Please wait a minute...
 
Remote Sensing for Land & Resources    2018, Vol. 30 Issue (4) : 33-40     DOI: 10.6046/gtzyyg.2018.04.06
|
Fusion of hyperspectral and LiDAR data: A case study for refined crop classification in agricultural region of Zhangye Oasis in the middle reaches of Heihe River
Sirui YANG1, Zhaohui XUE1(), Ling ZHANG2, Hongjun SU1, Shaoguang ZHOU1
1. School of Earth Sciences and Engineering, Hohai University, Nanjing 211100, China
2. School of Naval Architecture and Ocean Engineering, Jiangsu Maritime Vocational Institute, Nanjing 211170, China
Download: PDF(7694 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

Hyperspectral remote sensing can simultaneously acquire spatial images of space and fine spectral information so as to describe the features more accurately. However, when the phenomena of different spectra in the same objects or the same spectra in different objects occur, the classification of hyperspectral images will face a daunting challenge. Light detection and ranging (LiDAR) can obtain the terrain topology information and can be used to construct the surface 3D model. However, features cannot be accurately identified by using LiDAR data only. Based on the above two points, the authors carried out a study to fuse hyperspectral images and LiDAR data. Morphological attribute profile was used to extract features, and sparse multinomial logistic regression (SMLR) was used to do classification. The fusion and classification effect in different combinations of characteristics were also investigated. The CASI/SASI aerial hyperspectral image and LiDAR DSM data were used to validate this method based on the Zhangye Oasis agricultural area in the middle reaches of the Heihe River which is a good target for the classification of crop. The results show that the method using hyperspectral and LiDAR data can obtain better classification results with higher accuracy and stability, and the best classification accuracy is 94.50% by fusion features based on the extended morphological attribute profile.
Keywords hyperspectral images      LiDAR      extented morphological attribute profile      SMLR     
:  TP79  
Corresponding Authors: Zhaohui XUE     E-mail: xue@hhu.edu.cn
Issue Date: 07 December 2018
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Sirui YANG
Zhaohui XUE
Ling ZHANG
Hongjun SU
Shaoguang ZHOU
Cite this article:   
Sirui YANG,Zhaohui XUE,Ling ZHANG, et al. Fusion of hyperspectral and LiDAR data: A case study for refined crop classification in agricultural region of Zhangye Oasis in the middle reaches of Heihe River[J]. Remote Sensing for Land & Resources, 2018, 30(4): 33-40.
URL:  
https://www.gtzyyg.com/EN/10.6046/gtzyyg.2018.04.06     OR     https://www.gtzyyg.com/EN/Y2018/V30/I4/33
Fig.1  Geographical location of the study area [20]
Fig.2  Hyperspectral remote sensing image and ground reference data[20]
Fig.3  Survey data of vegetation types in the same period of the study area [21]
Fig. 4  LiDAR data of the study area
Fig.5  Flowchart of the proposed method
Fig.6  Classification results of a single feature based on EMAP and EAP
序号 类别 linear RBF-MRF
Xh EMAP(Xh) EAP(XL) Xh EMAP(Xh) EAP(XL)
1 玉米 87.20 87.28 54.16 94.59 86.40 70.53
2 韭菜 88.92 92.13 65.51 96.54 98.10 87.96
3 菜花 84.78 93.10 79.33 85.29 94.47 91.35
4 菜椒 87.02 84.75 79.48 95.02 97.14 74.17
5 土豆 94.09 84.53 53.07 97.70 88.08 42.57
6 冬笋 96.93 95.86 90.75 98.47 98.98 83.14
7 西瓜 81.92 87.55 72.83 95.45 80.50 66.68
8 建设用地 77.47 75.42 31.26 97.87 97.53 53.85
OA 84.41 83.96 53.09 95.08 91.70 66.70
AA 87.29 87.58 65.80 95.12 92.65 71.28
Kappa 78.82 78.24 41.45 93.10 88.59 56.37
Tab.1  Classification accuracy and Kappa coefficient for different single features (EMAP,EAP) based on SMLR in two forms(%)
