• / 129
  • 下载费用:5 金币  

基于立体视觉的多气囊柔性人体腹部重建研究.doc

关 键 词:
基于 立体 视觉 气囊 柔性 人体 腹部 重建 研究
资源描述:
学校代码:10255学 号:1119118基于立体视觉的多气囊柔性人体腹部重建研究Research on Abdomen Reconstruction for Multi-airbag Mannequin Based on Stereo Vision学 院:信息科学与技术学院专 业:模式识别与智能系统姓 名:刘 欢导 师:郝矿荣 教授2014 年 3 月附件一:东华大学学位论文原创性声明本人郑重声明:我恪守学术道德,崇尚严谨学风。所呈交的学位论文,是本人在导师的指导下,独立进行研究工作所取得的成果。除文中已明确注明和引用的内容外,本论文不包含任何其他个人或集体已经发表或撰写过的作品及成果的内容。论文为本人亲自撰写,我对所写的内容负责,并完全意识到本声明的法律结果由本人承担。学位论文作者签名:日期: 年 月 日附件二:东华大学学位论文版权使用授权书学位论文作者完全了解学校有关保留、使用学位论文的规定,同意学校保留并向国家有关部门或机构送交论文的复印件和电子版,允许论文被查阅或借阅。本人授权东华大学可以将本学位论文的全部或部分内容编入有关数据库进行检索,可以采用影印、缩印或扫描等复制手段保存和汇编本学位论文。保密 □,在 年解密后适用本版权书。本学位论文属于不保密 □。学位论文作者签名: 指导教师签名:日期: 年 月 日 日期: 年 月 日IV基于立体视觉的多气囊柔性人体腹部重建研究摘 要人体腹部体型三维重建技术是个性化服装设计、医疗保健、人机工程等领域的关键技术。本论文在对基于立体视觉的人体体型建模技术进行全面调研和总结之后,结合计算机立体视觉技术、数字图像相关方法、生物智能理论等,对人体腹部体型三维重建以及腹部动态变形的体型三维重建问题进行了深入的研究。本论文主要开展了如下几方面工作:(1)介绍了基于立体视觉的人体体型三维重建方法的基本原理,较为详细地阐述和总结了国内外基于立体视觉技术的体型重建方法的研究进展和现状以及应用领域;概述了基于立体视觉的三维重建所涉及的关键技术及相关研究,并介绍了数字图像相关方法的理论及其在图像变形匹配中的应用,为本文研究基于立体视觉的柔性人体腹部体型三维重建等问题提供了理论依据和基本思路。(2)对静态腹部体型三维重建方法进行研究,探索了一种适于真实拍摄环境下的人体腹部三维重建方法。该方法采用主动标记法在紧身衣的腹部位置缝织一些易于识别的标记点,结合立体视觉原理,充分考虑了拍摄过程中常出现的光照变化和模糊噪声干扰,设计了一种光照变化鲁棒且抗模糊的特征不变矩,用于解决立体视觉系统中图像特征的立体匹配问题,此外还引入严格的几何约束机制用于剔除误匹配对,再用全局种子点生长算法引导非特征点区域的匹配,获得腹部稠密的三维点云数据,实现柔性人体腹部体型三维重建。实验结果表明该方法能达到与三维扫描仪相同的精度级,能满足服装设计等领域的精度要求。(3)在已搭建的立体视觉图像采集平台和对静态腹部体型重建研究的基础上,进一步探索了腹部体型动态变形时的特征匹配方法,提出了一种腹部变形的体型三维形貌重建技术。该技术以数字图像相关方法的原理为基础,设计了一种子区大小可根据变形程度自适应调整的椭圆形匹配模板,另外,对基本的分形维进行了改进,提出了一种基于子区面积的分形维数,实现变形前后时间V序列腹部图像中同名特征点的整像素粗搜索;接着在整像素粗匹配的基础上设计了一种互相学习的自适应粒子群算法实现同名特征点的亚像素精确定位,经过这种粗-精相结合的特征点像素坐标定位方法,建立了变形前后图像中同名特征点的匹配对应关系模型,实现了腹部体型变形的三维重建。围绕多气囊柔性人体腹部变形体型三维重建展开实验验证,结果证实本方案在保证获得可靠精度的前提下,时间性能优于传统的特征点变形匹配方法,尤其是处理大数据量时,其时间优越性更为明显。(4)为了克服传统立体匹配过程的繁琐步骤和大量重复操作,构建了 B-T免疫神经网络实现特征点的立体匹配。通过分析图像立体匹配的左右一致性约束与生物免疫系统中 B 细胞与 T 细胞间的辅助和抑制作用机理,抽象出两者的相似性,在 T 细胞层加入几何约束机制以满足匹配的唯一性约束,建立基于生物智能的特征点立体匹配方法;为了达到更为精确的匹配效果,将圆形的匹配模板分成多个子栅格,由像素灰度值和表征图像结构信息的单元栅格熵两者组合构成新的特征描述矢量,最后,利用神经网络实现所有特征点的总体最优匹配。该方法结合 B-T 免疫网络灵活的双向调节机制和神经网络的良好组织架构,实现了智能化的柔性人体腹部体型三维重建。实验结果表明,本方法在确保与传统匹配方法相同精度的前提下,匹配时间优于传统立体匹配方法。这种智能匹配方法为今后立体匹配方法的研究提供了一种全新的思路。论文的最后对全文的研究工作做了简要的总结,并对下一步待研究的内容和方向进行了讨论和展望。关键词:腹部体型;立体视觉;三维重建;组合不变矩;立体匹配;变形匹配;B-T 免疫神经网络VIResearch on Abdomen Reconstruction for Multi-airbag Mannequin based on Stereo VisionABSTRACTThe human abdomen shape reconstruction is a crucial technology in a wide range of fields, such as personalized garment design, medical care, man-machine engineering. This thesis conducts a further study on abdomen shape reconstruction and abdomen deformation reconstruction according to the principle of computer stereo vision, digital image correlation method and the theory of biological intelligence. Based on the full investigation and review to precious works related to the techniques of human body reconstruction in terms of stereo vision system, the main contributions carried out in this thesis lie in:(1) The basic principle and method of human body 3D reconstruction by stereo vision are introduced, and then, a detailed exposition and summarization about the techniques and applications of body shape reconstruction at home and abroad by means of stereo vision are provided. Still, the critical techniques and related research works of 3D reconstruction based on stereo vision are outlined. In addition, the theory of digital image correlation method and its application in image deformation matching are also expounded. All these offer the theoretical basis and the fundamental route for solving the problems of 3D abdomen reconstruction for soft mannequin through stereo vision in the research.(2) Trying to explore a novel approach for the static 3D abdomen reconstruction that is suitable for real photographing condition aiming at recovering abdomen shape. With the explicit markers are woven actively in the tight dress on the part of belly, the proposed combing the stereo vision theory, taking full account of the frequent interferences from both illumination variance and blur noise in the process of photographing, an innovative illumination-robust and anti-blur descriptor is designed for solving the binocular images matching problem in stereo vision system. Meanwhile, the strict geometric constraints are involved for eliminating the error mapping pairs, more exact matching pairs obtained at this stage. Subsequently, these exact pairs are taken as seeds to produce dense cloud data by means of global seed growing algorithm for achieving the recover of 3D belly panorama for soft mannequin. The experimental results reveal that its precision can up to the highly similar VIImeasurement accuracy of 3D scanner, which can well satisfy the requirement of fashion designing and facilitates the costume design industry.