Patents by Inventor David J. Michael

David J. Michael 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: 10380767
    Abstract: A system and method for selecting among 3D alignment algorithms in a 3D vision system is provided. The system and method includes a 3D camera assembly to acquire at least a runtime image defined by a 3D point cloud or runtime 3D range image having features of a runtime object and a vision system processor. A training image is provided. It is defined by a 3D point cloud or 3D range image having features of a model. A selection process is operated by the vision processor. It analyzes at least one training region of the training image having the features of the model and determines a distribution of surface normals in the at least one training region. It also selects, based upon a characteristic of the distribution, at least one 3D alignment algorithm from a plurality of available 3D alignment algorithms to align the features of the model with respect to the features of the runtime object.
    Type: Grant
    Filed: June 27, 2017
    Date of Patent: August 13, 2019
    Assignee: Cognex Corporation
    Inventors: Simon Barker, David J. Michael
  • Patent number: 10192283
    Abstract: This invention provides a system and method for determining the level of clutter in an image in a manner that is rapid, and that allows a scoring process to quickly determine whether an image is above or below an acceptable level of clutter—for example to determine if the underlying imaged runtime object surface is defective without need to perform a more in-depth analysis of the features of the image. The system and method employs clutter test points that are associated with regions on the image that should contain a low gradient magnitude, indicative of emptiness. This enables the runtime image to be analyzed quickly by mapping trained clutter test points at locations in the coordinate space in which lack of emptiness indicates clutter, and if detected, can rapidly indicate differences and/or defects that allow for the subject of the image to be accepted or rejected without further image analysis.
    Type: Grant
    Filed: December 22, 2014
    Date of Patent: January 29, 2019
    Assignee: COGNEX CORPORATION
    Inventors: Jason Davis, David J. Michael, Nathaniel R. Bogan
  • Publication number: 20180374239
    Abstract: This invention provides an easy-to-manufacture, easy-to-analyze calibration object which combines measurable and repeatable, but not necessarily accurate, 3D features—such as a two-sided calibration object/target in (e.g.) the form of a frustum, with a pair of accurate and measurable features, more particularly parallel faces separated by a precise specified thickness, so as to provide for simple field calibration of opposite-facing DS sensors. Illustratively, a composite calibration object can be constructed, which includes the two-sided frustum that has been sandblasted and anodized (to provide measurable, repeatable features), with a flange whose above/below parallel surfaces have been ground to a precise specified thickness. The 3D corner positions of the two-sided frustum are used to calibrate the two sensors in X and Y, but cannot establish absolute Z without accurate information about the thickness of the two-sided frustum; the flange provides the absolute Z information.
    Type: Application
    Filed: October 13, 2017
    Publication date: December 27, 2018
    Inventors: Aaron S. Wallack, Robert A. Wolff, David J. Michael, Ruibing Wang, Hongwei Zhu
  • Patent number: 10057498
    Abstract: This invention provides a vision system camera assembly and method for using the same that employs a light-field camera with an associated vision system image sensor and overlying microlens optics to acquire images of a scene. The camera generates a light field allowing object features at varying depths of field to be clearly imaged in a concurrent manner. In an illustrative embodiment a vision system, and associated method of use thereof, which images an object or other subject in a scene includes a vision system camera with an optics assembly and a light field sensor assembly. The camera is constructed and arranged to generate light field image data from light received through the optics assembly. A light field process analyzes the light field image data and that generates selected image information. A vision system processor then operates a vision system process on the selected image information to generate results therefrom.
