顾及空间上下文关系的JointBoost点云分类及特征降维

›› 2013, Vol. 42 ›› Issue (5): 715-821.

顾及空间上下文关系的JointBoost点云分类及特征降维

郭波¹,黄先锋¹,张帆²,王晏民³

1. 武汉大学
2. 武汉大学测绘遥感信息工程国家重点实验室
3. 北京建筑工程学院测绘系

收稿日期:2012-12-13 修回日期:2013-12-04 出版日期:2013-10-20 发布日期:2014-01-23
通讯作者: 黄先锋 E-mail:huangxf@whu.edu.cn
基金资助:
复杂低空飞行的自主避险理论与方法研究（973）;国家自然科学基金项目;国家自然科学基金项目;国家自然科学基金项目;国家自然科学基金项目

Points Cloud Classification using JointBoost Combined with Contextual Information for Feature Reduction

Received:2012-12-13 Revised:2013-12-04 Online:2013-10-20 Published:2014-01-23

摘要/Abstract

摘要： 随着激光雷达技术的发展及广泛应用，点云数据的分类及理解成为了目前一个研究热点。本文研究了较复杂的电力线路走廊场景的点云自动分类方法，目标类别为地面、植被、建筑物、电力塔、电力线等。本文首先归纳、定义了点云分类所需的关键特征，并利用JointBoost实现地物分类；同时，考虑到点云数据量大，其分类速度较慢，本文结合地物空间上的相互关联关系，提出了一种序列化的点云分类及特征降维方法。该方法在保证分类精度的前提下，使分类所需特征维数降低，缩短了分类所需时间。实际的电力线路走廊的激光扫描点云数据分类实验证明本文研究的分类方法的有效性。

关键词: LiDAR, 点云分类, JointBoost, 空间上下文, 特征降维度

Abstract: The requirements of 3D scene classification and understanding have dramatically increased with the widespread using of airborne LiDAR. This paper therefore focuses on complex power-line corridors scenes and presents an approach to automatically classify point clouds in building, ground, vegetation, power-line, and tower classes. Many key features of points cloud are introduced in this paper for classification using the JointBoost classifier. Due to the data of points cloud is “Big Data” and its classification rate is slow, we propose a method of serialized points cloud classification using spatial contextual information between objects for features reduction. The experiments prove that the classification method we study in this paper can be effectively used for points cloud classification in power-line corridors scenes.

Key words: LiDAR, point cloud classification, JointBoost, spatial context, feature reduction

中图分类号:

P237

郭波黄先锋张帆王晏民. 顾及空间上下文关系的JointBoost点云分类及特征降维[J]. , 2013, 42(5): 715-821.

参考文献

AXELSSON P. Processing of Laser Scanner Data Algorithms and Applications[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 1999, 54(1): 138-147.
VOSSELMAN G. Slope Based Filtering of Laser Altimetry Data[J]. International Archives of Photogrammetry and Remote Sensing, 2000, 33(3): 935-942.
MONGUS D, ALIK B. Parameter-free Ground Filtering of LiDAR Data for Automatic DTM Generation[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2012, 67(1):1-12.
YANG Bisheng, WEI zheng, LI Qingquan, et al. A Classification-oriented Method of Feature Image Generation for Vehicle-borne Laser Scanning Point Clouds[J]. Acta Geodaetica et Cartographica Sinica, 2010, 39(5): 540-545.( 杨必胜, 魏征, 李清泉, 等. 面向车载激光扫描点云快速分类的点云特征图像生成方法[J]. 测绘学报, 2010, 39(5): 540-545. )
HUANG Xianfeng，Gunho Sohn，WANG Xiao，ZHANG Fan. Roof Detection Using LiDAR Data Based on Points’Normal with Weight [J]. Geomatics and Information Science of Wuhan University, 2009, 34(1) : 24-27. (黄先锋, Gunho Sohn, 王潇, 张帆. 基于带权点方向量的LiDAR数据屋顶检测方法[J] . 武汉大学学报: 信息科学版, 2009, 34(1) : 24-27. )
MUNOZ D, BAGNELL J A, et al. Contextual Classification with Functional Max-Margin Markov Networks[C] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Miami: [s. n.], 2009: 975-982.
HUANG Xin, ZHANG Liangpei, GONG Wei. Information Fusion of Aerial Images and LIDAR Data in Urban Areas: Vector-stacking, Re-classification and Post-processing Approaches[J]. International Journal of Remote Sensing, 2011, 32(1): 69-84.
CHEHATA N, GUO L, et al. Airborne Lidar Feature Selection for Urban Classification Using Random Forests [C] // Proceedings of Laser Scanning 2009, IAPRS. Paris: [s. n.], 1999: 207-212.
MALLET C, BRETAR F, et al. Relevance Assessment of Full-Waveform Lidar Data for Urban Area Classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(6): 71-84.
HUANG Xianfeng, SOHN G. A Competition Based Roof Detection Algorithm from Airborne LiDAR Data[J]. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2008, 37(3): 319-324.
DUCIC V, HOLLAUS M, et al. 3D vegetation mapping and classification using full-waveform laser scanning[C] // Proceedings of the Workshop on 3D Remote Sensing in Forestry, EARSeL/ISPRS. Vienna: [s. n.], 2006: 211-217.
WAGNER W, HOLLAUS M, et al. 3D Vegetation Mapping Using Small-Footprint Full-waveform Airborne Laser Scanners[J]. International Journal of Remote Sensing, 2008, 29(5): 1433-1452.
LODHA S K, FITZPATRICK D M, et al. Aerial Lidar Data Classification using Expectation-Maximization[C] // Proceedings of the SPIE Conference on Vision Geometry2007 XIV, 2007: 1-11.
KIM H B, SOHN G. 3D Classification of Power-line Scene from Airborne Laser Scanning Data Using Random Forests[C] // Proceeding of IAPRS, Saint-Mande: [s. n.], 2010: 207-212.
TORRALBA A, MURPHY K P, et al. Sharing Visual Features for Multiclass and Multi-view Object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 19(5): 854-869.
FRIEDMAN J, HASTIE T et al. Additive Logistic Regression: a Statistical View of Boosting[J]. The Annals of Statistics, 2000, 28(1): 337-407.
BISHOP C, Pattern Recognition and Machine Learning[M]. New York, Springer, 2006: 657-663.
GROSS H, THOENNESSEN U. Extraction of Lines from Laser Point Clouds[J]. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2006, 36 (3): 86–91.
COLLINS R T, LIU Y, et al. Online Selection of Discriminative Tracking Features[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1631-1643.
HINTON G E, SALAKHUTDINOV R R. Reducing the Dimensionality of Data with Neural Networks[J]. Science, 2006, 313(5786): 504-507.

