公开(公告)号：US20240071029A1

公开(公告)日：2024-02-29

申请号：US18272290

申请日：2022-01-24

Applicant: CARNEGIE MELLON UNIVERSITY

Inventor： Chenchen ZHU ,  Marios Savvides ,  Zhiqiang Shen ,  Fangyi Chen

IPC: G06V10/25 ,  G06V10/44 ,  G06V10/74 ,  G06V10/764

CPC classification number: G06V10/25 ,  G06V10/44 ,  G06V10/761 ,  G06V10/764 ,  G06V2201/07

Abstract: Disclosed herein is a method of soft anchor-point detection (SAPD), which implements a concise, single-stage anchor-point detector with both faster speed and higher accuracy. Also disclosed is a novel training strategy with two softened optimization techniques: soft-weighted anchor points and soft-selected pyramid levels.

公开(公告)号：US11915463B2

公开(公告)日：2024-02-27

申请号：US17408778

申请日：2021-08-23

Applicant: CARNEGIE MELLON UNIVERSITY

Inventor： Marios Savvides ,  Chenchen Zhu ,  Fangyi Chen ,  Uzair Ahmed ,  Ran Tao

IPC: G06V10/44 ,  G06T7/73 ,  G06V10/25 ,  G06V20/20 ,  G06F18/214

CPC classification number: G06V10/443 ,  G06F18/214 ,  G06T7/73 ,  G06V10/25 ,  G06V20/20

Abstract: Disclosed herein is a system and method of identifying new products on a retail shelf using a feature extractor trained to extract features from images of products on the shelf and output identifying information regarding the product in the product image. The extracted features are compared to extracted features in a product library and a best-fit is obtained. A new product is identified if the distance between the features of the product on the shelf and the features of the best-fit product from the product library are above a predetermined threshold.

公开(公告)号：US20220262101A1

公开(公告)日：2022-08-18

申请号：US17670737

申请日：2022-02-14

Applicant: CARNEGIE MELLON UNIVERSITY

Inventor： Marios Savvides ,  Zhiqiang Shen ,  Fangyi Chen ,  Han Zhang

IPC: G06V10/774

Abstract: Disclosed herein is a system and method for improving the accuracy of an object detector when trained with a dataset having a significant number of missing annotations. The method uses a novel Background Recalibration Loss (BRL) which adjusts the gradient direction according to its own activation to reduce the adverse effect of error signals by replacing the negative branch of the focal loss with a mirror of the positive branch when the activation is below a confusion threshold.

公开(公告)号：US20220058432A1

公开(公告)日：2022-02-24

申请号：US17408674

申请日：2021-08-23

Applicant: CARNEGIE MELLON UNIVERSITY

Inventor： Marios Savvides ,  Chenchen Zhu ,  Fangyi Chen ,  Uzair Ahmed ,  Ran Tao

IPC: G06K9/62 ,  G06N5/02 ,  G06N3/04

Abstract: Disclosed herein is an improved few-shot detector which utilizes semantic relation reasoning to learn novel objects from both visual information and the semantic relation of base class objects Specifically, a semantic space is constructed using word embeddings. Guided by the word embeddings of the classes, the detector is trained to project the objects from the visual space to the semantic space and to align their image representations with the corresponding class embeddings.

公开(公告)号：US20240104761A1

公开(公告)日：2024-03-28

申请号：US18272754

申请日：2022-03-09

Applicant: CARNEGIE MELLON UNIVERSITY

Inventor： Marios Savvides ,  Chenchen Zhu ,  Fangyi Chen ,  Han Zhang

IPC: G06T7/70 ,  G06V10/25 ,  G06V10/44 ,  G06V10/764

CPC classification number: G06T7/70 ,  G06V10/25 ,  G06V10/44 ,  G06V10/764 ,  G06V2201/07

Abstract: Disclosed herein is a system and method for generating quadrilateral bonding boxes which tightly cover the most representative faces of retail products having arbitrary poses. The quadrilateral boxes do not include unnecessary background information or miss parts of the objects, as would the axis-aligned bounding boxes produced by prior art detectors. A simple projection transformation can correct the pose of products for downstream tasks.