(3) A further exploration concerning the abdomen deformation modeling is performed based on the above proposed stereo vision platform and method for a static belly shape. A methodology of 3D abdomen panorama reconstruction is put forward in the course of the belly deformation. A novel strategy of adaptive ellipse subset relying on the deformation degree as well as a new improved fractal dimension on the basis of the subset area is designed for the aim of the integer-pixel displacement search for the same feature point between the abdomen images before and after deformation in sequence. Then, a mutual learning adaptive particle swarm optimization algorithm is employed at sub-pixel registration resolution stage to locate the sub-pixel precisely. Supported by the combined coarse-fine ideology, the corresponding points between images of before and after deformation are established exactly for accomplishing the 3D abdomen deformation reconstruction. Testing on the abdomen deformation reconstruction for soft mannequin, experimental results indicate that under the guarantee of its measurement accuracy without any loss, the time-consuming of the proposed scheme is significantly superior to that of the conventional method, particularly, at the large number of interest points.(4) In order to overcome the cockamamie steps of traditional matching method further, the stereo matching of feature points by B-T immune neural network is completed. The both similar mechanism between the left-right consistency constraints in image feature mapping and the mutual mechanism assistance and inhibition of B cells and T cells is abstracted. Moreover, the inherent geometry property is also introduced in T cell layer so as to ensure the uniqueness. For the more precise result, in each sub-grid of a circle template, a new combined feature vector is produced by means of involving entropy signifying the structure feature of image, as well as the gray information. Finally, neural network algorithm is utilized to obtain the global optimization effect for the all feature points. The intelligent 3D belly recover for soft mannequin is achieved in virtue of the flexible bidirectional regulation of B-T immune network and the well organization property. Experimental results demonstrate that the proposed approach greatly outperforms the traditional matching algorithm on time load under the condition of the same precise, which provides an revolutionary new idea and effective revolutionary for stereo matching in the future.Finally a conclusion is made for the whole contents of this dissertation, together with the perspectives of this field for the next step.VIIIKEY WORDS: abdomen shape; stereo vision; three-dimension reconstruction; combined invariant moments; stereo matching; deformation matching; B-T immune neural networkIX目 录摘 要 ............................................................................................................................IVABSTRACT.................................................................................................................VI第一章 绪 论 ................................................................................................................11.1 研究背景及意义 .................................................................................................11.2 三维数字化人体建模国内外研究综述 .............................................................21.2.1 三维人体数据获取 ........................................................................................41.2.2 三维人体建模方法 ........................................................................................61.3 论文主要内容和创新点 ...................................................................................101.4 论文的章节安排 ...............................................................................................11第二章 立体视觉的三维重建关键技术 ....................................................................132.1 引言 ...................................................................................................................132.2 立体视觉系统 ...................................................................................................142.3 摄像机标定 .......................................................................................................152.4 特征提取与描述 ...............................................................................................172.4.1 特征检测 ......................................................................................................182.4.2 特征描述 ......................................................................................................192.5 特征配准 ...........................................................................................................202.5.1 立体匹配 ......................................................................................................202.5.2 变形匹配 ......................................................................................................252.6 三维重建方法 ...................................................................................................272.7 小结 ...................................................................................................................28第三章 基于新组合不变矩与全局种子点生长算法的腹部三维重建 ....................293.1 引言 ...................................................................................................................293.2 光照鲁棒且抗模糊不变矩的立体匹配 ...........................................................303.2.1 光照鲁棒不变矩的构造 ..............................................................................303.2.2 抗模糊不变矩的构造 ..................................................................................313.2.3 融合梯度信息的典型相关分析 ..................................................................333.3 非特征点区域匹配 ...........................................................................................353.3.1 引入几何约束机制剔除误匹配对 ..............................................................353.3.2 全局种子点生长算法生成稠密三维点云 ..................................................363.4 实验与结果分析 ...............................................................................................373.4.1 新组合不变矩性能验证实验 ......................................................................373.4.2 人体腹部重建过程 ......................................................................................393.5 小结 ...................................................................................................................48X第四章 基于立体视觉的腹部变形体型的三维重建与测量 ....................................504.1 引言 ...................................................................................................................504.2 数字图像相关方法 ...........................................................................................504.2.1 整像素搜索原理 ..........................................................................................514.2.2 亚像素精确定位原理 ..................................................................................534.2.3 三维数字图像相关方法 ..............................................................................544.3 改进的三维数字图像算法 ...............................................................................564.3.1 整像素搜索算法改进方案 ..........................................................................564.3.2 基于互相学习的自适应 PSO 算法的亚像素精定位(MLADPSO ) .....594.4 实验结果与分析 ...............................................................................................614.4.1 实验设备及图像数据采集 .........................................................................614.4.2 整像素粗搜索实验 .....................................................................................664.4.3 亚像素精定位实验 .....................................................................................714.4.4 变形体型参数分析 .....................................................................................744.5 小结 ...................................................................................................................74第五章 基于 B-T 免疫神经网络的立体匹配方法及其腹部三维重建 ...................755.1 引言 ...................................................................................................................755.2 概述 ...................................................................................................................765.2.1 人工免疫系统原理及应用 ..........................................................................765.2.2 免疫系统与神经网络 ..................................................................................785.3 基于 B-T 免疫神经网络的立体匹配算法(Im-ANN) ................................795.3.1 B-T 免疫网络调节机理 ..............................................................................795.3.2 基于 B-T 免疫网络的立体匹配算法 .........................................................795.3.3 B-T 免疫神经网络模型 ..............................................................................845.4 实验结果与分析 ...............................................................................................865.4.1 实验设备及图像数据采集 .........................................................................865.4.2 三种方法的特征匹配效果比较 .................................................................865.4.3 腹部稠密三维点云生成及参数测量 .........................................................885.5 小结 ...................................................................................................................90第六章 总结与展望 ....................................................................................................916.1 总结 ...................................................................................................................916.2 展望 ...................................................................................................................92参考文献 ......................................................................................................................94致 谢 ..........................................................................................................................112附 录 ..........................................................................................................................113附录 A 攻读博士学位期间取得的成果 ..............................................................113附录 B 攻读博士学位期间参与的项目 ..............................................................114
展开阅读全文
1
  金牌文库所有资源均是用户自行上传分享,仅供网友学习交流,未经上传用户书面授权,请勿作他用。
0条评论

还可以输入200字符

暂无评论,赶快抢占沙发吧。

关于本文
本文标题:基于立体视觉的多气囊柔性人体腹部重建研究.doc
链接地址:http://www.gold-doc.com/p-258385.html
关于我们 - 网站声明 - 网站地图 - 资源地图 - 友情链接 - 网站客服客服 - 联系我们
copyright@ 2014-2018 金牌文库网站版权所有
经营许可证编号:浙ICP备15046084号-3
收起
展开