Patents by Inventor Marcus Große
Marcus Große 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: 11954767Abstract: Methods, systems, and computer readable media for generating a three-dimensional reconstruction of an object with reduced distortion are described. In some aspects, a system includes at least two image sensors, at least two projectors, and a processor. Each image sensor is configured to capture one or more images of an object. Each projector is configured to illuminate the object with an associated optical pattern and from a different perspective. The processor is configured to perform the acts of receiving, from each image sensor, for each projector, images of the object illuminated with the associated optical pattern and generating, from the received images, a three-dimensional reconstruction of the object. The three-dimensional reconstruction has reduced distortion due to the received images of the object being generated when each projector illuminates the object with an associated optical pattern from the different perspective.Type: GrantFiled: January 20, 2023Date of Patent: April 9, 2024Assignee: Cognex CorporationInventors: Martin Schaffer, Marcus Große
-
Patent number: 11776137Abstract: In some aspects, the techniques described herein relate to systems, methods, and computer readable media for detecting movement in a scene. A first temporal pixel image is generated based on a first set of images of a scene over time, and a second temporal pixel image is generated based on a second set of images. One or more derived values are determined based on values of the temporal pixels in the first temporal pixel image, the second temporal pixel image, or both. Correspondence data is determined based on the first temporal pixel image and the second temporal pixel image indicative of a set of correspondences between image points of the first set of images and image points of the second set of images. An indication of whether there is a likelihood of motion in the scene is determined based on the one or more derived values and the correspondence data.Type: GrantFiled: February 23, 2022Date of Patent: October 3, 2023Assignee: Cognex CorporationInventors: Marcus Große, Bastian Harendt
-
Publication number: 20230222707Abstract: Methods, systems, and computer readable media for generating a three-dimensional reconstruction of an object with reduced distortion are described. In some aspects, a system includes at least two image sensors, at least two projectors, and a processor. Each image sensor is configured to capture one or more images of an object. Each projector is configured to illuminate the object with an associated optical pattern and from a different perspective. The processor is configured to perform the acts of receiving, from each image sensor, for each projector, images of the object illuminated with the associated optical pattern and generating, from the received images, a three-dimensional reconstruction of the object. The three-dimensional reconstruction has reduced distortion due to the received images of the object being generated when each projector illuminates the object with an associated optical pattern from the different perspective.Type: ApplicationFiled: January 20, 2023Publication date: July 13, 2023Applicant: Cognex CorporationInventors: Martin Schaffer, Marcus Große
-
Patent number: 11593954Abstract: In some aspects, the techniques described herein relate to systems, methods, and computer readable media for data pre-processing for stereo-temporal image sequences to improve three-dimensional data reconstruction. In some aspects, the techniques described herein relate to systems, methods, and computer readable media for improved correspondence refinement for image areas affected by oversaturation. In some aspects, the techniques described herein relate to systems, methods, and computer readable media configured to fill missing correspondences to improve three-dimensional (3-D) reconstruction. The techniques include identifying image points without correspondences, using existing correspondences and/or other information to generate approximated correspondences, and cross-checking the approximated correspondences to determine whether the approximated correspondences should be used for the image processing.Type: GrantFiled: July 7, 2021Date of Patent: February 28, 2023Assignee: Cognex CorporationInventors: Marcus Große, Martin Schaffer, Simon Willeke
-
Patent number: 11587268Abstract: Methods, systems, and computer readable media for generating a three-dimensional reconstruction of an object with reduced distortion are described. In some aspects, a system includes at least two image sensors, at least two projectors, and a processor. Each image sensor is configured to capture one or more images of an object. Each projector is configured to illuminate the object with an associated optical pattern and from a different perspective. The processor is configured to perform the acts of receiving, from each image sensor, for each projector, images of the object illuminated with the associated optical pattern and generating, from the received images, a three-dimensional reconstruction of the object. The three-dimensional reconstruction has reduced distortion due to the received images of the object being generated when each projector illuminates the object with an associated optical pattern from the different perspective.Type: GrantFiled: August 29, 2019Date of Patent: February 21, 2023Assignee: Cognex CorporationInventors: Martin Schaffer, Marcus Große
