多源DEM融合的高差拟合神经网络方法

doi:10.11947/j.AGCS.2018.20180135

测绘学报 ›› 2018, Vol. 47 ›› Issue (6): 854-863.doi: 10.11947/j.AGCS.2018.20180135

• 数字摄影测量与深度学习方法 • 上一篇下一篇

多源DEM融合的高差拟合神经网络方法

沈焕锋¹, 刘露¹, 岳林蔚², 李星华³, 张良培⁴

1. 武汉大学资源与环境科学学院, 湖北武汉 430079;
2. 中国地质大学(武汉)信息工程学院, 湖北武汉 430074;
3. 武汉大学遥感信息工程学院, 湖北武汉 430079;
4. 武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉 430079

收稿日期:2017-11-30 修回日期:2018-03-28 出版日期:2018-06-20 发布日期:2018-06-21
作者简介:沈焕锋(1980-),男,教授,研究方向为影像质量改善、数据融合与同化、遥感制图与应用等。E-mail:shenhf@whu.edu.cn
基金资助:
国家自然科学基金（61671334；41701394；41661134015）

A Multi-source DEM Fusion Method Based on Elevation Difference Fitting Neural Network

SHEN Huanfeng¹, LIU Lu¹, YUE Linwei², LI Xinghua³, ZHANG Liangpei⁴

1. School of Resource and Environmental Sciences, Wuhan University, Wuhan 430079, China;
2. Faculty of Information Engineering, China University of Geosciences, Wuhan 430074, China;
3. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China;
4. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China

Received:2017-11-30 Revised:2018-03-28 Online:2018-06-20 Published:2018-06-21
Supported by:
The National Natural Science Foundation of China (Nos.61671334;41701394;41661134015)

摘要/Abstract

摘要： 本文侧重于介绍智能化摄影测量机器学习的高差拟合神经网络方法。观测手段和处理方式等限制导致全球高质量无缝DEM数据的缺乏，进而制约了它在水文、地质、气象及军事等领域的应用。本文提出了一种基于高差拟合神经网络的多源DEM融合方法，尝试融合全球DEM产品SRTM1、ASTER GDEM v2和激光雷达测高数据ICESat GLAS。首先，根据ICESat GLAS的相关参数及与DEM数据的高程差值，结合坡度自适应的思想设置高差阈值对ICESat GLAS进行滤波，剔除异常数据点。然后，以ICESat GLAS数据为控制点，利用神经网络模型拟合ASTER GDEM v2的误差分布。以地形坡度信息和经纬度坐标作为网络输入，ICESat GLAS和ASTER GDEM v2的高程差值作为目标输出，训练得到预测高差，将其与ASTER GDEM v2高程值相加即可获得校正结果。最后，引入TIN差分曲面的方法，利用校正后的ASTER GDEM v2高程值对SRTM1的数据空洞进行填充，融合生成空间无缝DEM。本文通过随机选取数据进行真实试验，对模型进行了精度验证，并给出了处理结果的定量评价和目视效果。结果表明，不论是空洞还是整体区域，本文方法相比其他DEM数据集和其他方法的处理结果都能够在RMSE上表现出优势，同时，本文提出的方法能够有效克服ASTER GDEM中异常值的影响，得到空间无缝DEM。

