浏览全部资源
扫码关注微信
Published： 07 April 2022 ，
扫 描 看 全 文
贾莉，郑柯，唐娉，霍连志.2022.地形校正对U-Net深度神经网络分类器分类精度的影响.遥感学报，26（4）： 698-710
Jia L，Zheng K，Tang P and Huo L Z. 2022. Topographic correction effect on classification accuracy for deep neural network classifier—A case study of the U-Net model. National Remote Sensing Bulletin， 26（4）：698-710
在国土资源监测、森林资源调查等多个领域中，基于遥感影像的分类技术受到了广泛应用。在利用传统分类器对地表覆盖分类提取中，地形效应是制约分类精度提升的一种因素，其影响可通过适当的校正模型减弱，且已证明地形校正能够对分类精度的提升起到积极作用。相比于传统分类器，基于深度学习理论的深度神经网络分类器具有深层特征学习和表达的优势，在图像分类领域兴起并逐渐用于土地覆盖分类且取得了不错的精度提升。本文初步探究了地形校正在利用深度神经网络分类器U-Net进行地表覆盖分类时对分类精度的影响情况。以Landsat 8 OLI 30 m影像为数据源，结合GDEM_V2 30 m地形数据，在GlobeLand 30和全国30 m森林分类结果的基础上，利用U-Net深度神经网络分类器实现了山区地表覆盖分类提取，并就不同训练样本获取方式及不同精细程度分类体系下地形校正前后的分类精度做了对比分析。分类结果表明：（1）规则网格裁切和坡向辅助裁切这两种训练样本获取方式下，地形校正后的分类精度较校正前不变或有极小幅度的降低，降低范围在0.9%—1.39%；（2）在对更精细的森林类型分类中，地形校正后的分类精度较校正前下降了1.66%。本文初步探究得到：在规则网格裁切和坡向辅助裁切这两种训练样本获取方式及不同精细程度的分类体系下，地形校正均未能提高U-Net深度神经网络分类器的分类精度。
Remote sensing image classification technology has been widely used in land resource monitoring
forest resource investigation
and other related fields. For the traditional classification methods
terrain effect is an unavoidable factor that restricts the improvement of classification accuracy in the classification of land cover types
and the influence can be weakened by an appropriate correction model
and topographic correction has been proven to play a positive role in improving classification accuracy. Compared with traditional classifiers
deep neural network classifiers based on deep learning theory have the advantages of deep feature learning and expression
which have emerged in the field of image classification and have been gradually applied to land cover classification with good results.Our study has some shortcomings. First
some errors remain in GlobeLand30 and national forest classification products compared with the actual surface cover types. Therefore
more detailed and accurate classification results need to be found as sample labels in the future. Second
the surface of sunny-shady slopes with different types of coverage is not considered in this study. Finally
U-Net should not be the sole focus. In subsequent research
we will attempt to select a variety of deep neural network classifiers to explore the classification accuracy changes before and after topographic correction of neural network models at a more precise scale to obtain further conclusions.
This paper further explores the influence of topographic correction on the classification accuracy of land cover classification by deep neural network classifiers.
Using Landsat 8 OLI image data and GDEM_V2 terrain data with 30 m resolution as data sources
and based on the classification results of GlobeLand30 and national forest types
this paper implemented the classification extraction of land cover types by the U-Net semantic segmentation network and made a comparative analysis of classification accuracy before and after topographic correction with different sample acquisition methods and different levels of classification systems.
Classification results show the following. (1) With two training sample acquisition methods
namely
grid clipping and aspect auxiliary clipping
the classification accuracy after topographic correction is unchanged or slightly reduced compared with that before correction
and the reduction range is 0.9%—1.39%. (2) For the classification of more precise forest types
the classification accuracy after topographic correction decreased by 1.66% compared with that before correction.
In this paper
we conduct a preliminary study and find that in the classification of land cover types by the U-Net model with different sample acquisition methods
namely
regular grid clipping and aspect auxiliary clipping
and under different classification systems
the classification accuracy of the deep neural network classifier-U-Net is not improved by the topographic correction process.
Our study has some shortcomings. First
some errors remain in GlobeLand30 and national forest classification products compared with the actual surface cover types. Therefore
more detailed and accurate classification results need to be found as sample labels in the future. Second
the surface of sunny-shady slopes with different types of coverage is not considered in this study. Finally
U-Net should not be the sole focus. In subsequent research
we will attempt to select a variety of deep neural network classifiers to explore the classification accuracy changes before and after topographic correction of neural network models at a more precise scale to obtain further conclusions.
