Intelligent video verification of point of sale (POS) transactions

• US 7,925,536 B2
• Filed: 05/25/2007
• Issued: 04/12/2011
• Est. Priority Date: 05/25/2006
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: ObjectVideo Incorporated (Alarm.com Holdings, Inc.)
• Inventors: Hu, Yongtong, Scanlon, W. Andrew, Yu, Li, Zhang, Zhong, Venetianer, Peter L., Lipton, Alan J., Yin, Weihong
• Primary Examiner(s): Gart; Matthew S
• Assistant Examiner(s): Iwarere; Oluseye
• Application Number:
  US11/802,895
• Publication Number:
  US 20070272734A1
• Time in Patent Office: 1,418 Days
• Field of Search: 705/16
• US Class Current: 705/16
• CPC Class Codes: G06Q 20/20 Point-of-sale [POS] network systems
• CPC Class Codes: G06Q 20/401 Transaction verification
• CPC Class Codes: G07G 1/0036 Checkout procedures
• CPC Class Codes: G07G 3/00 Alarm indicators, e.g. bells
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

Non video data regarding a point of sale (POS) transaction is received. POS primitives are generated based on the received non video POS data. Video data regarding a corresponding POS transaction is received. Video primitives are generated based on the received video data. An exceptional transaction is inferred based on a corresponding exceptional transaction rule and at least one of the generated POS primitives or video primitives.

Claims

1. A non-transitory computer-readable medium comprising software for monitoring a point of sale (POS) transaction, which software, when executed by a computer system, causes the computer system to perform operations comprising a method of:

receiving non video data regarding the point of sale (POS) transaction;

processing the received non video POS data to generate POS primitives, the POS primitives being data descriptions of the content of the received non video POS data;

receiving video data regarding the corresponding POS transaction;

processing the received video data to generate video primitives, the video primitives being data descriptions of the content of the received video data;

defining exceptional transaction rules based on at least one predetermined video data event and at least one predetermined non video data event; and

inferring an exceptional transaction based on a corresponding exceptional transaction rule and at least one of the generated POS primitives or video primitives.

2. The medium as set forth in claim 1, wherein the method further includes:

defining policy violation rules based at least on predetermined exceptional transactions; and

determining a policy violation based on a corresponding policy violation rule and the inferred exceptional transaction.

3. The medium as set forth in claim 2, wherein the method further includes:

generating a policy violation report based on the determined policy violation.

4. The medium as set forth in claim 1, wherein the method further includes:

generating an exceptional transaction report based on the inferred exceptional transaction.

5. The medium as set forth in claim 1, wherein the POS primitives and video primitives are generated contemporaneously.

6. The medium as set forth in claim 1, wherein the method further includes:

storing the video and POS primitives in a primitive database prior to the step of inferring; and

one of performing the step of inferring in real time or withdrawing the video and POS primitives from the primitive database and inferring the exceptional transaction based on the withdrawn video and POS primitives.

7. The medium as set forth in claim 1, wherein receiving video data includes:

receiving video data from a first video camera.

8. The medium as set forth in claim 7, wherein receiving video data further includes:

receiving auxiliary video data from one or more auxiliary video cameras.

9. The medium as set forth in claim 1, wherein the method is performed locally.

10. The medium as set forth in claim 1, wherein the method further includes:

receiving the non video data regarding the POS transaction via a communication channel at a remote location;

receiving the video data regarding the corresponding POS transaction via the communication channel at the remote location;

processing the received non video POS data to generate POS primitives at the remote location;

processing the received video data to generate video primitives at the remote location;

defining exceptional transactions rules based on at least one predetermined non video data event and at least one predetermined video data event at the remote location; and

inferring the exceptional transaction at the remote location.

13. The medium as set forth in claim 1, wherein the step of inferring further includes:

inferring an exceptional transaction based on a corresponding exceptional transaction rule, the generated POS primitives, and the generated video primitives.

