Please wait a minute...
Remote Sensing for Land & Resources    2018, Vol. 30 Issue (2) : 80-86     DOI: 10.6046/gtzyyg.2018.02.11
Multi-manifold LE algorithm for dimension reduction and classification of multitemporal hyperspectral image
Dongyang WU(), Li MA()
School of Mechanical Engineering and Electronic Information,China University of Geosciences(Wuhan), Wuhan 430074, China
Download: PDF(3210 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    

The traditional manifold learning algorithms are based on the assumption that categories of data are located in the same manifold structure; nevertheless, due to the different features of different data categories, it is more reasonable that the data are in respective different manifold structures. Hence, the assumption of multi-manifold is more applicable for data classification. This paper adopts the thought of multi-manifold spectral clustering algorithm, mainly focuses on multiple manifolds LE algorithm, and applies this algorithm to the processing of hyperspectral data. Combined with the features of the hyperspectral data, the multiple manifolds LE algorithm is further improved by adding the spatial information and data maker information. The experimental results show that, in many kinds of hyperspectral data, the multi-manifold LE algorithm has higher precision than the LE algorithm. In addition, the improved multi-manifold LE algorithm could classify data with higher precision than the LE algorithm and multi-manifold LE algorithm. The authors have reached the conclusion that the assumption of multi-manifold is in better agreement with the features of hyperspectral data and the improved algorithm is of high performance.

