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

US20110157373A1 SYSTEM AND METHOD FOR RUNTIME DETERMINATION OF CAMERA MISCALIBRATION 审中-公开
标题翻译：用于运动测定摄像机分离的系统和方法
公开(公告)号：US20110157373A1
公开(公告)日：2011-06-30
申请号：US12647192
申请日：2009-12-24
申请人： Xiangyun Ye , David Y. Li , Guruprasad Shivaram , David J. Michael
发明人： Xiangyun Ye , David Y. Li , Guruprasad Shivaram , David J. Michael
IPC分类号： H04N17/00
CPC分类号： G06T7/85 , G06T2207/10012 , G06T2207/30108
摘要： This invention provides a system and method for runtime determination (self-diagnosis) of camera miscalibration (accuracy), typically related to camera extrinsics, based on historical statistics of runtime alignment scores for objects acquired in the scene, which are defined based on matching of observed and expected image data of trained object models. This arrangement avoids a need to cease runtime operation of the vision system and/or stop the production line that is served by the vision system to diagnose if the system's camera(s) remain calibrated. Under the assumption that objects or features inspected by the vision system over time are substantially the same, the vision system accumulates statistics of part alignment results and stores intermediate results to be used as indicator of current system accuracy. For multi-camera vision systems, cross validation is illustratively employed to identify individual problematic cameras. The system and method allows for faster, less-expensive and more-straightforward diagnosis of vision system failures related to deteriorating camera calibration.
摘要翻译：本发明提供了一种用于基于场景中获取的对象的运行时对准分数的历史统计信息的通常与摄像机外部特征相关的摄像机误差（精确度）的运行时确定（自诊断）的系统和方法，其基于训练对象模型的观察和预期图像数据。这种安排避免了停止视觉系统的运行时操作和/或停止由视觉系统服务的生产线来诊断系统的相机是否保持校准的需要。在视觉系统随时间检查的对象或特征基本相同的假设下，视觉系统累积部分对齐结果的统计信息，并存储要用作当前系统精度指标的中间结果。对于多摄像机视觉系统，交叉验证被说明性地用于识别个别有问题的摄像机。该系统和方法允许对与相机校准恶化相关的视觉系统故障的更快，更便宜和更直接的诊断。

2. 发明授权

US09734419B1 System and method for validating camera calibration in a vision system 有权
公开(公告)号：US09734419B1
公开(公告)日：2017-08-15
申请号：US12346773
申请日：2008-12-30
申请人： Xiangyun Ye , Aaron S. Wallack , Guruprasad Shivaram , Cyril C. Marrion , David Y. Li
发明人： Xiangyun Ye , Aaron S. Wallack , Guruprasad Shivaram , Cyril C. Marrion , David Y. Li
IPC分类号： G06K9/20
CPC分类号： G06K9/209 , G06T7/85
摘要： This invention provides a system and method to validate the accuracy of camera calibration in a single or multiple-camera embodiment, utilizing either 2D cameras or 3D imaging sensors. It relies upon an initial calibration process that generates and stores camera calibration parameters and residual statistics based upon images of a first calibration object. A subsequent validation process (a) acquires images of the first calibration object or a second calibration object having a known pattern and dimensions; (b) extracts features of the images of the first calibration object or the second calibration object; (c) predicts positions expected of features of the first calibration object or the second calibration object using the camera calibration parameters; and (d) computes a set of discrepancies between positions of the extracted features and the predicted positions of the features. The validation process then uses the computed set of discrepancies in a decision process that determines whether at least one of the discrepancies exceeds a predetermined threshold value. If so, recalibration is required. Where multiple cameras are employed, extrinsic parameters are determined and used in conjunction with the intrinsics.