关键词: 多源DEM融合, 神经网络, TIN差分曲面, 坡度自适应

Abstract: This paper focuses on machine learning in intelligent photogrammetry:the elevation difference fitting neural network method.The limitations of observation technologies and processing methods lead to the lack of global high-accuracy seamless DEMs,which further restrict DEMs’ application in the fields of hydrology,geology,meteorology,military and other applications.In this paper,we propose a multi-source DEM fusion method using the neural network model trained based on elevation difference.The proposed method is employed to generate a high-quality seamless DEM dataset blending SRTM1,ASTER GDEM v2,and ICESat GLAS.At first,the ICESat GLAS data were filtered according to the relevant parameters and the elevation differences with DEMs.The threshold of elevation difference adaptively varied with terrain slope to remove the abnormal points effectively.The neural network was then applied to learn the error distribution of ASTER GDEM v2,using the ICESat GLAS data as the control points.We constructed the network input composed of slope information,latitude and longitude coordinates,while the elevation difference of ICESat GLAS and ASTER GDEM v2 were set as the target output.The corrected ASTER GDEM v2 results can be obtained by adding the predicted output to the original elevation values.At last,the corrected ASTER GDEM v2 values were utilized to fill the voids of SRTM1,where the vertical bias between the datasets were dealt with TIN delta surface method to blend the seamless DEM.Randomly selected data were used for actual experiments,and the proposed model was evaluated by comparing with other methods and DEM datasets through quantitative evaluation and visual discrimination.Experiment results show that the proposed method has lower value of RMSE than compared methods both in void or the whole area,which can effectively overcome the influence of outliers in ASTER GDEM v2,and generate seamless DEM.

Key words: multi-source DEM fusion, neural network, TIN delta surface, slope adaption

中图分类号:

P208

沈焕锋, 刘露, 岳林蔚, 李星华, 张良培. 多源DEM融合的高差拟合神经网络方法[J]. 测绘学报, 2018, 47(6): 854-863.

SHEN Huanfeng, LIU Lu, YUE Linwei, LI Xinghua, ZHANG Liangpei. A Multi-source DEM Fusion Method Based on Elevation Difference Fitting Neural Network[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(6): 854-863.