Fig.7  Classification results of multi features combination based on EMAP and EAP
序号 类别 linear RBF-MRF
Xh+
EMAP(Xh)		 Xh+
EAP(XL)		 EAP(XL)+
EMAP(Xh)		 Xh+EAP(XL)+
EMAP(Xh)		 Xh+
EMAP(Xh)		 Xh+
EAP(XL)		 EAP(XL)+
EMAP(Xh)		 Xh+EAP(XL)+
EMAP(Xh)
1 玉米 91.71 89.31 87.97 90.91 91.79 90.31 90.99 91.27
2 韭菜 95.21 92.26 91.37 94.69 96.54 91.64 86.96 92.42
3 菜花 90.00 87.39 94.99 94.85 94.86 91.59 95.45 93.82
4 菜椒 93.36 89.64 89.32 93.20 96.17 92.59 96.64 94.76
5 土豆 95.43 95.21 87.09 93.94 96.89 94.92 95.38 97.56
6 冬笋 98.31 98.49 95.25 98.29 97.83 98.98 98.98 99.11
7 西瓜 86.05 93.51 94.64 92.22 97.08 92.18 95.40 97.38
8 建设用地 86.49 82.81 78.16 83.40 97.19 98.31 96.31 98.68
OA 90.36 87.72 85.98 89.53 94.53 93.33 93.85 94.50
AA 92.07 91.08 89.85 92.69 96.04 93.81 94.51 95.62
Kappa 86.65 83.17 80.80 85.58 92.39 90.72 91.45 92.35
Tab.2  Classification accuracy and Kappa coefficient for multi features combination (EMAP,EAP) based on SMLR in two forms(%)
Fig.8  Relationship between the two types of feature combination’s classification results and the number of training samples based on SMLR
[1] 童庆禧, 张兵, 郑兰芬 . 高光谱遥感——原理、技术与应用[M]. 北京: 高等教育出版社, 2006.
[1] Tong Q X, Zhang B, Zheng L F. Hyperspectral Remote Sensing[M]. Beijing: Higher Education Press, 2006.
[2] 陈进 . 高光谱图像分类方法研究[D]. 长沙:国防科学技术大学, 2010.
[2] Chen J . On Classification Method of Hyperspectral Images[D]. Changsha: National University of Defense Technology, 2010.
[3] 刘丽娟 . 基于机载LiDAR和高光谱融合的森林参数反演研究[D]. 哈尔滨:东北林业大学, 2011.
[3] Liu L J . Fused Airborne LiDAR and Hyperspectral Data for Tree Species Identification in a Natural Temperate Forest[D]. Harbin:Northeast Forestry University, 2011.
[4] 张小红 . 机载激光雷达测量技术理论与方法[M]. 武汉: 武汉大学出版社, 2007.
[4] Zhang X H. Theory and Method of Airborne LiDAR Measurement Technology[M]. Wuhan: Wuhan University Press, 2007.
[5] Pedergnana M, Marpu P R, Mura M D , et al. Classification of remote sensing optical and LiDAR data using extended attribute profiles[J]. IEEE Journal of Selected Topics in Signal Processing, 2012,6(7):856-865.
doi: 10.1109/JSTSP.2012.2208177 url: http://ieeexplore.ieee.org/document/6237479/
[6] Ni L, Gao L R, Li S S , et al. Edge-constrained Markov random field classification by integrating hyperspectral image with LiDAR data overurban areas[J]. Journal of Applied Remote Sensing, 2014,8(1):205-207.
doi: 10.1117/1.JRS.8.085089 url: http://spie.org/Publications/Journal/10.1117/1.JRS.8.085089
[7] Zhang Y, Yang H L, Prasad S , et al. Ensemble multiple kernel active learning for classification of multisource remote sensing data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015,8(2):845-858.
doi: 10.1109/JSTARS.2014.2359136 url: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6960863
[8] Gu Y F, Wang Q W, Jia X P , et al. A novel MKL model of integrating LiDAR data and MSI for urban area classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015,53(10):5312-5326.
doi: 10.1109/TGRS.2015.2421051 url: http://ieeexplore.ieee.org/document/7103300/
[9] Liao W Z, Pizurica A, Bellens R , et al. Generalized graph-based fusion of hyperspectral and LiDAR data using morphological features[J]. IEEE Geoscienceand Remote Sensing Letters, 2015,12(3):552-556.
doi: 10.1109/LGRS.2014.2350263 url: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6891148
[10] Bigdeli B, Samadzadegan F, Reinartz P . Feature grouping-based multiple fuzzy classifier system for fusion of hyperspectral and LiDAR data[J].Journal of Applied Remote Sensing, 2014, 8(1):083509-1-15.
doi: 10.1117/1.JRS.8.083509 url: http://spie.org/Publications/Journal/10.1117/1.JRS.8.083509
[11] Bigdeli B, Samadzadegan F, Reinartz P . Fusion of hyperspectral and LiDAR data using decision template-based fuzzy multiple classifier system[J]. IEEE Journal of Applied Earth Observation and Geoinformation, 2015,38(1):309-320.