    Type: Grant
    Filed: March 15, 2013
    Date of Patent: August 21, 2018
    Assignee: Cognex Corporation
    Inventors: Laurens Nunnink, William Equitz, David J. Michael
  • Publication number: 20180225799
    Abstract: This invention provides a system and method for scoring a candidate pose in a geometric-pattern matching tool of a vision system by using trained color, grayscale and/or range (height) information (“color/grayscale/range”) in association with edge-aligned candidate poses. A trained pattern includes associated color/grayscale/range information in a set of test points. At runtime, a color, grayscale and/or range image is acquired and/or provided. A runtime pose is established with a coordinate space for the color/grayscale/range image with respect to the trained pattern, where the runtime pose is generated by an alignment tool. The color/grayscale/range test points are mapped onto the coordinate space for the image. The match is then determined at the respective mapped test points. Based on the test point match, a score is determined. The score is used in conjunction with the alignment result in runtime to accept or reject candidate poses from (e.g.) acquired images of runtime objects.
    Type: Application
    Filed: February 3, 2017
    Publication date: August 9, 2018
    Inventors: Jason Davis, David J. Michael
  • Patent number: 9995573
    Abstract: The present application discloses a probe placement module for placing probes on a virtual object depicted in an image. The probe placement module is configured to place probes on interest points of an image so that the probes can accurately represent a pattern depicted in the image. The probe placement module can be configured to place the probes so that the probes can extract balanced information on all degrees of freedom associated with the pattern's movement, which improves the accuracy of the model generated from the probes.
    Type: Grant
    Filed: January 23, 2015
    Date of Patent: June 12, 2018
    Assignee: Cognex Corporation
    Inventors: Simon Barker, David J. Michael, William M. Silver
  • Publication number: 20180130234
    Abstract: A system and method for selecting among 3D alignment algorithms in a 3D vision system is provided. The system and method includes a 3D camera assembly to acquire at least a runtime image defined by a 3D point cloud or runtime 3D range image having features of a runtime object and a vision system processor. A training image is provided. It is defined by a 3D point cloud or 3D range image having features of a model. A selection process is operated by the vision processor. It analyzes at least one training region of the training image having the features of the model and determines a distribution of surface normals in the at least one training region. It also selects, based upon a characteristic of the distribution, at least one 3D alignment algorithm from a plurality of available 3D alignment algorithms to align the features of the model with respect to the features of the runtime object.
    Type: Application
    Filed: June 27, 2017
    Publication date: May 10, 2018
    Inventors: Simon Barker, David J. Michael
  • Publication number: 20180130224
    Abstract: This invention provides a system and method for estimating match of a 3D alignment pose of a runtime 3D point cloud relative to a trained model 3D point cloud. It includes scoring a match of a candidate pose of the runtime 3D point cloud relative to the trained model 3D point cloud, including a visibility check that comprises (a) receiving a 3D camera optical center (b) receiving the trained model 3D point cloud; (c) receiving the runtime 3D point cloud; and (d) constructing a plurality of line segments from the optical center to a plurality of 3D points in the 3D point cloud at the runtime candidate pose. A system and method for determining an accurate representation of a 3D imaged object by omitting spurious points from a composite point cloud based on the presence or absence of such points in a given number of point clouds is also provided.
    Type: Application
    Filed: July 20, 2017
    Publication date: May 10, 2018
    Inventors: Andrew Hoelscher, Aaron S. Wallack, Adam Wagman, David J. Michael, Hongjun Jia
  • Patent number: 9679224
    Abstract: A system and method for training multiple pattern recognition and registration models commences with a first pattern model. The model is trained from multiple images. Composite models can be used to improve robustness or model small differences in appearance of a target region. Composite models combine data from noisy training images showing instances of underlying patterns to build a single model. A pattern recognition and registration model is generated that spans the entire range of appearances of the target pattern in the set of training images. The set of pattern models can be implemented as either separate instances of pattern finding models or as a pattern multi-model. The underlying models can be standard pattern finding models or pattern finding composite models, or a combination of both.
