Grouping items in video stream images into events

• US 7,933,455 B2
• Filed: 12/07/2009
• Issued: 04/26/2011
• Est. Priority Date: 04/05/2005
• Status: Active Grant

• Current Assignee: 3VR Security Incorporated (Identiv, Inc.)
• Original Assignee: 3VR Security Incorporated (Identiv, Inc.)
• Inventors: Fleischer, Stephen D., Frederick, Timothy B., Freeman, J. Andrew, Haupt, Gordon T., Russell, Stephen G., Vallone, Robert P.
• Primary Examiner(s): Mehta; Bhavesh M
• Assistant Examiner(s): DRENNAN, BARRY T
• Application Number:
  US12/632,726
• Publication Number:
  US 20100080492A1
• Time in Patent Office: 505 Days
• Field of Search: None
• US Class Current: 382/224
• CPC Class Codes: G06V 40/173 face re-identification, e.g. recognising unknown faces across different face tracks

Abstract

A technique is disclosed for determining when to close a group of a plurality of groups. A closed group is one to which an image set may not be added. Each group includes one or more image sets. Each image set includes one or more images of at least one object. Each group corresponds to an object that is common among images in the one or more image sets that belong to the group. Determining when to close a particular group is based, at least in part, on one or more factors, such as how many image sets are in the particular group, the length of time the particular group has been open, and data about the one or more image sets in the particular group.

Claims

1. A method of determining whether to close a group, the method comprising:

establishing a plurality of groups;

wherein each group of the plurality of groups is associated with an object and includes one or more image sets that have been determined to include the object that is associated with the group;

wherein each image set comprises one or more images of at least one object;

determining when to close a particular group of the plurality of groups based, at least in part, on one or more of;

how many image sets are in the particular group;

a total amount of time the particular group has been open;

a dissimilarity between a plurality of similarity scores associated with image sets that are already in the particular group;

quality measurements that are indicated in data that is stored in association with at least one image set in the particular group;

a positive identification, of an object associated with the particular group, based on a similarity score between (a) at least one image set in the particular group and (b) a stored event;

or

an object, associated with the particular group, being in an image but outside a field of view that is associated with a certain portion of the image;

before said particular group is closed;

receiving a first new image set, and

comparing the first new image set to one or more image sets in said particular group and to one or more images sets in one or more other groups of the plurality of groups;

after the particular group is closed;

receiving a second new image set, and

comparing the second new image set to one or more images sets in one or more groups of the plurality of groups without comparing the second new image set to any image set in said particular group;

wherein the method is performed by one or more processors.

2. The method of claim 1, wherein determining when to close a particular group of the plurality of groups is performed based, at least in part, on how many image sets are in the particular group.

3. The method of claim 1, wherein determining when to close a particular group of the plurality of groups is performed based, at least in part, on a total amount of time the particular group has been open.

4. The method of claim 1, wherein determining when to close a particular group of the plurality of groups is performed based, at least in part, on a dissimilarity between a plurality of similarity scores associated with image sets that are already in the particular group.

5. The method of claim 1, wherein determining when to close a particular group of the plurality of groups is performed based, at least in part, on quality measurements that are indicated in data that is stored in association with at least one image set in the particular group.

6. The method of claim 1, wherein determining when to close a particular group of the plurality of groups is performed based, at least in part, on a positive identification, of an object associated with the particular group, based on a similarity score between (a) at least one image set in the particular group and (b) a stored event.

7. The method of claim 1, wherein determining when to close a particular group of the plurality of groups is performed based, at least in part, on an object, associated with the particular group, being in an image but outside a field of view that is associated with a certain portion of the image.

8. The method of claim 1, the method further comprising, before the particular group is closed:

receiving a new image set;

selecting the particular group from the plurality of groups; and

adding the new image set to the particular group;

wherein selecting the particular group from the plurality of groups includes;

generating a similarity score between the new image set and one or more image sets in each group of the plurality of groups; and

selecting the particular group based, at least in part, on one or more of the following factors;

a highest weighted similarity score of each group, wherein the highest weighted similarity score of a group of the plurality of groups is weighted based on external information;

an average similarity score of each group, wherein the average similarity score for said each group is the average of the similarity scores of the plurality of image sets of said each group;

or

the number of image sets in each group that have corresponding similarity scores above a certain threshold.

9. One or more volatile or non-volatile storage media storing instructions which, when executed by one or more processors, cause the performance of the method recited in claim 1.

10. One or more volatile or non-volatile storage media storing instructions which, when executed by one or more processors, cause the performance of the method recited in claim 2.

11. One or more volatile or non-volatile storage media storing instructions which, when executed by one or more processors, cause the performance of the method recited in claim 3.

12. One or more volatile or non-volatile storage media storing instructions which, when executed by one or more processors, cause the performance of the method recited in claim 4.

13. One or more volatile or non-volatile storage media storing instructions which, when executed by one or more processors, cause the performance of the method recited in claim 5.

14. One or more volatile or non-volatile storage media storing instructions which, when executed by one or more processors, cause the performance of the method recited in claim 6.

15. One or more volatile or non-volatile storage media storing instructions which, when executed by one or more processors, cause the performance of the method recited in claim 7.

16. One or more volatile or non-volatile storage media storing instructions which, when executed by one or more processors, cause the performance of the method recited in claim 8.