参考文献

[1] JAFARZADEGAN K,MERWADE V.A DEM-based Approach for Large-scale Floodplain Mapping in Ungauged Watersheds[J].Journal of Hydrology,2017,550:650-662.
[2] HANCOCK G R,MARTINEZ C,EVANS K G,et al.A Comparison of SRTM and High-resolution Digital Elevation Models and Their Use in Catchment Geomorphology and Hydrology:Australian Examples[J].Earth Surface Processes and Landforms,2006,31(11):1394-1412.
[3] BU Xiaoqian,YUE Peng.A Scientific Workflow Approach for Hydrologic Analysis from Digital Elevation Model[C]//Proceedings of the 5th International Conference on Agro-Geoinformatics.Tianjin,China:IEEE Press,2016:17-21.
[4] KHROMOVA T E,DYURGEROV M B,BARRY R G.Late-twentieth Century Changes in Glacier Extent in the Ak-shirak Range,Central Asia,Determined from Historical Data and ASTER Imagery[J].Geophysical Research Letters,2003,30(16):1863.
[5] 徐彦怀.基于卫星遥感影像和DEM融合的地质断裂带研究[J].测绘与空间地理信息,2016,39(11):135-138. XU Yanhuai.The Study on Geological Fault Zone Base on the Merged Image between the Satellite Remote Sensing Image and DEM[J].Geomatics & Spatial Information Technology,2016,39(11):135-138.
[6] TOUTIN T.ASTER DEMs for Geomatic and Geoscientific Applications:A Review[J].International Journal of Remote Sensing,2008,29(7):1855-1875.
[7] 王祎婷,陈秀万,柏延臣,等.多源DEM和多时相遥感影像监测冰川体积变化——以青藏高原那木纳尼峰地区为例[J].冰川冻土,2010,32(1):126-132. WANG Yiting,CHEN Xiuwan,BO Yanchen,et al.Monitoring Glacier Volume Change Based on Multi-temporal Remote Sensing Images[J].Journal of Glaciology and Geocryology,2010,32(1):126-132.
[8] ROBINSON N,REGETZ J,GURALNICK R P.Earth Env-DEM90:A Nearly-global,Void-free,Multi-scale Smoothed,90 m Digital Elevation Model from Fused ASTER and SRTM Data[J].ISPRS Journal of Photogrammetry and Remote Sensing,2014,87:57-67.
[9] YUE Linwei,SHEN Huafeng,ZHANG Liangpei,et al.High-quality Seamless DEM Generation Blending SRTM-1,ASTER GDEM v2 and ICESat/GLAS Observations[J].ISPRS Journal of Photogrammetry and Remote Sensing,2017,123:20-34.
[10] KARKEE M,STEWARD B L,AZIZ S A.Improving Quality of Public Domain Digital Elevation Models through Data Fusion[J].Biosystems Engineering,2008,101(3):293-305.
[11] LI Xinghua,SHEN Hhuanfeng,FENG Ruitao,et al.DEM Generation from Contours and A Low-resolution DEM[J].ISPRS Journal of Photogrammetry and Remote Sensing,2017,134:135-147.
[12] LUEDELING E,SIEBERT S,BUERKERT A.Filling the Voids in the SRTM Elevation Model:A TIN-based Delta Surface Approach[J].ISPRS Journal of Photogrammetry and Remote Sensing,2007,62(4):283-294.
[13] LI Peng,SHI Chuang,LI Zhenhong,et al.Evaluation of ASTER GDEM Using GPS Benchmarks and SRTM in China[J].International Journal of Remote Sensing,2013,34(5):1744-1771.
[14] FARR T G,ROM P A,EDWARD C,et al.The Shuttle Radar Topography Mission[J].Reviews of Geophysics,2007,45(2):1-33.
[15] YANG Liping,MENG Xingmin,ZHANG Xiaoqiang.SRTM DEM and Its Application Advances[J].International Journal of Remote Sensing,2011,32(14):3875-3896.
[16] YUE Linwei,YU Wei,SHEN Huanfeng,et al.Accuracy Assessment of SRTM V4.1 and ASTER GDEM V2 in High-Altitude Mountainous Areas:A Case Study in Yulong Snow Mountain,China[C]//Proceedings of 2015 IEEE International Symposium on Geoscience and Remote Sensing.Milan,Italy:IEEE Press,2015,5011-5014.
[17] WANG Xianwei,GONG Peng,ZHAO Yuanyuan,et al.Water-level Changes in China's Large Lakes Determined from ICESat/GLAS Data[J].Remote Sensing of Environment,2013,132:131-144.
[18] AREFI H,REINARTZ P.Accuracy Enhancement of ASTER Global Digital Elevation Models Using ICESat Data[J].Remote Sensing,2011,3(7):1323-1343.
[19] REUTER H I,NELSON A,JARVIS A.An Evaluation of Void-filling Interpolation Methods for SRTM Data[J].International Journal of Geographical Information Science,2007,21(9):983-1008.
[20] YUE Tianxiang,CHEN Chuanfa,LI Bailian.A High-accuracy Method for Filling Voids and Its Verification[J].International Journal of Remote Sensing,2012,33(9):2815-2830.
[21] 陈传法,杜正平,岳天祥.基于高精度曲面建模方法的SRTM空缺插值填补研究[J].大地测量与地球动力学,2010,30(1):126-129,135. CHEN Chuanfa,DU Zhengping,YUE Tianxiang.Research of SRTM Void-filling Based on High Accuracy Surface Modelling[J].Journal of Geodesy and Geodynamics,2010,30(1):126-129,135.
[22] YUE Linwei,SHEN Huanfeng,YUAN Qiangqiang,et al.Fusion of Multi-scale DEMs Using A Regularized Super-resolution Method[J].International Journal of Geographical Information Science,2015,29(12):2095-2120.
[23] BAGHDAD N,LEMARQUAND N,ABDALLAH H,et al.The Relevance of GLAS/ICESat Elevation Data for the Monitoring of River Networks[J].Remote Sensing,2011,3(4):708-720.
[24] 周秀芝,文贡坚,王润生.自适应窗口快速立体匹配[J].计算机学报,2006,29(3):473-479 ZHOU Xiuzhi,WEN Gongjian,WANG Runsheng.Fast Stereo Matching Using Adaptive Window[J].Chinese Journal of Computers,2006,29(3):473-479.
[25] 李双成,郑度.人工神经网络模型在地学研究中的应用进展[J].地球科学进展,2003,18(1):68-76. LI Shuangcheng,ZHENG Du.Applications of Artificial Neural Networks to Geosciences:Review and Prospect[J].Advance in Earth Sciences,2003,18(1):68-76.
[26] ÖZTOPAL A.Artificial Neural Network Approach to Spatial Estimation of Wind Velocity Data[J].Energy Conversion and Management,2006,47(4):395-406.
[27] ZHANG Liangpei,WU Ke,ZHONG Yanfei,et al.A New Sub-pixel Mapping Algorithm Based on A BP Neural Network with an Observation Model[J].Neurocomputing,2008,71(10-12):2046-2054.
[28] 张朝忙,刘庆生,刘高焕,等.SRTM 3与ASTER GDEM数据处理及应用进展[J].地理与地理信息科学,2012,28(5):29-34. ZHANG Chaomang,LIU Qingshneg,LIU Gaohuan,et al.Data Processing and Application Progress of SRTM 3 and ASTER GDEM[J].Geography and Geo-Information Science,2012,28(5):29-34.

