Article deduction apparatus, article deduction method, and program

Patent metadata

Field	Value
Publication number	US-2023385799-A1
Application number	US-202318233623-A
Country	US
Kind code	A1
Filing date	Aug 14, 2023
Priority date	Mar 1, 2019
Publication date	Nov 30, 2023
Grant date	—

Abstract

An article information deduction apparatus (10) includes an acquisition unit (110) and an output unit (120). The acquisition unit (110) acquires data based on a change in a detected value of a weight sensor (30) (hereinafter described as weight change data). For example, the acquisition unit (110) determines data acquired by chronologically arranging data acquired from the weight sensor (30) as weight change data. Further, the acquisition unit (110) acquires data indicating a movement of a hand of a person positioned in a shelf-front space (hereinafter described as movement data). For example, the acquisition unit (110) acquires data acquired by chronologically arranging data output from a depth sensor (40) to the article information deduction apparatus (10) as movement data. The output unit (120) outputs article determination information of the article deduced to be taken out by the hand of the person positioned in the shelf-front space, by using the weight change data and the movement data.

First claim

1 . An article deduction apparatus comprising:
a memory storing instructions; and a processor configured to execute the instructions to: acquire weight change data being data based on a change in a detected value of a plurality of weight sensors provided on a shelf on which a plurality of articles can be placed and movement data indicating a movement of a hand of a person positioned in a shelf-front space being a space in front of the shelf, wherein the plurality of weight sensors is provided separately from one another on the shelf; and output article determination information of the article deduced to be taken out by the hand, by using the weight change data and the movement data.

2 . The article deduction apparatus according to claim 1 , wherein
the shelf is rectangular, and the plurality of weight sensors is provided at each of the four corners of the shelf.

3 . The article deduction apparatus according to claim 1 , wherein the processor is further configured to execute the instructions to:
generate the movement data by using a detected value of a depth sensor a detection range of which includes the shelf-front space; and when a relation between a height of a shelf in which a change in a detected value of the plurality of weight sensors have occurred and a detected value of a depth sensor that can acquire the movement data satisfies a criterion, output the article determination information associated with the shelf.

4 . The article deduction apparatus according to claim 3 , wherein
a plurality of shelves with different heights exist, at least one piece of the article determination information is associated with each of the plurality of shelves, and the weight change data indicate a variation in a weight for each of the plurality of shelves.

5 . The article deduction apparatus according to claim 1 , wherein
the processor is further configured to execute the instructions to output the article determination information associated with, out of a plurality of partial areas of the shelf, the partial area in which a change in a weight satisfies a criterion.

6 . The article deduction apparatus according to claim 1 , wherein
the processor is further configured to execute the instructions to cause a storage to store the article determination information in association with person determination information for determining the person.

7 . The article deduction apparatus according to claim 5 , wherein
the processor is further configured to execute the instructions to acquire the person determination information from a person tracking apparatus tracking a movement of the person.

8 . The article deduction apparatus according to claim 1 , wherein the processor is further configured to execute the instructions to:
repeatedly acquire a first image being an image including at least part of the shelf-front space; and deduce the article taken out by the hand, by further using an image of the article included in the first image.

9 . The article deduction apparatus according to claim 2 , wherein the processor is further configured to execute the instructions to:
repeatedly acquire a second image being an image of the shelf captured from a front; and determine the article determination information of the article taken out by the hand, by further using a change in the second image.

10 . The article deduction apparatus according to claim 1 , wherein
the shelf is installed in a store, the person is a customer, and the processor is further configured to execute the instructions to:
perform checkout processing by using the article determination information; and
output an electronic receipt based on the checkout processing.

11 . An article deduction method comprising, by a computer:
acquiring weight change data being data based on a change in a detected value of a plurality of weight sensors provided on a shelf on which a plurality of articles can be placed and movement data indicating a movement of a hand of a person positioned in a shelf-front space being a space in front of the shelf, wherein the plurality of weight sensors is provided separately from one another on the shelf; and outputting article determination information of the article deduced to be taken out by the hand, by using the weight change data and the movement data.

12 . The article deduction method according to claim 11 , wherein
the shelf is rectangular, and the plurality of weight sensors is provided at each of the four corners of the shelf.

13 . The article deduction method according to claim 11 , further comprising:
generating the movement data by using a detected value of a depth sensor a detection range of which includes the shelf-front space; and when a relation between a height of a shelf in which a change in a detected value of the plurality of weight sensors have occurred and a detected value of a depth sensor that can acquire the movement data satisfies a criterion, outputting the article determination information associated with the shelf.

14 . The article deduction method according to claim 11 , further comprising
outputting the article determination information associated with, out of a plurality of partial areas of the shelf, the partial area in which a change in a weight satisfies a criterion.

15 . The article deduction method according to claim 11 , further comprising causing a storage to store the article determination information in association with person determination information for determining the person.

16 . A non-transitory computer-readable medium storing a program for causing a computer to perform operations, the operations comprising:
acquiring weight change data being data based on a change in a detected value of a plurality of weight sensors provided on a shelf on which a plurality of articles can be placed and movement data indicating a movement of a hand of a person positioned in a shelf-front space being a space in front of the shelf, wherein the plurality of weight sensors is provided separately from one another on the shelf; and outputting article determination information of the article deduced to be taken out by the hand, by using the weight change data and the movement data.

17 . The non-transitory computer-readable medium according to claim 16 , wherein
the shelf is rectangular, and the plurality of weight sensors is provided at each of the four corners of the shelf.

18 . The non-transitory computer-readable medium according to claim 16 , wherein the operations further comprise:
generating the movement data by using a detected value of a depth sensor a detection range of which includes the shelf-front space; and when a relation between a height of a shelf in which a change in a detected value of the plurality of weight sensors have occurred and a detected value of a depth sensor that can acquire the movement data satisfies a criterion, outputting the article determination information associated with the shelf.

19 . The non-transitory computer-readable medium according to claim 16 , wherein
the operations further comprise outputting the article determination information associated with, out of a plurality of partial areas of the shelf, the partial area in which a change in a weight satisfies a criterion.

20 . The non-transitory computer-readable medium according to claim 16 , wherein
the operations further comprise causing a storage to store the article determination information in association with person determination information for determining the pers

Assignees

• Nec Corp

Inventors

• Nakamura Motoyuki
• MURA Hisayoshi
• Yamasaki Shinya

Classifications

• G06Q20/208 Primary

  Input by product or record sensing, e.g. weighing or scanner processing · CPC title

• G06T7/50

  Depth or shape recovery · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title

• G06V20/52

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title

• G06V40/10

  Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands · CPC title