IMAGE PROCESSING SYSTEM AND IMAGE PROCESSING METHOD

• US 20160217330A1
• Filed: 07/02/2014
• Published: 07/28/2016
• Est. Priority Date: 09/19/2013
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: OAMI, Ryoma, TAKAHASHI, Yusuke, MIYANO, Hiroyoshi
• Granted Patent: US 10,635,908 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06V 20/41 Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items segmenting video sequences G06V20/49
• 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: G08B 13/19613 Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
• CPC Class Codes: G08B 21/18 Status alarms G08B21/02 takes precedence

Abstract

To provide an image processing system, an image processing method, and a program, capable of detecting a group with high irregularity. An image processing system is provided with: a group detector that detects a group based on an input image captured with an image capturing at a first time; a repeating group analyzer that determines that a detected group has been previously detected; and an alert module that reports when the detected group has been determined by the repeating group analyzer to have been previously detected.

Claims

1. An image processing system comprising:

at least one processor that detects a group in an input image captured with an image capturing at a first time;

determines whether the detected group has been detected in a second time that is earlier than the first time; and

provides an alert when it is determined that the detected group has been detected in the second time.

2. The image processing system according to claim 1,

wherein the processor determines that the detected group has been detected in the past when a group that has a high degree of similarity to the detected group has been detected in the past.

3. The image processing system according to claim 2, further comprising a storage, wherein the at least one processor calculates a feature in the detected group,

the storage stores a calculated feature,

the processor determines the degree of similarity based on the feature.

4. The image processing system according to claim 1,

wherein the processor determines whether the detected group has been detected a number of times equal to or greater than a threshold, and

provides the alert when it is determined that the detected group has been detected the number of times equal to or greater than the threshold.

5. The image processing system according to claim 1,

wherein the processor determines whether the detected group has been discretely detected at a time interval equal to or longer than a first threshold interval, and

provides the alert when it is determined that the detected group has been discretely detected at a time interval equal to or longer than the first threshold interval.

6. The image processing system according to claim 5,

wherein the processor determines whether the detected group has been discretely detected at a time interval equal to or longer than the first threshold interval and the time interval is equal to or shorter than a second threshold interval, and

provides the alert when it is determined that the detected group has been discretely detected at a time interval equal to or longer than the first threshold interval and the time interval is equal to or shorter than the second threshold interval.

7. The image processing system according to claim 3, wherein the feature is calculated for each of persons making up the group.

8. The image processing system according to claim 3, wherein the feature is calculated for the entire group.

9. An image processing method performed by an image processing system, the method comprising:

detecting a group in an input image captured with an image capturing device;

determining whether the detected group has been detected in the past; and

providing an alert when it is determined that the detected group has been detected in the past.

10. A non-transitory computer-readable recording medium recorded with a program causing a computer to execute a set of processing, the processing comprising:

a processing to detect a group in an input image captured with an image capturing device;

a processing to determine whether the detected group has been detected in the past; and

a processing to provide an alert when it is determined that the detected group has been detected in the past.

11. An image processing method performed by an image processing system comprising;

monitoring an image from a surveillance camera to determine whether a group of persons in the image is present in the image at an interval of time;

generating an alert when the group of persons is present in the image at the interval of time.