Airborne LiDAR point cloud data classification based on relevance vector machine

Liu Zhiqing; Li Pengcheng; Guo Haitao; Zhang Baoming; Chen Xiaowei; Ding Lei; Zhao Chuan

doi:10.3788/IRLA201645.S130006

Aiming at the limitations of support vector machine(SVM) applied in Airborne LiDAR(Light Detection And Ranging) point data classification, such as weak model sparseness, predictions lack of probabilistic sense, and kernel function which must satisfy Mercer's condition, a novel LiDAR point cloud data classification method was proposed based on relevance vector machine(RVM). Firstly, the sparse Bayesian classification model and the process of parameter inference and prediction were analyzed. Then, the classification problem was transformed into the regression problem by making use of Laplace's method. Next, the hyperparameter estimation was attained by utilizing maximum likelihood method and a sequential sparse Bayesian learning algorithm was selected to improve training speed. Finally, multiple classifiers were built to realize multi-class classification. The LiDAR point cloud datum from Niagara and Africa were selected for experiment based on SVM, and experimental results show the advantages of classification method based on RVM.

Airborne LiDAR point cloud data classification based on relevance vector machine

1. Institute of Geospatial Information,Information Engineering University,Zhengzhou 450052,China

Received Date: 2016-02-20

Rev Recd Date: 2016-03-03

Publish Date: 2016-05-25

Key words:

Abstract: Aiming at the limitations of support vector machine(SVM) applied in Airborne LiDAR(Light Detection And Ranging) point data classification, such as weak model sparseness, predictions lack of probabilistic sense, and kernel function which must satisfy Mercer's condition, a novel LiDAR point cloud data classification method was proposed based on relevance vector machine(RVM). Firstly, the sparse Bayesian classification model and the process of parameter inference and prediction were analyzed. Then, the classification problem was transformed into the regression problem by making use of Laplace's method. Next, the hyperparameter estimation was attained by utilizing maximum likelihood method and a sequential sparse Bayesian learning algorithm was selected to improve training speed. Finally, multiple classifiers were built to realize multi-class classification. The LiDAR point cloud datum from Niagara and Africa were selected for experiment based on SVM, and experimental results show the advantages of classification method based on RVM.

HTML

Reference (13)

[1]	Sun Meiling, Li Yongshu, Chen Qiang, et al. Iterative multi-scale filter based on morphological opening by reconstruction for LiDAR urban data[J]. Infrared and Laser Engineering, 2015, 44(1):363-369. (in Chinese) 孙美玲, 李永树, 陈强, 等. 基于迭代多尺度形态学开重建的城区LiDAR滤波方法[J]. 红外与激光工程, 2015, 44(1):363-369.
[2]	Vosselman G. Slope based filtering of laser altimetry data[J]. International Archives of Photogrammetry and Remote Sensing, 2000, 33(B3/2):935-942.
[3]	Rottensteiner F. A new method for building extraction in urban areas from high-resolution LiDAR data[J]. International Archives of Photogrammetry Remote Sensing and Spatial Information Sciences, 2002, 343(3/A):295-301.
[4]	Straub B M, Heipke C. Automatic extraction of trees for 3D-city models from images and height data[J]. Automatic Extraction of Man-Made Objects from Aerial and Space Images(III), 2001, 3:267-277.
[5]	Samadzadegan F, Bigdeli B, Ramzi R. A multiple classifier system for classification of LiDAR remote sensing data using multi-class SVM[C]//Multiple Classifier Systems:9th International Workshop, MCS 2010, 2010:254-264.
[6]	Lodha S K, Kreps E J, Helmbold D P, et al. Aerial LiDAR data classification using support vector machines(SVM)[C]//IEEE Proceedings of the Third International Symposium on 3D Data Processing, Visualization, and Transmission(3DPVT'06), 2006:567-574.
[7]	Bishop C M, Tipping M E. Variational Relevance Vector Machines[C]//Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence, 2000:46-53.
[8]	Silva C, Ribeiro B. Scaling text classification with relevance vector machines[C]//IEEE International Conference on Systems, Man and Cybernetics, 2006:4186-4191.
[9]	Nikolaev N, Tino P. Sequential relevance vector machine learning from time series[C]//IEEE International Joint Conference on Neural Networks, 2005:1308-1313.
[10]	Zhou Xin, Wu Ying. Research on signals modulation classification based on SVM and RVM[J]. Journal on Communications, 2010, 31(8A):94-99. (in Chinese) 周欣, 吴瑛. 基于SVM和RVM的信号调制分类研究[J]. 通信学报, 2010, 31(8A):94-99.
[11]	Yang Guopeng, Yu Xuchu, Zhou Xin, et al. Research on relevance vector machine for hyperspectral imagery classification[J]. Acta Geodaetica et Cartographica Sinica, 2010, 39(6):572-578. (in Chinese) 杨国鹏, 余旭初, 周欣, 等. 基于相关向量机的高光谱影像分类研究[J]. 测绘学报, 2010, 39(6):572-578.
[12]	MacKay D J C. The evidence framework applied to classification networks[J]. Neural Computation, 1992, 4(5):720-736.
[13]	Tipping M E. Sparse bayesian learning and the relevance vector machine[J]. Journal of Machine Learning Research,2001, 1:211-244.

Airborne LiDAR point cloud data classification based on relevance vector machine

doi: 10.3788/IRLA201645.S130006

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views