    Type: Grant
    Filed: July 31, 2013
    Date of Patent: June 13, 2017
    Assignee: COGNEX CORPORATION
    Inventors: Simon Barker, David J. Michael
  • Patent number: 9659236
    Abstract: A system and method for training multiple pattern recognition and registration models commences with a first pattern model. The model is trained from multiple images. Composite models can be used to improve robustness or model small differences in appearance of a target region. Composite models combine data from noisy training images showing instances of underlying patterns to build a single model. A pattern recognition and registration model is generated that spans the entire range of appearances of the target pattern in the set of training images. The set of pattern models can be implemented as either separate instances of pattern finding models or as a pattern multi-model. The underlying models can be standard pattern finding models or pattern finding composite models, or a combination of both.
    Type: Grant
    Filed: November 25, 2015
    Date of Patent: May 23, 2017
    Assignee: Cognex Corporation
    Inventors: Simon Barker, David J. Michael
  • Publication number: 20170140537
    Abstract: This invention provides a system and method for aligning first three-dimensional (3D) point cloud image representing a model with a second 3D point cloud image representing a target, using a vision system processor. A passing overall score is established for possible alignments of the first 3D point cloud image with the second 3D point cloud image. A coverage score for at least one alignment of the first 3D point cloud image with the second 3D point cloud image is estimated so that the coverage score describes an amount of desired features in the first 3D point cloud image present in the second 3D point cloud image. A clutter score is estimated so that the clutter score describes extraneous features in the second 3D point cloud image. An overall score is computed as a difference between the coverage score and the clutter score.
    Type: Application
    Filed: November 12, 2015
    Publication date: May 18, 2017
    Inventors: Hongjun Jia, David J. Michael, Adam Wagman, Andrew Hoelscher
  • Publication number: 20160379351
    Abstract: A system and method for three dimensional (3D) vision inspection using a 3D vision system. The system and method comprising acquiring at least one 3D image of a 3D object using the 3D vision system, using the 3D vision system; extracting a 3D visible runtime mask of the 3D image; using the 3D vision system, comparing the 3D runtime visible mask to a 3D reference visible mask; and, using the 3D vision system, determining if a difference of pixels exists between the 3D runtime visible mask and the 3D reference visible mask.
    Type: Application
    Filed: June 24, 2016
    Publication date: December 29, 2016
    Inventors: DAVID J. MICHAEL, GANG LIU, ALI ZADEH
  • Patent number: 9488469
    Abstract: This invention provides a system and method for the high-accuracy measurement of an object's surface displacement at a plurality of measurement points using a laser displacement sensor and a sensor process that corrects for noise and other accuracy-reducing factors. A camera assembly with an imager and optics package acquires images of an object surface, and a laser assembly projects a line on the object surface. These tasks can include (a) defining patches of the surface based upon a grid; (b) registering the object and aligning the grid with respect to the object; (c) excluding from the analysis of the image, irregular surface features; (d) oversampling one or more patches to improve overall accuracy; (e) specifying measurement resolution (i.e. in the (x, y z) dimensions), including choosing appropriate pixel sizes and number of measurements per measurement point; and (f) selecting optimal acquisition/image formation parameters.
    Type: Grant
    Filed: April 21, 2014
    Date of Patent: November 8, 2016
    Assignee: COGNEX CORPORATION
    Inventors: David J. Michael, Aaron S. Wallack
  • Publication number: 20160216107
    Abstract: The present application discloses a probe placement module for placing probes on a virtual object depicted in an image. The probe placement module is configured to place probes on interest points of an image so that the probes can accurately represent a pattern depicted in the image. The probe placement module can be configured to place the probes so that the probes can extract balanced information on all degrees of freedom associated with the pattern's movement, which improves the accuracy of the model generated from the probes.
