中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Shadow detection using multi-features in SVM classifier

文献类型:会议论文

作者Wang ZP(王占鹏); Tian JD(田建东); Tang YD(唐延东); Zhang YZ(张艳珠); Xia Y(夏泳); Wang L(王玲)
出版日期2014
会议名称2nd International Conference on Precision Mechanical Instruments and Measurement Technology, ICPMIMT 2014
会议日期May 30-31, 2014
会议地点Chongqing, China
关键词Mathematical morphology Object recognition Security systems
页码1680-1683
中文摘要Shadows may cause many problems in computer vision, such as object recognition, image segmentation and video surveillance. In this paper, we present a new method to detect cast shadow in a single outdoor image. We build up an illumination model to explain the process of shadow formed, and through this model we introduce some useful features. The regions for extract features are acquired through canny edge detector, after a series of morphological operations. Then we use SVM classifier with a multi-kernel model to train these features for shadow region classification. Our results show that edges of shadow images can be detected effectively with our methods. © (2014) Trans Tech Publications, Switzerland.
收录类别EI
产权排序1
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978-3-03835-194-8
源URL[http://ir.sia.cn/handle/173321/15156]  
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
Wang ZP,Tian JD,Tang YD,et al. Shadow detection using multi-features in SVM classifier[C]. 见:2nd International Conference on Precision Mechanical Instruments and Measurement Technology, ICPMIMT 2014. Chongqing, China. May 30-31, 2014.

入库方式: OAI收割

来源:沈阳自动化研究所

浏览0
下载0
收藏0
其他版本

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。