激光与光电子学进展, 2016, 53 (3): 032801, 网络出版: 2016-03-04   

基于强度数据的地面激光点云自适应非监督分类 下载: 687次

Adaptive Unsupervised Classification of TLS Point Cloud Based on Intensity Data
作者单位
同济大学测绘与地理信息学院, 上海 200092
摘要
基于激光雷达测距方程与扫描仪的辐射机制,建立激光强度值的线性改正模型。考虑到各种噪声的影响及非线性效应,对参数进行修正,建立强度值的修正改正模型,去除激光测距值及激光入射角对强度值的影响,得到仅与目标反射特性相关的改正强度值。通过设置类别总数,初始阈值及阈值步长,利用改正后强度值,提出了一种点云自适应非监督分类的方法。实验结果表明:基于修正模型改正后强度值的点云自适应非监督分类方法可以精确地对点云进行分类,整体分类精度达到84%。
Abstract
Based on the laser radar range equation and the radiation mechanism of the laser scanner systems, the linear laser intensity correction model is established. Taking into account of the noise impacts and nonlinear effects, a modified correction model is established by revising the parameters, which aims to remove the effects of range and incidence angle to obtain a corrected intensity value associated merely with the target reflection characteristics. By setting the total number of categories, the initial threshold and the threshold step, an adaptive unsupervised classification method is proposed based on the corrected intensity. Experimental results show that the adaptive unsupervised classification method based on the corrected intensity data can accurately classify the point cloud, and the overall accuracy is 84%.
参考文献

[1] 吴永华, 胡以华, 顾有林, 等. 激光点云分类算法的探讨与展望[J]. 第九届全国光电技术学术交流会论文集, 2010.

    Wu Yonghua, Hu Yihua, Gu Youlin, et al.. Discussion and prospect of laser point cloud classification algorithms[J]. Ninth National Symposium on Optoelectronic Technology, 2010.

[2] Sappa A D, Devy M. Fast range image segmentation by an edge diction strategy[C]. Proceedings of 3 rd International Conference on 3D Digital Imaging and Modeling, 2001: 292-299.

[3] Ben G. Segmentation of TIN structured laser altimetry points clouds[C]. Symposium on Geospatial Theory, Processing and Application, 2002.

[4] Flood M, Gutelius B. Commercial implications of topographic terrain mapping using scanning air-borne laser radar[J]. Photogrammetric Engineering & Remote Sensing, 1997, 63(4): 327-329.

[5] 龚亮, 张永生, 施群山, 等. 基于高程统计方法的机载LiDAR 点云数据滤波[J]. 测绘与空间地理信息, 2012, 35(2): 41-44.

    Gong Liang, Zhang Yongsheng, Shi Qunshan, et al.. Airborne LiDAR point cloud data filtering based on elevation statistical methods[J]. Geomatics & Spatial Information Technology, 2012, 35(2): 41-44.

[6] 闫利, 张毅. 基于法向量模糊聚类的道路面点云数据滤波[J]. 武汉大学学报(信息科学版), 2007, 32(12): 1119-1122.

    Yan Li, Zhang Yi. Road points cloud filtering based on fuzzy clustering of normal vectors[J]. Geomatics and Information Science of Wuhan University, 2007, 32(12): 1119-1122.

[7] 葛宝臻, 项晨, 田庆国, 等. 基于曲率特征混合分类的高密度点云去噪方法[J]. 纳米技术与精密工程, 2012, 10(1): 64-67.

    Ge Baozhen, Xiang Chen, Tian Qingguo, et al.. Hybrid classification based on curvature feature for high-density point cloud denoising[J]. Nanotechnology and Precision Engineering, 2012, 10(1): 64-67.

[8] 贺美芳, 周来水, 神会存. 散乱点云数据的曲率估算及应用[J]. 南京航空航天大学学报, 2005, 37(4): 515-519.

    He Meifang, Zhou Laishui, Shen Huicun. Scattered data curvature estimation and application[J]. Journal of Nanjing University of Aeronautics & Astronautics, 2005, 37(4): 515-519.

[9] 史文中, 李必军, 李清泉. 基于投影点密度的车载激光扫描距离图像分割方法[J]. 测绘学报, 2005, 34(2): 95-100.

    Shi Wenzhong, Li Bijun, Li Qingquan. Vehicle laser scanning range image segmentation method based on projected point density[J]. Acta Geodaetica et Cartographica Sinica, 2005, 34(2): 95-100.

[10] 黄涛, 胡以华, 赵刚, 等. 基于激光成像雷达距离图像的目标提取与分类技术[J]. 红外与毫米波学报, 2011, 39(2): 179-183.

    Huang Tao, Hu Yihua, Zhao Gang, et al.. Target extraction and classification based on LADAR range image[J]. Journal of Infrared and Millimeter Waves, 2011, 39(2): 179-183.

[11] 徐景中, 万幼川. 一种机载激光雷达距离图像的自适应边缘检测方法[J]. 激光与红外, 2011, 37(11): 1226-1229.

    Xu Jingzhong, Wan Youchuan. An adaptive edge detection method for range image of light detection and ranging[J]. Laser & Infrared, 2011, 37(11): 1226-1229.

[12] Pfeifer N, H fle B, Briese C, et al.. Analysis of the backscattered energy in terrestrial laser scanning data[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2008, 37: 1045-1052.

[13] H fle B, Pfeifer N. Correction of laser scanning intensity data: Data and model-driven approaches[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2007, 62(6): 415-433.

[14] Kaasalainen S, Krooks A, Kukko A, et al.. Radiometric calibration of terrestrial laser scanners with external reference targets [J]. Remote Sensing, 2009, 1(3): 144-158.

[15] Jutzi B, Gross H. Normalization of LiDAR intensity data based on range and surface incidence angle[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2009, 38: 213-218.

[16] 谭凯, 程效军. 基于多项式模型的TLS 激光强度值改正[J]. 中国激光, 2014, 42(3): 0314002.

    Tan Kai, Cheng Xiaojun. TLS laser intensity correction based on polynomial model[J]. Chinese J Lasers, 2015, 42(3): 0314002

[17] 谭凯, 程效军. 激光强度值改正模型与点云分类精度[J]. 同济大学学报(自然科学版), 2014, 42(1): 131-134.

    Tai Kai, Cheng Xiaojun. Correction methods of laser intensity and accuiacy of point cloud classification[J]. Journal of Tongji University (Natural Science), 2014, 42(1): 131-134.

[18] 胡以华. 激光成像目标侦察[M]. 北京: 国防工业出版社, 2013.

    Hu Yihua. Laser Imaging Target Detection[M]. Beijing: National Defense Industry Press, 2013.

[19] Kaasalainen S, Jaakkola A, Kaasalainen M, et al.. Analysis of incidence angle and distance effects on terrestrial laser scanner intensity: Search for correction methods[J]. Remote Sensing, 2011, 3(10): 2207-2221.

[20] Andrews L. A template for the nearest neighbor problem[J]. C/C++ Users Journal, 2001, 19(11): 40-49.

[21] Arya S, Mount D M, Netanyahu N S, et al.. An optimal algorithm for approximate nearest neighbor searching in fixed dimensions[J]. Journal of the ACM, 1998, 45(6): 891-923.

谭凯, 程效军. 基于强度数据的地面激光点云自适应非监督分类[J]. 激光与光电子学进展, 2016, 53(3): 032801. Tan Kai, Cheng Xiaojun. Adaptive Unsupervised Classification of TLS Point Cloud Based on Intensity Data[J]. Laser & Optoelectronics Progress, 2016, 53(3): 032801.

本文已被 2 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!