激光与光电子学进展, 2016, 53 (8): 082802, 网络出版: 2016-08-11   

一种机载LiDAR点云分类的自适应特征选择方法 下载: 531次

A Method of Adaptive Feature Selection for Airborne LiDAR Point Cloud Classification
作者单位
首都师范大学三维信息获取与应用教育部重点实验室, 北京 100048
摘要
不同地形条件下,不同的特征组合、特征维数对点云的分类效率及分类结果有不同的影响。提出了一种机载LiDAR点云分类的自适应特征选择方法,该方法依据地形起伏情况对整体点云数据进行区域划分,自适应选择适宜该区域LiDAR点云分类的特征集合。为了验证这种特征选择方法的有效性,利用优选后的特征集合,分别采用随机森林和支持向量机算法进行分类实验验证,实验结果表明,在不同地形条件的区域里,适合LiDAR点云分类的特征集合不同。该方法可以有效地降低特征维数,缩短运算时间,且分类精度较高。
Abstract
In different terrain conditions, different feature combinations and dimensions have different influences on the effectiveness and accuracy of classification. A method is proposed to select the airborne LiDAR point cloud classification with adaptively feature selection. The whole point cloud is divided into different regions in accordance with the terrain conditions, and the suitable feature set is selected adaptively for classification. In order to evaluate the effective of this method, the random forest method and support vector machine classification method are used to classify the experimental data with the feature set after optimization. Experimental result shows that the suitable feature set for classification in different areas are different. The proposed method can reduce the feature dimensions effectively, shorten time consumption, and achieve high classification accuracy.
参考文献

[1] 左志权, 张祖勋, 张剑清. 区域回波比率与拓扑识别模型结合的城区激光雷达点云分类方法[J]. 中国激光, 2012, 39(4): 0414001.

    Zuo Zhiquan, Zhang Zuxun, Zhang Jianqing. Classification of LiDAR point clouds for urban area based on multi-echo region ratio and recognition topology model[J]. Chinese J Lasers, 2012, 39(4): 0414001.

[2] 张志伟, 刘志刚. 利用既有知识渐近数学形态学提取LiDAR数据中道路信息方法研究[J]. 测绘科学, 2010, 35(4): 154-156.

    Zhang Zhiwei, Liu Zhigang. Method extraction road information in LIDAR data based on the existing knowledge of asymptotic mathematical morphology[J]. Science of Surveying and Mapping, 2010, 35(4): 154-156.

[3] 卢维欣, 万幼川, 何培培, 等. 大场景内建筑物点云提取及平面分割算法[J]. 中国激光, 2015, 42(9): 0914004.

    Lu Weixin, Wan Youchun, He Peipei, et al. Extracting and plane segmenting building from large scene point cloud[J]. Chinese J Lasers, 2015, 42(9): 0914004.

[4] 苗启广, 郭雪, 宋建锋, 等. 基于区域预测的LiDAR点云数据形态学滤波算法[J]. 激光与光电子学进展, 2015, 52(1): 011003.

    Miao Qiguang, Guo Xue, Song Jianfeng, et al. LiDAR point cloud dta with morphological filter algorithm based on region prediction[J]. Laser & Optoelectronics Progress, 2015, 52(1): 011003.

[5] Strmbu V F, Strmbu B M. A graph-based segmentation algorithm for tree crown extraction using airborne LiDAR data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 104: 30-43.

[6] 龚亮, 李正国, 包全福. 融合航空影像的LiDAR地物点云分类[J]. 测绘工程, 2012, 21(1): 34-38.

    Gong Liang, Li Zhengguo, Bao Quanfu. Classifition of LiDAR object points by fusing aerial image[J]. Engineering of Surveying and Mapping, 2012, 21(1): 34-38.

[7] Gong L, Zhang Y, Li Z, et al. Automated road extraction from LiDAR data based on intensity and aerial photo[C]. 2010 3rd International Congress on Image and Signal Processing (CISP), 2010: 2130-2133.

[8] 刘丽娟, 庞勇, 范文义, 等. 机载LiDAR和高光谱融合实现温带天然林树种识别[J]. 遥感学报, 2013, 17(3): 679-695.

    Liu Lijuan, Pang Yong, Fan Wenyi, et al. Fused airborne LiDAR and hyperspectral data for tree species identification in a natural temperate forest[J]. Journal of Remote Sensing, 2013, 17(3): 679-695.