doi: 10.1016/j.jag.2015.01.017 url: https://linkinghub.elsevier.com/retrieve/pii/S0303243415000306
[12] Castrodad A, Khuon T, Rand R , et al. Sparse modeling for hyperspectral imagery with LiDAR data fusion for subpixel mapping[J]. IEEE International Geoscience and Remote Sensing Symposium, 2012,22(8):7275-7278.
doi: 10.1109/IGARSS.2012.6351982 url: http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=6351982
[13] Zhang Y, Prasad S . Multisource geospatial data fusion via local joint sparse representation[J]. IEEE Transactions on Geoscience Remote Sensing, 2016,54(6):3265-3276.
doi: 10.1109/TGRS.2016.2514481 url: http://ieeexplore.ieee.org/document/7387762/
[14] Yokoya N, Nakazawa S, Matsuki T , et al. Fusion of hyperspectral and LiDAR data for landscape visual quality assessment[J]. IEEE Journal of Selected Topics in Signal Applied Earth Observations and Remote Sensing, 2014,7(6):2419-2425.
doi: 10.1109/JSTARS.2014.2313356 url: http://ieeexplore.ieee.org/document/6783690/
[15] 满其霞 . 激光雷达和高光谱数据融合的城市土地利用分类方法研究[D]. 上海:华东师范大学, 2015.
[15] Man Q X . Fusion of Hyperspectral and LiDAR Data for Urban Land Use Classification[D]. Shanghai:East China Normal University, 2015.
[16] 董彦芳, 庞勇, 许丽娜 , 等. 高光谱遥感影像与机载LiDAR数据融合的地物提取方法研究[J]. 遥感信息, 2014,29(6):73-76,83.
doi: 10.3969/j.issn.1000-3177.2014.06.015 url: http://d.wanfangdata.com.cn/Periodical_ygxx201406015.aspx
[16] Dong Y F, Pang Y, Xu L N , et al. Feature extraction based on fusion of hyperspectral image and airborne LiDAR data[J]. Remote Sensing Information, 2014,29(6):73-76,83.
[17] 李光辉, 王成, 习晓环 , 等. 机载LiDAR和高光谱数据融合提取冰川雪线[J]. 国土资源遥感, 2013,25(3):79-84.doi: 10.6046/gtzyyg.2013.03.14.
[17] Li G H, Wang C, Xi X H , et al. Extraction of glacier snowline based on airborne LiDAR and hyperspectral data fusion[J]. Remote Sensing for Land and Resources, 2013,25(3):79-84.doi: 10.6046/gtzyyg.2013.03.14.
[18] 李新, 刘绍民, 马明国 , 等. 黑河流域生态—水文过程综合遥感观测联合试验总体设计[J]. 地球科学进展, 2012,27(5):481-498.
doi: 10.11867/j.issn.1001-8166.2012.05.0481 url: http://d.wanfangdata.com.cn/Periodical_dqkxjz201205001.aspx
[18] Li X, Liu S M, Ma M G , et al. HiWATER:An integrated remote sensing experiment on hydrological and ecological processes in the Heihe River Basin[J]. Advances in Earth Science, 2012,27(5):481-498.
[19] 角媛梅, 马明国, 肖笃宁 . 黑河流域中游张掖绿洲景观格局研究[J]. 冰川冻土, 2003,25(1):94-99.
doi: 10.3969/j.issn.1000-0240.2003.01.015 url: http://www.cqvip.com/qk/93756X/200301/7475037.html
[19] Jiao Y M, Ma M G, Xiao D N . Research on the landscape pattern of Zhangye Oasis in the middle reaches of Heihe River[J]. Journal of Glaciology and Geocryology, 2003,25(1):94-99.
[20] 薛朝辉 . 高光谱遥感影像稀疏图嵌入分类研究[D]. 南京:南京大学, 2015.
[20] Xue Z H . Hyperspectral Remote Sensing Image Classification via Sparse Graph Embedding[D]. Nanjing:Nanjing University, 2015.
[21] 张苗, 蒋志荣, 马明国 , 等. 基于CASI影像的黑河中游种植结构精细分类研究[J]. 遥感技术与应用, 2013,28(2):283-289.
[21] Zhang M, Jiang Z R, Ma M G , et al. Fine classification of planting structure in the middle reaches of Heihe River Basin based on hyperspectral compace airborne spectrographic imager(CASI) data[J]. Remote Sensing Technology and Application, 2013,28(2):283-289.