[1]	张勤, 赵超英, 陈雪蓉. 多源遥感地质灾害早期识别技术进展与发展趋势[J]. 测绘学报, 2022, 51(6): 885-896.
[2]	赵传, 郭海涛, 卢俊, 余东行, 林雨准, 姜怀刚. 结合区域增长与RANSAC的机载LiDAR点云屋顶面分割[J]. 测绘学报, 2021, 50(5): 621-633.
[3]	沈定涛, 钱天陆, 夏煜, 陈蓓青, 张煜, 王结臣. 机载LiDAR数据提取堤防工程特征信息圆环探测法[J]. 测绘学报, 2021, 50(2): 203-214.
[4]	方莉娜, 沈贵熙, 游志龙, 郭迎亚, 付化胜, 赵志远, 陈崇成. 融合点云和多视图的车载激光点云路侧多目标识别[J]. 测绘学报, 2021, 50(11): 1558-1573.
[5]	李永强, 李鹏鹏, 董亚涵, 范辉龙. 车载LiDAR点云数据中杆状地物自动提取与分类[J]. 测绘学报, 2020, 49(6): 724-735.
[6]	赵传, 郭海涛, 卢俊, 余东行, 张保明. 基于深度残差网络的机载LiDAR点云分类[J]. 测绘学报, 2020, 49(2): 202-213.
[7]	熊艳, 高仁强, 徐战亚. 机载LiDAR点云数据降维与分类的随机森林方法[J]. 测绘学报, 2018, 47(4): 508-518.
[8]	杨俊涛, 康志忠. 多尺度特征和马尔可夫随机场模型的电力线场景点云分类法[J]. 测绘学报, 2018, 47(2): 188-197.
[9]	潘锁艳, 管海燕. 机载多光谱LiDAR数据的地物分类方法[J]. 测绘学报, 2018, 47(2): 198-207.
[10]	李永强, 董亚涵, 张西童, 李鹏鹏. 车载LiDAR点云路灯提取方法[J]. 测绘学报, 2018, 47(2): 247-259.
[11]	何曼芸, 程英蕾, 邱浪波, 赵中阳. 一种改进顶帽变换与LBP高程纹理的城区建筑物提取算法[J]. 测绘学报, 2017, 46(9): 1116-1122.
[12]	赵传, 张保明, 陈小卫, 郭海涛, 卢俊. 一种利用点云邻域信息的建筑物屋顶面高精度自动提取方法[J]. 测绘学报, 2017, 46(9): 1123-1134.
[13]	何鄂龙, 王红平, 陈奇, 刘修国. 一种改进的空间上下文点云分类方法[J]. 测绘学报, 2017, 46(3): 362-370.
[14]	王滨辉, 宋沙磊, 龚威, 陈振威, 林鑫, 程学武, 李发泉, 史硕. 全波形激光雷达的波形优化分解算法[J]. 测绘学报, 2017, 46(11): 1859-1867.
[15]	盛庆红, 陈姝文, 柳建锋, 王惠南. 基于Plücker直线的LiDAR点云配准法[J]. 测绘学报, 2016, 45(1): 58-64.