公开(公告)号：US11281888B2

公开(公告)日：2022-03-22

申请号：US16923674

申请日：2020-07-08

Applicant: Mashgin Inc.

Inventor： Abhinai Srivastava ,  Mukul Dhankhar

IPC: G06K9/00 ,  G06T17/10 ,  G01B11/245 ,  G06T7/174 ,  G06T7/194 ,  G06T17/00 ,  H04N5/232 ,  G06T7/11 ,  G06K9/32

Abstract: Methods, systems, and programs are presented for simultaneous recognition of objects within a detection space utilizing three-dimensional (3D) cameras configured for capturing 3D images of the detection space. One system includes the 3D cameras, calibrated based on a pattern in a surface of the detection space, a memory, and a processor. The processor combines data of the 3D images to obtain pixel data and removes, from the pixel data, background pixels of the detection space to obtain object pixel data associated with objects in the detection space. Further, the processor creates a geometric model of the object pixel data, the geometric model including surface information of the objects in the detection space, generates one or more cuts in the geometric model to separate objects and obtain respective object geometric models, and performs object recognition to identify each object in the detection space based on the respective object geometric models.

公开(公告)号：US11036964B2

公开(公告)日：2021-06-15

申请号：US17079056

申请日：2020-10-23

Applicant: Mashgin Inc.

Inventor： Abhinai Srivastava ,  Mukul Dhankhar

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/08 ,  G06T3/40 ,  G06T3/00 ,  G06T9/20

Abstract: The method for item identification preferably includes determining visual information for an item; calculating a first encoding using the visual information; calculating a second encoding using the first encoding; determining an item identifier for the item using the second encoding; optionally presenting information associated with the item to a user; and optionally registering a new item.

公开(公告)号：US20240242517A1

公开(公告)日：2024-07-18

申请号：US18617183

申请日：2024-03-26

Applicant: Mashgin Inc.

Inventor： Abhinai Srivastava ,  Mukul Dhankar

IPC: G06V20/64 ,  G06N3/04 ,  G06T7/00 ,  G06T7/38 ,  G06T7/557 ,  G06T7/593 ,  G06T7/62 ,  G06V10/145 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82

CPC classification number: G06V20/64 ,  G06N3/04 ,  G06T7/38 ,  G06T7/557 ,  G06T7/593 ,  G06T7/62 ,  G06T7/97 ,  G06V10/145 ,  G06V10/764 ,  G06V10/809 ,  G06V10/82

Abstract: In variants, a method for item recognition can include: optionally calibrating a sampling system, determining visual data using the sampling system, determining a point cloud, determining region masks based on the point cloud, generating a surface reconstruction for each item, generating image segments for each item based on the surface reconstruction, and determining a class identifier for each item using the respective image segments.

公开(公告)号：US20240095709A1

公开(公告)日：2024-03-21

申请号：US17945912

申请日：2022-09-15

Applicant: Mashgin Inc.

Inventor： Abhinai Srivastava ,  Mukul Dhankhar

IPC: G06Q20/20 ,  G06Q20/14 ,  G06Q20/18 ,  G06Q30/04 ,  G06V10/26 ,  G06V10/74 ,  G06V10/764 ,  G06V10/82 ,  G06V20/50

CPC classification number: G06Q20/208 ,  G06Q20/14 ,  G06Q20/18 ,  G06Q30/04 ,  G06V10/26 ,  G06V10/761 ,  G06V10/764 ,  G06V10/82 ,  G06V20/50

Abstract: In variants, the self-checkout method can include: acquiring measurements of a batch of items, automatically identifying each item based on the measurements, and repeating the above until a checkout condition is met.

公开(公告)号：US10803292B2

公开(公告)日：2020-10-13

申请号：US15685455

申请日：2017-08-24

Applicant: Mashgin Inc.

Inventor： Abhinai Srivastava ,  Mukul Dhankhar

IPC: G06K9/00 ,  G06T17/10 ,  G01B11/245 ,  G06T7/174 ,  G06T7/194 ,  G06T17/00 ,  H04N5/232 ,  G06T7/11 ,  G06K9/32

Abstract: Methods, systems, and programs are presented for simultaneous recognition of objects within a detection space utilizing three-dimensional (3D) cameras configured for capturing 3D images of the detection space. One system includes the 3D cameras, calibrated based on a pattern in a surface of the detection space, a memory, and a processor. The processor combines data of the 3D images to obtain pixel data and removes, from the pixel data, background pixels of the detection space to obtain object pixel data associated with objects in the detection space. Further, the processor creates a geometric model of the object pixel data, the geometric model including surface information of the objects in the detection space, generates one or more cuts in the geometric model to separate objects and obtain respective object geometric models, and performs object recognition to identify each object in the detection space based on the respective object geometric models.

