利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

59 条记录 (耗时 0.02 秒)

    Method and apparatus for object pose estimation
    3.
    发明授权
    Method and apparatus for object pose estimation 有权
    物体姿态估计方法与装置

    公开(公告)号：US08467596B2

    公开(公告)日：2013-06-18

    申请号：US13220851

    申请日：2011-08-30

    申请人： Arash Abadpour ,  Guoyi Fu ,  Ivo Moravec

    发明人： Arash Abadpour ,  Guoyi Fu ,  Ivo Moravec

    IPC分类号： G06K9/00

    CPC分类号： G06T7/12 ,  G06T7/73

    摘要： A pose of an object is estimated from an from an input image and an object pose estimation is then stored by: inputting an image containing an object; creating a binary mask of the input image; extracting a set of singlets from the binary mask of the input image, each singlet representing points in an inner and outer contour of the object in the input image; connecting the set of singlets into a mesh represented as a duplex matrix; comparing two duplex matrices to produce a set of candidate poses; and producing an object pose estimate, and storing the object pose estimate. The estimated pose of the object is refined by: inputting an image of an object in an estimated pose, a model of the object, and parameters of a camera used to take the image of the object in the estimated pose; projecting the model of the object into a virtual image of the object using the parameters of the camera and initial pose parameters to obtain a binary mask image and image depth information; and updating the initial pose parameters to new pose parameters using the binary mask image and image depth information and updating the new pose parameters iteratively to minimize an energy function or until a maximum number of iterations is reached.

    摘要翻译： 从输入图像估计对象的姿态，然后通过以下方式存储对象姿势估计：输入包含对象的图像; 创建输入图像的二进制掩码; 从输入图像的二进制掩码中提取一组单元，每个单线代表输入图像中对象的内外轮廓中的点; 将该组单元连接成以双面矩阵表示的网格; 比较两个双工矩阵以产生一组候选姿势; 并产生物体姿态估计，并存储对象姿态估计。 通过以下方式来改善对象的估计姿态：在估计姿态中输入对象的图像，对象的模型以及用于在估计姿态中拍摄对象的图像的相机的参数; 使用相机的参数和初始姿态参数将对象的模型投影到对象的虚拟图像中，以获得二进制掩码图像和图像深度信息; 以及使用二进制掩模图像和图像深度信息将初始姿态参数更新为新的姿态参数，并且迭代地更新新的姿态参数以最小化能量函数或直到达到最大次数。

    Method And Apparatus For Object Pose Estimation
    4.
    发明申请
    Method And Apparatus For Object Pose Estimation 有权
    用于物体姿态估计的方法和装置

    公开(公告)号：US20130051626A1

    公开(公告)日：2013-02-28

    申请号：US13220851

    申请日：2011-08-30

    申请人： Arash Abadpour ,  Guoyi Fu ,  Ivo Moravec

    发明人： Arash Abadpour ,  Guoyi Fu ,  Ivo Moravec

    IPC分类号： G06K9/46

    CPC分类号： G06T7/12 ,  G06T7/73

    摘要： A pose of an object is estimated from an from an input image and an object pose estimation is then stored by: inputting an image containing an object; creating a binary mask of the input image; extracting a set of singlets from the binary mask of the input image, each singlet representing points in an inner and outer contour of the object in the input image; connecting the set of singlets into a mesh represented as a duplex matrix; comparing two duplex matrices to produce a set of candidate poses; and producing an object pose estimate, and storing the object pose estimate. The estimated pose of the object is refined by: inputting an image of an object in an estimated pose, a model of the object, and parameters of a camera used to take the image of the object in the estimated pose; projecting the model of the object into a virtual image of the object using the parameters of the camera and initial pose parameters to obtain a binary mask image and image depth information; and updating the initial pose parameters to new pose parameters using the binary mask image and image depth information and updating the new pose parameters iteratively to minimize an energy function or until a maximum number of iterations is reached.

    摘要翻译： 从输入图像估计对象的姿态，然后通过以下方式存储对象姿势估计：输入包含对象的图像; 创建输入图像的二进制掩码; 从输入图像的二进制掩码中提取一组单元，每个单线代表输入图像中对象的内外轮廓中的点; 将该组单元连接成以双面矩阵表示的网格; 比较两个双工矩阵以产生一组候选姿势; 并产生物体姿态估计，并存储对象姿态估计。 通过以下方式来改善对象的估计姿态：在估计姿态中输入对象的图像，对象的模型以及用于在估计姿态中拍摄对象的图像的相机的参数; 使用相机的参数和初始姿态参数将对象的模型投影到对象的虚拟图像中，以获得二进制掩码图像和图像深度信息; 以及使用二进制掩模图像和图像深度信息将初始姿态参数更新为新的姿态参数，并且迭代地更新新的姿态参数以最小化能量函数或直到达到最大次数。

