本科毕业论文基于双目立体视觉的行李规格检测学生姓名:张国锋专业:自动化学号:091141168指导教师:刘恒力所属学院:航空自动化学院二〇一三年六月中国民航大学本科毕业设计论文基于双目立体视觉的行李规格检测BaggageSpecificationDetectionBasedontheBinocularVision学生姓名:张国锋专业:自动化学号:091141168指导教师:刘恒力学院:航空自动化学院2013年6月中国民航大学本科毕业论文创见性声明本人声明:所呈交的毕业论文是本人在指导教师的指导下进行的工作和取得的成果,论文中所引用的他人已经发表或撰写过的研究成果,均加以特别标注并在此表示致谢。与我一同工作的同志对本论文所做的任何贡献也已在论文中作了明确的说明并表示谢意。毕业论文作者签名:签字日期:年月日本科毕业设计(论文)版权使用授权书本毕业设计(论文)作者完全了解中国民航大学有关保留、使用毕业设计(论文)的规定。特授权中国民航大学可以将毕业设计(论文)的全部或部分内容编入有关数据库进行检索,并采用影印、缩印或扫描等复制手段保存、汇编以供查阅和借阅。同意学校向国家有关部门或机构送交毕业设计(论文)的复印件和磁盘。(保密的毕业论文在解密后适用本授权说明)毕业论文作者签名:指导教师签名:签字日期:年月日签字日期:年月日中国民航大学本科毕业论文I摘要为实施国际航协提出的“简化商务、便捷出行”的核心计划,研发自助行李托运系统已经成为重要的解决方案。其中,行李信息的检测包括行李重量的采集、规格的检测以及行李标签的扫描。针对行李规格的自动检测问题,研究了基于双目立体视觉的检测算法,以实现自助行李托运系统中对行李的非接触检测。首先,基于自助行李托运系统特殊的硬件环境,设计了平行双目结构的行李图像采集系统,使系统能够在有限的空间内采集行李的立体图像对。设计了一种基于棋盘平面的系统标定法,获取摄像机的内外参数。其次,采用自适应最优阈值法对行李图像进行预处理并提取行李特征。设计了一种能够描述行李几何形状和轮廓的二维canny边缘检测算法。在外极线、唯一性、灰度相容性等基本约束和视差梯度附加约束条件下,设计了基于特征的区域灰度匹配方法,采用双向匹配策略,减少误匹配,提高了匹配的可靠性和稳定性。最后,考虑了双目视觉系统中空间点三维信息恢复方法,包括最小二乘法、中点法以及三角法。采用三角法并结合摄像机标定参数计算行李轮廓的三维信息。基于上述关键技术和方法,对几类行李进行检测实验,验证了本文算法的可行性和有效性,具有一定的应用价值。关键词:行李规格检测;立体视觉;特征提取;立体匹配;三维信息恢复中国民航大学本科毕业论文IIAbstractInordertoimplementfullysimplifybusinessprogramputforwardbyIATA(internationalairtransportassociation)andshortentheboardingtime,researchingtheself-serviceluggagesystemhasbecomeanimportantsolution.Passengerscanuseittomaketheidentificationandprintboardingpassandbaggagetag.Thesystemcanautomaticallydetectbaggageinformation,andfinallycompleteluggagechecked.Amongthem,thebaggageinformationdetectionincludesbaggageweightcollection,specificationsdetectionandluggagelabelscanning.Fortheluggagesizeautomaticdetectionproblem,asetofdetectionalgorithmbasedonbinocularstereovisionisproposedtorealizenon-contactdetectionontheself-serviceluggagesystem.Firstlyl,accordingtothehardwareenvironmentofself-serviceluggagesystemandbinocularstereovisionstructuremodel.Itdesignsluggageimageacquisitionhardwaresystemoftheparallelbinocularstructure.Atthesametime,thecameraimagingmodelandcalibrationmethodwerestudied,usingasystemcalibrationmethodbasedonthechessboardplanetogetthecameraparameters.Secondly,usingtheoptimalthresholdvaluemethodtopreprocesstheimages.Then,infeatureextraction,designing2Dcannyedgedetectionalgorithmtodescribetheluggagegeometricshape.Afterthat,Accordingtobasicconstraintsanddisparitygradientadditionalconstraintconditions,designingtheregionalgraymatchingmethodbasedonfeature,andusingthetwo-waymatchingstrategy,reducingtheerrormatching,Itensuresthereliabilityandstabilityofthematching.Finally,researchingthecalculationmethodsofspacepoint3Dinformationofthebinocularvisionsystem.Accordingtotheparallelbinocularstructure,usingthetriangularmethodtocalculate3dinformationofthebaggage.Basedonthetechnologyandmethodmentionedabove,testingtheshapeofdifferentsizeluggagecanrealizethenon-contactdetectionofbaggagespecifications.KeyWords:LuggageSpecificationsDetection;StereoVision;EdgeFeature;StereoMatching中国民航大学本科毕业论文III目录摘要....................................................................................................................................IAbstract...............................................................................................................................II第1章绪论.......................................................................................................................11.1论文的背景意义...................................................................................................11.2尺寸规格检测的技术现状...................................................................................41.3双目立体视觉测量的技术现状...........................................................................61.4论文研究内容.......................................................................................................8第2章基于行李图像的双目视觉测量系统设计...........................................................92.1双目立体视觉结构模型........................................................................................92.2摄像机立体标定..................................................................................................112.2.1摄像机坐标系统.......................................................................................112.2.2坐标系间转换关系...................................................................................112.2.3摄像机模型...............................................................................................112.2.4系统标定...................................................................................................112.3基于立体视觉的行李测量系统结构设计.........................................................12第3章行李特征提取与立体匹配算法.........................................................................133.1图像预处理..........................................................................................................133.2行李特征点提取..................................................................................................133.2.1边缘算子...................................................................................................133.2.2Canny检测法............................