Please wait a minute...
img

官方微信

遥感技术与应用  2021, Vol. 36 Issue (4): 713-727    DOI: 10.11873/j.issn.1004-0323.2021.4.0713
湿地遥感专栏     
基于面向对象—深度学习的闽东南低海拔海岸带地区湿地动态遥感分析
路春燕1,2(),雷依凡1,苏颖1,黄雨菲1,刘明月3,贾明明2()
1.福建农林大学 计算机与信息学院,福建 福州 350002
2.中国科学院东北地理与农业生态研究所 湿地生态与环境重点实验室,吉林 长春 130102
3.华北理工大学 矿业工程学院,河北 唐山 063210
Remote Sensing Analysis of Wetland Dynamics based on Object-oriented and Deep Learning in the Low-elevation Coastal Zone of Southeast Fujian
Chunyan Lu1,2(),Yifan Lei1,Ying Su1,Yufei Huang1,Mingyue Liu3,Mingming Jia2()
1.College of Computer and Information Sciences,Fujian Agriculture and Forestry University,Fuzhou 350002,China
2.Key Laboratory of Wetland Ecology and Environment,Northeast Institute of Geography and Agroecology,Chinese Academy of Sciences,Changchun 130102,China
3.College of Mining Engineering,North China University of Science and Technology,Tangshan 063210,China
 全文: PDF(5778 KB)   HTML
摘要:

海岸带湿地具有重要的生态价值和经济开发价值,明确其时空变化特征与影响因素对于维持区域生态系统平衡和可持续发展具有重要意义。以Landsat TM/ETM+/OLI影像为基本数据源,综合利用面向对象与深度学习分类方法对1985~2015年闽东南低海拔海岸带地区的湿地信息进行提取,以揭示其时空演变特征与驱动力因素。结果表明:基于面向对象—深度学习分类方法对湿地进行信息提取,整体分类精度可达93%以上,分类结果整体性好;1985~2015年自然湿地面积呈减少趋势,人工湿地面积呈增加趋势,分别减少和增加250.31 km2和251.36 km2;湿地二级类型中,30 a间河口/浅海水域和淤泥质海滩面积减少最大,盐田/水产养殖场面积增加最大;1985~2015年湿地变化类型多样,且2000~2015年较1985~2000年湿地变化更为剧烈;湿地变化是人类活动和自然环境变化共同作用的结果,其中人类活动是影响湿地变化的主要原因。该方法及研究结果可为海岸带湿地监测与保护管理提供技术支持和决策参考。

关键词: 低海拔海岸带地区湿地面向对象分类深度学习闽东南    
Abstract:

Wetlands located in coastal zone have important ecological and economic development value. It is of great significance to understand spatiotemporal characteristics and influencing factors of wetland change for maintaining regional ecosystem balance and sustainable development. Taking Landsat TM/ETM+/OLI images as the basic data source, wetland information extraction of low-elevation coastal zone of Southeast Fujian in 1985, 2000, and 2015 were carried out combing with object-oriented and deep learning classification methods. The spatiotemporal evolution characteristics and driving factors of wetland change were revealed. The results showed that: using object-oriented deep learning classification method, the overall classification accuracy of wetlands was more than 93%, and the classification results were desirable. During 1985~2015, the natural wetlands showed a decreasing trend, and the human-made wetlands showed an increasing trend, with -250.31 km2 and 251.36 km2, respectively. Among the second-class wetland types, the estuary/shallow sea water and mudflats decreased the most area in 30 years, and the salt pans/aquaculture ponds increased the most area. The types of wetland change were diverse from 1985 to 2015, and the wetland changes from 2000 to 2015 were more drastic than those from 1985 to 2000. The wetland dynamics attributed to natural environment change and the influence of human activities, in which human activities were the critical causes. This study can provide technical support and decision-making references for the monitoring, conservation, and management of coastal zone wetlands.

Key words: Low-elevation coastal zone    Wetlands    Object-oriented classification    Deep learning    Southeast Fujian
收稿日期: 2020-06-28 出版日期: 2021-09-26
ZTFLH:  TP79  
基金资助: 国家自然科学基金青年基金项目(41901375);福建农林大学杰出青年研究人才计划项目(XJQ201920);福建农林大学科技创新专项基金项目(CXZX2020106A);吉林省科技发展计划项目(20200301014RQ)
通讯作者: 贾明明     E-mail: luchunyan@fafu.edu.cn;jiamingming@iga.ac.cn
作者简介: 路春燕(1986-),女,山东邹平人,讲师,主要从事资源环境遥感研究。E?mail:luchunyan@fafu.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
路春燕
雷依凡
苏颖
黄雨菲
刘明月
贾明明

引用本文:

路春燕,雷依凡,苏颖,黄雨菲,刘明月,贾明明. 基于面向对象—深度学习的闽东南低海拔海岸带地区湿地动态遥感分析[J]. 遥感技术与应用, 2021, 36(4): 713-727.

