Patents by Inventor Guruprasad Shivaram
Guruprasad Shivaram has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11699247Abstract: 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.Type: GrantFiled: December 24, 2009Date of Patent: July 11, 2023Assignee: Cognex CorporationInventors: Xiangyun Ye, David Y. Li, Guruprasad Shivaram, David J. Michael
-
Patent number: 11544874Abstract: This invention provides a system and method for generating camera calibrations for a vision system camera along three discrete planes in a 3D volume space that uses at least two (e.g. parallel) object planes at different known heights. For any third (e.g. parallel) plane of a specified height, the system and method then automatically generates calibration data for the camera by interpolating/extrapolating from the first two calibrations. This alleviates the need to set the calibration object at more than two heights, speeding the calibration process and simplifying the user's calibration setup, and also allowing interpolation/extrapolation to heights that are space-constrained, and not readily accessible by a calibration object. The calibration plate can be calibrated at each height using a full 2D hand-eye calibration, or using a hand-eye calibration at the first height and then at a second height with translation to a known position along the height (e.g. Z) direction.Type: GrantFiled: May 22, 2020Date of Patent: January 3, 2023Assignee: Cognex CorporationInventors: Gang Liu, Guruprasad Shivaram, Cyril C. Marrion, Jr.
-
Patent number: 11072074Abstract: A vision-based manipulations system can be configured for, and can be operated with methods including, performing hand-eye calibrations at multiple workstations of the system, performing a cross-station calibration for the system, and determining relationships between the hand-eye calibrations and the cross-station calibration. In some embodiments, the system can be used to move a work object between the workstations based on the cross-station calibration.Type: GrantFiled: December 13, 2017Date of Patent: July 27, 2021Assignee: COGNEX CORPORATIONInventors: Guruprasad Shivaram, Gang Liu
-
Patent number: 11049280Abstract: 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.Type: GrantFiled: May 13, 2019Date of Patent: June 29, 2021Assignee: Cognex CorporationInventors: Guruprasad Shivaram, Cyril C. Marrion, Jr., Lifeng Liu, Tuotuo Li
-
Publication number: 20210012532Abstract: This invention provides a system and method for generating camera calibrations for a vision system camera along three discrete planes in a 3D volume space that uses at least two (e.g. parallel) object planes at different known heights. For any third (e.g. parallel) plane of a specified height, the system and method then automatically generates calibration data for the camera by interpolating/extrapolating from the first two calibrations. This alleviates the need to set the calibration object at more than two heights, speeding the calibration process and simplifying the user's calibration setup, and also allowing interpolation/extrapolation to heights that are space-constrained, and not readily accessible by a calibration object. The calibration plate can be calibrated at each height using a full 2D hand-eye calibration, or using a hand-eye calibration at the first height and then at a second height with translation to a known position along the height (e.g. Z) direction.Type: ApplicationFiled: May 22, 2020Publication date: January 14, 2021Inventors: Gang Liu, Guruprasad Shivaram, Cyril C. Marrion, JR.
-
Patent number: 10664994Abstract: This invention provides a system and method for generating camera calibrations for a vision system camera along three discrete planes in a 3D volume space that uses at least two (e.g. parallel) object planes at different known heights. For any third (e.g. parallel) plane of a specified height, the system and method then automatically generates calibration data for the camera by interpolating/extrapolating from the first two calibrations. This alleviates the need to set the calibration object at more than two heights, speeding the calibration process and simplifying the user's calibration setup, and also allowing interpolation/extrapolation to heights that are space-constrained, and not readily accessible by a calibration object. The calibration plate can be calibrated at each height using a full 2D hand-eye calibration, or using a hand-eye calibration at the first height and then at a second height with translation to a known position along the height (e.g. Z) direction.Type: GrantFiled: February 25, 2013Date of Patent: May 26, 2020Assignee: Cognex CorporationInventors: Gang Liu, Guruprasad Shivaram, Cyril C. Marrion, Jr.