11. A method for monitoring a point of sale (POS) transaction, comprising:

receiving non video data regarding the point of sale (POS) transaction;

processing the received non video POS data to generate POS primitives using a first computer processor, the POS primitives being data descriptions of the content of the received non video POS data;

receiving video data regarding the corresponding POS transaction;

processing the received video data to generate video primitives using the first or a second a computer processor, the video primitives being data descriptions of the content of the received video data;

defining exceptional transaction rules based on at least one predetermined video data event and at least one predetermined non video data event; and

inferring an exceptional transaction based on a corresponding exceptional transaction rule and at least one of the generated POS primitives or video primitives.

14. The method as set forth in claim 11, wherein the step of inferring further includes:

inferring an exceptional transaction based on a corresponding exceptional transaction rule, the generated POS primitives, and the generated video primitives.

12. A system, comprising:

a POS data parsing engine to receive non video data regarding a POS transaction and generate POS primitives, the POS primitives being data descriptions of the content of the received non video POS data;

a video content analysis engine to receive the video data regarding the corresponding POS transaction and generate video primitives, the video primitives being data descriptions of the content of the received video data;

an exceptional transaction inference engine to infer an exceptional transaction based on a corresponding exceptional transaction rule and at least on one of the generated POS primitives or video primitives; and

at least one computer processor to implement the POS data parsing engine, the video content analysis engine, and the exceptional transaction inference engine.

15. The system as set forth in claim 12, wherein the exception transaction inference engine infers an exceptional transaction based on a corresponding exceptional transaction rule, the generated POS primitives, and the generated video primitives.

16. A non-transitory computer-readable medium comprising software for monitoring a point of sale (POS) transaction, which software, when executed by a computer system, causes the computer system to perform operations comprising a method of:

receiving non video data regarding the point of sale (POS) transaction;

receiving video data regarding the corresponding POS transaction;

processing the received video data to generate video primitives, the video primitives being data descriptions of the content of the received video data;

defining exceptional transaction rules based on at least one predetermined video data event and at least one predetermined non video data event; and

inferring an exceptional transaction based on a corresponding exceptional transaction rule and at least one of the generated video primitives or the non video data.

17. The medium as set forth in claim 16, wherein the step of inferring further includes:

inferring an exceptional transaction based on a corresponding exceptional transaction rule, the generated video primitives, and the non video data.

18. A method for monitoring a point of sale (POS) transaction, comprising:

receiving non video data regarding the point of sale (POS) transaction;

receiving video data regarding the corresponding POS transaction;

processing the received video data to generate video primitives using the first or a second a computer processor, the video primitives being data descriptions of the content of the received video data;

defining exceptional transaction rules based on at least one predetermined video data event and at least one predetermined non video data event; and

inferring an exceptional transaction based on a corresponding exceptional transaction rule and at least one of the generated video primitives or non video data.

19. The method as set forth in claim 18, wherein the step of inferring further includes:

inferring an exceptional transaction based on a corresponding exceptional transaction rule, the generated video primitives, and the non video data.

20. A system, comprising:

a POS data parsing engine to receive non video data regarding a POS transaction;

a video content analysis engine to receive the video data regarding the corresponding POS transaction and generate video primitives, the video primitives being data descriptions of the content of the received video data;

an exceptional transaction inference engine to infer an exceptional transaction based on a corresponding exceptional transaction rule and at least on one of the generated video primitives or the non video data; and

at least one computer processor to implement the POS data parsing engine, the video content analysis engine, and the exceptional transaction inference engine.

21. The system as set forth in claim 20, wherein the exception transaction inference engine infers an exceptional transaction based on a corresponding exceptional transaction rule, the generated video primitives, and the non video data.

22. A non-transitory computer-readable medium comprising software for monitoring a point of sale (POS) transaction, which software, when executed by a computer system, causes the computer system to perform operations comprising a method of:

receiving non video data regarding the point of sale (POS) transaction;

receiving video data regarding the corresponding POS transaction;

processing the received video data to generate processed video data;

defining exceptional transaction rules based on at least one predetermined video data event and at least one predetermined non video data event; and

inferring an exceptional transaction based on a corresponding exceptional transaction rule and at least one of the processed video data or the non video data.