专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20160203387A1 VISION SYSTEM AND ANALYTICAL METHOD FOR PLANAR SURFACE SEGMENTATION 审中-公开
标题翻译：用于平面表面分割的视觉系统和分析方法
公开(公告)号：US20160203387A1
公开(公告)日：2016-07-14
申请号：US14592133
申请日：2015-01-08
申请人： GM GLOBAL TECHNOLOGY OPERATIONS LLC , SungKyunKwan University Foundation for Corporate Collaboration
发明人： Sukhan Lee , Hung Huu Nguyen , Jaewoong Kim , Jianying Shi
IPC分类号： G06K9/52 , G06T3/00 , G06T7/20 , H04N13/02 , G06T7/00
CPC分类号： G06K9/52 , G01B11/00 , G01B11/22 , G01B11/28 , G01C11/00 , G01C11/025 , G06K9/00201 , G06K9/00214 , G06K9/46 , G06K9/6209 , G06K2009/4666 , G06K2009/487 , G06T3/00 , G06T7/00 , G06T7/0004 , G06T7/13 , G06T7/187 , G06T7/20 , G06T7/50 , G06T7/521 , G06T7/593 , G06T7/60 , G06T7/62 , G06T7/73 , G06T15/00 , G06T17/00 , G06T17/05 , G06T17/20 , G06T17/205 , G06T2200/04 , G06T2200/08 , G06T2207/10028 , G06T2207/20168 , H04N2013/0081 , H04N2013/0092
摘要： A vision system is configured to dynamically inspect an object in a field of view. This includes capturing, using a camera, three-dimensional (3D) point cloud data of the field of view and transforming each of the points of the 3D point cloud data into a plurality of tangential surface vectors. Surface normal vectors are determined for each of the points of the 3D point cloud data based upon the plurality of tangential surface vectors. Distribution peaks in the surface normal vectors are detected employing a unit sphere mesh. Parallel planes are separated using the distance distribution peaks. A radially bounded nearest neighbor strategy combined with a process of nearest neighbor searching based upon cell division is executed to segment a planar patch. A planar surface is identified based upon the segmented planar patch.
摘要翻译：视觉系统被配置为在视野中动态地检查对象。这包括使用相机捕获视场的三维（3D）点云数据，并将3D点云数据的每个点变换为多个切向表面向量。基于多个切向表面向量，针对3D点云数据的每个点确定表面法向矢量。使用单位球网检测表面法向量中的分布峰。使用距离分布峰分离平行平面。执行与基于细胞分裂的最近邻搜索的过程组合的径向有界最近邻策略来分割平面补片。基于分段的平面贴片识别平面。

2. 发明授权

US10115035B2 Vision system and analytical method for planar surface segmentation 有权
公开(公告)号：US10115035B2
公开(公告)日：2018-10-30
申请号：US14592133
申请日：2015-01-08
申请人： GM GLOBAL TECHNOLOGY OPERATIONS LLC , SungKyunKwan University Foundation for Corporate Collaboration
发明人： Sukhan Lee , Hung Huu Nguyen , Jaewoong Kim , Jianying Shi
IPC分类号： G06K9/00 , G06K9/52 , G06K9/46 , G06K9/62 , G06K9/48 , G06T3/00 , G06T7/00 , G06T7/20 , G06T7/73 , G06T7/13 , G06T7/50 , G06T7/60 , G06T7/62 , G06T7/187 , G06T7/521 , G06T7/593 , G06T15/00 , G06T17/00 , G06T17/05 , G06T17/20 , G01B11/00 , G01B11/22 , G01B11/28 , G01C11/00 , G01C11/02 , H04N13/00
摘要： A vision system is configured to dynamically inspect an object in a field of view. This includes capturing, using a camera, three-dimensional (3D) point cloud data of the field of view and transforming each of the points of the 3D point cloud data into a plurality of tangential surface vectors. Surface normal vectors are determined for each of the points of the 3D point cloud data based upon the plurality of tangential surface vectors. Distribution peaks in the surface normal vectors are detected employing a unit sphere mesh. Parallel planes are separated using the distance distribution peaks. A radially bounded nearest neighbor strategy combined with a process of nearest neighbor searching based upon cell division is executed to segment a planar patch. A planar surface is identified based upon the segmented planar patch.

3. 发明授权

US09628659B2 Method and apparatus for inspecting an object employing machine vision 有权
公开(公告)号：US09628659B2
公开(公告)日：2017-04-18
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： G06K9/00 , H04N1/21 , G06K9/46 , G06K9/52 , G06K9/62 , G06T7/00
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.

4. 发明申请

US20160205283A1 METHOD AND APPARATUS FOR INSPECTING AN OBJECT EMPLOYING MACHINE VISION 有权
标题翻译：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。

5. 再颁专利

USRE48595E1 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.

6. 发明授权

US09500475B2 Method and apparatus for inspecting an object employing machine vision 有权
标题翻译：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。

7. 发明申请

US20160202050A1 METHOD AND APPARATUS FOR INSPECTING AN OBJECT EMPLOYING MACHINE VISION 有权
标题翻译：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。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式