Chunyan Lu,Yifan Lei,Ying Su,Yufei Huang,Mingyue Liu,Mingming Jia. Remote Sensing Analysis of Wetland Dynamics based on Object-oriented and Deep Learning in the Low-elevation Coastal Zone of Southeast Fujian. Remote Sensing Technology and Application, 2021, 36(4): 713-727.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2021.4.0713        http://www.rsta.ac.cn/CN/Y2021/V36/I4/713

图1  研究区位置图 审图号:GS(2000)4617
行列号时间传感器云覆盖量质量
1180421984/04/23TM0%
1180422000/08/09、2001/04/15TM、TM0%
1180422015/04/13OLI0%
1190421986/07/25TM0%
1190422000/05/04、2000/06/29ETM+、TM0%
1190422015/01/14、2016/07/27OLI、OLI0%
1190431986/07/25TM1%
1190432000/04/18、2000/06/29ETM+、TM0%
1190432015/10/13、2016/07/27OLI、OLI0%
1200431986/11/05TM0%
1200431999/09/30、2000/11/25ETM+、TM0%
1200432014/11/18、2015/02/06OLI、OLI0%
1200441986/11/05TM0%
1200441999/10/24、2000/02/05TM、ETM+0%
1200442014/11/18、2016/02/09OLI、OLI0%
表1  研究选用影像具体信息
湿地一级类型湿地二级类型解译标志影像示例*
近海与海岸湿地河口/浅海水域蓝色或深蓝色,分布于河流入海口及低潮时水深不超过6 m的近海水域;边界清晰,纹理细腻,与海域相接。
沙石海滩亮白色,纹理较粗糙,边界清晰,位于海岸线沿线,呈长条带状分布。
淤泥质海滩灰色或浅灰色,颜色有层次感,分布于海岸线沿线,与海水分界明显,呈现扇形或宽条带状分布。
潮间盐水沼泽生长于淤泥质海滩上,几何形状不规则,边界清晰,呈红、浅红色或青色,影像纹理细腻。
红树林几何形状不规则,边界清晰,呈红色,影像纹理细腻,生长于淤泥质海滩上。
河流湿地河流几何形状明显,河弯曲折不定,支干渠相对较直。质地较细腻、纹理清晰,颜色呈现深蓝色、蓝色或淡蓝色。
湖泊湿地湖泊呈不规则圆形或椭圆形,边界清晰;蓝色或深蓝色,纹理细腻;水位深浅的不同,其内部色调亦不同。
沼泽湿地草本沼泽位于河流、水库坑塘及湖泊周边;呈红色或浅红色;形状不规则。
人工湿地水库坑塘形状不规则,轮廓清晰;深蓝色、蓝色或浅蓝色;纹理较细腻;水库外缘有明显水闸工程痕迹。
运河水渠蓝色或深蓝色;边界清晰,多为弯曲条带状或局部明显平直;质地及纹理细腻。
盐田/水产养殖场分布于河流入海口附近及海岸线沿线,边界清晰,蓝色或蓝黑色,形状规整;内部条纹状纹理结构清晰。
表2  湿地遥感分类系统及其影像特征
图2  基于面向对象—深度学习的土地覆盖分类流程图
特征类型特征名称描述或公式*
光谱特征[18]波段亮度均值各影像波段亮度的均值
波段亮度标准差各影像波段亮度的标准差
NDVIρNIR-ρR/ρNIR+ρR
NDWIρG-ρNIR/ρG+ρNIR
NDBIρMIR-ρNIR/ρMIR+ρNIR
EVI2.5ρNIR-ρR/ρNIR+6ρR-7.5ρB+1
纹理特征[19]对比度

