Time-in store estimation using facial recognition

• US 9,607,212 B2
• Filed: 12/17/2015
• Issued: 03/28/2017
• Est. Priority Date: 12/12/2012
• Status: Active Grant

• Current Assignee: Cognyte Technologies Israel Ltd. (Cognyte Software Ltd.)
• Original Assignee: Verint Systems Limited (Verint Systems Incorporated)
• Inventors: Golan, Oren, Zimerman, Gadi, Figov, Zvi, Waisman, Ofer, Falckovitch, Elad, Yankovitch, Doron
• Primary Examiner(s): Tabatabai, Abolfazl
• Application Number:
  US14/973,074
• Publication Number:
  US 20160180153A1
• Time in Patent Office: 467 Days
• Field of Search: 382/103, 382/107, 382115-118, 382/236, 348169-172, 348/352, 348/150
• US Class Current: 1/1
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• 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 40/167 using comparisons between temporally consecutive images
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G06V 40/173 face re-identification, e.g. recognising unknown faces across different face tracks

Abstract

A method of monitoring the amount of time spent in a specified area by an individual comprises employing a first camera to automatically create one or more entrance images, each entrance image containing a face of an entering individual that passes a first location, and storing each entrance image in a database along with a corresponding entrance time that the entering individual passed the entrance location. An exit image is compared to the entrance images in the database to identify a matching entrance image containing the same face as the exit image. A stay time is then determined for the exiting individual by determining the difference between the entrance time corresponding to the matching entrance image and the exit time.

Claims

1. A method of monitoring the amount of time spent in a specified area by an individual, the method comprising:

receiving a plurality of entrance images from one or more cameras, each entrance image containing a face of an entering individual who passed a first location;

timestamping each entrance image with an entrance time corresponding to when the entering individual passed the first location and storing each entrance image in a database along with the corresponding entrance time;

receiving an exit image containing a face of an exiting individual who passed a second location;

timestamping the exit image with an exit time corresponding to when the exiting individual passed the second location and storing the exit image in the database along with the corresponding exit time;

identifying a matching entrance image containing the same face as the exit image by at least comparing the exit image stored in the database to the entrance images stored in the database; and

calculating a stay time for the exiting individual by at least determining the difference between the entrance time stored in the database corresponding to the matching entrance image and the exit time stored in the database corresponding to the exit image.

2. The method of claim 1, further including a first step of employing a first camera to automatically record an image of the first location;

and a step of creating the plurality of entrance images by at least;

processing the image of the first location with a face detection algorithm to detect a face;

determining a facial feature descriptor for the detected face using a facial recognition algorithm; and

generating an entrance image to include the facial feature descriptor.

3. The method of claim 1, further including a first step of employing a first camera to automatically record an image of the second location;

and

a step of creating the exit image by at least;

processing the image of the second location with a face detection algorithm to detect a face;

determining a facial feature descriptor for the detected face using a facial recognition algorithm; and

generating an exit image to include the facial feature descriptor.

4. The method of claim 1, further including a first step of employing a first camera to automatically record an image of the first location;

and

a step of creating the plurality of entrance images by at least;

processing the image of the first location with a person detection algorithm to detect a person;

using the person detection algorithm to identify a head area of the detected person in the image of the first location;

generating an entrance image based on the head area of the detected person.

5. The method of claim 4, further including using a facial feature extractor algorithm to determine a facial feature descriptor for the detected person.

6. The method of claim 1, further comprising determining stay times of multiple exiting individuals over a predefined time period based on a comparison of entrance and exit times or matching entrance and exit images.

7. The method of claim 6, further comprising averaging the stay times within the predefined time period to create an average stay time for the predefined time period.

8. The method of claim 7, further comprising creating a graphical depiction of average stay time over time.

9. The method of claim 1, wherein the step of identifying the matching entrance image includes locating an entrance image in the database, if any, that meets at least a predefined commonality threshold with the exit image.

10. A system for monitoring time spent in a location by an individual, the system comprising:

a first camera positioned to record images of individuals passing a first location;

a first image processing module configured to;

process the recorded images from the first camera using a face detection algorithm to detect faces within the recorded image;

create an entrance image of each detected face; and

timestamp each entrance image with an entrance time that corresponds to when an individual in the entrance image passed the first location;

a database configured to receive and store each entrance image and the corresponding entrance time;

a second camera positioned to record individuals passing a second location;

a second image processing module configured to;

process the recorded images from the second camera using a face detection algorithm to detect faces within the recorded image;

create an exit image of each detected face; and

timestamp the exit image with an exit time that corresponds to when an individual in the exit image passed the second location;

an image matching module configured to compare the exit image stored in the database to the entrance images stored in the database using a facial recognition algorithm to identify a matching entrance image containing the same face as an exiting individual of the exit image; and

a stay time calculator module configured to calculate a stay time for a matched exiting individual by determining the difference between the entrance time stored in the database corresponding to the matching entrance image and the exit time stored in the database corresponding to the exit image.

11. The system of claim 10, wherein the first camera is positioned to record individuals entering a store and the second camera is positioned to record individuals exiting the store;

and wherein the stay time for the exiting individual is the time that the exiting individual spent in the store.

12. The system of claim 10, having a centralized image processing module that receives data from both the first camera and the second camera, wherein the first image processing module and the second image processing module are encompassed in the centralized image processing module.

13. The system of claim 10, wherein unmatched entrance images are removed from the database of entrance images after a predefined period of time.

14. A method of monitoring a time-in-store for an individual, the method comprising:

recording an image of an entrance location with a first camera;

timestamping the image of the entrance location with an associated entrance time;

detecting one or more faces in the image of the entrance location using a face detection algorithm;

creating an entrance image of the one or more faces detected in the image of the entrance location;

storing the entrance image and the entrance time together in an entrance image database;

recording an image of an exit location with a second camera;

timestamping the image of the exit location with an associated exit time; and

detecting one or more faces in the image of the exit location using the face detection algorithm;

creating an exit image of the one or more faces detected in the image of the exit location;

storing the exit image and the exit time together in an exit image database;

detecting a matching entrance image by at least using a facial recognition algorithm to compare the exit image stored in the exit image database to one or more exit images stored in the entrance image database, wherein the matching entrance image contains a facial match to the exit image;

calculating a stay time for a matched exiting individual by at least determining the difference between the exit time stored in the database corresponding to the exit image and the entrance time stored in the database corresponding to the matching entrance image.

15. The method of claim 14, wherein recording an image of an entrance location includes continuously recording video images of the first location;

and

recording an image of an exit location includes continuously recording video images of the second location.

16. The method of claim 15, further including processing the video images of the first location or the second location to detect changes;

and

wherein the detecting one or more faces in the image of the entrance location includes processing the video images of the first location with the face detection algorithm after detecting a change in the images of the first location, and the detecting one or more faces in the image of the exit location includes processing the video images of the second location with the face detection algorithm after detecting a change in the images of the second location.

17. The method of claim 15, wherein the detecting one or more faces in the image of the entrance location includes continuously processing the video images of the first location and the second location using the face detection algorithm.

18. The method of claim 14, further comprising:

identifying unmatched entrance images in the entrance image database; and

removing unmatched entrance images from the entrance image database that have entrance times before a predefined time period.

19. The method of claim 14, further comprising calculating stay times for multiple matched entrance and exit images over a predefined time period and averaging the stay times within the predefined time period to create an average stay time for the predefined time period.

20. The method of claim 19, further comprising calculating an estimated arrival time at a check-out location for an individual passing an entrance location based on the average stay time.