融合点、体素和对象特征的多基元点云分类

doi:10.12082/dqxxkx.2022.210313

摘要/Abstract

摘要：

单一基元分类方法难以全面描述复杂的点云场景,采用多基元进行分类成为一种趋势,提出了一种融合点、体素和对象特征的点云分类方法。主要包括4个方面：① 分别确定各层面分类基元,点基元方面采用最优邻域方法,体素基元方面基于八叉树方法进行体素划分,对象基元方面使用改进的多要素分割方法进行点云分割;② 提取各基元分类特征,首先提取点基元分类特征并进行局部线性约束编码(Locality-constrained Linear Coding, LLC),然后以此为基础提取体素基元和对象基元的潜在狄利克雷分布特征(Latent Dirichlet Allocation, LDA)和最大池化特征(Max Pooling, MP);③ 降低分类特征维度,利用随机森林变量重要性算法对分类特征进行筛选与降维;④ 进行点云分类,使用随机森林算法实现点云分类。采用3种不同类型的点云数据进行试验,结果表明融合3种基元特征的分类精度相比于点基元分类分别提升了1.43%、7.02%和2.48%,分类特征降维可以有效降低特征冗余度,分类器分类时间减少约70%;通过与其他算法的对比,新算法分类精度更优,且适用于多种场景点云数据的分类。

关键词: 遥感, 激光雷达, 点云分类, 多基元分类, 基元构建, 特征提取, 特征降维, 随机森林

Abstract:

The single primitive classification method is difficult to fully describe the complex scene of point cloud, and multiple primitives classification is becoming a trend. A point cloud classification method combining point, voxel, and object features is proposed in this study. This method mainly includes the following four procedures: (1) Determining the classification primitives at each level. The point primitive adopts a method of optimal neighborhood, and the voxel primitive uses octree to carry out voxel division. In the aspect of object primitive, the improved multi-factor segmentation method is used to realize the point cloud segmentation; (2) Extracting the classification features of each primitive. Firstly, the classification features of point primitive are obtained, and then the Locality-constrained Linear Coding (LLC) is carried out. Secondly, the features of Latent Dirichlet Allocation (LDA) and Max Pooling (MP) are extracted; (3) Reducing the dimension of classification features. The variable importance algorithm of random forest is used to select classification features and reduce its dimension; (4) Completing point cloud classification. The point cloud classification is achieved using random forest algorithms. Three different types of point cloud data are used for the experiment. The result shows that the classification accuracy of multiple primitives is increased by 1.43%, 7.02%, and 2.48%, respectively on the basis of the point primitive classification. The feature dimension reduction can effectively reduce the feature redundancy, and the time cost of the classifier is reduced by about 70%. Compared with other algorithms, this proposed algorithm has a higher classification accuracy and is suitable for the classification of point cloud data acquired from different scenes.

Key words: remote sensing, light detection and ranging, point cloud classification, multiple primitives classification, primitive determination, feature extraction, features dimension reduction, random forest

汪文琪, 李宗春, 付永健, 熊峰, 赵昭明, 何华. 融合点、体素和对象特征的多基元点云分类[J]. 地球信息科学学报, 2022, 24(2): 365-377.DOI:10.12082/dqxxkx.2022.210313

WANG Wenqi, LI Zongchun, FU Yongjian, XIONG Feng, ZHAO Zhaoming, HE Hua. The Multiple Primitives Classification of Point Cloud Combining Point, Voxel and Object Features[J]. Journal of Geo-information Science, 2022, 24(2): 365-377.DOI:10.12082/dqxxkx.2022.210313

