Land Cover Classification of Remote Sensing Image of Hubei Province by Using PSP Net

CHAI Huabin; YAN Chao; ZOU Youfeng; CHEN Zhengchao

doi:10.13203/j.whugis20190296

Volume 46 Issue 8

Aug. 2021

Turn off MathJax

Article Contents

Abstract

References

Geomatics and Information Science of Wuhan University > 2021 > 46(8): 1224-1232. > DOI: 10.13203/j.whugis20190296

CHAI Huabin, YAN Chao, ZOU Youfeng, CHEN Zhengchao. Land Cover Classification of Remote Sensing Image of Hubei Province by Using PSP Net[J]. Geomatics and Information Science of Wuhan University, 2021, 46(8): 1224-1232. DOI: 10.13203/j.whugis20190296

Citation:

PDF (35284 KB)

Land Cover Classification of Remote Sensing Image of Hubei Province by Using PSP Net

1.
School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454003, China
2.
Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China

Funds:

The National Natural Science Foundation of China U1810203

More Information

Author Bio:
CHAI Huabin, PhD, professor, specializes in the deformation monitoring and remote sensing image processing.chaihb@hpu.edu.cn
Received Date: December 01, 2019
Published Date: August 04, 2021

Graphical Abstract

Abstract

Abstract

Objectives Pyramid scene parsing net (PSP Net), a kind of neural network with deep structure, extracts the features of remote sensing image better than the traditional model, e.g. artificial neural network, and supports vector machine. This algorithm can embed the contextual features of difficult scenes into the pixel prediction framework of the full convolutional neural network (FCN), fully understand the scene, realize accurate prediction of each pixel category, location and shape, and fuse local and global information together to propose an optimization strategy for moderate supervised loss. A deep learning algorithm based on PSP Net is proposed to achieve higher accuracy in image classification and effectively promote remote sensing image automation and intelligent interpretation.
Methods Conventional architecture for fast feature embedding (CAFFE) is a deep learning framework with is expressive, fast and thought modular, and supports a variety of deep learning architectures for image classification and segmentation. PSP Net model under the CAFFE framework is used by modifying and optimizing the network to eliminate the overfitting effect. Using the remote sensing image of Hubei Province as the experimental data, the land with the 30 m resolution is studied with the aid of the analysis ability of the context scene of PSP Net. The Python program is used in the CAFFE depth learning framework for operation. The operation network obtains the global feature information through the core structure (pyramid pooling module) and completes the generation of the data set. In the experiment, the 507 standard partial images of 900×600 pixels in the landsat image of Hubei Province are used, and the sample sets suitable for depth learning are generated by pre-processing. Among these, 300 data are selected, including 240 training sets, 44 prediction sets, and 16 validation sets. The overall accuracy (OA) index is used as the prediction accuracy index of the preliminary evaluation model to evaluate the accuracy of the prediction model.
Results PSP Net model under the deep learning framework of CAFFE is used to train the sample data. The learning rate of 10×10^-10 is set, and the million times training model is selected to protect against overfitting of the data. Through the generalization of the model and the generalization and iteration of the samples, the land cover of the 3 phases of TM images about Hubei Province are classified, and the classification accuracy is 82.2%, 83.4% and 83.7%, respectively.
Conclusions The results show that the land cover classification of remote sensing images can be realized quickly, effectively and accurately by PSP Net.
- remote sensing image,
- land cover classification,
- deep learning,
- pyramid scene analysis network (PSP Net)

FullText(HTML)

References (26)