i=0L-1j=0L-1i-j2Pi,j

反映影像对象斑块的清晰度和纹理沟纹深浅的程度

均匀度

i=0L-1j=0L-1Pi,j/1+i-j2

反映影像对象斑块纹理的同质性,度量其局部变化

i=0L-1j=0L-1Pi,jlogPi,j

反映影像对象斑块纹理的非均匀程度和复杂程度

非相似性

i=0Lj=0LPi,j*i-j

反映影像对象斑块纹理的灰度差别程度

相关性

i=0Lj=0Li-Mean*j-Mean*Pi,j2Variance

反映影像对象斑块纹理的线性相关程度

角二阶矩

i=0Lj=0LPi,j2

反映影像对象斑块纹理的均匀程度

形状特征[20]凹度

S-Sx/Sx

反映影像对象斑块凹多边形的程度

精密度

S/1+VarX+VarY

反映影像对象斑块的精密程度及与正方形的相似程度

偏心角为影像对象斑块长轴两端点与质心的夹角,较偏心率具有更高的形状特征识别度
表3  基于影像对象的光谱、纹理与形状特征
图3  1985~2015年研究区湿地空间分布图审图号:GS(2000)4617
湿地一级类型湿地二级类型1985年2000年2015年1985~2000年2000~2015年1985~2015年

面积

/km2

面积

/km2

面积

/km2

变化面积

/km2

变化率

/%

变化面积

/km2

变化率

/%

变化面积

/km2

变化率

/%

近海与海岸湿地河口/浅海水域4 030.564 005.863 844.36-24.70-0.61-161.50-4.03-186.20-4.62
沙石海滩70.9270.8669.39-0.06-0.08-1.47-2.08-1.53-2.16
淤泥质海滩632.16583.40529.90-48.76-7.71-53.50-9.17-102.26-16.18
潮间盐水沼泽35.5835.3067.58-0.28-0.7832.2891.4432.0089.94
红树林3.794.8410.041.0527.605.20107.386.25164.63
人工湿地水库坑塘85.47115.18147.2929.7234.7732.1127.8761.8272.33
运河水渠10.1610.2510.870.090.870.616.000.706.92
盐田/水产养殖场534.26641.27723.10107.0120.0381.8312.76188.8435.35
河流湿地河流98.2097.8999.45-0.31-0.321.571.601.261.28
湖泊湿地湖泊2.022.032.290.010.580.2612.660.2713.31
沼泽湿地草本沼泽0.630.700.550.0710.34-0.15-21.76-0.09-13.67
表4  1985~2015年研究区各湿地类型变化面积及变化率
一级变化类型1985~2000年2000~2015年