图/表 10

图1

图2

表1

表2

表3

表4

图3

图4

表5

表6

参考文献 25

[1]	杨必胜, 董震. 点云智能研究进展与趋势[J]. 测绘学报, 2019, 48(12):1575-1585.
	[ Yang B S, Dong Z. Progress and perspective of point cloud intelligence[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(12):1575-1585. ] DOI: 10.11947/j.AGCS.2019.20190465 doi: 10.11947/j.AGCS.2019.20190465
[2]	Gong Y X, Yan F, Feng Z K, et al. Extraction of crown volume using triangulated irregular network algorithm based on LiDARFull-text in English[J]. 红外与毫米波学报, 2016, 35(2):177-183,189.
	[ Gong Y X, Yan F, Feng Z K, et al. Extraction of crown volume using triangulated irregular network algorithm based on LiDARFull-text in English[J]. Journal of Infrared and Millimeter Waves, 2016, 35(2):177-183,189. ] DOI: 10.11972/j.issn.1001-9014.2016.02.010 doi: 10.11972/j.issn.1001-9014.2016.02.010
[3]	方莉娜, 黄志文, 罗海峰, 等. 结合SVM与图匹配的车载激光点云道路标线识别[J]. 地球信息科学学报, 2019, 21(7):994-1008. doi: 10.12082/dpxxkx.2019.180697
	[ Fang L N, Huang Z W, Luo H F, et al. Integrating SVM and graph matching for identifying road markings from mobile LiDAR point clouds[J]. Journal of Geo-information Science, 2019, 21(7):994-1008. ] DOI: 10.12082/dpxxkx.2019.180697 doi: 10.12082/dpxxkx.2019.180697
[4]	Nardinocchi C, Balsi M, Esposito S. Fully automatic point cloud analysis for powerline corridor mapping[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(12):8637-8648. DOI: 10.1109/TGRS.2020.2989470 doi: 10.1109/TGRS.2020.2989470
[5]	张继贤, 林祥国, 梁欣廉. 点云信息提取研究进展和展望[J]. 测绘学报, 2017, 46(10):1460-1469.
	[ Zhang J X, Lin X G, Liang X L. Advances and prospects of information extraction from point clouds[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10):1460-1469. ] DOI: 10.11947/j.AGCS.2017.20170345 doi: 10.11947/j.AGCS.2017.20170345
[6]	张爱武, 李文宁, 段乙好, 等. 结合点特征直方图的点云分类方法[J]. 计算机辅助设计与图形学学报, 2016, 28(5):795-801.
	[ Zhang A W, Li W N, Duan Y H, et al. Point cloud classification based on point feature histogram[J]. Journal of Computer-Aided Design & Computer Graphics, 2016, 28(5):795-801. ] DOI: 10.3969/j.issn.1003-9775.2016.05.012 doi: 10.3969/j.issn.1003-9775.2016.05.012
[7]	岳冲, 刘昌军, 王晓芳. 基于多尺度维度特征和SVM的高陡边坡点云数据分类算法研究[J]. 武汉大学学报·信息科学版, 2016, 41(7):882-888.
	[ Yue C, Liu C J, Wang X F. Classification algorithm for laser point clouds of high-steep slopes based on multi-scale dimensionality features and SVM[J]. Geomatics and Information Science of Wuhan University, 2016, 41(7):882-888. ] DOI: 10.13203/j.whugis2014335 doi: 10.13203/j.whugis2014335
[8]	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.
	[ Xiong Y, Gao R Q, Xu Z Y. Random forest method for dimension reduction and point cloud classification based on airborne LiDAR[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(4):508-518. ] DOI: 10.11947/j.AGCS.2018.20170417 doi: 10.11947/j.AGCS.2018.20170417
[9]	杨书娟, 张珂殊, 邵永社. 基于多尺度自适应特征的机载 LiDAR点云分类[J]. 光学学报, 2019, 39(2):0228001.
	[ Yang S J, Zhang K S, Shao Y S. Classification of airborne LiDAR point cloud data based on multiscale adaptive features[J]. Acta Optica Sinica, 2019, 39(2):0228001. ] DOI: 10.3788/AOS201939.0228001 doi: 10.3788/AOS201939.0228001
[10]	董震, 杨必胜. 车载激光扫描数据中多类目标的层次化提取方法[J]. 测绘学报, 2015, 44(9):980-987.
	[ Dong Z, Yang B S. Hierarchical extraction of multiple objects from mobile laser scanning data[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(9):980-987. ] DOI: 10.11947/j.AGCS.2015.20140339 doi: 10.11947/j.AGCS.2015.20140339
[11]	Ramiya A M, Nidamanuri R R, Ramakrishnan K. A supervoxel-based spectro-spatial approach for 3D urban point cloud labelling[J]. International Journal of Remote Sensing, 2016, 37(17):4172-4200. DOI: 10.1080/01431161.2016.1211348 doi: 10.1080/01431161.2016.1211348