References

[1]	李镇, 张岩, 杨松, 等. QuickBird影像目视解译法提取切沟形态参数的精度分析[J]. 农业工程学报, 2014, 30(20): 179-186 doi: 10.3969/j.issn.1002-6819.2014.20.022 Li Zhen, Zhang Yan, Yang Song, et al. Error Assessment of Extracting Morphological Parameters of Bank Gullies by Manual Visual Interpretation Based on QuickBird Imagery[J]. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(20): 179-186 doi: 10.3969/j.issn.1002-6819.2014.20.022
[2]	王志杰. 基于遥感影像分割单元的土地利用变化快速检测方法[J]. 南京林业大学学报(自然科学版), 2015, 39(3): 1-5 https://www.cnki.com.cn/Article/CJFDTOTAL-NJLY201503001.htm Wang Zhijie. Rapid Detection Method for Land Use Change Based on Remote Sensing Images Segmentation Units[J]. Journal of Nanjing Forestry University (Natural Sciences Edition), 2015, 39(3): 1-5 https://www.cnki.com.cn/Article/CJFDTOTAL-NJLY201503001.htm
[3]	黄利文, 毛政元, 李二振, 等. 基于几何概率的聚类分析方法及其在遥感影像分类中的应用[J]. 中国图像图形学报, 2007, 12(4): 633-639 https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB200704013.htm Huang Liwen, Mao Zhengyuan, Li Erzhen, et al. The Cluster Analysis Approaches Based on Geometric Probability and Its Application in the Classification of Remotely Sensed Images[J]. Journal of Image and Graphics, 2007, 12(4): 633-639 https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB200704013.htm
[4]	唐韵玮, 张景雄. 遥感影像土地覆盖分类的多点地统计学方法[J]. 武汉大学学报·信息科学版, 2014, 39(5): 546-550 doi: 10.13203/j.whugis20130023 Tang Yunwei, Zhang Jingxiong. Land Cover Classification of Remotely Sensed Imagery Using Multiple-Point Geostatistics[J]. Geomatics and Information Science of Wuhan University, 2014, 39(5): 546-550 doi: 10.13203/j.whugis20130023
[5]	林怡, 刘冰, 陈映鹰, 等. 多特征差分核支持向量机遥感影像变化检测方法[J]. 武汉大学学报·信息科学版, 2013, 38(8): 978-982 http://ch.whu.edu.cn/article/id/2731 Lin Yi, Liu Bing, Chen Yingying, et al. Change Detection Method Based on Multi-feature Different Kernel SVM for Remote Sensing Imagery[J]. Geomatics and Information Science of Wuhan University, 2013, 38(8): 978-982 http://ch.whu.edu.cn/article/id/2731
[6]	张晓贺, 翟亮, 张继贤, 等. AdaTree算法在遥感影像分类中的应用[J]. 武汉大学学报·信息科学版, 2013, 38(12): 1 460-1 463 http://ch.whu.edu.cn/article/id/2830 Zhang Xiaohe, Zhai Liang, Zhang Jixian, et al. Application of AdaTree Algorithm to Remote Sensing Image Classification[J]. Geomatics and Information Science of Wuhan University, 2013, 38(12): 1 460-1 463 http://ch.whu.edu.cn/article/id/2830
[7]	Turner D P, Ritts W D, Cohen W B, et al. Scaling Gross Primary Production (GPP) Over Boreal and Deciduous Forest Landscapes in Support of MODIS GPP Product Validation[J]. Remote Sensing of Environment, 2003, 88(3): 256-270 doi: 10.1016/j.rse.2003.06.005
[8]	孟庆祥, 段学琳. 基于DCNN的高分辨率遥感影像场景分类[J]. 华中师范大学学报(自然科学版), 2019, 53(4): 568-574 https://www.cnki.com.cn/Article/CJFDTOTAL-HZSZ201904017.htm Meng Qingxiang, Duan Xuelin. High Resolution Remote Sensing Image Scene Classification Based on DCNN[J]. Journal of Central China Normal University(Natural Sciences), 2019, 53(4): 568-574 https://www.cnki.com.cn/Article/CJFDTOTAL-HZSZ201904017.htm
[9]	张佳, 谢玉凤. 高光谱遥感影像分类方法综述[J]. 安徽农学通报, 2017, 23(14): 155-165 doi: 10.3969/j.issn.1007-7731.2017.14.063 Zhang Jia, Xie Yufeng. Summary of Hyperspectral Remote Sensing Image Classification Methods[J]. Anhui Agricultural Science Bulletin, 2017, 23(14): 155-165 doi: 10.3969/j.issn.1007-7731.2017.14.063
[10]	王斌, 范冬林. 深度学习在遥感影像分类与识别中的研究进展综述[J]. 测绘通报, 2019(2): 99-102 https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB201902021.htm Wang Bin, Fan Donglin. Research Progress of Deep Learning in Classification and Recognition of Remote Sensing Images[J]. Bulletin of Surveying and Mapping, 2019(2): 99-102 https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB201902021.htm
[11]	Bhosle K, Musande V. Evaluation of Deep Learning CNN Model for Land Use Land Cover Classification and Crop Identification Using Hyperspectral Remote Sensing Images[J]. Journal of the Indian Society of Remote Sensing, 2019, 47 (11): 1 949-1 958 doi: 10.1007/s12524-019-01041-2
[12]	Boualleg Y, Farah M, Farah I R. Remote Sensing Scene Classification Using Convolutional Features and Deep Forest Classifier[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(12): 1 944-1 948 doi: 10.1109/LGRS.2019.2911855
[13]	石斌斌, 何海清, 游琦, 一种多尺度全卷积神经网络驱动的遥感影像修复方法[J]. 测绘地理信息, 2018, 43(3): 124-126 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG201803032.htm Shi Binbin, He Haiqing, You Qi. A Method of Multi-scale Total Convolution Network Driven Remote Sensing Image Repair[J]. Journal of Geomatics, 2018, 43(3): 124-126 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG201803032.htm