面积

/km2

百分比

/%

面积

/km2

百分比

/%

其他→人工湿地101.7449.1399.5523.05
其他→湖泊湿地0.010.010.260.06
其他→河流湿地1.730.843.060.71
其他→沼泽湿地0.000.000.000.00
河流湿地→其他1.850.891.240.29
河流湿地→人工湿地0.010.000.250.06
河流湿地→沼泽湿地0.260.130.210.05
近海与海岸湿地→其他18.739.0470.1416.24
近海与海岸湿地→近海与海岸湿地8.554.1347.1310.91
近海与海岸湿地→人工湿地54.4026.27110.2225.52
人工湿地→其他18.929.1494.1421.80
人工湿地→河流湿地0.070.030.040.01
人工湿地→近海与海岸湿地0.440.211.380.32
人工湿地→人工湿地0.040.023.480.80
人工湿地→沼泽湿地0.070.030.220.05
沼泽湿地→河流湿地0.000.000.150.03
沼泽湿地→其他0.100.050.210.05
沼泽湿地→人工湿地0.170.080.220.05
总计207.09100.00431.90100.00
表5  1985~2015年研究区湿地一级类型转化对比
图4  1985~2015年研究区湿地二级类型时空变化(11为河口/浅海水域、12为沙石海滩、13为淤泥质海滩、14为潮间盐水沼泽、15为红树林、21为河流、31为湖泊、41为草本沼泽、51为水库坑塘、52为运河水渠、53为盐田/水产养殖场、60为裸地、70为草地、80为林地、90为耕地、10为人工表面)审图号:GS(2000)4617
图5  研究区各湿地二级类型转化桑基图
图6  1985~2015年闽东南地区人口与GDP变化趋势
图7  2000~2015年福建省海平面变化趋势
图8  1985~2015年研究区年平均气温与年降水量变化趋势
1 Liu J Y. Status of marine biodiversity of the China seas[J]. PLoS One, 2013, 8(1): e50719. DOI: 10.1371/journal.pone.0050719.
doi: 10.1371/journal.pone.0050719
2 Thorne K, MacDonald G, Guntenspergen G, et al. US Pacific coastal wetland resilience and vulnerability to sea-level rise[J]. Science Advances,2018,4(2):eaao3270. DOI: 10.1126/sciadv.aao3270.
doi: 10.1126/sciadv.aao3270
3 Hou Xiyong, Xu Xinliang. Spatial patterns of land use in coastal zones of China in the early 21st century[J]. Geographical Research, 2011, 30(8): 1370-1379.
3 侯西勇,徐新良.21世纪初中国海岸带土地利用空间格局特征[J]. 地理研究, 2011, 30(8): 1370-1379.
4 Thia-Eng C. Essential elements of integrated coastal zone management[J]. Ocean & Coastal Management, 1993, 21(1-3): 81-108.
5 Li H Y, Man W D, Li X Y, et al. Remote sensing investigation of anthropogenic land cover expansion in the low-elevation coastal zone of Liaoning Province, China[J]. Ocean & Coastal Management, 2017, 148:245-259.
6 Liu Fuqiang, Wu Tao, Jiang Guojun, et al. Dynamic response of the coastline and coastal landscape patterns to Hemeroby: A case study along the south coast of Yingkou[J]. Acta Ecologica Sinica, 2017, 37(2): 7427-7437.
6 刘富强,吴涛,蒋国俊,等.海岸线与海岸景观格局对人为干扰度的动态响应—以营口市南部海岸为例[J].生态学报,2017,37(2):7427-7437.
7 Bai Yehui, Li Hongzhong, Li Xiangxin, et al. Landscape patterns of coastline and coastal zone in Shenzhen City and their responses to intensity of human activities for 4 periods since 1990[J]. Wetland Science, 2019, 17(3): 335-343.
7 柏叶辉,李洪忠,李向新,等.1990年以来4个时期深圳市海岸线与海岸带景观格局及其对人类活动强度的响应[J].湿地科学,2019,17(3):335-343.
8 Yan Xiaolu, Zhong Jingqiu, Han Zenglin, et al. Driving forces analysis and landscape succession features of coastal wetland both outside and inside reclamation areas in the Northern Liaodong Bay, China in recent 40 years [J]. Scientia Geographica Sinica, 2019, 39(7): 1155-1165.
8 闫晓露,钟敬秋,韩增林,等.近40年辽东湾北部围垦区内外滨海湿地景观演替特征及驱动力分析[J]. 地理科学,2019,39(7):1155-1165.
9 Li Jingxian, Wang Jun, Du Yihang, et al. Change characteristics of coastal wetlands in the Pearl River Delta under rapid urbanization[J]. Wetland Science, 2019, 17(3): 267-276.
9 李婧贤,王钧,杜依杭,等.快速城市化背景下珠江三角洲滨海湿地变化特征[J].湿地科学,2019,17(3):267-276.
10 Lu Chunyan, Gao Yibin, Chen Yuanli, et al. Dynamic change analysis of mangrove swamps based on RS/GIS in Quanzhou Bay [J]. Journal of Forest and Environment, 2019, 39(2): 143-152.