[12]	Kang Z Z, Yang J T, Zhong R F, et al. Voxel-based extraction and classification of 3-D pole-like objects from mobile LiDAR point cloud data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(11):4287-4298. DOI: 10.1109/JSTARS.2018.2869801. doi: 10.1109/JSTARS.2018.2869801
[13]	Zhang J X, Duan M Y, Yan Q, et al. Automatic vehicle extraction from airborne LiDAR data using an object-based point cloud analysis method[J]. Remote Sensing, 2014, 6(9):8405-8423. DOI: 10.3390/rs6098405 doi: 10.3390/rs6098405
[14]	Vosselman G, Coenen M, Rottensteiner F. Contextual segment-based classification of airborne laser scanner data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 128:354-371. DOI: 10.1016/j.isprsjprs.2017.03.010 doi: 10.1016/j.isprsjprs.2017.03.010
[15]	Ni H, Lin X G, Zhang J X. Classification of ALS point cloud with improved point cloud segmentation and random forests[J]. Remote Sensing, 2017, 9(3):288. DOI: 10.3390/rs9030288. doi: 10.3390/rs9030288
[16]	Xu S, Vosselman G, Oude Elberink S. Multiple-entity based classification of airborne laser scanning data in urban areas[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 88:1-15. DOI: 10.1016/j.isprsjprs.2013.11.008 doi: 10.1016/j.isprsjprs.2013.11.008
[17]	Zhang Z X, Zhang L Q, Tong X H, et al. A multilevel point-cluster-based discriminative feature for ALS point cloud classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(6):3309-3321. DOI: 10.1109/TGRS.2016.2514508 doi: 10.1109/TGRS.2016.2514508
[18]	Tong, Li, Zhang, et al. Point set multi-level aggregation feature extraction based on multi-scale max pooling and LDA for point cloud classification[J]. Remote Sensing, 2019, 11(23):2846. DOI: 10.3390/rs11232846 doi: 10.3390/rs11232846
[19]	Weinmann M, Jutzi B, Mallet C. Semantic 3D scene interpretation: A framework combining optimal neighborhood size selection with relevant features[J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2014, II-3:181-188. DOI: 10.5194/isprsannals-II-3-181-2014 doi: 10.5194/isprsannals-II-3-181-2014
[20]	Weinmann M, Jutzi B, Hinz S, et al. Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 105:286-304. DOI: 10.1016/j.isprsjprs.2015.01.016 doi: 10.1016/j.isprsjprs.2015.01.016
[21]	汪文琪, 李宗春, 付永健, 等. 基于改进多规则区域生长的点云多要素分割[J]. 光学学报, 2021, 41(5):198-212.
	[ Wang W Q, Li Z C, Fu Y J, et al. Multi-factor segmentation of point cloud based on improved multi-rule region growing[J]. Acta Optica Sinica, 2021, 41(5):198-212. ] DOI: 10.3788/AOS202141.0528001. doi: 10.3788/AOS202141.0528001
[22]	Wang J J, Yang J C, Yu K, et al. Locality-constrained Linear Coding for image classification[C]// 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, 2010:3360-3367. DOI: 10.1109/CVPR.2010.5540018. doi: 10.1109/CVPR.2010.5540018
[23]	Foulds J, Boyles L, DuBois C, et al. Stochastic collapsed variational Bayesian inference for latent Dirichlet allocation[C]// KDD '13: Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining. 2013:446-454. DOI: 10.1145/2487575.2487697 doi: 10.1145/2487575.2487697
[24]	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 D J, Yang J, Zhan X J. Feature selection algorithm based on random forest[J]. Journal of Jilin University (Engineering and Technology Edition), 2014, 44(1):137-141. ] DOI: 10.13229/j.cnki.jdxbgxb201401024 doi: 10.13229/j.cnki.jdxbgxb201401024
[25]	Roynard X, Deschaud J E, Goulette F. Paris-Lille-3D: A large and high-quality ground-truth urban point cloud dataset for automatic segmentation and classification[J]. The International Journal of Robotics Research, 2018, 37(6):545-557. DOI: 10.1177/0278364918767506 doi: 10.1177/0278364918767506