    Type: Application
    Filed: January 23, 2015
    Publication date: July 28, 2016
    Inventors: Simon BARKER, David J. MICHAEL, William M. SILVER
  • Publication number: 20160180198
    Abstract: This invention provides a system and method for determining the level of clutter in an image in a manner that is rapid, and that allows a scoring process to quickly determine whether an image is above or below an acceptable level of clutter—for example to determine if the underlying imaged runtime object surface is defective without need to perform a more in-depth analysis of the features of the image. The system and method employs clutter test points that are associated with regions on the image that should contain a low gradient magnitude, indicative of emptiness. This enables the runtime image to be analyzed quickly by mapping trained clutter test points at locations in the coordinate space in which lack of emptiness indicates clutter, and if detected, can rapidly indicate differences and/or defects that allow for the subject of the image to be accepted or rejected without further image analysis.
    Type: Application
    Filed: December 22, 2014
    Publication date: June 23, 2016
    Inventors: Jason Davis, David J. Michael, Nathaniel R. Bogan
  • Publication number: 20160155022
    Abstract: A system and method for training multiple pattern recognition and registration models commences with a first pattern model. The model is trained from multiple images. Composite models can be used to improve robustness or model small differences in appearance of a target region. Composite models combine data from noisy training images showing instances of underlying patterns to build a single model. A pattern recognition and registration model is generated that spans the entire range of appearances of the target pattern in the set of training images. The set of pattern models can be implemented as either separate instances of pattern finding models or as a pattern multi-model. The underlying models can be standard pattern finding models or pattern finding composite models, or a combination of both.
    Type: Application
    Filed: November 25, 2015
    Publication date: June 2, 2016
    Inventors: Simon Barker, David J. Michael
  • Patent number: 9124873
    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.
    Type: Grant
    Filed: October 24, 2013
    Date of Patent: September 1, 2015
    Assignee: Cognex Corporation
    Inventors: Lifeng Liu, Aaron S. Wallack, Cyril C. Marrion, Jr., David J. Michael
  • Patent number: 9121751
    Abstract: The disclosure relates to weighing moving objects in a weighing platform functionally coupled to a computer-vision tracking platform. The objects can translate, rotate, and translate and rotate. Weighing of the objects can be accomplished through combination of object imaging and upstream weighing. Object imaging can permit tracking, through computer vision, a logical object moving in a trajectory from the first location to the second location, wherein a logical object is a formal representation of one or more physical objects. Upstream weighing can permit updating a record indicative of weight of the one or more physical objects associated with the tracked logical object. As a part of weighing termination, data integrity check(s) can be performed on a plurality of records indicative of a weight of a single physical object. Based on outcome of the data integrity check(s), a record indicative of the weight of the single physical object can be supplied.
    Type: Grant
    Filed: November 15, 2011
    Date of Patent: September 1, 2015
    Assignee: Cognex Corporation
    Inventor: David J. Michael
  • Publication number: 20150003726
    Abstract: A system and method for training multiple pattern recognition and registration models commences with a first pattern model. The model is trained from multiple images. Composite models can be used to improve robustness or model small differences in appearance of a target region. Composite models combine data from noisy training images showing instances of underlying patterns to build a single model. A pattern recognition and registration model is generated that spans the entire range of appearances of the target pattern in the set of training images. The set of pattern models can be implemented as either separate instances of pattern finding models or as a pattern multi-model. The underlying models can be standard pattern finding models or pattern finding composite models, or a combination of both.
    Type: Application
    Filed: July 31, 2013
    Publication date: January 1, 2015
    Applicant: Cognex Corporation
    Inventors: Simon Barker, David J. Michael
  • Patent number: 8872911
    Abstract: A method and apparatus for assessing at least one of motion linearity of a motion stage, stage motion straightness of a motion stage, image capture repeatability of a motion stage and camera and accuracy of a calibration plate used to assess motion stage characteristics, the method including using a line scan camera to generate two dimensional images of a calibration plate having a plurality imageable features thereon, examining the images to identify actual coordinates of the imageable features and using the actual coordinates to assess linearity, straightness, repeatability and/or plate accuracy.
    Type: Grant
    Filed: January 5, 2010
    Date of Patent: October 28, 2014
    Assignee: Cognex Corporation
    Inventors: Aaron S. Wallack, David J. Michael