遥感分类深度神经网络U-Net模型地形校正地表覆盖分类分类精度
remote sensing classificationdeep neural networkU-Net modeltopographic correctionland cover classificationclassification accuracy
Álvarez-Martínez J M, Silió-Calzada A and Barquín J. 2018. Can training data counteract topographic effects in supervised image classification? A sensitivity analysis in the Cantabrian Mountains (Spain). International Journal of Remote Sensing, 39(23): 8646-8669 [DOI: 10.1080/01431161.2018.1489163http://dx.doi.org/10.1080/01431161.2018.1489163]
Brown D G, Lusch D P and Duda K A. 1998. Supervised classification of types of glaciated landscapes using digital elevation data. Geomorphology, 21(3/4): 233-250 [DOI: 10.1016/s0169-555x(97)00063-9http://dx.doi.org/10.1016/s0169-555x(97)00063-9]
Chen C X, Hu C M, Huo L Z and Tang P. 2014. Effect of different radiation correction methods of Landsat TM data on land-cover remote sensing classification. Journal of Remote Sensing, 18(2): 320-334
陈趁新, 胡昌苗, 霍连志, 唐娉. 2014. Landsat TM数据不同辐射校正方法对土地覆盖遥感分类的影响. 遥感学报, 18(2): 320-334 [DOI: 10.11834/jrs.20143211http://dx.doi.org/10.11834/jrs.20143211]
Chen J, Chen J, Liao A P, Cao X, Chen L J, Chen X H, He C Y, Han G, Peng S, Lu M, Zhang W W, Tong X H and Mills J. 2015. Global land cover mapping at 30m resolution: a POK-based operational approach. ISPRS Journal of Photogrammetry and Remote Sensing, 103: 7-27 [DOI: 10.1016/j.isprsjprs.2014.09.002http://dx.doi.org/10.1016/j.isprsjprs.2014.09.002]
Chen J, Liao A P, Chen J, Peng S, Chen L J and Zhang H W. 2017. 30-meter global land cover data product- GlobeLand30. WorldGeomatics, 24(1): 1-8
陈军, 廖安平, 陈晋, 彭舒, 陈利军, 张宏伟. 2017. 全球30m地表覆盖遥感数据产品-GlobeLand30. 地理信息世界, 24(1): 1-8 [DOI: 10.3969/j.issn.1672-1586.2017.01.002http://dx.doi.org/10.3969/j.issn.1672-1586.2017.01.002]
Deng Y, Huang J and He M. 2018. Study on terrain radiometric correction of Landsat 8 in Chong Qing mountainous area. Rural Economy and Science-Technology, 29(11): 16-18
邓禹, 黄健, 何敏. 2018. 重庆山区Landsat 8地形辐射校正研究. 农村经济与科技, 29(11): 16-18 [DOI: 10.3969/j.issn.1007-7103.2018.11.008http://dx.doi.org/10.3969/j.issn.1007-7103.2018.11.008]
Gao Y N and Zhang W C. 2007. Variable empirical coefficient algorithm for removal of topographic effects on remotely sensed data from rugged terrain//Proceedings of 2007 IEEE International Geoscience and Remote Sensing Symposium. Barcelona: IEEE: 4733-4736 [DOI: 10.1109/IGARSS.2007.4423917http://dx.doi.org/10.1109/IGARSS.2007.4423917]
Gu D G and Gillespie A. 1998. Topographic normalization of Landsat tm images of forest based on subpixel sun-canopy-sensor geometry. Remote Sensing of Environment, 64(2): 166-175 [DOI: 10.1016/S0034-4257(97)00177-6http://dx.doi.org/10.1016/S0034-4257(97)00177-6]
Han X M, Li X H, Zhu R F and Shi X Y. 2010. Topographic correction method of remote sensing image considering Bi-directional reflectance//Proceedings of 2010 International Conference on Computer Application and System Modeling. Taiyuan, China: IEEE [DOI: 10.1109/ICCASM.2010.5622511http://dx.doi.org/10.1109/ICCASM.2010.5622511]
He C, Chen J Z and Yue C R. 2014. Comparison test and research progress of normalization topographic correction model. Forest Inventory and Planning, 39(3): 12-16, 34
何超, 陈建珍, 岳彩荣. 2014. 归一化地形校正模型研究进展及其对比实验. 林业调查规划, 39(3): 12-16, 34 [DOI: 10.3969/j.issn.1671-3168.2014.03.003http://dx.doi.org/10.3969/j.issn.1671-3168.2014.03.003]
Isikdogan F, Bovik A C and Passalacqua P. 2017. Surface water mapping by deep learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(11): 4909-4918 [DOI: 10.1109/JSTARS.2017.2735443http://dx.doi.org/10.1109/JSTARS.2017.2735443]
Jia K, Li Q Z, Tian Y C and Wu B F. 2011. A review of classification methods of remote sensing imagery. Spectroscopy and Spectral Analysis, 31(10): 2618-2623
贾坤, 李强子, 田亦陈, 吴炳方. 2011. 遥感影像分类方法研究进展. 光谱学与光谱分析, 3110): 2618-2623 [DOI: 10.3964/j.issn.1000-0593http://dx.doi.org/10.3964/j.issn.1000-0593(201110-2618-06]
Jiang K, Hu C M, Yu K and Zhao Y C. 2014. Landsat TM/ETM+topographic correction method based on smoothed terrain and semi-empirical model. Journal of Remote Sensing, 18(2): 287-306
