METHOD FOR ANALYZING VIDEO DATA

• US 20170337426A1
• Filed: 05/18/2017
• Published: 11/23/2017
• Est. Priority Date: 05/18/2016
• Status: Active Grant

• Current Assignee: Idemia Identity & Security Germany AG (Advent International Corporation)
• Original Assignee: L - 1 Identity Solutions AG (Advent International Corporation)
• Inventors: Werner, Martin, Swann, Brian Scott
• Granted Patent: US 10,262,209 B2
• Time in Patent Office: Days
• CPC Class Codes: G06V 20/44 Event detection
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• 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 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

The invention provides a method of analyzing video data comprising the steps of recording the video data using one or more video recording devices; analyzing at least one video frame of the video data to extract identification information regarding a specific object of interest that is comprised in a watch list of a plurality of objects of interest, the watch list including at least one entry for each of the plurality of objects of interest; computing a matching value by comparing the extracted identification information with predetermined identification information of the specific object of interest; and storing object data and the matching value as an additional entry in the watch list in association with the specific object of interest.

Claims

1. Method of analyzing video data, the method comprising the steps of:

recording the video data using one or more video recording devices;

analyzing at least one video frame of the video data to extract identification information regarding a specific object of interest that is comprised in a watch table of a plurality of objects of interest, the watch table including at least one entry for each of the plurality of objects of interest;

computing a matching value by comparing the extracted identification information with predetermined identification information of the specific object of interest; and

storing object data and the matching value as an additional entry in the watch table in association with the specific object of interest.

2. Method according to claim 1, wherein the stored object data comprise at least a part of the video frame and/or metadata of the at least a part of the video frame.

3. Method according to claim 2, wherein the at least a part of the video frame comprises an image of the specific object of interest.

4. Method according to claim 2, wherein the metadata comprise at least one of a recording location, a recording time, and event data related to an event that is associated with the recording location and/or recording time.

5. Method according to claim 1, further

comprising the step of sorting the watch table with respect to the matching values of the entries regarding the specific object of interest, in particular in an order of decreasing matching values of the entries.

6. Method according to claim 1, wherein the watch table has a predefined maximum number of permanent entries for the specific object of interest and in case the maximum number of entries has been exceeded by storing the additional entry, the entry having the lowest matching value is removed from the watch table.

7. Method according to claim 1, wherein the specific object of interest is a specific person of interest, and wherein the stored object data preferably comprises an image of the specific person of interest, more preferably an image of a face of the specific person of interest.

8. Method according to claim 1, wherein the steps of computing a matching value and storing object data are repeated each time further identification information is extracted for the specific object of interest and/or for each further specific object of interest.

9. Method according to claim 1, further comprising the step of extracting items from the watch table related to a defined range in recording time and/or a defined region of recording locations.

10. Method according to claim 1, further comprising the step of displaying the location of the one or more video recording devices on a map and for each video recording device the matching value and/or the recording time for the specific object of interest.

11. Method according to claim 10, wherein a motion track for the specific object of interest is displayed on the map.

12. Method according to claim 1, wherein the extraction of identification information is performed by using at least one of a pattern recognition method and a face recognition method and/or wherein the step of computing a matching value is performed by using at least one of a pattern recognition method and a face recognition method.

13. Method according to claim 1, wherein the recording and analyzing of the video data is performed continuously, in particular in real time.

14. Method according to claim 1, wherein the watch table includes a white-list of persons allowed to perform a particular action or a black-list of persons not allowed to perform a particular action.

15. Method according to claim 1, wherein the predetermined identification information of the specific object of interest is pre-stored in the watch table.

16. Method according to claim 3, wherein the metadata comprise at least one of a recording location, a recording time, and event data related to an event that is associated with the recording location and/or recording time.

17. Method according to claim 2, further comprising the step of sorting the watch table with respect to the matching values of the entries regarding the specific object of interest, in particular in an order of decreasing matching values of the entries.

18. Method according to claim 3, further comprising the step of sorting the watch table with respect to the matching values of the entries regarding the specific object of interest, in particular in an order of decreasing matching values of the entries.

19. Method according to claim 4, further comprising the step of sorting the watch table with respect to the matching values of the entries regarding the specific object of interest, in particular in an order of decreasing matching values of the entries.

20. Method according to claim 2, wherein the watch table has a predefined maximum number of permanent entries for the specific object of interest and in case the maximum number of entries has been exceeded by storing the additional entry, the entry having the lowest matching value is removed from the watch table.