公开(公告)号：US20240202694A1

公开(公告)日：2024-06-20

申请号：US18169012

申请日：2023-02-14

Applicant: Maplebear Inc. (dba Instacart)

Inventor： Ganglu Wu ,  Shiyuan Yang ,  Xiao Zhou ,  Qi Wang ,  Qunwei Liu ,  Youming Luo

IPC: G06Q20/20 ,  G06K7/14 ,  G06Q30/0601 ,  G06T3/40 ,  G06V10/25

CPC classification number: G06Q20/208 ,  G06K7/1443 ,  G06Q30/0633 ,  G06Q30/0641 ,  G06T3/40 ,  G06V10/25

Abstract: An automated checkout system modifies received images of machine-readable labels to improve the performance of a label detection model that the system uses to decode item identifiers encoded in the machine-readable labels. For example, the automated checkout system may transform subregions of an image of a machine-readable label to adjust for distortions in the image's depiction of the machine-readable label. Similarly, the automated checkout system may identify readable regions within received images of machine-readable labels and apply a label detection model to those readable regions. By modifying received images of machine-readable labels, these techniques improve on existing computer-vision technologies by allowing for the effective decoding of machine-readable labels based on real-world images using relatively clean training data.

公开(公告)号：US12205098B2

公开(公告)日：2025-01-21

申请号：US17874956

申请日：2022-07-27

Applicant: Maplebear Inc.

Inventor： Yilin Huang ,  Ganglu Wu ,  Xiao Zhou ,  Youming Luo ,  Shiyuan Yang

IPC: G06V10/25 ,  G01G19/12 ,  G01G19/40 ,  G06Q20/20 ,  G06V10/778 ,  G06V10/80 ,  G06V20/50

Abstract: A smart shopping cart includes internally facing cameras and an integrated scale to identify objects that are placed in the cart. To avoid unnecessary processing of images that are irrelevant, and thereby save battery life, the cart uses the scale to detect when an object is placed in the cart. The cart obtains images from a cache and sends those to an object detection machine learning model. The cart captures and sends a load curve as input to the trained model for object detection. Labeled load data and labeled image data are used by a model training system to train the machine learning model to identify an item when it is added to the shopping cart. The shopping cart also uses weight data and the image data from a timeframe associated with the addition of the item to the cart as inputs.

公开(公告)号：US20250104040A1

公开(公告)日：2025-03-27

申请号：US18974543

申请日：2024-12-09

Applicant: Maplebear Inc.

Inventor： Yilin Huang ,  Ganglu Wu ,  Xiao Zhou ,  Youming Luo ,  Shiyuan Yang

IPC: G06Q20/20 ,  G01G19/12 ,  G01G19/40 ,  G06V10/25 ,  G06V10/778 ,  G06V10/80 ,  G06V20/50

Abstract: A smart shopping cart includes internally facing cameras and an integrated scale to identify objects that are placed in the cart. To avoid unnecessary processing of images that are irrelevant, and thereby save battery life, the cart uses the scale to detect when an object is placed in the cart. The cart obtains images from a cache and sends those to an object detection machine learning model. The cart captures and sends a load curve as input to the trained model for object detection. Labeled load data and labeled image data are used by a model training system to train the machine learning model to identify an item when it is added to the shopping cart. The shopping cart also uses weight data and the image data from a timeframe associated with the addition of the item to the cart as inputs.

公开(公告)号：US20240202475A1

公开(公告)日：2024-06-20

申请号：US18587719

申请日：2024-02-26

Applicant: Maplebear Inc.

