Image processing apparatus, image processing method, and storage medium

Patent metadata

Field	Value
Publication number	US-12260718-B2
Application number	US-202117353036-A
Country	US
Kind code	B2
Filing date	Jun 21, 2021
Priority date	Jun 30, 2020
Publication date	Mar 25, 2025
Grant date	Mar 25, 2025

Abstract

An image processing apparatus that outputs information about a specified product includes a detection unit configured to detect person information including a behavior history of a person detected from a video, and an output unit configured to output information about a product that meets a predetermined condition, based on the detected behavior history in the person information relating to a person to be retrieved.

First claim

What is claimed is:

1. An image processing apparatus comprising:
one or more memories storing instructions;
one or more processors that, upon execution of the stored instructions, configures the one or more processors to:
determine, based on a selection input by a user, a person to be retrieved among at least one person detected from a video image that was previously captured and stored on a storage device;
obtain, for the determined person, person information including a behavior history of the determined person and position information of the determined person at each time the determined person is detected within the video image;
specify a specific product having inconsistency in a sum of a quantity of stock, a quantity of sales, and a quantity of disposal between an initial time and a time at which the stored video image was captured;
obtain, product information identifying placement of the specific product;
extract, based on the person information and the product information, from the stored video image, at least one image that includes the determined person and the specific product and when the position information determined of the person indicates the determined person approaches the specific product; and

control a display to display the at least one image extracted from the stored video image.

2. The image processing apparatus according to claim 1 , wherein execution of the stored instructions further configures the one or more processors to store a behavior history for each detected person in a storage.

3. The image processing apparatus according to claim 1 , wherein the person to be retrieved is determined by a user designation.

4. The image processing apparatus according to claim 1 ,
wherein the person to be retrieved is a suspect thief, and
wherein the specific product is a product with a possibility of having been stolen by the suspect thief.

5. The image processing apparatus according to claim 4 , wherein execution of the stored instructions further configures the one or more processors to accept an input, by a user based on the at least one image displayed on the display, for confirming, as a stolen product, the specific product with a possibility of having been stolen by the suspect thief.

6. The image processing apparatus according to claim 5 , wherein execution of the stored instructions further configures the one or more processors to control the display to display a report including the person information related to the person to be retrieved and the product information related to the specific product in a case where the input for confirming, as the stolen product, the specific product with the possibility of having been stolen by the suspect thief is accepted.

7. The image processing apparatus according to claim 1 , wherein execution of the stored instructions further configures the one or more processors to:
cause the video image to be displayed; and
accept an input for designating the person to be retrieved from the displayed video image by a user.

8. The image processing apparatus according to claim 1 , wherein the at least one image including the person to be retrieved who has approached the specific product is extracted based on the behavior history of the person to be retrieved and the product information.

9. The image processing apparatus according to claim 1 , wherein the at least one image including the person to be retrieved who has touched the specific product is extracted based on the behavior history of the person to be retrieved and the product information.

10. The image processing apparatus according to claim 1 ,
wherein execution of the stored instructions further configures the one or more processors to accept an input to designate a period for searching the video image, and
wherein the at least one image is extracted from the video image during the period.

11. The image processing apparatus according to claim 1 , wherein execution of the stored instructions further configures the one or more processors to obtain, as the person information, a result of detection and tracking of a person from the video image, and a human body attribute relating to an appearance of the person.

12. The image processing apparatus according to claim 1 , wherein the product information includes at least one of information indicating a placement in a store, information indicating a quantity of stock, information indicating a quantity of sales, and information indicating a quantity of disposal.

13. An image processing method comprising:
determining, based on a selection input by a user, a person to be retrieved among at least one person detected from a video image that was previously captured and stored on a storage device;
obtaining, for the determined person, person information including a behavior history of the determined person and position information of the determined person at each time the determined person is detected within the video image;
specifying a specific product having inconsistency in a sum of a quantity of stock, a quantity of sales, and a quantity of disposal between an initial time and a time at which the stored video image was captured;
obtaining product information identifying a placement of the specific product;
extract, based on the person information and the product information, from the stored video image, at least one image that includes the determined person and the specific product and when the position information of the determined person indicates the determined person approaches the specific product; and
controlling a display to display the at least one image extracted from the stored video image.

14. A non-transitory computer readable storage medium storing a program for causing a computer to perform an image processing method comprising:
determining, based on a selection input by a user, a person to be retrieved among at least one person detected from a video image that was previously captured and stored on a storage device;
obtaining, for the determined person, person information including a behavior history of the determined person and position information of the determined person at each time the determined person is detected within the video image;
specifying a specific product having inconsistency in a sum of a quantity of stock, a quantity of sales, and a quantity of disposal between an initial time and a time at which the stored video image was captured;
obtaining product information identifying a placement of the specific product;
extract, based on the person information and the product information, from the stored video image, at least one image that includes the determined person and the specific product and when the position information of the determined person indicates the determined person approaches the specific product; and
controlling a display to display the at least one image extracted from the stored video image.

Assignees

• Canon Kk

Inventors

• Saito Sho
• Kawano Atsushi
• Yamamoto Shinji
• Tanaka Akifumi
• Mayuzumi Ichiko

Classifications

• G06V40/103

  Static body considered as a whole, e.g. static pedestrian or occupant recognition · CPC title

• G06V20/52

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

• G06V20/20

  in augmented reality scenes · CPC title

• G08B13/19608

  Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position · CPC title

• G08B13/19671

  Addition of non-video data, i.e. metadata, to video stream · CPC title