-
Publication number: 20220230332Abstract: In some aspects, the techniques described herein relate to systems, methods, and computer readable media for detecting movement in a scene. A first temporal pixel image is generated based on a first set of images of a scene over time, and a second temporal pixel image is generated based on a second set of images. One or more derived values are determined based on values of the temporal pixels in the first temporal pixel image, the second temporal pixel image, or both. Correspondence data is determined based on the first temporal pixel image and the second temporal pixel image indicative of a set of correspondences between image points of the first set of images and image points of the second set of images. An indication of whether there is a likelihood of motion in the scene is determined based on the one or more derived values and the correspondence data.Type: ApplicationFiled: February 23, 2022Publication date: July 21, 2022Applicant: Cognex CorporationInventors: Marcus Große, Bastian Harendt
-
Patent number: 11388375Abstract: A method for calibrating an image capturing sensor including at least one sensor camera using a time coded pattern target including: displaying the target on a flat screen display, displaying a pattern sequence on the display and capturing the pattern sequence by the at least one sensor camera as a sequence of a camera images, performing an association between pixels of the target and captured image points of the camera images for at least one fixed position of the display in space or respectively for at least two different positions of the display in space, performing the calibration through corresponding points, performing a gamma correction wherein a gamma curve of the display is captured and corrected in any position of the display and/or in addition to capturing the pattern sequence in any position of the display by the at least one sensor camera before displaying the target.Type: GrantFiled: December 19, 2018Date of Patent: July 12, 2022Assignee: Cognex CorporationInventors: Marcus Grosse, Bastian Harendt
-
Patent number: 11288819Abstract: In some aspects, the techniques described herein relate to systems, methods, and computer readable media for detecting movement in a scene. A first temporal pixel image is generated based on a first set of images of a scene over time, and a second temporal pixel image is generated based on a second set of images. One or more derived values are determined based on values of the temporal pixels in the first temporal pixel image, the second temporal pixel image, or both. Correspondence data is determined based on the first temporal pixel image and the second temporal pixel image indicative of a set of correspondences between image points of the first set of images and image points of the second set of images. An indication of whether there is a likelihood of motion in the scene is determined based on the one or more derived values and the correspondence data.Type: GrantFiled: June 28, 2019Date of Patent: March 29, 2022Assignee: Cognex CorporationInventors: Marcus Große, Bastian Harendt
-
Patent number: 11240435Abstract: The techniques described herein relate to methods, apparatus, and computer readable media configured to determine parameters for image acquisition. One or more image sensors are each arranged to capture a set of images of a scene, and each image sensor comprises a set of adjustable imaging parameters. A projector is configured to project a moving pattern on the scene, wherein the projector comprises a set of adjustable projector parameters. The set of adjustable projector parameters and the set of adjustable imaging parameters are determined, based on a set of one or more constraints, to reduce noise in 3D data generated based on the set of images.Type: GrantFiled: September 28, 2020Date of Patent: February 1, 2022Assignee: Cognex CorporationInventors: Robert Wolff, Thomas Penny, Marcus Große
-
Publication number: 20210407110Abstract: In some aspects, the techniques described herein relate to systems, methods, and computer readable media for data pre-processing for stereo-temporal image sequences to improve three-dimensional data reconstruction. In some aspects, the techniques described herein relate to systems, methods, and computer readable media for improved correspondence refinement for image areas affected by oversaturation. In some aspects, the techniques described herein relate to systems, methods, and computer readable media configured to fill missing correspondences to improve three-dimensional (3-D) reconstruction. The techniques include identifying image points without correspondences, using existing correspondences and/or other information to generate approximated correspondences, and cross-checking the approximated correspondences to determine whether the approximated correspondences should be used for the image processing.Type: ApplicationFiled: July 7, 2021Publication date: December 30, 2021Applicant: Cognex CorporationInventors: Marcus Große, Martin Schaffer, Simon Willeke
