公开(公告)号：US20230154181A1

公开(公告)日：2023-05-18

申请号：US18092689

申请日：2023-01-03

Applicant: Cape Analytics, Inc.

Inventor： Peter Lorenzen

IPC: G06V20/10 ,  G06V10/44 ,  G06F18/2413 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06V20/176 ,  G06V10/451 ,  G06F18/2413 ,  G06V10/764 ,  G06V10/82 ,  H04N23/11

Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.

公开(公告)号：US11631235B2

公开(公告)日：2023-04-18

申请号：US17870279

申请日：2022-07-21

Applicant: Cape Analytics, Inc.

Inventor： Giacomo Vianello ,  Peter Lorenzen

IPC: G06T7/00 ,  G06V10/26 ,  G06T7/60 ,  G06Q30/02 ,  G06T7/11

Abstract: In variants, the method for occlusion correction can include: determining a measurement depicting an occluded object of interest (OOI), optionally infilling the occluded portion of the object of interest within the measurement, and determining an attribute of the object of interest based on the infilled measurement.

公开(公告)号：US20220004762A1

公开(公告)日：2022-01-06

申请号：US17475523

申请日：2021-09-15

Applicant: Cape Analytics, Inc.

Inventor： Ryan Kottenstette ,  Peter Lorenzen ,  Suat Gedikli

IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62

Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.

公开(公告)号：US20240265630A1

公开(公告)日：2024-08-08

申请号：US18429868

申请日：2024-02-01

Applicant: Cape Analytics, Inc.

Inventor： Giacomo Vianello ,  Peter Lorenzen ,  Yirui Jiang

IPC: G06T17/00 ,  G06V10/25 ,  G06V10/44

CPC classification number: G06T17/00 ,  G06V10/25 ,  G06V10/44 ,  G06V2201/07

Abstract: In variants, the method for 3D modeling can include: determining a property of interest, determining property information for the property of interest, determining property component parameter values based on property information, determining a 3D model based on property component parameter values, and optionally determining a set of property attributes. However, the method can additionally and/or alternatively include any other suitable elements.

公开(公告)号：US20240249518A1

公开(公告)日：2024-07-25

申请号：US18628845

申请日：2024-04-08

Applicant: Cape Analytics, Inc.

Inventor： Peter Lorenzen

IPC: G06V20/10 ,  G06F18/2413 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  H04N23/11

CPC classification number: G06V20/176 ,  G06F18/2413 ,  G06V10/451 ,  G06V10/764 ,  G06V10/82 ,  H04N23/11

Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.

公开(公告)号：US10311302B2

公开(公告)日：2019-06-04

申请号：US15253488

申请日：2016-08-31

Applicant: Cape Analytics, Inc.

Inventor： Ryan Kottenstette ,  Peter Lorenzen ,  Suat Gedikli

IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62 ,  H04N5/33

Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.

公开(公告)号：US10366288B1

公开(公告)日：2019-07-30

申请号：US16353361

申请日：2019-03-14

Applicant: Cape Analytics, Inc.

Inventor： Ryan Kottenstette ,  Peter Lorenzen ,  Suat Gedikli

IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62 ,  H04N5/33

Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.

公开(公告)号：US12293579B2

公开(公告)日：2025-05-06

申请号：US18628845

申请日：2024-04-08

Applicant: Cape Analytics, Inc.

Inventor： Peter Lorenzen

IPC: G06V20/00 ,  G06F18/2413 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  G06V20/10 ,  H04N23/10 ,  H04N23/11

Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.

公开(公告)号：US12243301B2

公开(公告)日：2025-03-04

申请号：US18092689

申请日：2023-01-03

Applicant: Cape Analytics, Inc.

Inventor： Peter Lorenzen

IPC: G06V20/00 ,  G06F18/2413 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  G06V20/10 ,  H04N23/11

Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.

公开(公告)号：US20230222758A1

公开(公告)日：2023-07-13

申请号：US18121114

申请日：2023-03-14

Applicant: Cape Analytics, Inc.

Inventor： Giacomo Vianello ,  Peter Lorenzen

IPC: G06V10/26 ,  G06T7/11 ,  G06Q30/02 ,  G06T7/60

CPC classification number: G06V10/273 ,  G06T7/11 ,  G06Q30/0278 ,  G06T7/60 ,  G06T2200/04

Abstract: In variants, the method for occlusion correction can include: determining a measurement depicting an occluded object of interest (OOI), optionally infilling the occluded portion of the object of interest within the measurement, and determining an attribute of the object of interest based on the infilled measurement.