利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

7 条记录 (耗时 0.023 秒)

    METHOD AND APPARATUS FOR INSPECTING AN OBJECT EMPLOYING MACHINE VISION
    3.
    发明申请
    METHOD AND APPARATUS FOR INSPECTING AN OBJECT EMPLOYING MACHINE VISION 有权
    检查使用机器目标的方法和装置

    公开(公告)号：US20160205283A1

    公开(公告)日：2016-07-14

    申请号：US14592135

    申请日：2015-01-08

    申请人： GM GLOBAL TECHNOLOGY OPERATIONS LLC ,  SungKyunKwan University Foundation for Corporate Collaboration

    发明人： Jaewoong Kim ,  Sukhan Lee ,  Jianying Shi

    IPC分类号： H04N1/21 ,  G06K9/62 ,  G06K9/52 ,  G06T7/00 ,  G06K9/46

    CPC分类号： H04N1/2129 ,  G06K9/4604 ,  G06K9/4661 ,  G06K9/52 ,  G06K9/6218 ,  G06T7/0004 ,  G06T7/13 ,  G06T7/181

    摘要： A machine vision system including a digital camera can be employed to inspect an object in a field of view, including capturing an original digital image including a multiplicity of pixels and associated light intensities for the field of view including the object. A bitmap image file is generated, and a mean value and a standard deviation of the light intensities of the multiplicity of pixels of the bitmap image file for the original digital image are dynamically determined. New image files are generated, each including a portion of the multiplicity of pixels having associated light intensities within a prescribed range of light intensities defined by the mean value and the standard deviation. Line segments are extracted from each of the new image files, and the extracted line segments from the new image files are merged and clustered to generate integral lines based thereon.

    摘要翻译： 可以采用包括数字照相机的机器视觉系统来检查视场中的物体，包括捕获包括多个像素的原始数字图像和用于包括对象的视野的相关联的光强度。 生成位图图像文件，动态地确定原始数字图像的位图图像文件的多个像素的光强度的平均值和标准偏差。 产生新的图像文件，每个图像文件包括在由平均值和标准偏差定义的光强度的规定范围内的具有相关联的光强度的多个像素的一部分。 从每个新的图像文件中提取线段，并且将来自新图像文件的提取的线段合并并聚类以基于此生成积分线。

    Method and system for determining optimal exposure of structured light based 3D camera
    5.
    再颁专利
    Method and system for determining optimal exposure of structured light based 3D camera 有权

    公开(公告)号：USRE48595E1

    公开(公告)日：2021-06-15

    申请号：US16121341

    申请日：2018-09-04

    申请人： SUNGKYUNKWAN UNIVERSITY FOUNDATION FOR CORPORATE COLLABORATION

    发明人： Sukhan Lee ,  Moon Wook Ryu ,  Dae Sik Kim

    IPC分类号： G03B7/00

    摘要： Provided are a method and system for determining an optimal exposure of a structured light based 3D camera. The system includes a projecting means for illuminating a predetermined pattern on a target object, an image capturing means for capturing an image of the target object with the pattern projected, and a processing means for reconstructing 3D data for the target object by identifying the pattern of the captured images from the image capturing means. The system automatically determines an optimal exposure of the structured light based 3D camera system through analyzing the captured image of the target object.

    METHOD AND APPARATUS FOR INSPECTING AN OBJECT EMPLOYING MACHINE VISION
    6.
    发明申请
    METHOD AND APPARATUS FOR INSPECTING AN OBJECT EMPLOYING MACHINE VISION 有权
    检查使用机器目标的方法和装置

    公开(公告)号：US20160202050A1

    公开(公告)日：2016-07-14

    申请号：US14592125

    申请日：2015-01-08

    申请人： GM Global Technology Operations LLC ,  SungyKyunKwan University Foundation for Corporate Collaboration

    发明人： Sukhan Lee ,  Quang-Lam Bui ,  Jianying Shi

    IPC分类号： G01B11/25

    CPC分类号： G01B11/2513

    摘要： A machine vision system including a digital camera can be employed to inspect an object in a field of view. This includes projecting digitally-generated light patterns including first and second boundary patterns and first and second spatial patterns onto the object in the field of view. Images associated with the projected light patterns including the object are captured. Spatial cells are found in the field of view by matching codes in the first and second spatial patterns to boundaries determined based upon one of the first and second boundary patterns. The spatial cells are found in the field of view by matching codes in the spatial patterns to boundaries determined based upon the boundary patterns. The spatial cells are decoded and matched to the boundaries. Three-dimensional (3D) point cloud data of the object is generated based upon the decoded spatial cells matched to the boundaries.

    摘要翻译： 可以使用包括数字照相机的机器视觉系统来在视场中检查物体。 这包括在视场中将包括第一和第二边界图案以及第一和第二空间图案的数字生成的光图案投影到对象上。 捕获与包括物体在内的投影光图案相关联的图像。 通过将第一和第二空间图案中的代码与基于第一和第二边界图案之一确定的边界匹配，在视野中找到空间单元。 通过将空间图案中的代码与基于边界图案确定的边界匹配，在视场中找到空间单元格。 空间单元被解码并与边界匹配。 基于与边界匹配的解码空间单元，生成对象的三维（3D）点云数据。

    Method and apparatus for inspecting an object employing machine vision
    7.
    发明授权
    Method and apparatus for inspecting an object employing machine vision 有权
    用于检查使用机器视觉的物体的方法和装置

    公开(公告)号：US09500475B2

    公开(公告)日：2016-11-22

    申请号：US14592125

    申请日：2015-01-08

    申请人： GM GLOBAL TECHNOLOGY OPERATIONS LLC ,  SungyKyunKwan University Foundation for Corporate Collaboration

    发明人： Sukhan Lee ,  Quang-Lam Bui ,  Jianying Shi

    IPC分类号： G06K7/10 ,  G01B11/25

    CPC分类号： G01B11/2513

    摘要： A machine vision system including a digital camera can be employed to inspect an object in a field of view. This includes projecting digitally-generated light patterns including first and second boundary patterns and first and second spatial patterns onto the object in the field of view. Images associated with the projected light patterns including the object are captured. Spatial cells are found in the field of view by matching codes in the first and second spatial patterns to boundaries determined based upon one of the first and second boundary patterns. The spatial cells are found in the field of view by matching codes in the spatial patterns to boundaries determined based upon the boundary patterns. The spatial cells are decoded and matched to the boundaries. Three-dimensional (3D) point cloud data of the object is generated based upon the decoded spatial cells matched to the boundaries.

    摘要翻译： 可以使用包括数字照相机的机器视觉系统来在视场中检查物体。 这包括在视场中将包括第一和第二边界图案以及第一和第二空间图案的数字生成的光图案投影到对象上。 捕获与包括物体在内的投影光图案相关联的图像。 通过将第一和第二空间图案中的代码与基于第一和第二边界图案之一确定的边界匹配，在视野中找到空间单元。 通过将空间图案中的代码与基于边界图案确定的边界匹配，在视场中找到空间单元格。 空间单元被解码并与边界匹配。 基于与边界匹配的解码空间单元，生成对象的三维（3D）点云数据。