    IMAGE REGISTRATION PARAMETERS AND CONFIDENCE ESTIMATION FROM SENSOR DATA
    5.
    发明申请
    IMAGE REGISTRATION PARAMETERS AND CONFIDENCE ESTIMATION FROM SENSOR DATA 有权
    图像注册参数和传感器数据的信心估计

    公开(公告)号：US20120194873A1

    公开(公告)日：2012-08-02

    申请号：US13015278

    申请日：2011-01-27

    申请人： Guoyi Fu ,  Mikhail Brusnitsyn

    发明人： Guoyi Fu ,  Mikhail Brusnitsyn

    IPC分类号： H04N1/40

    CPC分类号： H04N1/3876 ,  H04N1/047 ,  H04N1/107 ,  H04N1/19594 ,  H04N2201/0414 ,  H04N2201/0471 ,  H04N2201/04734 ,  H04N2201/04737 ,  H04N2201/04743

    摘要： An off page condition or invalid sensors position data is detected by checking the errors from an initial transformation parameter estimation. If an abnormally large error is encountered, a sensor's reading (position data) may be invalid or the sensor was off page. Then the invalid sensor data will be identified and removed. Finally the transformation parameters will be re-estimated using valid sensor position data only. A weighted least-square minimization is used by considering the sensor lift situation. If a sensor is lifted, the weight for the error related to the sensor will be set to a small weight or zero. Also considered are the geometric properties of sensor locations in weighting the sensor error. A confidence measurement of the sensor data and associated error is performed. The confidence measurement is derived from an error ellipse at 95% confidence level.

    摘要翻译： 通过从初始变换参数估计检查误差来检测离页条件或无效传感器位置数据。 如果遇到异常大的错误，传感器的读数（位置数据）可能无效或传感器不在页面上。 然后将识别和移除无效的传感器数据。 最后，转换参数将仅使用有效的传感器位置数据重新估计。 通过考虑传感器升力情况，使用加权最小二乘法最小化。 如果传感器被提起，与传感器相关的误差的重量将被设置为小的重量或零。 还考虑了加权传感器误差时传感器位置的几何特性。 执行传感器数据和相关错误的置信度测量。 可信度测量来自95％置信水平的误差椭圆。

    Nano-structured particles with high thermal stability
    7.
    发明授权
    Nano-structured particles with high thermal stability 有权
    具有高热稳定性的纳米结构颗粒

    公开(公告)号：US07125536B2

    公开(公告)日：2006-10-24

    申请号：US10773941

    申请日：2004-02-06

    申请人： Guoyi Fu ,  BillieJo Monk ,  Corinne Lehaut

    发明人： Guoyi Fu ,  BillieJo Monk ,  Corinne Lehaut

    IPC分类号： B01J21/00 ,  B01J23/00 ,  C01G1/00 ,  C01G25/00

    CPC分类号： B01J21/066 ,  B01J21/06 ,  B01J27/188 ,  B01J35/023 ,  B82Y30/00 ,  C01G25/00 ,  C01G25/02 ,  C01P2002/72 ,  C01P2004/64 ,  C01P2006/12 ,  C01P2006/16 ,  C01P2006/17 ,  Y10S977/773 ,  Y10S977/775 ,  Y10S977/811

    摘要： This invention relates to a composition comprising nano-structured metal oxide particles (particularly, zirconia) and at least one stabilizing agent, a method to produce the composition, and a method to produce the thermally stable nano-structured particles. The method to produce the nano-structured particles comprises first preparing a base solution and a nanoparticle precursor solution, then combining these solutions at a final pH 7 or greater to precipitate a colloidal hydrous oxide. The colloidal hydrous oxide is then treated with at least one silicate, phosphate, or aluminum phosphate stabilizing agent and dried. These nano-structured particle products have high thermal stability and are particularly advantageous in applications as catalysts or catalyst supports that operate at high temperatures.

    摘要翻译： 本发明涉及包含纳米结构金属氧化物颗粒（特别是氧化锆）和至少一种稳定剂的组合物，制备该组合物的方法和一种制备该热稳定纳米结构颗粒的方法。 制备纳米结构颗粒的方法包括首先制备碱溶液和纳米颗粒前体溶液，然后将这些溶液在最终pH 7或更高的pH值下混合以沉淀出胶体水合氧化物。 然后用至少一种硅酸盐，磷酸盐或磷酸铝稳定剂处理胶体水合氧化物并干燥。 这些纳米结构的颗粒产品具有高热稳定性，并且在作为在高温下操作的催化剂或催化剂载体的应用中是特别有利的。