Counting and monitoring method using face detection

• US 9,928,409 B2
• Filed: 11/01/2016
• Issued: 03/27/2018
• Est. Priority Date: 01/11/2014
• Status: Active Grant

• Current Assignee: Cognyte Technologies Israel Ltd. (Cognyte Software Ltd.)
• Original Assignee: Verint Systems Limited (Verint Systems Incorporated)
• Inventors: Dudovich, Boaz
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US15/340,383
• Publication Number:
  US 20170116469A1
• Time in Patent Office: 511 Days
• Field of Search: 382100, 382103-107, 382115, 382118, 382151, 382155, 382162, 382168, 382173, 382181, 382189, 382199, 382209, 382219, 382224, 382232, 382254, 382274, 382276, 382286-291, 382305, 382312, 382321, 348150, 348170, 3482312, 348161, 707756, 705 728, 709225, 37916702
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06V 20/40 in video content extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44
• 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 40/173 face re-identification, e.g. recognising unknown faces across different face tracks

Abstract

Video is often used to count and identify people entering and exiting an area, such as a store. This information may be used to determine the number and amount of time people are in the area, and other statistics and characteristics. These variables may be skewed by the associates employed or working in the area, instead of patrons or others. The present disclosure is directed to method for eliminating associates from video by facial analysis and the application of analytics.

Claims

1. A method for detecting a person in a store via a video processing system, comprising:

receiving, by a video processing system, video captured by a video source at a predetermined location, wherein the video source captures video containing people passing through a field of view of the video source at the predetermined location;

processing the video, by the video processing system, to determine at least one bodily characteristic of each person passing through the field of view of the video source;

storing, by the video processing system, an image of each person in a database, the image being from the video, wherein the image is stored in the database in accordance with the at least one bodily characteristic;

profiling, by the video processing system, each body part of store associates based on an analysis of full body images of the store associates;

determining, by the video processing system, if each person is a customer or store associate based upon the at least one bodily characteristic and using the profiled store associates;

creating, by the video processing system, an album comprising a plurality of images, wherein each of the plural images is of a unique person retrieved from the database; and

providing, by the video processing system, the album to a user interface for display.

2. The method of claim 1, wherein the at least one bodily characteristic includes one of facial characteristics, colors, hair, mouth, head shape, gender, age, and body part characteristics.

3. The method of claim 1, further comprising providing, by the video processing system, an indication within the album that a face associated with at least one of the plural images is associated with a person wanted by law enforcement.

4. The method of claim 1, further comprising tracking, by the video processing system, movement of the store associate.

5. The method of claim 1, further comprising tracking, by the video processing system, movement of the customer.

6. The method of claim 5, further comprising determining, by the video processing system, if the customer is part of a shopping group comprising a family of two of more customers.

7. The method of claim 1, wherein the only images stored in the database are images that were determined to be of customers and not of store associates.

8. The method of claim 1, wherein the field of view is an entrance or an exit of a store.

9. The method of claim 8, further comprising comparing, by the video processing system, an image of the customer captured at the entrance with an image of the customer captured at the exit to determine a length of time the customer was in the store.

10. The method of claim 1, wherein the at least one bodily characteristic is a face.

11. The method of claim 1, further comprising providing, by the video processing system, a face album to a user interface, the face album presenting images of customers.

12. A video processing system for detecting a person in a store, the video processing system comprising:

a memory; and

a processor, which is configured to;

receive video captured by a video source at a predetermined location, wherein the video source captures video containing people passing through a field of view of the video source at the predetermined location;

process the video to determine at least one bodily characteristic of each person passing through the field of view of the video source;

store an image of each person in a database, the image being from the video, wherein the image is stored in the database in accordance with the at least one bodily characteristic;

profile each body part of store associates based on an analysis of full body images of the store associates;

determine if each person is a customer or store associate based upon the at least one bodily characteristic and using the profiled store associates;

create an album comprising a plurality of images, wherein each of the plural images is of a unique person retrieved from the database; and

provide the album to a user interface for display.

13. The video processing system of claim 12, wherein the bodily characteristics include at least one of eyes and hair.

14. The video processing system of claim 12, wherein the processor is further configured to provide an indication within the album that a face associated with at least one of the plural images is associated with a person wanted by law enforcement.

15. A non-transitory tangible computer readable medium containing computer executable instructions that when executed by a processor of a video processing system cause the video processing system to perform a method comprising:

receiving captured by a video source at a predetermined location, wherein the video source captures video containing people passing through a field of view of the video source at the predetermined location;

processing the video to determine at least one bodily characteristic of each person passing through the field of view of the video source;

storing an image of each person in a database, the image being from the video, wherein the image is stored in the database in accordance with the at least one bodily characteristic;

profiling each body part of store associates based on an analysis of full body images of the store associates;

determining if each person is a customer or store associate based upon the at least one bodily characteristic and using the profiled store associates;

creating an album comprising a plurality of images, wherein each of the plural images is of a unique person retrieved from the database; and

providing the album to a user interface for display.

16. The non-transitory tangible computer readable medium of claim 15, wherein the at least one bodily characteristic includes one of facial characteristics, colors, hair, mouth, head shape, gender, age, and body part characteristics.

17. The non-transitory tangible computer readable medium of claim 15, further comprising instructions for tracking movement of the customer.

18. The non-transitory tangible computer readable medium of claim 17, further comprising instructions for determining if the customer is part of a shopping group comprising a family of two of more customers.