Information processing apparatus and method, storage medium, and monitoring system

Patent metadata

Field	Value
Publication number	US-11417189-B2
Application number	US-201916363192-A
Country	US
Kind code	B2
Filing date	Mar 25, 2019
Priority date	Mar 29, 2018
Publication date	Aug 16, 2022
Grant date	Aug 16, 2022

Abstract

An apparatus for monitoring an object in a video received from at least one camera, comprises a storage unit storing a plurality of pieces of rule information each defining a condition of an object and a movement of the object to be observed in the condition, an input unit inputting information for identifying a monitored object and information representing a condition of the object, an acquiring unit acquiring rule information defining a movement to be observed for the object by referring to the storage unit based on the information representing the condition of the object, which is input by the input unit; and a monitoring unit determining whether the object in the video exhibits the movement to be observed, which is represented by the rule information acquired by the acquiring unit, and output a result of the determination.

First claim

What is claimed is:

1. An information processing apparatus for monitoring an object in a video, comprising:
a first storage unit configured to store a plurality of pieces of rule information defining a target part and a moving amount of the target part to be detected in a condition;
a second storage unit configured to store a plurality of IDs each specifying an object and the rule information corresponding to each of the plurality of IDs;
a third storage unit configured to store a plurality of IDs each specifying an object and feature data for recognizing each of the objects;
an input unit configured to input information identifying a monitored object and information representing a condition of the monitored object;
an acquiring unit configured to acquire, from the first storage unit, the rule information defining the target part and the moving amount of the target part using the condition inputted by the input unit, as the rule information corresponding to the monitored object;
a determination unit configured to receive, from a camera, a video captured by the camera, detect an object in the video and determine whether the detected object in the video is the monitored object using the information identifying the monitored object inputted by the input unit; and
an output unit configured to, if the determination unit determines that the detected object in the video is the monitored object, determine whether the detected object in the video moves the target part more than the moving amount, which is represented by the rule information acquired by the acquiring unit, and output a result of the determination,
wherein the input unit inputs the condition of the monitored object and an ID of the monitored object,
wherein the acquiring unit registers the ID of the monitored object input by the input unit and the rule information acquired from the first storage unit based on the condition of the monitored object into the second storage unit, and
wherein the determination unit acquires an ID of an object in the video by recognizing the object in the video by referring to the third storage unit, determines whether the second storage unit stores an ID matching with the acquired ID, and determines that the object in the video is the monitored object if it is determined that the second storage unit stores the ID matching with the acquired ID.

2. The apparatus according to claim 1 , wherein the monitored object is a person, and the condition of the monitored object includes a health condition.

3. The apparatus according to claim 2 , wherein a movement indicated by the rule information includes a dangerous movement.

4. The apparatus according to claim 3 , wherein the rule information includes a threshold of a danger level, and defines a movement which exceeds the threshold as the dangerous movement.

5. The apparatus according to claim 2 , wherein the input unit analyzes medical data and inputs the health condition.

6. The apparatus according to claim 2 , further comprising a patient database configured to store information used to identify a patient,
wherein the output unit refers to the patient database based on feature information obtained from an image of the person in the video received from the camera, determines whether the person in the video is a patient, and upon determining that the person is a patient, starts monitoring the person in the video.

7. The apparatus according to claim 1 , wherein a health condition includes a disease name.

8. The apparatus according to claim 1 , wherein the monitored object is one of a person and a machine, and the condition of the monitored object is a stage of a work.

9. The apparatus according to claim 8 , wherein a movement indicated by the rule information includes an abnormal movement.

10. The apparatus according to claim 1 , wherein the rule information includes an allowable range for a movement and defines a movement which exceeds the allowable range as the movement to be detected.

11. The apparatus according to claim 1 , wherein the rule information includes a restriction/prohibition for a movement and defines a movement which violates the restriction/prohibition as the movement to be detected.

12. The apparatus according to claim 1 , further comprising a correction unit configured to correct the rule information.

13. The apparatus according to claim 12 , wherein the correction unit is further configured to correct the rule information after a predetermined period.

14. The apparatus according to claim 12 , wherein the correction unit is further configured to correct the rule information based on an image capturing environment of the video.

15. The apparatus according to claim 1 , wherein the rule information is described in a text form.

16. The apparatus according to claim 1 , further comprising a creating unit configured to set and create the rule information.

17. The apparatus according to claim 1 , wherein in a case in which the monitored object moves the target part more than the moving amount which is represented by the rule information acquired by the acquiring unit, the output unit outputs, to a terminal set in advance, information representing that the condition to be detected is obtained.

18. A method of controlling an information processing apparatus that includes a first storage unit configured to store a plurality of pieces of rule information defining a target part and a moving amount of the target part to be detected in a condition, a second storage unit configured to store a plurality of IDs each specifying an object and the rule information corresponding to each of the plurality of IDs, and a third storage unit configured to store a plurality of IDs each specifying an object and feature data for recognizing each of the objects, and that monitors an object in a video, the method comprising:
inputting information identifying a monitored object and information representing a condition of the monitored object;
acquiring, from the first storage unit, the rule information defining the target part and the moving amount of the target part using the condition inputted in the inputting, as rule information corresponding to the monitored object;
receiving, from a camera, a video captured by the camera, detecting an object in the video and determining whether the detected object in the video is the monitored object using the information identifying the monitored object inputted in the inputting; and
if it is determined that the detected object in the video is the monitored object, determining whether the detected object in the video moves the target part more than the moving amount, which is represented by the acquired rule information and outputting a result of the determination,
wherein in the inputting, the condition of the monitored object and an ID of the monitored object are inputted,
wherein in the acquiring, the ID of the monitored object inputted in the inputting and the rule information acquired from the first storage unit based on the condition of the monitored object are registered into the second storage unit, and
wherein in the determining, an ID of an object in the video by recognizing the object in the video is acquired by referring to the third storage unit, it is determined whether the second storage unit stores an ID matching with the acquired ID, and it is determined that the object in the video is the monitored object if it is determined that the second storage unit stores the ID matching with the acquired ID.

19. A non-transitory computer-readable storage medium storing

Assignees

• Canon Kk

Inventors

• Takeuchi Koichi
• Matsugu Masakazu

Classifications

• G08B21/043 Primary

  detecting an emergency event, e.g. a fall · CPC title

• A61B5/0013

  Medical image data (A61B1/00011, A61B6/56, A61B8/56 take precedence) · CPC title

• G08B21/0415

  detecting absence of activity per se · CPC title

• G08B21/0476

  Cameras to detect unsafe condition, e.g. video cameras · CPC title

• A61B5/1128

  using image analysis (A61B5/1127 takes precedence) · CPC title