-
Publication number: 20200065995Abstract: 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.Type: ApplicationFiled: May 13, 2019Publication date: February 27, 2020Inventors: Guruprasad Shivaram, Cyril C. Marrion, JR., Lifeng Liu, Tuotuo Li
-
Publication number: 20190176335Abstract: A vision-based manipulations system can be configured for, and can be operated with methods including, performing hand-eye calibrations at multiple workstations of the system, performing a cross-station calibration for the system, and determining relationships between the hand-eye calibrations and the cross-station calibration. In some embodiments, the system can be used to move a work object between the workstations based on the cross-station calibration.Type: ApplicationFiled: December 13, 2017Publication date: June 13, 2019Inventors: Guruprasad Shivaram, Gang Liu
-
Patent number: 10290118Abstract: 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.Type: GrantFiled: July 29, 2016Date of Patent: May 14, 2019Assignee: COGNEX CORPORATIONInventors: Guruprasad Shivaram, Cyril C. Marrion, Jr., Lifeng Liu, Tuotuo Li
-
Patent number: 10223589Abstract: This invention provides a system and method for guiding the workpieces to optimal positions to train an assembly system that is generally free of the use of a CMM or similar metrology device. The system and method expresses the image features of the workpieces, when they are in their respective stations, in a common coordinate system. This ability allows a user to visualize the result of assembling the workpieces without actually assembling them, in a “virtual assembly”. The virtual assembly assists guiding placement of workpieces in respective stations into a desired relative alignment. The system and method illustratively generates a composite image using the images from cameras used in guiding the workpieces that helps the user visualize how the part would appear following assembly. The user can reposition the images of workpieces in their respective stations until the composite image has a desired appearance.Type: GrantFiled: March 1, 2016Date of Patent: March 5, 2019Assignee: Cognex CorporationInventors: Guruprasad Shivaram, Willard Foster
-
Patent number: 9734419Abstract: 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.Type: GrantFiled: December 30, 2008Date of Patent: August 15, 2017Assignee: COGNEX CORPORATIONInventors: Xiangyun Ye, Aaron S. Wallack, Guruprasad Shivaram, Cyril C. Marrion, David Y. Li
-
Publication number: 20170132807Abstract: 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.Type: ApplicationFiled: July 29, 2016Publication date: May 11, 2017Inventors: Guruprasad Shivaram, Cyril C. Marrion, Jr., Lifeng Liu, Tuotuo Li
-
Patent number: 9569850Abstract: This invention provides a system and method for determining the pose of shapes that are known to a vision system that undergo both affine transformation and deformation. The object image with fiducial is acquired. The fiducial has affine parameters, including degrees of freedom (DOFs), search ranges and search step sizes, and control points with associated DOFs and step sizes. Each 2D affine parameter's search range and the distortion control points' DOFs are sampled and all combinations are obtained. The coarsely specified fiducial is transformed for each combination and a match metric is computed for the transformed fiducial, generating a score surface. Peaks are computed on this surface, as potential candidates, which are refined until a match metric is maximized. The refined representation exceeding a predetermined score is returned as potential shapes in the scene. Alternately the candidate with the best score can be used as a training fiducial.Type: GrantFiled: October 15, 2014Date of Patent: February 14, 2017Assignee: COGNEX CORPORATIONInventors: Guruprasad Shivaram, Lowell D. Jacobson, David Y. Li
-
Publication number: 20170024613Abstract: This invention provides a system and method for guiding the workpieces to optimal positions to train an assembly system that is generally free of the use of a CMM or similar metrology device. The system and method expresses the image features of the workpieces, when they are in their respective stations, in a common coordinate system. This ability allows a user to visualize the result of assembling the workpieces without actually assembling them, in a “virtual assembly”. The virtual assembly assists guiding placement of workpieces in respective stations into a desired relative alignment. The system and method illustratively generates a composite image using the images from cameras used in guiding the workpieces that helps the user visualize how the part would appear following assembly. The user can reposition the images of workpieces in their respective stations until the composite image has a desired appearance.Type: ApplicationFiled: March 1, 2016Publication date: January 26, 2017Inventors: Guruprasad Shivaram, Willard Foster
-
Publication number: 20150104068Abstract: This invention provides a system and method for determining the pose of shapes that are known to a vision system that undergo both affine transformation and deformation. The object image with fiducial is acquired. The fiducial has affine parameters, including degrees of freedom (DOFs), search ranges and search step sizes, and control points with associated DOFs and step sizes. Each 2D affine parameter's search range and the distortion control points' DOFs are sampled and all combinations are obtained. The coarsely specified fiducial is transformed for each combination and a match metric is computed for the transformed fiducial, generating a score surface. Peaks are computed on this surface, as potential candidates, which are refined until a match metric is maximized. The refined representation exceeding a predetermined score is returned as potential shapes in the scene. Alternately the candidate with the best score can be used as a training fiducial.Type: ApplicationFiled: October 15, 2014Publication date: April 16, 2015Inventors: Guruprasad Shivaram, Lowell D. Jacobson, David Y. Li
-
Patent number: 8442304Abstract: 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.Type: GrantFiled: December 29, 2008Date of Patent: May 14, 2013Assignee: Cognex CorporationInventors: Cyril C. Marrion, Nigel J. Foster, Lifeng Liu, David Y. Li, Guruprasad Shivaram, Aaron S. Wallack, Xiangyun Ye
-
Publication number: 20110157373Abstract: 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.Type: ApplicationFiled: December 24, 2009Publication date: June 30, 2011Applicant: COGNEX CORPORATIONInventors: Xiangyun Ye, David Y. Li, Guruprasad Shivaram, David J. Michael
-
Publication number: 20100166294Abstract: 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.Type: ApplicationFiled: December 29, 2008Publication date: July 1, 2010Applicant: COGNEX CORPORATIONInventors: Cyril C. Marrion, Nigel J. Foster, Lifeng Liu, David Y. Li, Guruprasad Shivaram, Aaron S. Wallack, Xiangyun Ye