Parameter optimization criteria guided 3D point cloud classification

doi:10.1007/s11042-018-6838-z

	Parameter optimization criteria guided 3D point cloud classification
	Li, Hongjun 1; Meng, Weiliang2 ; Liu, Xinying2 ; Xiang, Shiming2 ; Zhang, Xiaopeng2
刊名	MULTIMEDIA TOOLS AND APPLICATIONS
	2019-02-01
卷号	78 期号:4 页码:5081-5104
关键词	Point cloud classification Feature extraction Conditional random field Parameter optimization criterion Probabilistic neural network
ISSN号	1380-7501
DOI	10.1007/s11042-018-6838-z
通讯作者	Li, Hongjun(lihongjun69@bjfu.edu.cn)
英文摘要	3D point cloud classification is one of the basic topics in multimedia analysis and understanding. By the construction of the discriminant model and efficient parameter optimization, point cloud classification can be achieved after the training. However, most parameter optimization methods do not guarantee the highest global classification accuracy with a high classification accuracy on smaller classes. In addition, geometric features of the point cloud are not sufficiently utilized. In this paper, we use local geometric shape features including the nearest neighbor tetrahedral volume, Gaussian curvature, the neighbourhood normal vector consistency and the neighbourhood minimum principal curvature direction consistency. We propose three discrete criteria for parameter optimization to design explicit functions, and we present concrete algorithms, in which Monte Carlo method and Probabilistic Neural Network method are employed to estimate these parameters respectively. Experimental results show that our criteria can be applied to the classification of the 3D point cloud of the scene, and can be used to improve the classification accuracy of small-scale point sets when different classes have great disparities in the number.
资助项目	Fundamental Research Funds for the Central Universities[2015ZCQ-LY-01] ; National Natural Science Foundation of China[61372190] ; National Natural Science Foundation of China[61571439] ; National Natural Science Foundation of China[61561003] ; National Natural Science Foundation of China[61502490] ; National Natural Science Foundation of China[61501464] ; National Natural Science Foundation of China[6140001010207]
WOS关键词	MULTISCALE
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000463917200059
资助机构	Fundamental Research Funds for the Central Universities ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/24936]
专题	中国科学院自动化研究所
通讯作者	Li, Hongjun
作者单位	1.Beijing Forestry Univ, Coll Sci, Beijing, Peoples R China 2.CAS Inst Automat, LIAMA NLPR, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Li, Hongjun,Meng, Weiliang,Liu, Xinying,et al. Parameter optimization criteria guided 3D point cloud classification[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2019,78(4):5081-5104.
APA	Li, Hongjun,Meng, Weiliang,Liu, Xinying,Xiang, Shiming,&Zhang, Xiaopeng.(2019).Parameter optimization criteria guided 3D point cloud classification.MULTIMEDIA TOOLS AND APPLICATIONS,78(4),5081-5104.
MLA	Li, Hongjun,et al."Parameter optimization criteria guided 3D point cloud classification".MULTIMEDIA TOOLS AND APPLICATIONS 78.4(2019):5081-5104.