[22] 杜培军, 夏俊士, 薛朝辉 , 等. 高光谱遥感影像分类研究进展[J]. 遥感学报, 2016: 20(2):236-256.
doi: 10.11834/jrs.20165022 url: http://d.wanfangdata.com.cn/Periodical/ygxb201602008
[22] Du P J, Xia J S, Xue Z H , et al. Review of hyperspectral remote sensing image classification[J]. Journal of Remote Sensing, 2016,20(2):236-256.
[23] 杨雨薇, 戴晓爱, 牛育天 , 等. 基于CASI数据的黑河绿洲区叶面积指数反演[J]. 国土资源遥感, 2017,29(4):179-184.doi: 10.6046/gtzyyg.2017.04.27.
[23] Yang Y W, Dai X A, Niu Y T , et al. Inversion of leaf area index in Heihe Oasis based on CASI data[J]. Remote Sensing for Land and Resources, 2017,29(4):179-184.doi: 10.6046/gtzyyg.2017.04.27.
[1] WU Fang, LI Yu, JIN Dingjian, LI Tianqi, GUO Hua, ZHANG Qijie. Application of 3D information extraction technology of ground obstacles in the flight trajectory planning of UAV airborne geophysical exploration[J]. Remote Sensing for Natural Resources, 2022, 34(1): 286-292.
[2] GAO Wenlong, ZHANG Shengwei, LIN Xi, LUO Meng, REN Zhaoyi. The remote sensing-based estimation and spatial-temporal dynamic analysis of SOM in coal mining[J]. Remote Sensing for Natural Resources, 2021, 33(4): 235-242.
[3] Lei MENG, Chao LIN. Discussion on quality inspection and solution of DEM generated by airborne LiDAR technology[J]. Remote Sensing for Land & Resources, 2020, 32(1): 7-12.
[4] Zhenyu MA, Bowei CHEN, Yong PANG, Shengxi LIAO, Xianlin QIN, Huaiqing ZHANG. Forest fire potential forecast based on FCCS model[J]. Remote Sensing for Land & Resources, 2020, 32(1): 43-50.
[5] Qi LI, Jianchao WANG, Yachao HAN, Zihong GAO, Yongjun ZHANG, Dingjian JIN. Potential evaluation of China’s coastal airborne LiDAR bathymetry based on CZMIL Nova[J]. Remote Sensing for Land & Resources, 2020, 32(1): 184-190.
[6] Chong LI, Haolin LI, Yi SHE. Quality inspection of geographic information products based on multi-source remote sensing data[J]. Remote Sensing for Land & Resources, 2019, 31(4): 258-263.
[7] Juntao ZHU, Lei WANG, Chuan ZHAO, Xudong ZHENG. Point cloud segmentation on the roof of complicated building based on the algorithm of region growing[J]. Remote Sensing for Land & Resources, 2019, 31(4): 20-25.
[8] Ruhan A, Fang HE, Biaobiao WANG. Hyperspectral images classification via weighted spatial-spectral dimensionality reduction principle component analysis[J]. Remote Sensing for Land & Resources, 2019, 31(2): 17-23.
[9] Lei DU, Jie CHEN, Minmin LI, Xiongwei ZHENG, Jing LI, Zihong GAO. The application of airborne LiDAR technology to landslide survey: A case study of Zhangjiawan Village landslides in Three Gorges Reservoir area[J]. Remote Sensing for Land & Resources, 2019, 31(1): 180-186.
[10] Bing TU, Xiaofei ZHANG, Guoyun ZHANG, Jinping WANG, Yao ZHOU. Hyperspectral image classification via recursive filtering and KNN[J]. Remote Sensing for Land & Resources, 2019, 31(1): 22-32.
[11] Li YAN, Yao LI, Hong XIE. Automatic reconstruction of LoD3 city building model based on airborne and vehicle-mounted LiDAR data[J]. Remote Sensing for Land & Resources, 2018, 30(4): 97-101.
[12] Jiasi YI, Xiangyun HU. Extracting impervious surfaces from multi-source remote sensing data based on Grabcut[J]. Remote Sensing for Land & Resources, 2018, 30(3): 174-180.
[13] LI Yunfan, TAN Debao, LIU Rui, WU Jianwei. An improved RANSAC algorithm for building point clouds segmentation in consideration of roof structure[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(4): 20-25.
[14] DONG Anguo, GONG Wenjuan, HAN Xue. Band selection method for hyperspectral image based on linear representation[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(4): 39-42.
[15] LI Jiajun, ZHONG Ruofei. Route design of light airborne LiDAR[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(2): 97-103.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech