正在加载图片...
第12卷第4期 智能系统学报 Vol.12 No.4 2017年8月 CAAI Transactions on Intelligent Systems Aug.2017 D0I:10.11992/is.201607021 网络出版地址:http://kns.cmki.net/kcms/detail/23.1538.tp.20170407.1734.006.html 维度加权模式动态纹理特征的火焰检测 严云洋12,陈垂雄2,刘以安2,高尚兵 (1.淮阴工学院计算机与软件工程学院,江苏淮安223003:2.江南大学物联网工程学院,江苏无锡214122) 摘要:对疑似火焰区域提取纹理特征时,用局部三值模式描述火焰静态纹理特征不利于区分火焰与其他纹理均匀 的干扰物,用KNN算法(k-nearest neighbor algorithm)分类效率较低。针对这些问题,提出用三正交平面局部混合模 式(three orthogonal planes local mixed pattern,LMP-TOP)描述火焰的静动态纹理,再输人维度加权的支持向量机进行 分类识别。LMP.TOP是对第一维Y平面,采用八邻域的均匀局部二值模式(uniform local binary pattern,LBP2)三 正交平面局部混合模式表示火焰的静态纹理特征:对第二维XT和第三维YT平面,则采用局部三值模式(1oCal ternary patter,.LTP)融入火焰在时间维度上的变化信息,这样在得到火焰的静态特征的同时也融入了其动态特征。 根据3个维度单独用于识别的准确率,赋予其相应的权重,用维度加权的支持向量机进行分类识别。实验结果表明, 相比Sthevanie等算法,本文所提出的方法火焰识别率和检测效率均较高。 关键词:静态纹理:动态纹理:正交特征:加权特征:支持向量机:火焰检测:特征提取:局部二值模式 中图分类号:TP391文献标志码:A文章编号:1673-4785(2017)04-0548-08 中文引用格式:严云洋,陈垂雄,刘以安,等.维度加权模式动态纹理特征的火焰检测[J].智能系统学报,2017,12(4):548-555. 英文引用格式:YAN Yunyang,CHEN Chuixiong,LIU Yi'an,etal.Fire detection based on dynamic texture features under a dimension-weighted mode[J].CAAI transactions on intelligent systems,2017,12(4):548-555. Fire detection based on dynamic texture features under a dimension-weighted mode YAN Yunyang'2,CHEN Chuixiong'2,LIU Yi'an?,GAO Shangbing' (1.Faculty of Computer Software Engineering,Huaiyin Institute of Technology,Huaian 223003,China;2.School of Internet of Things Engineering,Jiangnan University,Wuxi 214122,China) Abstract:In fire detection modeling,a local ternary pattern is generally used to extract the static and dynamic textures of the suspected flame.But it is difficult to distinguish the flame from other uniform texture interferences when a local ternary pattern is used to describe the static texture features.The efficiency is low when the KNN(k- Nearest Neighbor)algorithm is used for classification.Aimed at solving these problems,a novel method is proposed here,whereby an LMP-TOP (local mixed pattern-three orthogonal planes)method is used to depict the static and dynamic textures of a suspected flame area.A dimension-weighted support vector machine was used for the classification.Applying LMP-TOP,an eight neighborhood uniform local binary pattern (LBP)was used to denote the static texture features of the flame on the 1st-dimension plane XY,and a local ternary pattern was used to describe the change in flame information on the 2nd-and 3rd-dimension planes,XT and YT respectively,by fusing with information in the time dimension.The static and dynamic characteristics of the flame were therefore integrated. The dimension weight was assigned according to the individual recognition accuracy.Then,a support vector machine with dimension weighting was used for classification.Experimental results show that the accuracy of flame identification and the detection efficiency are better with the proposed method than with corresponding algorithms such as Sthevanie. Keywords:static texture;dynamic texture;orthogonal feature;weighted feature;support vector machine;flame detection;feature extraction;local binary pattern 基于视觉的火灾检测相比传统的火灾检测方 法具有反应快、适用范围广等优点,因此正成为火 灾检测技术应用研究的热点,而基于视觉的火焰检 收稿日期:2016-07-22.网络出版日期:2017-04-07. 基金项目:国家自然科学基金项目(61402192):江苏省“六大人才高峰”项目 测是基于视觉的火灾检测的一个重要依据。但基 (2013DZXX-023):江苏省“333工程”(BRA2013208):淮安市科技 于视觉的火焰检测方法目前仍存在着鲁棒性差、检 计划项目(HAG2013057,HAG2013059) 通信作者:严云洋.E-mail:areyyyke@163.com. 测效率低等问题。