10 路春燕,高弋斌,陈远丽,等.基于RS/GIS的泉州湾红树林湿地时空动态变化分析[J].森林与环境学报,2019,39(2):143-152.
11 Jiang Jiawen, Wen Xiaorong, Wang Hailong, et al. Extraction and dynamic change analysis of coastal wetland type information in Yancheng over the past decade [J]. Journal of Northwest Forestry University, 2019,34(3):167-173,184.
11 蒋佳文,温小荣,王海龙,等.10年间盐城滨海湿地类型信息提取及动态变化分析[J].西北林学院学报,2019,34(3):167-173,184.
12 Chen Chen. Research on classification of hyperspectral remote sensing images of coastal wetlands based on deep learning CNN[D]. Qingdao: First Institute of Oceanography, Ministry of Natural Resources of China, 2018.
12 陈琛.基于深度学习CNN的滨海湿地高光谱遥感影像分类研究[D].青岛:国家海洋局第一海洋研究所,2018.
13 McGranahan G, Balk D, Anderson B. The rising tide: assessing the risks of climate change and human settlements in low elevation coastal zones[J]. Environment and Urbanization, 2007, 19(1): 17-37.
14 Jia M, Liu M, Wang Z, et al. Evaluating the effectiveness of conservation on mangroves: a remote sensing-based comparison for two adjacent protected areas in Shenzhen and Hong kong,China[J].Remote Sensing,2016,8(8):627. DOI:10. 3390/rs8080627.
doi: 10. 3390/rs8080627
15 Qiu Zhongfeng, He Yijun, Xianqing Lü. Tidal adjoint assimilation with the TOPEX/Poseidon altimetry data in the Huanghai and Bohai Seas[J]. Acta Oceanologica Sinica, 2005,27(4): 10-18.
15 丘仲锋,何宜军,吕咸青.黄海、渤海TOPEX/Poseidon高度计资料潮汐伴随同化[J].海洋学报, 2005,27(4): 10-18.
16 Yan Li, Tan Fuhong. Watershed segmentation based on multiscale marking for remote sensing images [J]. Journal of Geomatics, 2020, 45(3): 16-19.
16 闫利,谭福宏.基于多尺度标记的遥感影像分水岭分割[J].测绘地理信息,2020,45(3):16-19.
17 Lu C Y, Liu J F, Jia M M, et al. 2018. Dynamic analysis of mangrove forests based on an optimal segmentation scale model and multi-seasonal images in Quanzhou Bay, China[J]. Remote Sensing, 2020,10(12). DOI:10.3390/rs10122020.
doi: 10.3390/rs10122020
18 Cao J J, Liu K, Liu L, et al. Identifying mangrove species using field close-range snapshot Hyperspectral imaging and machine-learning techniques[J]. Remote Sensing,2018,10(12):2047. DOI:10.3390/rs10122047.
doi: 10.3390/rs10122047
19 Cao J J, Leng W C, Liu K, et al. Object-based mangrove species classification using unmanned aerial vehicle Hyperspectral images and digital surface models[J]. Remote Sensing, 2018, 10(1):89. DOI:10.3390/rs10010089.
doi: 10.3390/rs10010089
20 Jia Mingming. Remote sensing analysis of China’s mangrove forests dynamics during 1973 to 2013[D]. Changchun: Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, 2014.贾明明. 1973~2013年中国红树林动态变化遥感分析[D].长春:中国科学院东北地理与农业生态研究所,2014.
21 Wei S, Zhang H, Wang C, et al. Multi-temporal SAR data large-scale crop mapping based on U-Net model[J]. Remote Sensing, 2019, 11(1):68. DOI:10.3390/rs11010068.
doi: 10.3390/rs11010068
22 Li Yueshuai, Zheng Hongwei, Luo Geping, et al. Extraction and counting of Populus Euphratica crown using UAV images integrated with U-Net method[J]. Remote Sensing Technology and Application, 2019, 34(5):939–949.
22 李越帅,郑宏伟,罗格平,等.集成U-Net方法的无人机影像胡杨树冠提取和计数.遥感技术与应用,2019,34(5):939–949.
23 Ma L, Li M, Gao Y, et al. A novel wrapper approach for feature selection in object-based image classification using polygon-based cross-validation[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(3): 409-413.