-
Patent number: 11107268Abstract: The techniques described herein relate to methods, apparatus, and computer readable media for efficiently processing data of initial correspondence assignments, e.g., for three-dimensional reconstruction of an object. In some aspects, the system includes a processor configured to perform the acts of receiving a first set of images of a scene and a second set of images of the scene, determining a first pixel fingerprint based on the first set of images and a second pixel fingerprint based on the second set of images, generating a first binary pixel fingerprint based on the first pixel fingerprint and a second binary pixel fingerprint based on the second pixel fingerprint, and determining whether there exists a stereo correspondence between the first pixel fingerprint and the second pixel fingerprint at least in part based on comparing the first binary pixel fingerprint and the second binary pixel fingerprint.Type: GrantFiled: August 29, 2019Date of Patent: August 31, 2021Assignee: Cognex CorporationInventors: Marcus Große, Martin Schaffer, Simon Willeke, Bastian Harendt
-
Patent number: 11074700Abstract: In some aspects, the techniques described herein relate to systems, methods, and computer readable media for generating, based on a set of images, a temporal pixel image comprising a set of temporal pixels, where each temporal pixel in the set of temporal pixels comprises a set of pixel values at an associated position from each image of the set of images. For a first temporal pixel from the set of temporal pixels, saturation data comprising a set of saturation values is generated, where each saturation value of the set of saturation values is associated with a pixel value of the set of pixel values of the first temporal pixel, and each pixel value is compared to a metric to determine a corresponding saturation value.Type: GrantFiled: April 23, 2019Date of Patent: July 27, 2021Assignee: Cognex CorporationInventors: Marcus Große, Martin Schaffer, Bastian Harendt
-
Patent number: 11069074Abstract: In some aspects, the techniques described herein relate to systems, methods, and computer readable media for data pre-processing for stereo-temporal image sequences to improve three-dimensional data reconstruction. In some aspects, the techniques described herein relate to systems, methods, and computer readable media for improved correspondence refinement for image areas affected by oversaturation. In some aspects, the techniques described herein relate to systems, methods, and computer readable media configured to fill missing correspondences to improve three-dimensional (3-D) reconstruction. The techniques include identifying image points without correspondences, using existing correspondences and/or other information to generate approximated correspondences, and cross-checking the approximated correspondences to determine whether the approximated correspondences should be used for the image processing.Type: GrantFiled: April 23, 2019Date of Patent: July 20, 2021Assignee: Cognex CorporationInventors: Marcus Große, Martin Schaffer, Simon Willeke
-
Patent number: 11017540Abstract: In some aspects, the techniques described herein relate to systems, methods, and computer readable media for data pre-processing for stereo-temporal image sequences to improve three-dimensional data reconstruction. In some aspects, the techniques described herein relate to systems, methods, and computer readable media for improved correspondence refinement for image areas affected by oversaturation. In some aspects, the techniques described herein relate to systems, methods, and computer readable media configured to fill missing correspondences to improve three-dimensional (3-D) reconstruction. The techniques include identifying image points without correspondences, using existing correspondences and/or other information to generate approximated correspondences, and cross-checking the approximated correspondences to determine whether the approximated correspondences should be used for the image processing.Type: GrantFiled: April 23, 2019Date of Patent: May 25, 2021Assignee: Cognex CorporationInventor: Marcus Große
-
Publication number: 20210092300Abstract: The techniques described herein relate to methods, apparatus, and computer readable media configured to determine parameters for image acquisition. One or more image sensors are each arranged to capture a set of images of a scene, and each image sensor comprises a set of adjustable imaging parameters. A projector is configured to project a moving pattern on the scene, wherein the projector comprises a set of adjustable projector parameters. The set of adjustable projector parameters and the set of adjustable imaging parameters are determined, based on a set of one or more constraints, to reduce noise in 3D data generated based on the set of images.Type: ApplicationFiled: September 28, 2020Publication date: March 25, 2021Applicant: Cognex CorporationInventors: Robert Wolff, Thomas Penny, Marcus Große