[14]	付伟锋, 邹维宝. 深度学习在遥感影像分类中的研究进展[J]. 计算机应用研究, 2018, 35(12): 3 521-3 524 https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ201812001.htm Fu Weifeng, Zou Weibao. Review of Remote Sensing Image Classification Based on Deep Learning[J]. Application Research of Computers, 2018, 35(12): 3 521-3 524 https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ201812001.htm
[15]	张春雷. 基于军事飞机图像结合FCN的目标检测技术应用[J]. 理论与算法, 2019 (10): 53-55 https://www.cnki.com.cn/Article/CJFDTOTAL-WDZC201910023.htm Zhang Chunlei. Application of Target Detection Technology Based on Military Aircraft Image Combined with FCN[J]. Theory and Algorithm, 2019 (10): 53-55 https://www.cnki.com.cn/Article/CJFDTOTAL-WDZC201910023.htm
[16]	杨建宇, 周振旭, 杜贞容, 等. 基于SegNet语义模型的高分辨率遥感影像农村建设用地提取[J]. 农业工程学报, 2019, 35(5): 251-258 https://www.cnki.com.cn/Article/CJFDTOTAL-NYGU201905031.htm Yang Jianyu, Zhou Zhenxu, Du Zhenrong, et al. Rural Construction Land Extraction from High Spatial Resolution Remote Sensing Image Based on SegNet Semantic Segmentation Model[J]. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(5): 251-258 https://www.cnki.com.cn/Article/CJFDTOTAL-NYGU201905031.htm
[17]	张兵. 遥感大数据时代与智能信息提取[J]. 武汉大学学报·信息科学版, 2018, 43(12): 1 861-1 871 doi: 10.13203/j.whugis20180172 Zhang Bing. Remote Sensing Big Data Era and Intelligent Information Extraction[J]. Geomatics and Information Science of Wuhan University, 2018, 43(12): 1 861-1 871 doi: 10.13203/j.whugis20180172
[18]	蔡博文, 王树根, 王磊, 等. 基于深度学习模型的城市高分辨率遥感影像不透水面提取[J]. 地球信息科学学报, 2019, 21(9): 1 420-1 429 https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX201909013.htm Cai Bowen, Wang Shugen, Wang Lei, et al. Extraction of Urban Impervious Surface from High-Resolution Remote Sensing Imagery Based on Deep Learning[J]. Journal of Geo-information Science, 2019, 21(9): 1 420-1 429 https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX201909013.htm
[19]	刘万军, 梁雪剑, 曲海成. 不同池化模型的卷积神经网络学习性能研究[J]. 中国图象图形学报, 2016, 21(9): 1 178-1 190 https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201609007.htm Liu Wanjun, Liang Xuejian, Qu Haicheng. Learning Performance of Convolutional Neural Networks with Different Pooling Models[J]. Journal of Image and Graphics, 2016, 21(9): 1 178-1 190 https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201609007.htm
[20]	Takeki A, Trinh T T, Yoshihashi R, et al. Combining Deep Features for Object Detection at Various Scales: Finding Small Birds in Landscape Images[J]. IPSJ Transactions on Computer Vision and Applications, 2016, 8(1): 5-7 doi: 10.1186/s41074-016-0006-z
[21]	冯锦, 李玉惠. 基于卷积神经网络的车型颜色综合识别[J]. 电子科技, 2018, 31(6): 89-92 https://www.cnki.com.cn/Article/CJFDTOTAL-DZKK201806024.htm Feng Jin, Li Yuhui. Synthetic Recognition of Vehicle Color Based on Convolution Neural Network[J]. Electronic Science and Technology, 2018, 31(6): 89-92 https://www.cnki.com.cn/Article/CJFDTOTAL-DZKK201806024.htm
[22]	赵忠明, 高连如, 陈东, 等. 卫星遥感及图像处理平台发展[J]. 中国图象图形学报, 2019, 24(12): 2 098-2 110 https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201912003.htm Zhao Zhongming, Gao Lianru, Chen Dong, et al. Satellite Remote Sensing and Image Processing Platform Development[J]. Journal of Image and Graphics, 2019, 24(12): 2 098-2 110 https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201912003.htm
[23]	柳海鹰, 高吉喜, 李政海. 土地覆盖及土地利用遥感研究进展[J]. 国土资源遥感, 2001, 13(4) : 7-12 doi: 10.3969/j.issn.1001-070X.2001.04.002 Liu Haiying, Gao Jixi, Li Zhenghai. The Advances in the Application of Remote Sensing Technology to the Study of Land Covering and Land Utilization[J]. Remote Sensing for Land & Resources, 2001, 13(4): 7-12 doi: 10.3969/j.issn.1001-070X.2001.04.002
[24]	季顺平, 田思琦, 张驰. 利用全空洞卷积神经元网络进行城市土地覆盖分类与变化检测[J]. 武汉大学学报·信息科学版, 2020, 45(2): 233-241 doi: 10.13203/j.whugis20180481 Ji Shunping, Tian Siqi, Zhang Chi. Urban Land Cover Classification and Change Detection Using Fully Atrous Convolutional Neural Network[J]. Geomatics and Information Science of Wuhan University, 2020, 45(2): 233-241 doi: 10.13203/j.whugis20180481
[25]	张策, 臧淑英, 金竺, 等. 基于支持向量机的扎龙湿地遥感分类研究[J]. 湿地科学, 2011, 9(3): 263-269 https://www.cnki.com.cn/Article/CJFDTOTAL-KXSD201103011.htm Zhang Ce, Zang Shuying, Jin Zhu, et al. Research on Zhalong Wetland Classification Based on Support Vector Machines[J]. Wetland Science, 2011, 9(3): 263-269 https://www.cnki.com.cn/Article/CJFDTOTAL-KXSD201103011.htm
[26]	王海军. AGA-BP模型在遥感影像分类中的应用研究[J]. 计算机测量与控制, 2017, 25(5): 212-214 https://www.cnki.com.cn/Article/CJFDTOTAL-JZCK201705058.htm Wang Haijun. The Application Research of AGA-BP Model in Remote Sensing Image Classification[J]. Computer Measurement and Control, 2017, 25(5): 212-214 https://www.cnki.com.cn/Article/CJFDTOTAL-JZCK201705058.htm

