收稿：2017-12-07，
录用：2018-8-29，
纸质出版：2019-09
移动端阅览
城市地区地表覆盖分类在城市研究中是一个十分重要的方向。遥感作为获取地物物理属性的一种重要技术手段，已初步应用于分类研究中。然而，随着城镇化的不断推进，城市内部地物类型越来越复杂，单一的遥感影像已无法满足城区地表覆盖分类中高精度的要求。高光谱影像和LiDAR数据能够分别表征地物的光谱信息及高程而被广泛应用。因此，根据两者之间互补的优势，本文提出了基于高光谱影像和LiDAR数据多级融合的城区地表覆盖分类方法。首先对两幅影像分别进行特征提取，将提取到的光谱、空间及高程信息进行层叠实现特征级融合。对得到的特征影像的所有像素点进行分类，然后利用LiDAR点云数据提取的建筑物掩膜，对非建筑物部分进行分类，再次实现特征级融合，以此改善建筑物区域与非建筑物区域的混淆。然后将未使用掩膜得到的分类结果与利用掩膜得到的分类结果进行投票实现决策级融合。最后利用条件随机场模型对分类结果进行后处理操作，达到平滑图像去除噪声点的目的。
Land Use/Land Cover (LU/LC) classification of urban areas is of great significance to urban studies and has become a highly important research direction. However
with continuous urbanization and more types of inner cities diversified
single remote sensing image has been unable to meet the requirements of high precision. Therefore
urban LU/LC classification by data fusion has emerged. In this study
hyperspectral images are widely used in urban LU/LC classification because of their abundant spectral information. However
an objective limitation is that similar spectral characters with different elevation cannot be distinguished. LiDAR data can obtain accurate elevation information. Therefore
such data will obtain better classification maps when merged with hyperspectral images. This work proposes an urban LU/LC classification method based on the multi-level fusion of hyperspectral imagery and LiDAR data by using the complementary of their advantages. First
the spectral
spatial
and elevation information extracted from two images are stacked to achieve level fusion. Then
the classification is divided into two frameworks. One framework classifies all pixels of the feature images
while the other uses LiDAR data to extract the building mask and classify the off-building area. Classification maps of this framework are obtained by combining the classification map of the latter framework and the off-building area. The classification results are then obtained by voting the classification results obtained by the two frameworks to complete the decision-level fusion. Finally
the conditional random fields are processed to smoothen the image and remove noise. The data set of 2013 IEEE GRSS data fusion contest was experimented on to verify the effect of the proposed algorithm. The OA was 93.22%
and Kappa was 0.93. The accuracy of the proposed method exceeded 90% in most categories
while the classification accuracy of synthetic grassland
soil
tennis court
and running track was 100%. Experiment results showed that the proposed algorithm greatly improved the classification of buildings
roads
and parking lots. In this study
hyperspectral imagery and LiDAR data are applied to classify LU/LC in urban areas. It also combines feature level and decision level and achieves good results. The following problems will be considered in future works: increasing the accuracy of building extraction to improve the effect of feature-level fusion
considering the increasing intensity of LiDAR point cloud data in feature-level fusion
and increasing the number and diversity of classifiers when using the multiple classifier classification.
Akaike H. 1998. Information theory and an extension of the maximum likelihood principle//Parzen E, Tanabe K and Kitagawa G, eds. Selected Papers of Hirotugu Akaike. New York: Springer: 199-213 [DOI: 10.1007/978-1-4612-1694-0_15]
Benediktsson J A, Palmason J A and Sveinsson J R. 2005. Classification of hyperspectral data from urban areas based on extended morphological profiles. IEEE Transactions on Geoscience and Remote Sensing, 43(3): 480–491
Chen B, Huang B and Xu B. 2017a. Multi-source remotely sensed data fusion for improving land cover classification. ISPRS Journal of Photogrammetry and Remote Sensing, 124: 27–39
Chen B W, Shi S, Gong W, Zhang Q J, Yang J, Du L, Sun J, Zhang Z B and Song S L. 2017c. Multispectral LiDAR point cloud classification: a two-step approach. Remote Sensing, 9(4): 373
Chen Y, Nasrabadi N M and Tran T D. 2011. Hyperspectral image classification using dictionary-based sparse representation. IEEE Transactions on Geoscience and Remote Sensing, 49(10): 3973–3985
Chen Y S, Li C Y, Ghamisi P, Jia X P and Gu Y F. 2017b. Deep fusion of remote sensing data for accurate classification. IEEE Geoscience and Remote Sensing Letters, 14(8): 1253–1257
Cortes C and Vapnik V. 1995. Support-vector networks. Machine Learning, 20(3): 273–297
Fauvel M, Benediktsson J A, Chanussot J and Sveinsson J R. 2008. Spectral and spatial classification of hyperspectral data using svms and morphological profiles. IEEE Transactions on Geoscience and Remote Sensing, 46(11): 3804–3814
Galar M, Fernandez A, Barrenechea E, Bustince H and Herrera F. 2012. A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 42(4): 463–484
Ghamisi P, Benediktsson J A and Phinn S. 2014. Fusion of hyperspectral and LiDAR data in classification of urban areas//Proceedings of 2014 IEEE Geoscience and Remote Sensing Symposium. Quebec City, Canada: IEEE: 181-184 [DOI: 10.1109/IGARSS.2014.6946386]
Pedram G, Höfle B and Zhu X X. 2017. Hyperspectral and LiDAR data fusion using extinction profiles and deep convolutional neural network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(6): 3011–3024
Ghassemian H. 2016. A review of remote sensing image fusion methods. Information Fusion, 32: 75–89
Kim H C, Pang S N, Je H M, Kim D and Bang S Y. 2003. Constructing support vector machine ensemble. Pattern Recognition, 36(12): 2757–2767
Kittler J, Hatef M, Duin R P W and Matas J. 1998. On combining classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(3): 226–239
Lahat D, Adali T and Jutten C. 2015. Multimodal data fusion: an overview of methods, challenges, and prospects. Proceedings of the IEEE, 103(9): 1449–1477
Li J, Bioucas-Dias J M and Plaza A. 2011. Hyperspectral image segmentation using a new bayesian approach with active learning. IEEE Transactions on Geoscience and Remote Sensing, 49(10): 3947–3960
Liao W Z, Bellens R, Pižurica A, Gautama S and Philips W. 2017. Combining feature fusion and decision fusion for classification of hyperspectral and LiDAR data//Proceedings of 2014 IEEE Geoscience and Remote Sensing Symposium. Quebec City, Canada: IEEE: 1241-1244 [DOI: 10.1109/IGARSS.2014.6946657]
Liao W Z, Pižurica A, Bellens R, Gautama S and Philips W. 2015. Generalized graph-based fusion of hyperspectral and LiDAR data using morphological features. IEEE Geoscience and Remote Sensing Letters, 12(3): 552–556
满其霞. 2015. 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. 上海: 华东师范大学
Man Q X. 2015. Fusion of Hyperspectral and LiDAR Data for Urban Land Use Classification. Shanghai: East China Normal University.