公开(公告)号：US20240273772A1

公开(公告)日：2024-08-15

申请号：US18645960

申请日：2024-04-25

Applicant: Mashgin Inc.

Inventor： Abhinai Srivastava ,  Mukul Dhankhar

IPC: G06T9/00 ,  G06F16/51 ,  G06F18/214 ,  G06F18/22 ,  G06F18/24 ,  G06N3/04 ,  G06N20/00 ,  G06Q20/20 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82 ,  G06V20/10

CPC classification number: G06T9/002 ,  G06F16/51 ,  G06F18/214 ,  G06F18/22 ,  G06F18/24 ,  G06N20/00 ,  G06Q20/201 ,  G06Q20/202 ,  G06Q20/203 ,  G06V10/764 ,  G06V10/806 ,  G06V10/82 ,  G06V20/10 ,  G06N3/04

Abstract: The method for item identification preferably includes determining visual information for an item; calculating a first encoding using the visual information; calculating a second encoding using the first encoding; determining an item identifier for the item using the second encoding; optionally presenting information associated with the item to a user; and optionally registering a new item.

公开(公告)号：US20230063197A1

公开(公告)日：2023-03-02

申请号：US17982763

申请日：2022-11-08

Applicant: Mashgin Inc.

Inventor： Abhinai Srivastava ,  Mukul Dhankhar

IPC: G06T7/593 ,  G06N3/04 ,  G06T7/00 ,  G06T7/62 ,  G06T7/557 ,  G06T7/38

Abstract: In variants, a method for item recognition can include: optionally calibrating a sampling system, determining visual data using the sampling system, determining a point cloud, determining region masks based on the point cloud, generating a surface reconstruction for each item, generating image segments for each item based on the surface reconstruction, and determining a class identifier for each item using the respective image segments.

公开(公告)号：US20210174529A1

公开(公告)日：2021-06-10

申请号：US17113757

申请日：2020-12-07

Applicant: Mashgin Inc.

Inventor： Abhinai Srivastava ,  Mukul Dhankhar

IPC: G06T7/593 ,  G06N3/04 ,  G06T7/00 ,  G06T7/62 ,  G06T7/557 ,  G06T7/38

Abstract: The method for item recognition can include: optionally calibrating a sampling system, determining visual data using the sampling system, determining a point cloud, determining region masks based on the point cloud, generating a surface reconstruction for each item, generating image segments for each item based on the surface reconstruction, and determining a class identifier for each item using the respective image segments.

公开(公告)号：US11030763B1

公开(公告)日：2021-06-08

申请号：US17113757

申请日：2020-12-07

Applicant: Mashgin Inc.

Inventor： Abhinai Srivastava ,  Mukul Dhankhar

IPC: G06T7/593 ,  G06N3/04 ,  G06T7/38 ,  G06T7/62 ,  G06T7/557 ,  G06T7/00

Abstract: The method for item recognition can include: optionally calibrating a sampling system, determining visual data using the sampling system, determining a point cloud, determining region masks based on the point cloud, generating a surface reconstruction for each item, generating image segments for each item based on the surface reconstruction, and determining a class identifier for each item using the respective image segments.

公开(公告)号：US20200342208A1

公开(公告)日：2020-10-29

申请号：US16923674

申请日：2020-07-08

Applicant: Mashgin Inc.

Inventor： Abhinai Srivastava ,  Mukul Dhankhar

IPC: G06K9/00 ,  G06T17/10 ,  G01B11/245 ,  G06T7/174 ,  G06T7/194 ,  G06T17/00 ,  H04N5/232 ,  G06T7/11

Abstract: Methods, systems, and programs are presented for simultaneous recognition of objects within a detection space utilizing three-dimensional (3D) cameras configured for capturing 3D images of the detection space. One system includes the 3D cameras, calibrated based on a pattern in a surface of the detection space, a memory, and a processor. The processor combines data of the 3D images to obtain pixel data and removes, from the pixel data, background pixels of the detection space to obtain object pixel data associated with objects in the detection space. Further, the processor creates a geometric model of the object pixel data, the geometric model including surface information of the objects in the detection space, generates one or more cuts in the geometric model to separate objects and obtain respective object geometric models, and performs object recognition to identify each object in the detection space based on the respective object geometric models.