MONITORING SYSTEM, MONITORING METHOD, MONITORING PROGRAM, AND RECORDING MEDIUM IN WHICH MONITORING PROGRAM IS RECORDED

• US 20150098632A1
• Filed: 09/22/2014
• Published: 04/09/2015
• Est. Priority Date: 10/08/2013
• Status: Active Grant

• Current Assignee: Omron Corporation
• Original Assignee: Omron Corporation
• Inventors: Monta, Yoshito, Furuta, Mizuki, Tanaka, Kiyoaki
• Granted Patent: US 9,424,464 B2
• Time in Patent Office: Days
• US Class Current: 382/118
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06V 20/53 Recognition of crowd images, e.g. recognition of crowd congestion
• CPC Class Codes: G06V 40/166 using acquisition arrangements
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G06V 40/173 face re-identification, e.g. recognising unknown faces across different face tracks

Abstract

A monitoring system configured to monitor a monitoring target, the monitoring system includes:

• • a face feature quantity extraction unit configured to extract a person'"'"'s face feature quantity from input images captured by first and second imaging devices;
  • a matching unit configured to determine whether a person in the input image is a person of a face feature quantity list by comparing the face feature quantities,
  • wherein a second face feature quantity list is a subset or an empty set of a first face feature quantity list,
  • the matching unit matches the face feature quantity of the person in the input image captured by the first imaging device against each face feature quantity of the first face feature quantity list, and matches the face feature quantity of the person in the input image captured by the second imaging device against each face feature quantity of the second face feature quantity list.

Claims

1. A monitoring system configured to monitor a monitoring target area using captured images of the monitoring target area, the monitoring system comprising:

one first imaging device or a plurality of first imaging devices;

one second imaging device or a plurality of second imaging devices;

an image acquisition unit configured to take in images captured by the first imaging device and the second imaging device as an input image;

a face feature quantity extraction unit configured to extract a face feature quantity of a person from the input image;

a storage storing a face feature quantity list, comprising face feature quantities of persons, is stored; and

a matching unit configured to determine whether a person in the input image matches a person of the face feature quantity list by comparing the face feature quantities of the face feature quantity list to the face feature quantity extracted by the face feature quantity extraction unit,

wherein the storage is used to store a first face feature quantity list and a second face feature quantity list therein, the second face feature quantity list is a subset or an empty set of the first face feature quantity list,

the matching unit matches the face feature quantity of the person in the input image against each face feature quantity of the first face feature quantity list when the input image is the image captured by the first imaging device, and the matching unit matches the face feature quantity of the person in the input image against each face feature quantity of the second face feature quantity list when the input image is the image captured by the second imaging device.

2. The monitoring system according to claim 1, further comprising:

a monitoring target person information input and output unit,

wherein the monitoring target person information input and output unit registers a face feature quantity of a person of the first face feature quantity list in the second face feature quantity list, when the input image is the image captured by the first imaging device, and a person in the input image is determined to match the person of the first face feature quantity list as a result of matching the face feature quantity of the person in the input image against each face feature quantity of the first face feature quantity list.

3. The monitoring system according to claim 1, further comprising:

a monitoring target person information input and output unit,

wherein the monitoring target person information input and output unit registers a face feature quantity of a person of the first face feature quantity list in the second face feature quantity list, when the input image is the image captured by the first imaging device, a person in the input image is determined to match the person of the first face feature quantity list as a result of matching of the face feature quantity of the person in the input image against each face feature quantity of the first face feature quantity list, and the number of times the person in the input image is determined to match the person of the first face feature quantity list is greater than or equal to a predetermined number of times.

4. The monitoring system according to claim 2, further comprising:

one third imaging device or a plurality of third imaging devices,

wherein the image acquisition unit is further configured to take in images captured by the third imaging device as an input image,

the matching unit matches a face feature quantity of a person in the input image against each face feature quantity of the second face feature quantity list when the input image is an image captured by the third imaging device, and

the monitoring target person information input and output unit deletes the face feature quantity of the person of the second face feature quantity list from the second face feature quantity list, when the person in the input image is determined to match the person of the second face feature quantity list as a result of matching the face feature quantity of the person in the input image captured by the third imaging device against each face feature quantity of the second face feature quantity list.