Keywords manifold learning      multi-manifold hypothesis      hyperspectral data      classification     
:  TP79  
Corresponding Authors: Li MA     E-mail:;
Issue Date: 30 May 2018
E-mail this article
E-mail Alert
Articles by authors
Dongyang WU
Cite this article:   
Dongyang WU,Li MA. Multi-manifold LE algorithm for dimension reduction and classification of multitemporal hyperspectral image[J]. Remote Sensing for Land & Resources, 2018, 30(2): 80-86.
URL:     OR
Fig.1  Comparion of spectral graph with spatial information added before and after
Fig.2  Assign classes to blocks
算法 训练数据比例
10% 30% 50%
LE 0.666 0.742 0.766
MLE 0.706 0.783 0.800
MLE_Spatial 0.875 0.915 0.929
MLE_Spatial_Label 0.920 0.954 0.970
Tab.1  Optimal accuracy of different algorithms on BOT data
算法 训练数据比例
10% 30% 50%
LE 0.754 0.796 0.812
MLE 0.756 0.806 0.821
MLE_Spatial 0.834 0.880 0.893
MLE_Spatial_Label 0.865 0.913 0.918
Tab.2  Optimal accuracy of different algorithms on KSC data
算法 训练数据比例
10% 30% 50%
LE 0.646 0.667 0.670
MLE 0.670 0.720 0.731
MLE_Spatial 0.730 0.770 0.786
MLE_Spatial_Label 0.771 0.845 0.846
Tab.3  Optimal accuracy of different algorithms on PU data
Fig.3  Classification accuracy of four kinds of algorithms in different kinds of data
纯净点数 块数
40 80 120 160 200 240
未添加空间信息时 275 418 558 689 758 853
添加空间信息时 654 1 047 1 254 1 392 1 480 1 502
纯净点数 块数
20 60 100 140 180 220
未添加空间信息时 484 565 655 814 879 949
添加空间信息时 564 952 1 105 1 231 1 284 1 357
纯净点数 块数
100 150 200 250 300
未添加空间信息时 313 434 554 683 793
添加空间信息时 812 1 078 1 294 1 460 1 564
Fig.4  Accuracy under different blocks
Fig.5  Distribution of same kind of data in two bands before and after spatial information added
Fig.6  Accuracy of classification with different values of the neighborhood
[1] Tenenbaum J B, De Silva V, Langford J C . A global geometric framework for nonlinear dimensionality reduction[J]. Science, 2000,290(5500):2319-2923.
doi: 10.1126/science.290.5500.2319 url:
[2] Belkin M, Niyogi P . Laplacian eigenmaps for dimensionality reduction and data representation[J]. Neural Computation, 2003,15(6):1373-1396.
doi: 10.1162/089976603321780317 url:
[3] Roweis S T, Saul L K . Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000,290(5500):2323-2326.
doi: 10.1126/science.290.5500.2323 url:
[4] Zhang Z Y, Zha H Y . Principal manifolds and nonlinear dimensionality reduction via tangent space alignment[J]. Journal of Shanghai University (English Edition), 2004,8(4):406-424.
doi: 10.1137/S1064827502419154 url:
[5] Yan S C, Xu D, Zhang B Y , et al. Graph embedding and extensions:A general framework for dimensionality reduction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007,29(1):40-51.
doi: 10.1109/TPAMI.2007.250598 url:
[6] Xiao R, Zhao Q J, Zhang D , et al. Facial expression recognition on multiple manifolds[J]. Pattern Recognition, 2011,44(1):107-116.
doi: 10.1016/j.patcog.2010.07.017 url:
[7] He X F, Niyogi P. Locality preserving projections [C]//Advances in Neural Information Processing Systems. 2003: 186-197.
[8] Huang H B, Huo H, Fang T . Hierarchical manifold learning with applications to supervised classification for high-resolution remotely sensed images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014,52(3):1677-1692.
doi: 10.1109/TGRS.2013.2253559 url:
[9] 高琰, 谷士文, 唐琎 , 等. 机器学习中谱聚类方法的研究[J]. 计算机科学, 2007,34(2):201-203.
doi: 10.3969/j.issn.1002-137X.2007.02.051 url:
[9] Gao Y, Gu S W, Tang J , et al. Research on spectral clustering in machine learning[J]. Computer Science, 2007,34(2):201-203.
[10] Wang Y, Jiang Y, Wu Y , et al. Spectral clustering on multiple manifolds[J]. IEEE Transactions on Neural Networks, 2011,22(7):1149-1161.
doi: 10.1109/TNN.2011.2147798 pmid: 21690009 url:
[11] 戴竹红, 塔西甫拉提·特依拜.遥感影像中同谱异类问题的研究[J].中国科技信息, 2006(20):278-280.
[11] Dai Z H, Tashpolat ·Tiyip . Research on same spectrum with different objects in remote sensing image[J].China Science and Technology Information, 2006(20):278-280.
[1] SHI Feifei, GAO Xiaohong, XIAO Jianshe, LI Hongda, LI Runxiang, ZHANG Hao. Classification of wolfberry planting areas based on ensemble learning and multi-temporal remote sensing images[J]. Remote Sensing for Natural Resources, 2022, 34(1): 115-126.
[2] WU Linlin, LI Xiaoyan, MAO Dehua, WANG Zongming. Urban land use classification based on remote sensing and multi-source geographic data[J]. Remote Sensing for Natural Resources, 2022, 34(1): 127-134.
[3] LI Yuan, WU Lin, QI Wenwen, GUO Zhengwei, LI Ning. A SAR image classification method based on an improved OGMRF-RC model[J]. Remote Sensing for Natural Resources, 2021, 33(4): 98-104.
[4] FAN Yinglin, LOU Debo, ZHANG Changqing, WEI Yingjuan, JIA Fudong. Information extraction technologies of iron mine tailings based on object-oriented classification: A case study of Beijing-2 remote sensing images of the Qianxi Area, Hebei Province[J]. Remote Sensing for Natural Resources, 2021, 33(4): 153-161.
[5] BAI Junlong, WANG Zhangqiong, YAN Haitao. A K-means clustering-guided threshold-based approach to classifying UAV remote sensed images[J]. Remote Sensing for Natural Resources, 2021, 33(3): 114-120.
[6] WANG Rong, ZHAO Hongli, JIANG Yunzhong, HE Yi, DUAN Hao. Application and analyses of texture features based on GF-1 WFV images in monthly information extraction of crops[J]. Remote Sensing for Natural Resources, 2021, 33(3): 72-79.
[7] JIANG Xiao, ZHONG Chang, LIAN Zheng, WU Liangting, SHAO Zhitao. Research progress on classification criterion of geological information products based on satellite remote sensing[J]. Remote Sensing for Natural Resources, 2021, 33(3): 279-283.
[8] LING Xiao, LIU Jiamei, WANG Tao, ZHU Yueqin, YUAN Lingling, CHEN Yangyang. Application of information value model based on symmetrical factors classification method in landslide hazard assessment[J]. Remote Sensing for Land & Resources, 2021, 33(2): 172-181.
[9] HAN Yanling, CUI Pengxia, YANG Shuhu, LIU Yekun, WANG Jing, ZHANG Yun. Classification of hyperspectral image based on feature fusion of residual network[J]. Remote Sensing for Land & Resources, 2021, 33(2): 11-19.
[10] MENG Qing, BAI Hongying, ZHAO Ting, GUO Shaozhuang, QI Guizeng. The eco-barrier effect of Qinling Mountain on aerosols[J]. Remote Sensing for Land & Resources, 2021, 33(1): 240-248.
[11] XU Yun, XU Aiwen. Classification and detection of cloud, snow and fog in remote sensing images based on random forest[J]. Remote Sensing for Land & Resources, 2021, 33(1): 96-101.
[12] ZHANG Li, XIE Yanan, QU Chenyang, WANG Mingquan, CHANG Zheng, WANG Maohua. Estimation of electric power consumption using nighttime light remote sensing data based on K-Means city classification algorithm[J]. Remote Sensing for Land & Resources, 2020, 32(4): 182-189.
[13] WANG Dejun, JIANG Qigang, LI Yuanhua, GUAN Haitao, ZHAO Pengfei, XI Jing. Land use classification of farming areas based on time series Sentinel-2A/B data and random forest algorithm[J]. Remote Sensing for Land & Resources, 2020, 32(4): 236-243.
[14] WANG Yuefeng, WU Huizhi, HE Shujun, HUANG Di, BAI Chaojun. Method research of intelligentized extraction of natural resources information from Shihe District,Xinyang City,Henan Province[J]. Remote Sensing for Land & Resources, 2020, 32(4): 244-250.
[15] SUN Ke. Remote sensing image classification based on super pixel and peak density[J]. Remote Sensing for Land & Resources, 2020, 32(4): 41-45.
Full text



Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech