Title:
MANAGEMENT SYSTEM, MANAGEMENT METHOD, AND PROGRAM FOR MANAGING PRODUCTS IN UNATTENDED STORE
Document Type and Number:
WIPO Patent Application WO/2022/254958
Kind Code:
A1
Abstract:
The present invention relates to application of a skeleton detection model to an image captured by a camera, and the objective thereof is to facilitate advance learning processing and actual application by minimizing an application target and obtaining an estimated hand point by calculation. This management system for managing products includes: a means for acquiring weight information transmitted from a weight sensor installed on a product shelf; a means for acquiring position information relating to a customer from an image captured by a first camera sensor; a means for acquiring feature points of the human body of the customer from an image captured by a second camera sensor, by applying a skeleton detection model, and for calculating an estimated hand point using the feature points of the human body; and a means for determining a pickup of a product on the basis of the customer position information and a correlation between the calculated estimated hand point and a position of the product shelf, and a change in an output from the weight sensor.
Inventors:
YAMAMOTO HIROKI (JP)
MIYAJIMA YOSUKE (JP)
WATANABE SHUJI (JP)
MIZUSHIMA TATSUYA (JP)
MIYAJIMA YOSUKE (JP)
WATANABE SHUJI (JP)
MIZUSHIMA TATSUYA (JP)
Application Number:
PCT/JP2022/016902
Publication Date:
December 08, 2022
Filing Date:
March 31, 2022
Export Citation:
Assignee:
CLASSMETHOD INC (JP)
International Classes:
G06Q30/06; G16Y40/10
Domestic Patent References:
| WO2019181499A1 | 2019-09-26 |
Foreign References:
| CN112434566A | 2021-03-02 | |||
| US20200193347A1 | 2020-06-18 | |||
| CN111831673A | 2020-10-27 | |||
| JP2021012518A | 2021-02-04 |
Other References:
MIYAJIMA YOSUKE: "Using Cubemos' Skeleton Detection SDK and RealSense to Detect Human Reaching a Shelf", DEVELOPSIO, 18 May 2020 (2020-05-18), pages 1 - 10, XP093010961, Retrieved from the Internet
MIZUKI MARUYAMA, SHUVOZIT GHOSE, KATSUFUMI INOUE, PARTHA PRATIM ROY, MASAKAZU IWAMURA, MICHIFUMI YOSHIOKA: "Word-level sign language recognition with Multi-stream Neural Networks Focusing on Local Region", IEICE TECHNICAL REPORT, PRMU, vol. 120, no. 409 (PRMU2020-78), 25 February 2021 (2021-02-25), JP, pages 53 - 58, XP009541632
MIZUKI MARUYAMA, SHUVOZIT GHOSE, KATSUFUMI INOUE, PARTHA PRATIM ROY, MASAKAZU IWAMURA, MICHIFUMI YOSHIOKA: "Word-level sign language recognition with Multi-stream Neural Networks Focusing on Local Region", IEICE TECHNICAL REPORT, PRMU, vol. 120, no. 409 (PRMU2020-78), 25 February 2021 (2021-02-25), JP, pages 53 - 58, XP009541632
Attorney, Agent or Firm:
TAKEMOTO Yukihiro (JP)
Download PDF:
Previous Patent: CONDUCTOR, SHEET WITH CONDUCTOR, LAMINATED PLATE, AND SENSOR SYSTEM
Next Patent: CANNED-MOTOR-PUMP BEARING STRUCTURE
Next Patent: CANNED-MOTOR-PUMP BEARING STRUCTURE