24 Lu Chunyan, Wang Zongming, Liu Mingyue, et al. Analysis of conservation effectiveness of wetland protected areas based on remote sensing in West Songnen Plain[J]. China Environmental Science, 2015, 35(2): 599-609.
24 路春燕,王宗明,刘明月,等.松嫩平原西部湿地自然保护区保护有效性遥感分析[J]. 中国环境科学,2015,35(2): 599-609.
25 Liu M, Li H, Li L, et al. Monitoring the invasion of Spartina alterniflora using multi-source high-resolution imagery in the Zhangjiang Estuary, China[J]. Remote Sensing, 2017, 9(6): 539. DOI: 10.3390/rs9060539.
doi: 10.3390/rs9060539
26 Zhang Ying, Lu Jianbo. Progress on Monitoring of Two Invasive Species Smooth Cordgrass (Spatina alterniflora)and Water Hyacinth (Eichhornia crassipes) by Remote Sensing[J]. Bulletin of Science and Technology, 2010,26(1):130-137.
26 章莹,卢剑波.外来入侵物种互花米草(Spartina alterniflora)及凤眼莲(Eichhornia crassipes)的遥感监测研究进展[J].科技通报,2010,26(1):130-137.
27 Zhong Lianxiu, Lu Chunyan, Wang Zongming, et al. Health assessment of mangrove swamp in Zhangjiang Estuary based on GIS and RS[J]. Chinese Journal of Ecology, 2019,38(8):2553-2563.
27 钟连秀,路春燕,王宗明,等.基于GIS与RS的漳江口红树林湿地生态系统健康评价[J].生态学杂志,2019,38(8):2553-2563.
28 Lu Chunyan. Spatial distribution patterns and evolution of wetlands in Fujian province in recent 30 years[M]. Xi’an: Xi'an Jiaotong University Press, 2019.路春燕. 近30年福建省湿地空间分布格局及其演变[M]. 西安: 西安交通大学出版社, 2019.
29 Yuan Q, Shen H, Li T, et al. Deep learning in environmental remote sensing: achievements and challenges[J]. Remote Sensing of Environment, 2020, 241: 111716. DOI: 10.1016/j.rse.2020.111716.
doi: 10.1016/j.rse.2020.111716
30 Sun Z, Di L, Fang H, et al. Deep Learning Classification for Crop Types in North Dakota[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13: 2200-2213.
31 Jia M, Wang Z, Mao D, et al. Rapid, robust, and automated mapping of tidal flats in China using time series Sentinel-2 images and Google Earth Engine[J]. Remote Sensing of En-vironment,2021,255:112285. DOI: 10.1016/j.rse.2021. 112285.
doi: 10.1016/j.rse.2021. 112285
[1] 李佳佳,束进芳,裘增欢,符冉迪,金炜. 面向滨海湿地的全色/多光谱影像融合方法与应用分析——以杭州湾(1999~2018年)为例[J]. 遥感技术与应用, 2021, 36(3): 627-637.
[2] 胡乃勋,陈涛,甄娜,牛瑞卿. 基于卷积神经网络的面向对象露天采场提取[J]. 遥感技术与应用, 2021, 36(2): 265-274.
[3] 林娜,冯丽蓉,张小青. 基于优化Faster-RCNN的遥感影像飞机检测[J]. 遥感技术与应用, 2021, 36(2): 275-284.
[4] 李庆,陈俊杰,李庆亭,李柏鹏,卢凯旋,昝露洋,陈正超. 基于SSD模型的京津冀地区尾矿库检测[J]. 遥感技术与应用, 2021, 36(2): 293-303.
[5] 王晨丞,王永前,王利花. 基于SAR纹理信息的农作物识别研究——以农安县为例[J]. 遥感技术与应用, 2021, 36(2): 372-380.
[6] 曹霸,凌成星. 基于GF-1遥感数据的若尔盖高寒沼泽湿地地上生物量与土壤有机碳密度估算[J]. 遥感技术与应用, 2021, 36(1): 229-236.
[7] 徐瑾昊,冯敏,王建邦,冉有华,祁元,杨联安,李新. 基于高分遥感数据和深度学习的石冰川自动提取研究[J]. 遥感技术与应用, 2020, 35(6): 1329-1336.
[8] 张永宏,曹海啸,阚希. 基于FY-4A/AGRI时空特征融合的新疆地区积雪判识[J]. 遥感技术与应用, 2020, 35(6): 1337-1347.
[9] 张晓川,王杰. 基于遥感时空融合的升金湖湿地生态水文结构分析[J]. 遥感技术与应用, 2020, 35(5): 1109-1117.
[10] 杨瑞,祁元,苏阳. 深度学习U-Net方法及其在高分辨卫星影像分类中的应用[J]. 遥感技术与应用, 2020, 35(4): 767-774.
[11] 张峰极,吴艳兰,姚雪东,梁泽毓. 基于改进DenseNet网络的多源遥感影像露天开采区智能提取方法[J]. 遥感技术与应用, 2020, 35(3): 673-684.
[12] 李强,冯德俊,瑚敏君,伍燚垚,杨历辉. 集成特征分量的高分二号影像阴影检测[J]. 遥感技术与应用, 2019, 34(6): 1252-1260.
[13] 李越帅,郑宏伟,罗格平,杨辽,王伟胜,桂东伟. 集成U-Net方法的无人机影像胡杨树冠提取和计数[J]. 遥感技术与应用, 2019, 34(5): 939-949.
[14] 刘天福,陈学泓,董琪,曹鑫,陈晋. 深度学习在GlobeLand30-2010产品分类精度优化中应用研究[J]. 遥感技术与应用, 2019, 34(4): 685-693.
[15] 林志玮,丁启禄,黄嘉航,涂伟豪,胡典,刘金福. 基于DenseNet的无人机光学图像树种分类研究[J]. 遥感技术与应用, 2019, 34(4): 704-711.