Insulator recognition based on moments invariant features and Cascade AdaBoost classifier
He SY(何思远); Wang L(王玲); Xia Y(夏泳); Tang YD(唐延东)
2013
会议名称2013 2nd International Conference on Mechatronics and Control Engineering, ICMCE 2013
会议日期August 28-29, 2013
会议地点Dalian, China
关键词Classification (of information) Median filters Principal component analysis
页码362-367
中文摘要A method based on moments invariant features and cascade AdaBoost classifier for insulator recognition is put forward to solve the problem of poor performance of insulator recognition. At first, the insulator image is preprocessed by median filtering, dilating, eroding and Otsu thresholding. Then, for the better extraction of moments invariant features, the preprocessed insulator image is tilted correctly based on PCA (Principal Component Analysis). Next, the moments invariant features are extracted and chosen to compose complex classifier in the process of training AdaBoost. Finally, the complex AdaBoost classifiers are combined in a cascade method for insulator recognition. The results of experiments demonstrate that the proposed method can recognize the insulator from complex background in the mountainous area, and it has better robustness, accuracy and validity. © (2013) Trans Tech Publications, Switzerland.
收录类别EI ; CPCI(ISTP)
产权排序1
会议主办者Queensland University of Technology; Korea Maritime University; Hong Kong Industrial Technology Research Centre; Inha University
会议录Applied Mechanics and Materials
会议录出版者Trans Tech Publications Ltd,
会议录出版地Zurich-Durnten, Switzerland
语种英语
ISSN号1660-9336
ISBN号978-3-03785-894-3
WOS记录号WOS:000335121000071
内容类型会议论文
源URL[http://ir.sia.cn/handle/173321/13918]  
专题沈阳自动化研究所_机器人学研究室
推荐引用方式
GB/T 7714
He SY,Wang L,Xia Y,et al. Insulator recognition based on moments invariant features and Cascade AdaBoost classifier[C]. 见:2013 2nd International Conference on Mechatronics and Control Engineering, ICMCE 2013. Dalian, China. August 28-29, 2013.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace