公开(公告)号：US20190308326A1

公开(公告)日：2019-10-10

申请号：US16448925

申请日：2019-06-21

Applicant: Cognex Corporation

Inventor： Lifeng Liu ,  Cyril C. Marrion ,  Tian Gan ,  David Michael ,  Han Xiao

IPC: B25J9/16 ,  G06T7/73 ,  G06T7/80 ,  G06T7/70

Abstract: Described are machine vision systems and methods for simultaneous kinematic and hand-eye calibration. A machine vision system includes a robot and a 3D sensor in communication with a control system. The control system is configured to move the robot to poses, and for each pose: capture a 3D image of calibration target features and robot joint angles. The control system is configured to obtain initial values for robot calibration parameters, and determine initial values for hand-eye calibration parameters based on the initial values for the robot calibration parameters, the 3D image, and joint angles. The control system is configured to determine final values for the hand-eye calibration parameters and robot calibration parameters by refining the hand-eye calibration parameters and robot calibration parameters to minimize a cost function.

公开(公告)号：US20170132807A1

公开(公告)日：2017-05-11

申请号：US15223436

申请日：2016-07-29

Applicant: Cognex Corporation

Inventor： Guruprasad Shivaram ,  Cyril C. Marrion, Jr. ,  Lifeng Liu ,  Tuotuo Li

IPC: G06T7/80 ,  B25J9/16 ,  G06T7/73 ,  G06T7/33 ,  H04N5/247 ,  G06K9/46

CPC classification number: G06T7/80 ,  B25J9/1692 ,  B25J9/1697 ,  G05B2219/39039 ,  G06K9/4604 ,  G06T7/337 ,  G06T7/344 ,  G06T7/74 ,  G06T2207/30164 ,  H04N5/247 ,  Y10S901/47

Abstract: This invention provides a system and method that ties the coordinate spaces at the two locations together during calibration time using features on a runtime workpiece instead of a calibration target. Three possible scenarios are contemplated: wherein the same workpiece features are imaged and identified at both locations; wherein the imaged features of the runtime workpiece differ at each location (with a CAD or measured workpiece rendition available); and wherein the first location containing a motion stage has been calibrated to the motion stage using hand-eye calibration and the second location is hand-eye calibrated to the same motion stage by transferring the runtime part back and forth between locations. Illustratively, the quality of the first two techniques can be improved by running multiple runtime workpieces each with a different pose, extracting and accumulating such features at each location; and then using the accumulated features to tie the two coordinate spaces.

公开(公告)号：US20130155199A1

公开(公告)日：2013-06-20

申请号：US13714524

申请日：2012-12-14

Applicant: Cognex Corporation

Inventor： Lifeng Liu ,  Cyril C. Marrion

IPC: H04N13/02

CPC classification number: H04N13/239 ,  G06T7/85 ,  G06T2207/10012 ,  G06T2207/30108

Abstract: Described are methods, systems, and apparatus, including computer program products for finding correspondences of one or more parts in a camera image of two or more cameras. For a first part in a first camera image of a first camera, a first 3D ray that is a first back-projection of a first feature coordinate of the first part in the first camera image to a 3D physical space is calculated. For a second part in a second camera image of a second camera, a second 3D ray that is a second back-projection of a second feature coordinate of the second part in the second camera image to the 3D physical space is calculated, wherein the first feature coordinate and the second feature coordinate correspond to a first feature as identified in a model. A first distance between the first 3D ray and the second 3D ray is calculated.

Abstract translation: 描述了方法，系统和装置，包括用于找到两个或更多个相机的相机图像中的一个或多个部分的对应的计算机程序产品。 对于第一相机的第一相机图像中的第一部分，计算作为第一相机图像中的第一部分的第一特征坐标的第一后投影到3D物理空间的第一3D投影。 对于第二相机的第二相机图像中的第二部分，计算作为第二相机图像中的第二部分的第二特征坐标与3D物理空间的第二背投影的第二3D射线，其中第一 特征坐标和第二特征坐标对应于在模型中识别的第一特征。 计算第一3D射线和第二3D射线之间的第一距离。

公开(公告)号：US11049280B2

公开(公告)日：2021-06-29

申请号：US16410672

申请日：2019-05-13

Applicant: Cognex Corporation

Inventor： Guruprasad Shivaram ,  Cyril C. Marrion, Jr. ,  Lifeng Liu ,  Tuotuo Li

IPC: G06T7/80 ,  B25J9/16 ,  G06T7/73 ,  G06T7/33 ,  G06K9/46 ,  H04N5/247

Abstract: This invention provides a system and method that ties the coordinate spaces at the two locations together during calibration time using features on a runtime workpiece instead of a calibration target. Three possible scenarios are contemplated: wherein the same workpiece features are imaged and identified at both locations; wherein the imaged features of the runtime workpiece differ at each location (with a CAD or measured workpiece rendition available); and wherein the first location containing a motion stage has been calibrated to the motion stage using hand-eye calibration and the second location is hand-eye calibrated to the same motion stage by transferring the runtime part back and forth between locations. Illustratively, the quality of the first two techniques can be improved by running multiple runtime workpieces each with a different pose, extracting and accumulating such features at each location; and then using the accumulated features to tie the two coordinate spaces.

公开(公告)号：US10097811B2

公开(公告)日：2018-10-09

申请号：US13714524

申请日：2012-12-14

Applicant: Cognex Corporation

Inventor： Lifeng Liu ,  Cyril C. Marrion

IPC: H04N13/239 ,  G06T7/80

Abstract: Described are methods, systems, and apparatus, including computer program products for finding correspondences of one or more parts in a camera image of two or more cameras. For a first part in a first camera image of a first camera, a first 3D ray that is a first back-projection of a first feature coordinate of the first part in the first camera image to a 3D physical space is calculated. For a second part in a second camera image of a second camera, a second 3D ray that is a second back-projection of a second feature coordinate of the second part in the second camera image to the 3D physical space is calculated, wherein the first feature coordinate and the second feature coordinate correspond to a first feature as identified in a model. A first distance between the first 3D ray and the second 3D ray is calculated.

公开(公告)号：US20160039096A1

公开(公告)日：2016-02-11

申请号：US14921731

申请日：2015-10-23

Applicant: Cognex Corporation

Inventor： Aaron S. Wallack ,  Lifeng Liu ,  Xiangyun Ye

IPC: B25J9/16 ,  G06T7/00

Abstract: 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.

Abstract translation: 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。

公开(公告)号：US09124873B2

公开(公告)日：2015-09-01

申请号：US14062718

申请日：2013-10-24

Applicant: Cognex Corporation

Inventor： Lifeng Liu ,  Aaron S. Wallack ,  Cyril C. Marrion, Jr. ,  David J. Michael

IPC: G06K9/00 ,  G06K9/36 ,  H04N13/02 ,  G06K9/20 ,  G06T7/00

CPC classification number: H04N13/204 ,  G06K9/209 ,  G06T7/75 ,  G06T7/80 ,  G06T2207/10012 ,  G06T2207/10056 ,  G06T2207/30164 ,  G06T2207/30208

Abstract: This invention provides a system and method for determining correspondence between camera assemblies in a 3D vision system implementation having a plurality of cameras arranged at different orientations with respect to a scene involving microscopic and near microscopic objects under manufacture moved by a manipulator, so as to acquire contemporaneous images of a runtime object and determine the pose of the object for the purpose of guiding manipulator motion. At least one of the camera assemblies includes a non-perspective lens. The searched 2D object features of the acquired non-perspective image, corresponding to trained object features in the non-perspective camera assembly can be combined with the searched 2D object features in images of other camera assemblies, based on their trained object features to generate a set of 3D features and thereby determine a 3D pose of the object.

Abstract translation: 本发明提供一种用于确定3D视觉系统实现中的相机组件之间的对应关系的系统和方法，其具有相对于由机械手移动的涉及在制造过程中的微观和近似微观物体的场景以不同取向布置的多个照相机，以便获得 运行时对象的同时期图像，并且为了引导操纵器运动而确定对象的姿态。 至少一个相机组件包括非透视透镜。 所获取的非透视图像的2D对象特征对应于非透视摄像机组件中经过训练的对象特征可以基于其训练对象特征与其他相机组件的图像中的搜索到的2D对象特征组合，以产生 一组3D特征，从而确定对象的3D姿态。

公开(公告)号：US20140118500A1

公开(公告)日：2014-05-01

申请号：US14062718

申请日：2013-10-24

Applicant: Cognex Corporation

Inventor： Lifeng Liu ,  Aaron S. Wallack ,  Cyril C. Marrion, JR. ,  David J. Michael

IPC: G06T7/00 ,  H04N13/02

CPC classification number: H04N13/204 ,  G06K9/209 ,  G06T7/75 ,  G06T7/80 ,  G06T2207/10012 ,  G06T2207/10056 ,  G06T2207/30164 ,  G06T2207/30208

Abstract: This invention provides a system and method for determining correspondence between camera assemblies in a 3D vision system implementation having a plurality of cameras arranged at different orientations with respect to a scene involving microscopic and near microscopic objects under manufacture moved by a manipulator, so as to acquire contemporaneous images of a runtime object and determine the pose of the object for the purpose of guiding manipulator motion. At least one of the camera assemblies includes a non-perspective lens. The searched 2D object features of the acquired non-perspective image, corresponding to trained object features in the non-perspective camera assembly can be combined with the searched 2D object features in images of other camera assemblies, based on their trained object features to generate a set of 3D features and thereby determine a 3D pose of the object.

Abstract translation: 本发明提供一种用于确定3D视觉系统实现中的相机组件之间的对应关系的系统和方法，其具有相对于由机械手移动的涉及在制造过程中的微观和近似微观物体的场景以不同取向布置的多个照相机，以便获得 运行时对象的同时期图像，并且为了引导操纵器运动而确定对象的姿态。 至少一个相机组件包括非透视透镜。 所获取的非透视图像的2D对象特征对应于非透视摄像机组件中经过训练的对象特征可以基于其训练对象特征与其他相机组件的图像中的搜索到的2D对象特征组合，以产生 一组3D特征，从而确定对象的3D姿态。