	训练数据					验证数据
	植被	建筑	地面	车辆	电力线	植被	建筑	地面	车辆	电力线
场景I	18 336	5788	11 453	-	-	592 888	109 983	370 338	-	-
场景II	5658	8611	11 832	5377	-	277 246	421 960	579 808	48 402	-
场景III	1718	10 683	4225	-	753	84 208	701 538	277 461	-	14 321

指标		类别
指标		植被	建筑	地面
R	策略①	96.79	84.81	96.41
	策略②	96.79	88.48	96.90
	策略③	97.66	92.57	96.88
	策略④	97.50	92.65	97.09
P	策略①	96.49	88.04	95.85
	策略②	97.00	90.06	96.06
	策略③	97.33	94.72	96.75
	策略④	97.47	94.70	96.52
F₁	策略①	96.64	86.40	96.13
	策略②	96.90	89.26	96.48
	策略③	97.50	93.63	96.81
	策略④	97.48	93.67	96.81
OA	策略① 95.43 策略② 95.98 策略③ 96.87 策略④ 96.86

指标		类别
指标		植被	建筑	地面	车辆
R	策略①	84.20	86.68	98.75	94.96
	策略②	91.87	93.34	99.26	98.09
	策略③	97.83	98.74	98.78	99.65
	策略④	97.93	98.73	99.12	99.57
P	策略①	89.06	94.41	99.37	45.21
	策略②	96.25	97.17	99.34	60.82
	策略③	98.52	98.80	99.34	89.56
	策略④	98.71	99.04	99.42	89.80
F₁	策略①	86.57	90.38	99.06	61.25
	策略②	94.01	95.22	99.30	75.09
	策略③	98.18	98.77	99.06	94.34
	策略④	98.32	98.88	99.27	94.43
OA	策略① 91.74 策略② 95.80 策略③ 98.60 策略④ 98.76

指标		类别
指标		植被	建筑	地面	电力线
R	策略①	83.28	97.63	97.65	94.76
	策略②	94.54	98.90	98.14	96.83
	策略③	98.17	99.30	98.19	97.75
	策略④	97.99	99.35	98.30	97.72
P	策略①	84.60	97.02	98.66	96.43
	策略②	96.16	98.60	98.44	96.12
	策略③	99.84	99.05	98.34	98.09
	策略④	99.84	99.07	98.41	98.40
F₁	策略①	83.94	97.32	98.15	95.58
	策略②	95.34	98.75	98.29	96.47
	策略③	98.99	99.18	98.25	97.92
	策略④	98.91	99.21	98.36	98.06
OA	策略① 96.47 策略② 98.34 策略③ 98.91 策略④ 98.95

	降维前			降维后
	训练/s	测试/s	OA/%	训练/s	测试/s	OA/%
场景I	190.96	15.22	96.86	42.19	7.22	96.98
场景II	121.04	16.43	98.76	41.66	8.78	98.86
场景III	67.70	12.57	98.95	8.51	5.15	99.03