Inventor： Ganglu Wu ,  Shiyuan Yang ,  Xiao Zhou ,  Qi Wang ,  Qunwei Liu ,  Youming Luo

IPC: G06K7/14 ,  G06Q30/0601 ,  G06T9/00 ,  G06V10/25

CPC classification number: G06K7/1413 ,  G06Q30/0633 ,  G06Q30/0641 ,  G06T9/00 ,  G06V10/25 ,  G06V2201/07

Abstract: An automated checkout system modifies received images of machine-readable labels to improve the performance of a label detection model that the system uses to decode item identifiers encoded in the machine-readable labels. For example, the automated checkout system may transform subregions of an image of a machine-readable label to adjust for distortions in the image's depiction of the machine-readable label. Similarly, the automated checkout system may identify readable regions within received images of machine-readable labels and apply a label detection model to those readable regions. By modifying received images of machine-readable labels, these techniques improve on existing computer-vision technologies by allowing for the effective decoding of machine-readable labels based on real-world images using relatively clean training data.

公开(公告)号：US11948044B2

公开(公告)日：2024-04-02

申请号：US18169010

申请日：2023-02-14

Applicant: Maplebear Inc.

Inventor： Ganglu Wu ,  Shiyuan Yang ,  Xiao Zhou ,  Qi Wang ,  Qunwei Liu ,  Youming Luo

IPC: G06K7/14 ,  G06Q30/0601 ,  G06T9/00 ,  G06V10/25

CPC classification number: G06K7/1413 ,  G06Q30/0633 ,  G06Q30/0641 ,  G06T9/00 ,  G06V10/25 ,  G06V2201/07

Abstract: An automated checkout system modifies received images of machine-readable labels to improve the performance of a label detection model that the system uses to decode item identifiers encoded in the machine-readable labels. For example, the automated checkout system may transform subregions of an image of a machine-readable label to adjust for distortions in the image's depiction of the machine-readable label. Similarly, the automated checkout system may identify readable regions within received images of machine-readable labels and apply a label detection model to those readable regions. By modifying received images of machine-readable labels, these techniques improve on existing computer-vision technologies by allowing for the effective decoding of machine-readable labels based on real-world images using relatively clean training data.

公开(公告)号：US20240013184A1

公开(公告)日：2024-01-11

申请号：US17874956

申请日：2022-07-27

Applicant: Maplebear Inc. (dba Instacart)

Inventor： Yilin Huang ,  Ganglu Wu ,  Xiao Zhou ,  Youming Luo ,  Shiyuan Yang

IPC: G06Q20/20 ,  G06V10/778 ,  G06V10/25 ,  G06V20/50

CPC classification number: G06Q20/208 ,  G06V10/778 ,  G06V10/25 ,  G06V20/50

Abstract: A smart shopping cart includes internally facing cameras and an integrated scale to identify objects that are placed in the cart. To avoid unnecessary processing of images that are irrelevant, and thereby save battery life, the cart uses the scale to detect when an object is placed in the cart. The cart obtains images from a cache and sends those to an object detection machine learning model. The cart captures and sends a load curve as input to the trained model for object detection. Labeled load data and labeled image data are used by a model training system to train the machine learning model to identify an item when it is added to the shopping cart. The shopping cart also uses weight data and the image data from a timeframe associated with the addition of the item to the cart as inputs.

公开(公告)号：US20230267292A1

公开(公告)日：2023-08-24

申请号：US18169010

申请日：2023-02-14

Applicant: Maplebear Inc. (dba Instacart)

Inventor： Ganglu Wu ,  Shiyuan Yang ,  Xiao Zhou ,  Qi Wang ,  Qunwei Liu ,  Youming Luo

IPC: G06K7/14 ,  G06T9/00 ,  G06V10/25 ,  G06Q30/0601

CPC classification number: G06K7/1413 ,  G06T9/00 ,  G06V10/25 ,  G06Q30/0633 ,  G06Q30/0641 ,  G06V2201/07

Abstract: An automated checkout system modifies received images of machine-readable labels to improve the performance of a label detection model that the system uses to decode item identifiers encoded in the machine-readable labels. For example, the automated checkout system may transform subregions of an image of a machine-readable label to adjust for distortions in the image's depiction of the machine-readable label. Similarly, the automated checkout system may identify readable regions within received images of machine-readable labels and apply a label detection model to those readable regions. By modifying received images of machine-readable labels, these techniques improve on existing computer-vision technologies by allowing for the effective decoding of machine-readable labels based on real-world images using relatively clean training data.