5. The monitoring system according to claim 3, further comprising:

one third imaging device or a plurality of third imaging devices,

wherein the image acquisition unit is further configured to take in images captured by the third imaging device as an input image,

the matching unit matches a face feature quantity of a person in the input image against each face feature quantity of the second face feature quantity list when the input image is an image captured by the third imaging device, and

the monitoring target person information input and output unit deletes the face feature quantity of the person of the second face feature quantity list from the second face feature quantity list, when the person in the input image is determined to match the person of the second face feature quantity list as a result of matching the face feature quantity of the person in the input image captured by the third imaging device against each face feature quantity of the second face feature quantity list.

6. The monitoring system according to claim 2, wherein the monitoring target person information input and output unit deletes all the face feature quantities of the second face feature quantity list at a previously-set clock time.

7. The monitoring system according to claim 3, wherein the monitoring target person information input and output unit deletes all the face feature quantities of the second face feature quantity list at a previously-set clock time.

8. A monitoring method in which a monitoring system comprising:

a first face feature quantity list and a second face feature quantity list that is a subset or an empty set of the first face feature quantity list, monitors a monitoring target area using an image captured by an imaging device that is installed so as to partially capture the monitoring target area, the monitoring method comprising the steps of;

taking in the image captured by the imaging device as an input image;

extracting a face feature quantity of a person from the input image; and

matching the face feature quantity extracted from the input image against each face feature quantity of the first face feature quantity list when the input image is an image captured by an imaging device satisfying a predetermined condition, and matching the face feature quantity of the person in the input image against each face feature quantity of the second face feature quantity list when the input image is an image captured by an imaging device except the imaging device satisfying the predetermined condition.

9. The monitoring method according to claim 8, further comprising:

the step of producing the second face feature quantity list as a subset of the first face feature quantity list.

10. The monitoring method according to claim 9, wherein, in the step of producing the second face feature quantity list as the subset of the first face feature quantity list, the second face feature quantity list is produced as the subset of the first face feature quantity list by registering the face feature quantity of the person of the first face feature quantity list in the second face feature quantity list, when

the input image is the image captured by the imaging device satisfying the predetermined condition, and the person in the input image is determined to match a person of the first face feature quantity list as a result of matching the face feature quantity extracted from the input image captured by the imaging device satisfying the predetermined condition against each face feature quantity of the first face feature quantity list.

11. A program configured to cause a computer, the computer configured to be able to use a first face feature quantity list and a second face feature quantity list that is a subset or an empty set of the first face feature quantity list, to perform the steps of:

taking in an image captured by an imaging device as an input image;

extracting a face feature quantity of a person from the input image; and

matching the face feature quantity extracted from the input image against each face feature quantity of the first face feature quantity list when the input image is the image captured by the imaging device satisfying a predetermined condition, and matching the face feature quantity of the person in the input image against each face feature quantity of the second face feature quantity list when the input image is an image captured by an imaging device except the imaging device satisfying the predetermined condition.

13. A computer-readable non-transitory recording medium in which the program according to claim 11 is recorded.

12. A program configured to cause a computer, the computer configured to be able to use a first face feature quantity list and a second face feature quantity list that is of a subset or an empty set of the first face feature quantity list, to perform the steps of:

taking in a face feature quantity extracted by a face feature quantity extraction device; and

matching the face feature quantity against each face feature quantity of the first face feature quantity list when the face feature quantity extraction device is connected to an imaging device satisfying a predetermined condition, and matching the face feature quantity against each face feature quantity of the second face feature quantity list when the face feature quantity extraction device is connected to an imaging device except the imaging device satisfying the predetermined condition.

14. A computer-readable non-transitory recording medium in which the program according to claim 12 is recorded.