[1]	GUO Jiachun, LIU Yi, SHEN Wenbin, SHI Guigang. Concept Analysis of Map Projection and Its Applications Based on Manifold Mapping Principle[J]. Geomatics and Information Science of Wuhan University, 2024, 49(12): 2313-2322. DOI: 10.13203/j.whugis20230138
[2]	JIAO Chenchen, LI Songlin, LI Houpu, BIAN Shaofeng, ZHONG Yexun. Non‑iterative Algorithm for Calculating the Reference Latitude of Conformal Conic Projection[J]. Geomatics and Information Science of Wuhan University, 2023, 48(2): 301-307. DOI: 10.13203/j.whugis20200301
[3]	ZENG Xiaoniu, LI Xihai, LIU Jihao, NIU Chao, HOU Weijun. Simultaneous Interpolation and Denoising Method for Airborne Gravity Data Based on Improved Projection onto Convex Sets Theory[J]. Geomatics and Information Science of Wuhan University, 2020, 45(10): 1555-1562. DOI: 10.13203/j.whugis20180470
[4]	LIU Wenchao, WEN Chaojiang, BIAN Hongwei, ZHENG Xiaobing. An Improved Method of Polar Ellipsoid Transverse Mercator Projection Based on Double Projection[J]. Geomatics and Information Science of Wuhan University, 2019, 44(8): 1138-1143. DOI: 10.13203/j.whugis20180028
[5]	SUN Weiwei, JIANG Man, LI Weiyue. Band Selection Using Sparse Self-representation for Hyperspectral Imagery[J]. Geomatics and Information Science of Wuhan University, 2017, 42(4): 441-448. DOI: 10.13203/j.whugis20150052
[6]	LIAO Li, ZHOU Xueqin, LI Qingqing, CHEN Lu, ZHOU Jianzhong. A Dual Iterative Clustering Based Fuzzy Projection Pursuit Clustering Algorithm[J]. Geomatics and Information Science of Wuhan University, 2016, 41(7): 932-938. DOI: 10.13203/j.whugis20140152
[7]	ZHAO Hu, LI Lin, GONG Jianya. Universal Map Projection Selection[J]. Geomatics and Information Science of Wuhan University, 2010, 35(2): 244-247.
[8]	CHENMi, YIYaohua, LIDeren, QINQianqing. Application of Projection Pursuit Based on Dynamical Evolutionary Algorithm to Anomaly Target Detection in Hyperspectral Images[J]. Geomatics and Information Science of Wuhan University, 2006, 31(1): 55-58.
[9]	Chen Yongqi. Selection of Projection Technique and Reduction of Geodetic Observations for Huge Engineering Project SSC[J]. Geomatics and Information Science of Wuhan University, 1993, 18(2): 10-14.
[10]	Hu Yuju. The Possibility of Making Further Additions to the Map Projection Classifications——On the Poly-eylindrical Projection[J]. Geomatics and Information Science of Wuhan University, 1986, 11(3): 55-61.