Man Q X, Dong P L and Guo H D. 2015. Pixel- and feature-level fusion of hyperspectral and lidar data for urban land-use classification. International Journal of Remote Sensing, 36(6): 1618–1644
Merentitis A, Debes C, Heremans R and Frangiadakis N. 2014. Automatic fusion and classification of hyperspectral and LiDAR data using random forests//Proceedings of 2014 IEEE Geoscience and Remote Sensing Symposium. Quebec City, Canada: IEEE: 1245-1248 [DOI: 10.1109/IGARSS.2014.6946658]
Momeni R, Aplin P and Boyd D. 2016. Mapping complex urban land cover from spaceborne imagery: the influence of spatial resolution, spectral band set and classification approach. Remote Sensing, 8(2): 88
Rasti B, Ghamisi P and Gloaguen R. 2017a. Hyperspectral and LiDAR fusion using extinction profiles and total variation component analysis. IEEE Transactions on Geoscience and Remote Sensing, 55(7): 3997–4007
Rasti B, Ghamisi P, Plaza J and Plaza A. 2017b. Fusion of hyperspectral and LiDAR data using sparse and low-rank component analysis. IEEE Transactions on Geoscience and Remote Sensing, 55(11): 6354–6365
童庆禧, 张兵, 郑兰芬. 2006. 高光谱遥感. 北京: 高等教育出版社
Tong Q X, Zhang B and Zheng L F. 2006. Hyperspectral Remote Sensing. Beijing: Higher Education Press
Wu H and Prasad S. 2013. Infinite Gaussian mixture models for robust decision fusion of hyperspectral imagery and full waveform LiDAR data//Proceedings of 2013 IEEE Global Conference on Signal and Information Processing. Austin, USA: IEEE: 1025-1028 [DOI: 10.1109/GlobalSIP.2013.6737068]
Xu X D, Li W, Ran Q, Du Q, Gao L R and Zhang B. 2018. Multisource remote sensing data classification based on convolutional neural network. IEEE Transactions on Geoscience and Remote Sensing, 56(2): 937–949
Zhang J X, Lin X G and Ning X G. 2013. SVM-based classification of segmented airborne LiDAR point clouds in urban areas. Remote Sensing, 5(8): 3749–3775
张良培, 沈焕锋. 2016. 遥感数据融合的进展与前瞻. 遥感学报, 20(5): 1050–1061
Zhang L P and Shen H F. 2016. Progress and future of remote sensing data fusion. Journal of Remote Sensing, 20(5): 1050–1061
赵济. 2017. 面向高分辨率遥感影像分类的条件随机场模型研究. 武汉: 武汉大学
Zhao J. 2017. Conditional Random Fields for High Resolution Remote Sensing Image Classification. Wuhan: Wuhan University
Zhao J, Zhong Y F, Shu H and Zhang L P. 2016. High-resolution image classification integrating spectral-spatial-location cues by conditional random fields. IEEE Transactions on Image Processing, 25(9): 4033–4045
Zhao J, Zhong Y F and Zhang L P. 2015. Detail-preserving smoothing classifier based on conditional random fields for high spatial resolution remote sensing imagery. IEEE Transactions on Geoscience and Remote Sensing, 53(5): 2440–2452
Zhong Y F, Cao Q, Zhao J, Ma A L, Zhao B and Zhang L P. 2017a. Optimal decision fusion for urban land-use/land-cover classification based on adaptive differential evolution using hyperspectral and LiDAR data. Remote Sensing, 9(8): 868
Zhong Y F, Jia T Y, Zhao J, Wang X Y and Jin S Y. 2017b. Spatial-spectral-emissivity land-cover classification fusing visible and thermal infrared hyperspectral imagery. Remote Sensing, 9(9): 910
Zhong Y F, Ma A L, Ong Y S, Zhu Z X and Zhang L P. 2018. Computational intelligence in optical remote sensing image processing. Applied Soft Computing, 64: 75–93
相关作者
相关机构
京公网安备11010802024621
