Movement timestamping and analytics

• US 8,457,354 B1
• Filed: 07/09/2010
• Issued: 06/04/2013
• Est. Priority Date: 07/09/2010
• Status: Expired due to Fees

• Current Assignee: Target Brands Inc. (Target Corporation)
• Original Assignee: Target Brands Inc. (Target Corporation)
• Inventors: Kolar, Clare E., Foster, Robert F.
• Primary Examiner(s): Repko, Jason M
• Assistant Examiner(s): FUJITA, KATRINA R
• Application Number:
  US12/833,499
• Time in Patent Office: 1,061 Days
• Field of Search: 382/103, 348/143, 348/169
• US Class Current: 382/103
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G06V 10/809 of classification results, e.g. where the classifiers operate on the same input data
• CPC Class Codes: G06V 20/30 in albums, collections or shared content, e.g. social network photos or video
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

In selected embodiments, a computer-implemented method for analyzing customer movement in a retail environment includes capturing an image of an individual at multiple locations within a retail environment and tracking the elapsed time between the individual'"'"'s appearance at the various locations. For areas of the store at increased risk for shoplifting, the elapsed times may be compared to predetermined upper and/or lower elapsed time thresholds or windows to determine whether an individual is likely to commit a crime in the retail environment. The thresholds or window may be empirically determined based on analysis of historical security video footage and security incident records.

Claims

1. A method for analyzing a person'"'"'s movement in a retail environment, comprising:

capturing a first image of a first person at a first location at a first time;

capturing a second image of a second person at a second location, remote from the first location, at a second time;

identifying, by analyzing with at least one computing device, one or more characteristics associated with the image of the first person and the image of the second person;

determining, by analyzing with the at least one computing device, whether the first person and the second person are likely to be the same individual;

in response to a determination that the first person is likely to be the second person, comparing, with the at least one computing device, the elapsed time between the first time and the second time with a maximum elapsed time threshold that is indicative of a likelihood that the first person has committed or will commit a crime within the retail environment; and

determining, by analyzing with the at least one computing device, how many of a plurality of locations in a retail environment the first person traveled to within a predetermined period of time include a merchandise display that is likely a target of shoplifting.

2. The method of claim 1, wherein the maximum elapsed time threshold is based at least in part on the distance between the first location and second location and the nature of the retail environment.

3. The method of claim 1, wherein the maximum elapsed time threshold is based in part on an empirical assessment of data associated with previous monitoring of the first location and the second location.

4. The method of claim 1, further comprising determining whether the elapsed time is above a minimum elapsed time threshold.

5. The method of claim 4, wherein the minimum elapsed time threshold and the maximum elapsed time threshold cooperatively define an elapsed time window indicative of an increased likelihood that the first person has committed or will commit a crime within the retail environment.

6. The method of claim 1, wherein the one or more characteristics comprise color, size, shape, gender, clothing, facial feature, body feature, an item associated with the person, or combinations thereof.

7. The method of claim 1, wherein the first location is proximate an entry to the retail environment.

8. The method of claim 1, wherein the first location is proximate a product display including items at increased risk for shoplifting.

9. A system for analyzing a person'"'"'s movement, the system comprising:

an electronic image capture system configured to capture (i) a first image of a first scene of a first location and (ii) a second image of a second scene of a second location remote from the first location, the first and second images being associated with first and second time stamps, respectively;

at least one computing device having instructions to recognize (i) a first character in the first image and (ii) a second character in the second image, wherein first and second parameters characterize attributes of the first and second characters, respectively; and

a video analytics system having instructions that (i) determines, using at least the first and second parameters, that the first and second characters correspond to one actor;

(ii) determines whether a predetermined time criterion exists between the first scene and the second scene;

(iii) compares a maximum elapsed time criterion with a time difference between the first and second time stamps only if a predetermined time criterion exists between the first scene and the second scene, the maximum elapsed time criterion is indicative of the likelihood that the first character will commit a crime; and

(iv) determines how many of a plurality of locations in a retail environment the first character traveled to within a predetermined period of time include a merchandise display that is a likely target of shoplifting.

10. The system of claim 9, wherein each of the first and second parameters includes a parameter selected from:

color, size, shape, gender, clothing, facial feature, body feature, an item associated with the actor, and combinations thereof.

11. The system of claim 9, wherein the video analytics system further determines whether the time difference is greater than a minimum elapsed time threshold, thereby determining whether the elapsed time is within an elapsed time window.

12. The system claim 11, wherein the elapsed time window is based at least in part on previous monitoring of the first and second scenes using the electronic image capture system.

13. The system of claim 12, wherein the previous monitoring comprises:

performing observation over a period of time, using the electronic image capture system, of at least part of an area that includes the first and second scenes; and

identifying, among multiple actors in the area, a first actor who engages in prohibited behavior during the period of time;

wherein the time limit is defined based at least in part on the observation of the first actor.

14. The system claim 9, wherein both the first and second scenes include a retail store ingress or egress.

15. The system claim 9, wherein both the first and second scenes include a retail product display.

16. The system claim 15, wherein only one of the first and second scenes includes products at an increased risk of shoplifting.

17. The system claim 15, wherein the first and second scenes both include products at an increased risk of shoplifting.

18. The system of claim 9, wherein only one of the first and second scenes include a retail ingress.

19. The system of claim 9, wherein the actor is a human.

20. A computer-implemented method of analyzing an individual'"'"'s movements in a retail environment, comprising the steps of:

operating a video surveillance system to monitor a plurality of locations at a retail environment, at least some of the plurality of locations include a merchandise display that is a likely target of shoplifting;

determining, by analyzing with at least one computing device, a plurality of locations at the retail environment that a first individual travels to within a predetermined period of time and assigning a crime score to the first individual based at least in part on how many of the plurality of locations that the first individual traveled to within the predetermined period of time include a merchandise display that is a likely target of shoplifting, the at least one computing device being configured to differentiate the first individual from other individuals at the retail environment;

determining the elapsed time the first individual traveled from a first location at the retail environment to a second location of the retail environment, at least one of the first location and the second location includes a merchandise display that is a likely target of shoplifting;

adjusting the crime score of the first individual based at least in part on the elapsed time the first individual traveled from the first location to the second location; and

,

generating a security notification specific to the first individual if the first individual'"'"'s crime score exceeds a predetermined value.