Cited By

Cited by

Periodical cited type(5)

1.	李殷娜，李正强，郑杨，侯伟真，徐文斌，马??，樊程，葛邦宇，姚前，史正. 基于非负矩阵分解的中红外地表特性光谱重建方法. 光谱学与光谱分析. 2024(02): 563-570 .
2.	钟雷洋，周颖，高松，夏吉喆，李珍，李晓明，乐阳，李清泉. 突发公共卫生事件下的人口流动模式变化识别. 武汉大学学报(信息科学版). 2024(07): 1237-1249 .
3.	李玉，甄畅，石雪，朱磊. 基于波段影像统计信息量加权K-means聚类的高光谱影像分类. 控制与决策. 2021(05): 1119-1126 .
4.	赵玉英，任明武. 基于SNMF聚类与类间可分性因子的高光谱波段选择. 计算机与数字工程. 2021(09): 1884-1888 .
5.	曾梦，宁彬，蔡之华，谷琼. 使用深度对抗子空间聚类实现高光谱波段选择. 计算机应用. 2020(02): 381-385 .

Other cited types(2)

Get Citation

PDF

XML

Article views (1539) PDF downloads (165) Cited by(7)

Land Cover Classification of Remote Sensing Image of Hubei Province by Using PSP Net

Abstract

References

Related Articles

Cited by

Periodical cited type(5)

Other cited types(2)

Catalog

Related

Land Cover Classification of Remote Sensing Image of Hubei Province by Using PSP Net

Abstract

References

Related Articles

Cited by

Periodical cited type(5)

Other cited types(2)

Catalog

Related

Export File

Citation

Format

Content