandsci.2018.02.001http://dx.doi.org/10.13248/j.cnki.wetlandsci.2018.02.001]
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
刘玉斌, 韩美, 潘彬, 刘延荣. 2017. 黄河三角洲新生湿地植物生物量和土壤含盐量空间分布. 湿地科学, 15(3): 364-368 [DOI: 10.13248/j.cnki.wetlandsci.2017.03.007http://dx.doi.org/10.13248/j.cnki.wetlandsci.2017.03.007]
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
卢宏涛, 张秦川. 2016. 深度卷积神经网络在计算机视觉中的应用研究综述. 数据采集与处理, 31(1): 1-17 [DOI: 10.16337/j.1004-9037.2016.01.001http://dx.doi.org/10.16337/j.1004-9037.2016.01.001]
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.
Meng X R. 2019. Study on Remote Sensing Finer Classification of Freshwater Wetland Based on Deep Learning. Harbin: Harbin Normal University
孟祥锐. 2019. 基于深度学习的淡水湿地遥感精细分类研究. 哈尔滨: 哈尔滨师范大学 [DOI: 10.27064/d.cnki.ghasu.2019.000087http://dx.doi.org/10.27064/d.cnki.ghasu.2019.000087]
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 [DOI: 10.1177/002076409904500102http://dx.doi.org/10.1177/002076409904500102]
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 [DOI: 10.1016/0034-4257(94)90134-1http://dx.doi.org/10.1016/0034-4257(94)90134-1]
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 [DOI: 10.1007/978-3-319-24574-4_28http://dx.doi.org/10.1007/978-3-319-24574-4_28]
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
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 [DOI: 10.1109/cvpr.2019.00584http://dx.doi.org/10.1109/cvpr.2019.00584]
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 [DOI: 10.1080/01431161.2015.1054049http://dx.doi.org/10.1080/01431161.2015.1054049]
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
王建步, 张杰, 马毅, 任广波. 2014. 黄河口湿地典型地物类型高光谱分类方法. 海洋学研究, 32(3): 36-41[DOI: 10.3969/j.issn.1001-909X.2014.03.005http://dx.doi.org/10.3969/j.issn.1001-909X.2014.03.005]
Xu D X and Zhang G X. 2007. Impact of Human activities on coastal wetlands in China. Wetland Science, 5(3): 282-288
徐东霞, 章光新. 2007. 人类活动对中国滨海湿地的影响及其保护对策. 湿地科学, 5(3): 282-288 [DOI: 10.13248/j.cnki.wetlandsci.2007.03.013http://dx.doi.org/10.13248/j.cnki.wetlandsci.2007.03.013]
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 [DOI: 10.1109/IGARSS.2016.7729224http://dx.doi.org/10.1109/IGARSS.2016.7729224]
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
张宸嘉, 朱磊, 俞璐. 卷积神经网络中的注意力机制综述. 计算机工程与应用, 2021, 57(20):64-72
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
张磊, 宫兆宁, 王启为, 金点点, 汪星. 2019. Sentinel-2影像多特征优选的黄河三角洲湿地信息提取. 遥感学报, 23(2): 313-326 [DOI: 10.11834/jrs.20198083http://dx.doi.org/10.11834/jrs.20198083]
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 [DOI: 10.1109/CVPR.2017.660http://dx.doi.org/10.1109/CVPR.2017.660]
Zhou F Y, Jin L P and Dong J. 2017. Review of convolutional neural network. Chinese Journal of Computers, 40(6): 1229-1251
周飞燕, 金林鹏, 董军. 2017. 卷积神经网络研究综述. 计算机学报, 40(6): 1229-1251 [DOI: 10.11897/SP.J.1016.2017.01229http://dx.doi.org/10.11897/SP.J.1016.2017.01229]
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) [DOI: 10.27058/d.cnki.gohyy.2020.000007http://dx.doi.org/10.27058/d.cnki.gohyy.2020.000007]
相关文章
相关作者
相关机构