纹理特征是火焰图像的一种静第 12 卷第 4 期 智 能 系 统 学 报 Vol.12 №.4 2017 年 8 月 CAAI Transactions on Intelligent Systems Aug. 2017 DOI:10.11992 / tis.201607021 网络出版地址:http: / / kns.cnki.net / kcms/ detail / 23.1538.tp.20170407.1734.006.html 维度加权模式动态纹理特征的火焰检测 严云洋1,2 ,陈垂雄1,2 ,刘以安2 ,高尚兵1 (1.淮阴工学院 计算机与软件工程学院,江苏 淮安 223003; 2.江南大学 物联网工程学院,江苏 无锡 214122) 摘 要:对疑似火焰区域提取纹理特征时,用局部三值模式描述火焰静态纹理特征不利于区分火焰与其他纹理均匀 的干扰物,用 KNN 算法(k⁃nearest neighbor algorithm)分类效率较低。 针对这些问题,提出用三正交平面局部混合模 式(three orthogonal planes local mixed pattern, LMP⁃TOP)描述火焰的静动态纹理,再输入维度加权的支持向量机进行 分类识别。 LMP⁃TOP 是对第一维 XY 平面,采用八邻域的均匀局部二值模式( uniform local binary pattern, LBP u2 )三 正交平面局部混合模式表示火焰的静态纹理特征;对第二维 XT 和第三维 YT 平面,则采用局部三值模式( local ternary patter, LTP)融入火焰在时间维度上的变化信息,这样在得到火焰的静态特征的同时也融入了其动态特征。 根据 3 个维度单独用于识别的准确率,赋予其相应的权重,用维度加权的支持向量机进行分类识别。 实验结果表明, 相比 Sthevanie 等算法,本文所提出的方法火焰识别率和检测效率均较高。 关键词:静态纹理;动态纹理;正交特征;加权特征;支持向量机;火焰检测;特征提取;局部二值模式 中图分类号:TP391 文献标志码:A 文章编号:1673-4785(2017)04-0548-08 中文引用格式:严云洋,陈垂雄,刘以安,等. 维度加权模式动态纹理特征的火焰检测[J]. 智能系统学报, 2017, 12(4): 548-555. 英文引用格式:YAN Yunyang, CHEN Chuixiong, LIU Yi’ an, et al. Fire detection based on dynamic texture features under a dimension⁃weighted mode[J]. CAAI transactions on intelligent systems, 2017, 12(4): 548-555. Fire detection based on dynamic texture features under a dimension⁃weighted mode YAN Yunyang 1,2 , CHEN Chuixiong 1,2 , LIU Yi’an 2 , GAO Shangbing 1 (1. Faculty of Computer & Software Engineering, Huaiyin Institute of Technology, Huaian 223003, China;2. School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China) Abstract:In fire detection modeling, a local ternary pattern is generally used to extract the static and dynamic textures of the suspected flame. But it is difficult to distinguish the flame from other uniform texture interferences when a local ternary pattern is used to describe the static texture features. The efficiency is low when the KNN (k⁃ Nearest Neighbor) algorithm is used for classification. Aimed at solving these problems, a novel method is proposed here, whereby an LMP⁃TOP (local mixed pattern⁃three orthogonal planes) method is used to depict the static and dynamic textures of a suspected flame area. A dimension⁃weighted support vector machine was used for the classification. Applying LMP⁃TOP, an eight neighborhood uniform local binary pattern (LBP u2 ) was used to denote the static texture features of the flame on the 1st⁃dimension plane XY, and a local ternary pattern was used to describe the change in flame information on the 2nd⁃and 3rd ⁃dimension planes, XT and YT respectively, by fusing with information in the time dimension. The static and dynamic characteristics of the flame were therefore integrated. The dimension weight was assigned according to the individual recognition accuracy. Then, a support vector machine with dimension weighting was used for classification. Experimental results show that the accuracy of flame identification and the detection efficiency are better with the proposed method than with corresponding algorithms such as Sthevanie. Keywords: static texture; dynamic texture; orthogonal feature; weighted feature; support vector machine; flame detection; feature extraction; local binary pattern 收稿日期:2016-07-22. 网络出版日期:2017-04-07. 基金项目:国家自然科学基金项目(61402192);江苏省“六大人才高峰”项目 (2013DZXX⁃023);江苏省“333 工程”(BRA2013208);淮安市科技 计划项目(HAG2013057,HAG2013059). 通信作者:严云洋. E⁃mail:areyyyke@ 163.com. 基于视觉的火灾检测相比传统的火灾检测方 法具有反应快、适用范围广等优点,因此正成为火 灾检测技术应用研究的热点,而基于视觉的火焰检 测是基于视觉的火灾检测的一个重要依据。 但基 于视觉的火焰检测方法目前仍存在着鲁棒性差、检 测效率低等问题。 纹理特征是火焰图像的一种静
向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有