SYSTEM FOR ITEM RECOGNITION USING COMPUTER VISION

    公开(公告)号:US20220343660A1

    公开(公告)日:2022-10-27

    申请号:US17726385

    申请日:2022-04-21

    Abstract: An item recognition system uses a top camera and one or more peripheral cameras to identify items. The item recognition system may use image embeddings generated based on images captured by the cameras to generate a concatenated embedding that describes an item depicted in the image. The item recognition system may compare the concatenated embedding to reference embeddings to identify the item. Furthermore, the item recognition system may detect when items are overlapping in an image. For example, the item recognition system may apply an overlap detection model to a top image and a pixel-wise mask for the top image to detect whether an item is overlapping with another in the top image. The item recognition system notifies a user of the overlap if detected.

    Overlap detection for an item recognition system

    公开(公告)号:US12217236B2

    公开(公告)日:2025-02-04

    申请号:US17726389

    申请日:2022-04-21

    Applicant: Maplebear Inc.

    Abstract: An item recognition system uses a top camera and one or more peripheral cameras to identify items. The item recognition system may use image embeddings generated based on images captured by the cameras to generate a concatenated embedding that describes an item depicted in the image. The item recognition system may compare the concatenated embedding to reference embeddings to identify the item. Furthermore, the item recognition system may detect when items are overlapping in an image. For example, the item recognition system may apply an overlap detection model to a top image and a pixel-wise mask for the top image to detect whether an item is overlapping with another in the top image. The item recognition system notifies a user of the overlap if detected.

    OVERLAP DETECTION FOR AN ITEM RECOGNITION SYSTEM

    公开(公告)号:US20250094956A1

    公开(公告)日:2025-03-20

    申请号:US18961337

    申请日:2024-11-26

    Applicant: Maplebear Inc.

    Abstract: An item recognition system uses a top camera and one or more peripheral cameras to identify items. The item recognition system may use image embeddings generated based on images captured by the cameras to generate a concatenated embedding that describes an item depicted in the image. The item recognition system may compare the concatenated embedding to reference embeddings to identify the item. Furthermore, the item recognition system may detect when items are overlapping in an image. For example, the item recognition system may apply an overlap detection model to a top image and a pixel-wise mask for the top image to detect whether an item is overlapping with another in the top image. The item recognition system notifies a user of the overlap if detected.

    OVERLAP DETECTION FOR AN ITEM RECOGNITION SYSTEM

    公开(公告)号:US20220343308A1

    公开(公告)日:2022-10-27

    申请号:US17726389

    申请日:2022-04-21

    Abstract: An item recognition system uses a top camera and one or more peripheral cameras to identify items. The item recognition system may use image embeddings generated based on images captured by the cameras to generate a concatenated embedding that describes an item depicted in the image. The item recognition system may compare the concatenated embedding to reference embeddings to identify the item. Furthermore, the item recognition system may detect when items are overlapping in an image. For example, the item recognition system may apply an overlap detection model to a top image and a pixel-wise mask for the top image to detect whether an item is overlapping with another in the top image. The item recognition system notifies a user of the overlap if detected.

Patent Agency Ranking