Three dimensional shape reconstitution device and estimation device
    1.
    发明授权
    Three dimensional shape reconstitution device and estimation device 有权
    三维形状重构装置及估计装置

    公开(公告)号:US08107735B2

    公开(公告)日:2012-01-31

    申请号:US11906557

    申请日:2007-10-02

    IPC分类号: G06K9/00

    CPC分类号: G06K9/00248 G06K9/00281

    摘要: A face model providing portion provides an stored average face model to an estimation portion estimating an affine parameter for obtaining a head pose. An individual face model learning portion obtains a result of tracking feature points by the estimation portion and learns an individual face model. The individual face model learning portion terminates the learning when a free energy of the individual face model is over a free energy of the average face model, and switches a face model provided to the estimation portion from the average face model to the individual face model. While learning the individual face mode, an observation matrix is factorized using a reliability matrix showing reliability of each observation value forming the observation matrix with emphasis on the feature point having higher reliability.

    摘要翻译: 面部模型提供部分将估计部分的存储的平均面部模型提供给用于获得头部姿势的仿射参数。 个人面部模型学习部分通过估计部分获得跟踪特征点的结果,并学习个人面部模型。 当个人面部模型的自由能超过平均面部模型的自由能时,个人面部模型学习部分终止学习,并将提供给估计部分的面部模型从平均面部模型切换到个人面部模型。 在学习个人面部模式的同时,使用显示形成观察矩阵的每个观察值的可靠性的可靠度矩阵来分解观察矩阵,强调特征点具有较高的可靠性。

    Three dimensional shape reconstitution device and estimation device
    2.
    发明申请
    Three dimensional shape reconstitution device and estimation device 有权
    三维形状重构装置及估计装置

    公开(公告)号:US20080253610A1

    公开(公告)日:2008-10-16

    申请号:US11906557

    申请日:2007-10-02

    IPC分类号: G06K9/00 G06K9/46

    CPC分类号: G06K9/00248 G06K9/00281

    摘要: A face model providing portion provides an stored average face model to an estimation portion estimating an affine parameter for obtaining a head pose. An individual face model learning portion obtains a result of tracking feature points by the estimation portion and learns an individual face model. The individual face model learning portion terminates the learning when a free energy of the individual face model is over a free energy of the average face model, and switches a face model provided to the estimation portion from the average face model to the individual face model. While learning the individual face mode, an observation matrix is factorized using a reliability matrix showing reliability of each observation value forming the observation matrix with emphasis on the feature point having higher reliability.

    摘要翻译: 面部模型提供部分将估计部分的存储的平均面部模型提供给用于获得头部姿势的仿射参数。 个人面部模型学习部分通过估计部分获得跟踪特征点的结果,并学习个人面部模型。 当个人面部模型的自由能超过平均面部模型的自由能时,个人面部模型学习部分终止学习,并将提供给估计部分的面部模型从平均面部模型切换到个人面部模型。 在学习个人面部模式的同时,使用显示形成观察矩阵的每个观察值的可靠性的可靠度矩阵来分解观察矩阵,强调特征点具有较高的可靠性。

    Fluorine resin type weather-resistant film
    8.
    发明授权
    Fluorine resin type weather-resistant film 失效
    氟树脂型耐候膜

    公开(公告)号:US5132164A

    公开(公告)日:1992-07-21

    申请号:US595804

    申请日:1990-10-10

    摘要: A fluorine resin type weather-resistant film of multi-layer structure comprising a front surface layer made of a composition (A) comprising, as main commponents, from 50 to 95 parts by weight of a vinylidene fluoride resin and from 5 to 50 parts by weight of a methacrylate resin and a rear surface layer made of a composition (B) comprising, as main components, from 50 to 95 parts by weight of a methacrylate resin, from 5 to 50 parts by weight of a vinylidene fluoride resin and from 0.1 to 15 parts by weight of an ultraviolet absorber, wherein the overall thickness of the film of multi-layer structure is from 10 to 150 .mu.m, and the thickness of the front surface layer of the film is from 2 to 50 .mu.m.

    摘要翻译: 一种多层结构的氟树脂型耐候膜,包括由组合物(A)制成的前表面层,主要成分为50〜95重量份的偏二氟乙烯树脂和5〜50重量份的 甲基丙烯酸酯树脂的重量和由组合物(B)制成的背面层,所述组合物(B)主要包含50至95重量份的甲基丙烯酸酯树脂,5至50重量份的偏二氟乙烯树脂和0.1 至15重量份的紫外线吸收剂,其中多层结构的膜的总厚度为10〜150μm,膜的表面层的厚度为2〜50μm。