-
Publication number: 20200410693Abstract: In some aspects, the techniques described herein relate to systems, methods, and computer readable media for detecting movement in a scene. A first temporal pixel image is generated based on a first set of images of a scene over time, and a second temporal pixel image is generated based on a second set of images. One or more derived values are determined based on values of the temporal pixels in the first temporal pixel image, the second temporal pixel image, or both. Correspondence data is determined based on the first temporal pixel image and the second temporal pixel image indicative of a set of correspondences between image points of the first set of images and image points of the second set of images. An indication of whether there is a likelihood of motion in the scene is determined based on the one or more derived values and the correspondence data.Type: ApplicationFiled: June 28, 2019Publication date: December 31, 2020Applicant: Cognex CorporationInventors: Marcus Große, Bastian Harendt
-
Patent number: 10791277Abstract: The techniques described herein relate to methods, apparatus, and computer readable media configured to determine parameters for image acquisition. One or more image sensors are each arranged to capture a set of images of a scene, and each image sensor comprises a set of adjustable imaging parameters. A projector is configured to project a moving pattern on the scene, wherein the projector comprises a set of adjustable projector parameters. The set of adjustable projector parameters and the set of adjustable imaging parameters are determined, based on a set of one or more constraints, to reduce noise in 3D data generated based on the set of images.Type: GrantFiled: September 11, 2018Date of Patent: September 29, 2020Assignee: Cognex CorporationInventors: Robert Wolff, Thomas Penny, Marcus Große
-
Publication number: 20200082605Abstract: The techniques described herein relate to methods, apparatus, and computer readable media for efficiently processing data of initial correspondence assignments, e.g., for three-dimensional reconstruction of an object. In some aspects, the system includes a processor configured to perform the acts of receiving a first set of images of a scene and a second set of images of the scene, determining a first pixel fingerprint based on the first set of images and a second pixel fingerprint based on the second set of images, generating a first binary pixel fingerprint based on the first pixel fingerprint and a second binary pixel fingerprint based on the second pixel fingerprint, and determining whether there exists a stereo correspondence between the first pixel fingerprint and the second pixel fingerprint at least in part based on comparing the first binary pixel fingerprint and the second binary pixel fingerprint.Type: ApplicationFiled: August 29, 2019Publication date: March 12, 2020Applicant: Cognex CorporationInventors: Marcus Große, Martin Schaffer, Simon Willeke, Bastian Harendt
-
Publication number: 20200084384Abstract: The techniques described herein relate to methods, apparatus, and computer readable media configured to determine parameters for image acquisition. One or more image sensors are each arranged to capture a set of images of a scene, and each image sensor comprises a set of adjustable imaging parameters. A projector is configured to project a moving pattern on the scene, wherein the projector comprises a set of adjustable projector parameters. The set of adjustable projector parameters and the set of adjustable imaging parameters are determined, based on a set of one or more constraints, to reduce noise in 3D data generated based on the set of images.Type: ApplicationFiled: September 11, 2018Publication date: March 12, 2020Applicant: Cognex CorporationInventors: Robert Wolff, Thomas Penny, Marcus Große
-
Publication number: 20200074698Abstract: Methods, systems, and computer readable media for generating a three-dimensional reconstruction of an object with reduced distortion are described. In some aspects, a system includes at least two image sensors, at least two projectors, and a processor. Each image sensor is configured to capture one or more images of an object. Each projector is configured to illuminate the object with an associated optical pattern and from a different perspective. The processor is configured to perform the acts of receiving, from each image sensor, for each projector, images of the object illuminated with the associated optical pattern and generating, from the received images, a three-dimensional reconstruction of the object. The three-dimensional reconstruction has reduced distortion due to the received images of the object being generated when each projector illuminates the object with an associated optical pattern from the different perspective.Type: ApplicationFiled: August 29, 2019Publication date: March 5, 2020Applicant: Cognex CorporationInventors: Martin Schaffer, Marcus Große