3. 发明授权

US08442304B2 System and method for three-dimensional alignment of objects using machine vision 有权
标题翻译：使用机器视觉对象的三维对准的系统和方法
公开(公告)号：US08442304B2
公开(公告)日：2013-05-14
申请号：US12345130
申请日：2008-12-29
申请人： Cyril C. Marrion , Nigel J. Foster , Lifeng Liu , David Y. Li , Guruprasad Shivaram , Aaron S. Wallack , Xiangyun Ye
发明人： Cyril C. Marrion , Nigel J. Foster , Lifeng Liu , David Y. Li , Guruprasad Shivaram , Aaron S. Wallack , Xiangyun Ye
IPC分类号： G06K9/00
CPC分类号： G06K9/00214 , G06K9/6211
摘要： This invention provides a system and method for determining the three-dimensional alignment of a modeled object or scene. A 3D (stereo) sensor system views the object to derive a runtime 3D representation of the scene containing the object. Rectified images from each stereo head are preprocessed to enhance their edge features. 3D points are computed for each pair of cameras to derive a 3D point cloud. The amount of 3D data from the point cloud is reduced by extracting higher-level geometric shapes (HLGS), such as line segments. Found HLGS from runtime are corresponded to HLGS on the model to produce candidate 3D poses. A coarse scoring process prunes the number of poses. The remaining candidate poses are then subjected to a further more-refined scoring process. These surviving candidate poses are then verified whereby the closest match is the best refined three-dimensional pose.
摘要翻译：本发明提供了一种用于确定建模对象或场景的三维对准的系统和方法。 3D（立体声）传感器系统查看对象以导出包含对象的场景的运行时3D表示。来自每个立体声头的整流图像被预处理以增强其边缘特征。为每对相机计算3D点以导出3D点云。通过提取诸如线段的较高级几何形状（HLGS）来减少来自点云的3D数据量。从运行时发现的HLGS对应于模型上的HLGS，以产生候选的3D姿势。粗略的评分过程会减少姿势的数量。然后，剩下的候选姿势进一步进行更精细的评分过程。然后验证这些存活的候选姿势，从而最接近的匹配是最好的精制三维姿态。

4. 发明申请

US20100166294A1 SYSTEM AND METHOD FOR THREE-DIMENSIONAL ALIGNMENT OF OBJECTS USING MACHINE VISION 有权
标题翻译：使用机器视觉的三维对准对象的系统和方法
公开(公告)号：US20100166294A1
公开(公告)日：2010-07-01
申请号：US12345130
申请日：2008-12-29
申请人： Cyril C. Marrion , Nigel J. Foster , Lifeng Liu , David Y. Li , Guruprasad Shivaram , Aaron S. Wallack , Xiangyun Ye
发明人： Cyril C. Marrion , Nigel J. Foster , Lifeng Liu , David Y. Li , Guruprasad Shivaram , Aaron S. Wallack , Xiangyun Ye
IPC分类号： G06K9/00
CPC分类号： G06K9/00214 , G06K9/6211
摘要： This invention provides a system and method for determining the three-dimensional alignment of a modeledobject or scene. After calibration, a 3D (stereo) sensor system views the object to derive a runtime 3D representation of the scene containing the object. Rectified images from each stereo head are preprocessed to enhance their edge features. A stereo matching process is then performed on at least two (a pair) of the rectified preprocessed images at a time by locating a predetermined feature on a first image and then locating the same feature in the other image. 3D points are computed for each pair of cameras to derive a 3D point cloud. The 3D point cloud is generated by transforming the 3D points of each camera pair into the world 3D space from the world calibration. The amount of 3D data from the point cloud is reduced by extracting higher-level geometric shapes (HLGS), such as line segments. Found HLGS from runtime are corresponded to HLGS on the model to produce candidate 3D poses. A coarse scoring process prunes the number of poses. The remaining candidate poses are then subjected to a further more-refined scoring process. These surviving candidate poses are then verified by, for example, fitting found 3D or 2D points of the candidate poses to a larger set of corresponding three-dimensional or two-dimensional model points, whereby the closest match is the best refined three-dimensional pose.
摘要翻译：本发明提供一种用于确定建模对象或场景的三维对准的系统和方法。校准后，3D（立体声）传感器系统会查看对象以导出包含对象的场景的运行时3D表示。来自每个立体声头的整流图像被预处理以增强其边缘特征。然后，通过在第一图像上定位预定特征，然后将另一图像中的相同特征定位，对至少两（一对）经整流的预处理图像执行立体匹配处理。为每对相机计算3D点以导出3D点云。 3D点云是通过将世界三维空间中的每个摄像机对的3D点变换为世界校准而产生的。通过提取诸如线段的较高级几何形状（HLGS）来减少来自点云的3D数据量。从运行时发现的HLGS对应于模型上的HLGS，以产生候选的3D姿势。粗略的评分过程会减少姿势的数量。然后，剩下的候选姿势进一步进行更精细的评分过程。然后通过例如将候选姿势的3D或2D点拟合到较大的一组相应的三维或二维模型点来验证这些幸存的候选姿势，由此最接近的匹配是最佳精细三维姿态。

5. 发明申请

US20130112752A1 Method And Apparatus For Performing Different Decoding Algorithms In Different Locations 有权
标题翻译：用于在不同位置执行不同解码算法的方法和装置
公开(公告)号：US20130112752A1
公开(公告)日：2013-05-09
申请号：US13288098
申请日：2011-11-03
申请人： James Negro , Xiangyun Ye
发明人： James Negro , Xiangyun Ye
IPC分类号： G06K7/14
CPC分类号： G06K7/1447 , G06K7/10722 , G06K7/10881 , G06K7/1404 , G06K7/1417 , G06K9/18 , G06K19/06037
摘要： A method and apparatus for decoding codes applied to objects for use with an image sensor that includes a two dimensional field of view (FOV), the method comprising the steps of providing a processor programmed to perform the steps of obtaining an image of the FOV and applying different decode algorithms to code candidates in the obtained image to attempt to decode the code candidates wherein the decode algorithm applied to each candidate is a function of the location of the code candidate in the FOV.
摘要翻译：一种用于对应用于包括二维视场（FOV）的图像传感器使用的对象的代码进行解码的方法和装置，所述方法包括以下步骤：提供被编程为执行以下步骤的处理器：获得所述FOV的图像;以及应用不同的解码算法对所获得的图像中的候选进行编码，以尝试对代码候选进行解码，其中应用于每个候选的解码算法是FOV中代码候选的位置的函数。

6. 发明申请

US20110280472A1 SYSTEM AND METHOD FOR ROBUST CALIBRATION BETWEEN A MACHINE VISION SYSTEM AND A ROBOT 有权
标题翻译：机器视觉系统与机器人之间的稳健校准的系统和方法
公开(公告)号：US20110280472A1
公开(公告)日：2011-11-17
申请号：US12780119
申请日：2010-05-14
申请人： Aaron S. Wallack , Lifeng Liu , Xiangyun Ye
发明人： Aaron S. Wallack , Lifeng Liu , Xiangyun Ye
IPC分类号： G06T7/00
CPC分类号： B25J9/1692 , B25J9/1607 , B25J9/1697 , G05B2219/39008 , G05B2219/39022 , G05B2219/39045 , G05B2219/39057 , G06T7/80 , Y10S901/09
摘要： A system and method for robustly calibrating a vision system and a robot is provided. The system and method enables a plurality of cameras to be calibrated into a robot base coordinate system to enable a machine vision/robot control system to accurately identify the location of objects of interest within robot base coordinates.
摘要翻译：提供了用于鲁棒校准视觉系统和机器人的系统和方法。该系统和方法使得能够将多个摄像机校准成机器人基座坐标系，以使机器视觉/机器人控制系统能够精确地识别机器人基准坐标内的感兴趣物体的位置。

7. 发明申请

US20090090781A1 Decoding distorted symbols 有权
标题翻译：解码失真的符号
公开(公告)号：US20090090781A1
公开(公告)日：2009-04-09
申请号：US11312703
申请日：2005-12-20
申请人： Xiangyun Ye , Sateesha Nadabar
发明人： Xiangyun Ye , Sateesha Nadabar
IPC分类号： G06K7/10 , G06K9/40
CPC分类号： G06T3/00 , G06K7/14
摘要： A method is provided for reading distorted optical symbols using known locating and decoding methods, without requiring a separate and elaborate camera calibration procedure, without excessive computational complexity, and without compromised burst noise handling. The invention exploits a distortion-tolerant method for locating and decoding 2D code symbols to provide a correspondence between a set of points in an acquired image and a set of points in the symbol. A coordinate transformation is then constructed using the correspondence, and run-time images are corrected using the coordinate transformation. Each corrected run-time image provides a distortion-free representation of a symbol that can be read by traditional code readers that normally cannot read distorted symbols. The method can handle both optical distortion and printing distortion. The method is applicable to “portable” readers when an incident angle with the surface is maintained, the reader being disposed at any distance from the surface.
摘要翻译：提供了一种使用已知的定位和解码方法来读取失真的光学符号的方法，而不需要单独的精心设计的相机校准过程，而没有过多的计算复杂度，并且没有受到破坏的突发噪声处理。本发明利用了一种用于定位和解码2D码符号以提供所获取的图像中的一组点与符号中的一组点之间的对应关系的容错方法。然后使用对应关系构建坐标变换，并使用坐标变换校正运行时图像。每个校正的运行时间图像提供了可以由通常不能读取失真的符号的传统代码读取器读取的符号的无失真表示。该方法可以处理光学失真和打印失真。当与表面的入射角保持时，该方法适用于“便携式”读取器，读取器被布置在与表面相距的任何距离处。

