基于人体红外辐射的身份识别新方法  

Human recognition based on body infrared ray

作　　者：薛召军[1,2] 曹继华[1,2] 丁学文[1,2] 万柏坤[3] 明东[3] 

机构地区：[1]天津职业技术师范大学电子工程学院,天津300222 [2]天津市现场总线控制技术工程中心,天津300222 [3]天津大学精密仪器与光电子工程学院,天津300072

出　　处：《天津职业技术师范大学学报》2012年第1期1-5,共5页Journal of Tianjin University of Technology and Education

基　　金：国家自然科学基金重大研究计划培育项目(90920015);天津市高等学校科技发展基金计划项目(20100114)

摘　　要：为解决传统可见光成像在步态信息检测与身份识别中存在的诸多问题,提出了利用人体红外辐射成像及身份认证的新方法。首先将人体自身辐射的红外光转换为红外热图像,然后分割人体目标并将目标轮廓归一化,同时将轮廓序列叠加以获取红外信息能量图,再对其进行小波分解;提取红外信息能量图分解后的边界矩参数及骨架特征参数,以此作为特征参量输入支持向量机进行身份识别,正确识别率(PCR)为78%～91%,且识别效果不受人体携带外物(如背包、抱球)的影响,仅受衣着的影响较大。研究表明:基于人体红外辐射的身份识别有利于人体目标检测与精确描述。In order to remove noises from gait information detection and human recognition based on conventional imaging,the new method based on Infrared(IR) thermal imaging is applied for automatic human recognition.The infrared ray from human body is transformed to infrared thermal imaging.Then body silhouette sequences are extracted and added together to obtain the infrared gait energy image.The wavelet transform,invariant moments and skeleton theory are also used to extract gait features.The support vector machines(SVM)is presented for classification.This method achieved 78%-91% for the probability of correct recognition.The recognition rates are insensitive for the items of holding ball and loading package.However,there is significant influence for the item of wearing heavy coat.The human recognition based on infrared thermal imaging is potential for better description of human body.

关 键 词：红外辐射 身份识别 特征提取 支持向量机 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]