TARGET OBJECT IDENTIFYING DEVICE, TARGET OBJECT IDENTIFYING METHOD AND TARGET OBJECT IDENTIFYING PROGRAM

• US 20150371403A1
• Filed: 01/31/2014
• Published: 12/24/2015
• Est. Priority Date: 03/29/2013
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: KOYAMA, Kazuya, ARIKUMA, Takeshi
• Granted Patent: US 10,430,666 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/292 Multi-camera tracking
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 20/53 Recognition of crowd images, e.g. recognition of crowd congestion
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/173 face re-identification, e.g. recognising unknown faces across different face tracks

Abstract

Monitoring target matching means 71 matches monitoring targets shown in video captured by one or more imaging devices, and identifies monitoring targets estimated to be the same monitoring target, as an identified monitoring target. Target object identifying means 72 identifies a desired target object from one or more identified monitoring targets captured, using imaging times of each of the one or more identified monitoring targets.

Claims

1. A target object identifying device comprising:

a monitoring target matching unit which matches monitoring targets shown in video captured by one or more imaging devices, and identifies monitoring targets estimated to be the same monitoring target, as an identified monitoring target; and

a target object identifying unit which identifies a desired target object from one or more identified monitoring targets, using imaging times of each of the one or more identified monitoring targets.

2. The target object identifying device according to claim 1, wherein the target object identifying unit identifies, as the target object, an identified monitoring target whose frequency of imaging times in a predetermined period is greater than or equal to a predetermined frequency or whose time width between imaging times in the predetermined period is greater than or equal to a predetermined time.

3. The target object identifying device according to claim 1, wherein the target object identifying unit identifies, as the target object, an identified monitoring target whose time width between an earliest imaging time and a latest imaging time, among time widths between imaging times in a predetermined period, is greater than or equal to a predetermined threshold specified by a determination condition.

4. The target object identifying device according to claim 3, wherein the target object identifying unit identifies the target object based on the determination condition for specifying, for each imaging device, a condition of the time width between the earliest imaging time and the latest imaging time.

5. The target object identifying device according to claim 3, comprising

a determination condition generation unit which generates the determination condition for specifying a condition of the time width between the earliest imaging time and the latest imaging time, based on imaging times of monitoring targets not identified as the target object.

6. The target object identifying device according to claim 1, wherein the target object identifying unit identifies, as the target object, an identified monitoring target whose time width between successive imaging times, among time widths between imaging times in a predetermined period, is greater than or equal to a predetermined threshold specified by a determination condition.

7. The target object identifying device according to claim 6, wherein the target object identifying unit identifies, as the target object, the identified monitoring target whose time width between the successive imaging times meets the determination condition between imaging devices.

8. The target object identifying device according to claim 1, wherein the target object identifying unit identifies the target object based on a determination condition for specifying, for each imaging device, a frequency of imaging times of an identified monitoring target included in a predetermined period.

9. The target object identifying device according to claim 8, wherein the target object identifying unit identifies the target object based on a determination condition for specifying, for each predetermined imaging device group, the frequency of the imaging times of the identified monitoring target included in the predetermined period.

10. The target object identifying device according to claim 8, wherein the monitoring target matching unit calculates a likelihood of the monitoring targets estimated to be the same monitoring target, and

wherein the target object identifying unit identifies the target object, based on the frequency calculated based on the likelihood.

11. The target object identifying device according to claim 1, wherein the monitoring target matching unit matches face images extracted from the video captured by the one or more imaging devices, and identifies monitoring targets estimated to be the same person.

12. A target object identifying method comprising:

matching monitoring targets shown in video captured by one or more imaging devices, and identifying monitoring targets estimated to be the same monitoring target, as an identified monitoring target; and

identifying a desired target object from one or more identified monitoring targets, using imaging times of each of the one or more identified monitoring targets.

13. The target object identifying method according to claim 12, wherein an identified monitoring target whose frequency of imaging times in a predetermined period is greater than or equal to a predetermined frequency or whose time width between imaging times in the predetermined period is greater than or equal to a predetermined time is identified as the target object.

14. A non-transitory computer readable information recording medium storing a target object identifying program, when executed by a processor, that performs a method for:

matching monitoring targets shown in video captured by one or more imaging devices, and identifying monitoring targets estimated to be the same monitoring target, as an identified monitoring target; and

identifying a desired target object from one or more identified monitoring targets, using imaging times of each of the one or more identified monitoring targets.

15. The non-transitory computer readable information recording medium according to claim 14, wherein an identified monitoring target whose frequency of imaging times in a predetermined period is greater than or equal to a predetermined frequency or whose time width between imaging times in the predetermined period is greater than or equal to a predetermined time is identified as the target object.