CASIA OpenIR
Parameter optimization criteria guided 3D point cloud classification
Li, Hongjun1; Meng, Weiliang2; Liu, Xinying2; Xiang, Shiming2; Zhang, Xiaopeng2
Source PublicationMULTIMEDIA TOOLS AND APPLICATIONS
ISSN1380-7501
2019-02-01
Volume78Issue:4Pages:5081-5104
Corresponding AuthorLi, Hongjun(lihongjun69@bjfu.edu.cn)
Abstract3D 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.
KeywordPoint cloud classification Feature extraction Conditional random field Parameter optimization criterion Probabilistic neural network
DOI10.1007/s11042-018-6838-z
WOS KeywordMULTISCALE
Indexed BySCI
Language英语
Funding ProjectFundamental 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]
Funding OrganizationFundamental Research Funds for the Central Universities ; National Natural Science Foundation of China
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000463917200059
PublisherSPRINGER
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/24937
Collection中国科学院自动化研究所
Corresponding AuthorLi, Hongjun
Affiliation1.Beijing Forestry Univ, Coll Sci, Beijing, Peoples R China
2.CAS Inst Automat, LIAMA NLPR, Beijing, Peoples R China
Recommended Citation
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.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li, Hongjun]'s Articles
[Meng, Weiliang]'s Articles
[Liu, Xinying]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, Hongjun]'s Articles
[Meng, Weiliang]'s Articles
[Liu, Xinying]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, Hongjun]'s Articles
[Meng, Weiliang]'s Articles
[Liu, Xinying]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.