8. 发明授权

US09393694B2 System and method for robust calibration between a machine vision system and a robot 有权
标题翻译：机器视觉系统和机器人之间的鲁棒校准的系统和方法
公开(公告)号：US09393694B2
公开(公告)日：2016-07-19
申请号：US12780119
申请日：2010-05-14
申请人： Aaron S. Wallack , Lifeng Liu , Xiangyun Ye
发明人： Aaron S. Wallack , Lifeng Liu , Xiangyun Ye
IPC分类号： G06K9/00 , B25J9/16 , G06T7/00
CPC分类号： B25J9/1692 , B25J9/1607 , B25J9/1697 , G05B2219/39008 , G05B2219/39022 , G05B2219/39045 , G05B2219/39057 , G06T7/80 , Y10S901/09
摘要： A system and method for robustly calibrating a vision system and a robot is provided. The system and method enables a plurality of cameras to be calibrated into a robot base coordinate system to enable a machine vision/robot control system to accurately identify the location of objects of interest within robot base coordinates.
摘要翻译：提供了用于鲁棒校准视觉系统和机器人的系统和方法。该系统和方法使得能够将多个摄像机校准成机器人基座坐标系，以使机器视觉/机器人控制系统能够精确地识别机器人基准坐标内的感兴趣物体的位置。

9. 发明授权

US09367725B2 Method and apparatus for performing different decoding algorithms in different locations 有权
标题翻译：用于在不同位置执行不同解码算法的方法和装置
公开(公告)号：US09367725B2
公开(公告)日：2016-06-14
申请号：US13288098
申请日：2011-11-03
申请人： James Negro , Xiangyun Ye
发明人： James Negro , Xiangyun Ye
IPC分类号： G06K9/18 , G06K7/14 , G06K7/10
CPC分类号： G06K7/1447 , G06K7/10722 , G06K7/10881 , G06K7/1404 , G06K7/1417 , G06K9/18 , G06K19/06037
摘要： A method and apparatus for decoding codes applied to objects for use with an image sensor that includes a two dimensional field of view (FOV), the method comprising the steps of providing a processor programmed to perform the steps of obtaining an image of the FOV and applying different decode algorithms to code candidates in the obtained image to attempt to decode the code candidates wherein the decode algorithm applied to each candidate is a function of the location of the code candidate in the FOV.
摘要翻译：一种用于对应用于包括二维视场（FOV）的图像传感器使用的对象的代码进行解码的方法和装置，所述方法包括以下步骤：提供被编程为执行以下步骤的处理器：获得所述FOV的图像;以及应用不同的解码算法对所获得的图像中的候选进行编码，以尝试对代码候选进行解码，其中应用于每个候选的解码算法是FOV中代码候选的位置的函数。

10. 发明申请

US20140270539A1 SYSTEMS AND METHODS FOR PATTERN STITCHING AND DECODING USING MULTIPLE CAPTURED IMAGES 有权
标题翻译：使用多个捕获图像进行图案拼接和解码的系统和方法
公开(公告)号：US20140270539A1
公开(公告)日：2014-09-18
申请号：US13843057
申请日：2013-03-15
申请人： Xianju Wang , Xiangyun Ye
发明人： Xianju Wang , Xiangyun Ye
IPC分类号： G06K7/14
CPC分类号： G06K7/1417 , G06K7/1491
摘要： Systems and methods read machine readable symbols, the systems and methods capture multiple images of the symbol and can locate symbol data region(s) from an image even when the symbol data is corrupted and not decodable. Binary matrices are generated of the symbol data regions obtained from the multiple images and can be accumulated to generate a decodable image. A correspondence can be established among multiple images acquired on the same symbol when the symbol has moved from one image to the next.
摘要翻译：系统和方法读取机器可读符号，系统和方法捕获符号的多个图像，并且可以从图像中定位符号数据区域，即使符号数据已损坏且不可解码。生成从多个图像获得的符号数据区域的二进制矩阵，并且可以被累积以产生可解码的图像。当符号已经从一个图像移动到下一个图像时，可以在相同符号上获取的多个图像之间建立对应关系。

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