公开(公告)号：US20250005881A1

公开(公告)日：2025-01-02

申请号：US18709685

申请日：2022-12-08

Applicant: CARNEGIE MELLON UNIVERSITY

Inventor： Marios SAVVIDES ,  Uzair AHMED ,  Fangyi CHEN ,  Han ZHANG

IPC: G06V10/25 ,  G06V10/72 ,  G06V10/764 ,  G06V10/766 ,  G06V10/77 ,  G06V10/82 ,  G06V20/60

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

公开(公告)号：US20240161469A1

公开(公告)日：2024-05-16

申请号：US18508328

申请日：2023-11-14

Applicant: CARNEGIE MELLON UNIVERSITY

Inventor： Fangyi CHEN ,  Marios SAVVIDES ,  Han ZHANG ,  Kai HU

IPC: G06V10/774

CPC classification number: G06V10/774

Abstract: Disclosed herein are training strategies for query-based object detectors, referred to herein as Query Recollection (QR). In one variation or QR, dense query recollection, every intermediate query is collected and independently forwarded to every downstream stage. In a second variation or QR, selective query recollection, intermediate queries are collected from the two nearest previous stages and forwarded to the next downstream stage. This eliminates the phenomena wherein intermediate stages of the decoder produce more accurate results than later stages of the decoder.

公开(公告)号：US20220083959A1

公开(公告)日：2022-03-17

申请号：US17425293

申请日：2020-04-13

Applicant: CARNEGIE MELLON UNIVERSITY ,  BOSSA NOVA ROBOTICS

Inventor： Sarjoun SKAFF ,  Marios SAVVIDES ,  Chenchen ZHU ,  Fangyi CHEN ,  Han ZHANG ,  Uzair AHMED ,  Sreena NALLAMOTHU

IPC: G06Q10/08 ,  G06V20/52 ,  G06T3/40 ,  G06T7/70 ,  G06T7/60 ,  G06V10/764 ,  H04N7/18 ,  B65G1/137

Abstract: An automated inventory monitoring system includes an image capture module able to create a panoramic image of an aisle of a retail store. Images captured from the all of the store are stitched together to create a panoramic image of the aisle. Product images and label images are isolated from the panoramic image and classified, and a list of product images and label images is provided.