多源DEM融合的高差拟合神经网络方法

A Multi-source DEM Fusion Method Based on Elevation Difference Fitting Neural Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	杜佳威, 武芳, 朱丽, 刘呈熠, 王安东. 图形、图像融合利用的集成学习智能化简方法及其在岛屿岸线化简中的应用[J]. 测绘学报, 2022, 51(3): 373-387.
[2]	张玉鑫, 颜青松, 邓非. 高分辨率遥感影像建筑物提取多路径RSU网络法[J]. 测绘学报, 2022, 51(1): 135-144.
[3]	杨秋莲, 刘艳飞, 丁乐乐, 孟凡效. 高分影像场景分类的半监督深度卷积神经网络学习方法[J]. 测绘学报, 2021, 50(7): 930-938.
[4]	叶发茂, 孟祥龙, 董萌, 聂运菊, 葛芸, 陈晓勇. 遥感图像蚁群算法和加权图像到类距离检索法[J]. 测绘学报, 2021, 50(5): 612-620.
[5]	张传辉, 姚国标, 张力, 艾海滨, 满孝成, 黄鹏飞. 多分支网络联合的倾斜影像仿射不变特征匹配[J]. 测绘学报, 2021, 50(5): 641-651.
[6]	施慧慧, 徐雁南, 滕文秀, 王妮. 高分辨率遥感影像深度迁移可变形卷积的场景分类法[J]. 测绘学报, 2021, 50(5): 652-663.
[7]	蓝朝桢, 卢万杰, 于君明, 徐青. 异源遥感影像特征匹配的深度学习算法[J]. 测绘学报, 2021, 50(2): 189-202.
[8]	汤寓麟, 金绍华, 边刚, 张永厚, 李凡. 侧扫声呐识别沉船影像的迁移学习卷积神经网络法[J]. 测绘学报, 2021, 50(2): 260-269.
[9]	成飞飞, 付志涛, 黄亮, 陈朋弟, 黄琨. 结合自适应PCNN的非下采样剪切波遥感影像融合[J]. 测绘学报, 2021, 50(10): 1380-1389.
[10]	阳凡林, 朱正任, 李家彪, 冯成凯, 邢喆, 吴自银. 利用深层卷积神经网络实现地形辅助的多波束海底底质分类[J]. 测绘学报, 2021, 50(1): 71-84.
[11]	王旭, 柴洪洲, 王昶, 种洋. 优选小波函数的小波神经网络预报GPS卫星钟差[J]. 测绘学报, 2020, 49(8): 983-992.
[12]	吕栋, 欧吉坤, 于胜文. 基于MEA-BP神经网络的卫星钟差预报[J]. 测绘学报, 2020, 49(8): 993-1003.
[13]	李道纪, 郭海涛, 卢俊, 赵传, 林雨准, 余东行. 遥感影像地物分类多注意力融和U型网络法[J]. 测绘学报, 2020, 49(8): 1051-1064.
[14]	杨必胜, 宗泽亮, 陈驰, 孙文鹿, 米晓新, 吴唯同, 黄荣刚. 车载探地雷达地下目标实时探测法[J]. 测绘学报, 2020, 49(7): 874-882.
[15]	李佳田, 王聪聪, 阿晓荟, 晏玲, 朱志浩, 高鹏. 多向前方交会与单隐层神经网络结合的近景前方交会法[J]. 测绘学报, 2020, 49(6): 736-745.