姜亢, 胡昌苗, 于凯, 赵永超. 2014. 地形抹平与半经验模型的Landsat TM/ETM+地形校正方法. 遥感学报, 18(2): 287-306 [DOI: 10.11834/jrs.20143258http://dx.doi.org/10.11834/jrs.20143258]
Kang X W and Feng Z K. 2011. An introduction to ASTER GDEM and procedure reading. Remote Sensing Information, (6): 69-72
康晓伟, 冯钟葵. 2011. ASTER GDEM数据介绍与程序读取. 遥感信息, (6): 69-72 [DOI: 10.3969/j.issn.1000-3177.2011.06.014http://dx.doi.org/10.3969/j.issn.1000-3177.2011.06.014]
Li C C, Wang J, Hu L Y, Yu L, Clinton N, Huang H B, Yang J and Gong P. 2014. A circa 2010 thirty meter resolution forest map for China. Remote Sensing, 6(6): 5325-5343 [DOI: 10.3390/rs6065325http://dx.doi.org/10.3390/rs6065325]
Li M Q, Im J and Beier C. 2013. Machine learning approaches for forest classification and change analysis using multi-temporal Landsat tm images over Huntington wildlife forest. GIScience and Remote Sensing, 50(4): 361-384 [DOI: 10.1080/15481603.2013.819161http://dx.doi.org/10.1080/15481603.2013.819161]
Li Y D, Hao Z B and Lei H. 2016. Survey of convolutional neural network. Journal of Computer Applications, 36(9): 2508-2515
李彦冬, 郝宗波, 雷航. 2016. 卷积神经网络研究综述. 计算机应用, 36(9): 2508-2515 [DOI: 10.11772/j.issn.1001-9081.2016.09.2508http://dx.doi.org/10.11772/j.issn.1001-9081.2016.09.2508]
Liu T and Chen X. 2018. Application of deep learning in globeland30-2010 product refinement. ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-3: 1111-1116 [DOI: 10.5194/isprs-archives-XLII-3-1111-2018http://dx.doi.org/10.5194/isprs-archives-XLII-3-1111-2018]
Ma Y F, Zhao J B, Li J and Qiao X S. 2018. Remote Sensing Image Classification Based on Artificial Neural Networks. Standardization of Surveying and Mapping, 34(4): 34-37
马亚飞, 赵静波, 李健, 乔小松. 2018. 基于人工神经网络的遥感影像分类研究. 测绘标准化, 34(4): 34-37
Maggiori E, Tarabalka Y, Charpiat G and Alliez P. 2016. Fully convolutional neural networks for remote sensing image classification//Proceedings of 2016 IEEE International Geoscience and Remote Sensing Symposium. Beijing, China: IEEE [DOI: 10.1109/IGARSS.2016.7730322http://dx.doi.org/10.1109/IGARSS.2016.7730322]
Pimple U, Sitthi A, Simonetti D, Pungkul S, Leadprathom K and Chidthaisong A. 2017. Topographic correction of Landsat TM-5 and Landsat OLI-8 imagery to improve the performance of forest classification in the mountainous terrain of northeast Thailand. Sustainability, 9(2): 258 [DOI: 10.3390/su9020258http://dx.doi.org/10.3390/su9020258]
Ronneberger O, Fischer P and Brox T. 2015. U-Net: convolutional networks for biomedical image segmentation//Proceedings of the 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]
Shelhamer E, Long J and Darrell T. 2017. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4): 640-651 [DOI: 10.1109/TPAMI.2016.2572683http://dx.doi.org/10.1109/TPAMI.2016.2572683]
Soenen S A, Peddle D R and Coburn C A. 2005. SCS+C: A modified sun-canopy-sensor topographic correction in forested terrain. IEEE Transactions on Geoscience and Remote Sensing, 43(9): 2148-2159 [DOI: 10.1109/TGRS.2005.852480http://dx.doi.org/10.1109/TGRS.2005.852480]
Tang P, Zheng K, Shan X J, Hu C M, Huo L Z, Zhao L J and Li H Y. 2016. Framework of remote sensing image automatic processing with “invariant feature point set” as control data set. Journal of Remote Sensing, 20(5): 1126-1137
唐娉, 郑柯, 单小军, 胡昌苗, 霍连志, 赵理君, 李宏益. 2016. 以“不变特征点集”为控制数据集的遥感图像自动化处理框架. 遥感学报, 20(5): 1126-1137 [DOI: 10.11834/jrs.20166222http://dx.doi.org/10.11834/jrs.20166222]
Vermote E, Justice C, Claverie M and Franch B. 2016. Preliminary analysis of the performance of the Landsat 8/OLI land surface reflectance product. Remote Sensing of Environment, 185: 46-56 [DOI: 10.1016/j.rse.2016.04.008http://dx.doi.org/10.1016/j.rse.2016.04.008]
Xu H M. 2018. Method research of high resolution remote sensing image classification based on U-net model of Deep learning. Chengdu: Southwest Jiaotong University
许慧敏. 2018. 基于深度学习U-Net模型的高分辨率遥感影像分类方法研究. 成都: 西南交通大学
相关文章
相关作者
相关机构
京公网安备11010802024621