[9] Mallet C, Bretar F, Roux M, et al. Relevance assessment of full-waveform lidar data for urban area classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(6): S71-S84.

[10] Kononenko I. Estimating attributes: Analysis and extensions of RELIEF[J]. Machine Learning, 2005, 784: 171-182.

[11] Chen Y W, Lin C J. Combining SVMs with various feature selection strategies[M]. Berlin: Springer, 2006: 315-324.

[12] Guo L, Chehata N, Mallet C, et al. Relevance of airborne lidar and multispectral image data for urban scene classification using random forests[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(1): 56-66.

[13] 孙杰, 赖祖龙. 利用随机森林的城区机载LiDAR数据特征选择与分类[J]. 武汉大学学报·信息科学版, 2014, 11(39): 1310-1313.

    Sun Jie, Lai Zulong. Airborne LiDAR feature selectiong for urban classification using random forests[J]. Geomatics and Information Science of Wuhan University, 2014, 39(11): 1310-1313.

[14] 郭波, 黄先锋, 张帆, 等. 顾及空间上下文关系的Joint Boost点云分类及特征降维[J]. 测绘学报, 2014, 42(5): 715-821.

    Guo Bo, Huang Xianfeng, Zhang Fan, et al. Points cloud classification using jointboost combined with contextual information for feature reduction[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(5): 715-721.

[15] Torralba A, Murphy K P, Freeman W T. Sharing visual features for multiclass and multiview object detection[J]. Pattern Analysis and Machine Intelligence, 2007, 29(5): 854-869.

[16] 范士俊, 张爱武, 胡少兴, 等. 基于随机森林的机载激光全波形点云数据分类方法[J]. 中国激光, 2013, 40(9): 0914001.

    Fan Shijun, Zhang Aiwu, Hu Shaoxin, et al. A method of classification for airborne full waveform LiDAR data based on random forest[J]. Chinese J Lasers, 2013, 40(9): 0914001.

[17] 孟放. 大型三维点云数据的交互绘制研究[D]. 北京: 北京大学, 2005.

    Meng Fang. The study of interactive rendering for large scale three dimesional point cloud data[D]. Beijing: Beijing University, 2005.

[18] Carlberg M, Gao P, Chen G, et al. Classifying urban landscape in aerial LiDAR using 3D shape analysis[C]. Image Processing (ICIP), 2009: 1681-1684.

[19] Gross H, Thoennessen U. Extraction of lines from laser point clouds[C]. Symposium of ISPRS Commission III: Photogrammetric Computer Vision PCV06 International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2006: 86-91.

[20] 李含伦, 张爱武, 刘诏, 等. 基于LiDAR波形分解的点云SVM分类方法研究[J]. 测绘通报, 2014, 1: 28-32.

    Li Hanlun, Zhang Aiwu, Liu Zhao, et al. A LiDAR point classification method based on SVM and waveform decomposition[J]. Bulletin of Surveying and Mapping, 2014, 1: 28-32.

[21] Breiman L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.

[22] 姚登举, 杨静, 詹晓娟. 基于随机森林的特征选择算法[J]. 吉林大学学报(工学版), 2014, 44(1): 137-141.

    Yao Dengju, Yang Jing, Zhan Xiaojuan. Feature selection algorithm based on random forest[J]. Journal of Jilin Univerdity (Engineering and Technology Edition), 2014, 44(1): 137-141.

[23] Verikas A, Gelzinis A, Bacauskiene M. Mining data with random forests: A survey and results of new tests[J]. Pattern Recognition, 2011, 44(2): 330-349.

[24] Vapnik V N. Statistical learning theory[M]. New York: Wiley, 1998.

[25] Luts J, Ojeda F, van de Plas D, et al. A tutorial on support vector machine-based methods for classification problems in chemometrics[J]. Analytica Chimica Acta, 2010, 665(2): 129-145.

张爱武, 肖涛, 段乙好. 一种机载LiDAR点云分类的自适应特征选择方法[J]. 激光与光电子学进展, 2016, 53(8): 082802. Zhang Aiwu, Xiao Tao, Duan Yihao. A Method of Adaptive Feature Selection for Airborne LiDAR Point Cloud Classification[J]. Laser & Optoelectronics Progress, 2016, 53(8): 082802.

本文已被 8 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!