基于多波段像元形状指数的点云和高光谱数据分类研究
A Multiple Bands Pixel Shape Index for Classification of LiDAR and Hyperspectral Data

作者: 李波 :武汉大学测绘遥感信息工程国家重点实验室,湖北 武汉;

关键词: 高光谱影像点云数据像元形状指数数据融合分类Hyperspectral Image LiDAR Data Pixel Shape Index Data Fusion Classification

摘要: 本文提出了一种利用高光谱影像和点云数据融合提取空间特征的方法。点云辅助高光谱数据分类通常是利用高光谱数据的光谱特征、空间特征和点云数据高程特征简单组合后进行分类。然而,这种方法没有充分利用多源数据的互补信息。本文提出一种融合多源数据进行空间特征提取的方法,并利用光谱角距离优化像元形状指数,使之适用于高维数据形状结构特征提取。该方法首先对光谱特征和点云特征进行融合,增强不同地物之间的差异性。然后,利用光谱角距离像元形状指数提取融合数据的空间特征。最后,将三种特征组合后输入SVM分类器。实验结果表明,相比传统的nDSM辅助高光谱数据分类,本文所提出的“先融合、后提取”的方法可以获得更好的分类效果和精度。

Abstract: In this paper, we proposed a spatial feature extraction method by fusing the hyperspectral image and LiDAR point cloud data. Conventional data fusion methods in classification are often the simple combination of spectral and spatial information of the images and the height information of the LiDAR data. However, these methods cannot make full use of the complementary information of multi-source data. We proposed to extract the spatial features by fusing multi-source data. In order to obtain the shape index of high-dimensional fused data, we improved the pixel shape index by applying the spectral angle distance measurement. The proposed method firstly fused the hyperspectral image and LiDAR data to enhance the heterogeneity between different classes. Then, the shape features are extracted with the SAD-based pixel shape index. Finally, the spectral, spatial and height information are prepared to the SVM classifier. The experiment shows that the proposed method achieves better results and accuracy, compared to the conventional means.

文章引用: 李波 (2016) 基于多波段像元形状指数的点云和高光谱数据分类研究。 测绘科学技术, 4, 117-127. doi: 10.12677/GST.2016.44014

参考文献

[1] 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.

[2] Zhang, L., Huang, X., Huang, B. and Li, P. (2006) A Pixel Shape Index Coupled with Spectral Information for Classification of High Spatial Resolution Remotely Sensed Imagery. IEEE Transactions on Geoscience and Remote Sensing, 44, 2950-2961.
http://dx.doi.org/10.1109/TGRS.2006.876704

[3] Man Q., Dong, P. and Guo, H. (2015) Pixel- and Feature-Level Fusion of Hyperspectral and LiDAR Data for Urban Land-Use Classification. International Journal of Remote Sensing, 36, 1618-1644.
http://dx.doi.org/10.1080/01431161.2015.1015657

[4] 董保根. 机载LiDAR点云与遥感影像融合的地物分类技术研究[D]: [博士学位论文]. 郑州: 解放军信息工程大学, 2013.

[5] Gamba, P. (2013) Image and Data Fusion in Remote Sensing of Urban Areas: Status Issues and Research Trends. International Journal of Image and Data Fusion, 5, 2-12.
http://dx.doi.org/10.1080/19479832.2013.848477

[6] 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): 73-83.

[7] Gu, Y.F., Wang, Q.W., Jia, X.P. and Benediktsson, J.A. (2015) A Novel MKL Model of Integrating LiDAR Data and MSI for Urban Area Classification. IEEE Transactions on Geoscience and Remote Sensing, 53, 5312-5326.
http://dx.doi.org/10.1109/TGRS.2015.2421051

[8] Yan, W.Y., Shaker, A. and El-Ashmawy, N. (2015) Urban Land Cover Classification Using Airborne LiDAR Data: A Review. Remote Sensing of Environment, 158, 295-310.
http://dx.doi.org/10.1016/j.rse.2014.11.001

[9] Jung, J., Pasolli, E., PraSAD, S., Tilton, J.C. and Crawford, M.M. (2014) A Framework for Land Cover Classification Using Discrete Return LiDAR Data: Adopting Pseudo-Waveform and Hierarchical Seg-mentation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7, 491-502.
http://dx.doi.org/10.1109/JSTARS.2013.2292032

[10] 黄昕, 张良培, 李平湘. 融合形状和光谱的高空间分辨率遥感影像分类[J]. 遥感学报, 2007, 11(2): 193-200.

[11] 2013 IEEE GRSS Data Fusion Contest [EB/OL]. http://www.grss-ieee.org/community/technical-committees/data-fusion/2013-ieee-grss-data-fusion-contest/

分享
Top