Determination of inventory conditions based on image processing

• US 8,009,864 B2
• Filed: 08/31/2007
• Issued: 08/30/2011
• Est. Priority Date: 08/31/2007
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services Limited (Accenture PLC)
• Inventors: Fano, Andrew, Opalach, Agata, Linaker, Fredrik, Groenevelt, Robert Bernard (Robin)
• Primary Examiner(s): BHATNAGAR, ANAND P
• Application Number:
  US11/849,177
• Publication Number:
  US 20090060349A1
• Time in Patent Office: 1,460 Days
• Field of Search: 382/100, 382/103, 382/110, 382/141, 382/142, 382/143, 382/181, 382/190, 382/192, 382/195, 382/206, 705/22, 705/28, 705/14.24, 235/385
• US Class Current: 382/103
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 20/203 Inventory monitoring
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59

Abstract

Image analysis techniques, including object recognition analysis, are applied to images obtained by one or more image capture devices deployed within inventory environments. The object recognition analysis provides object recognition data (that may include one or more recognized product instances) based on stored product (training) images. In turn, a variety of functionalities may be enabled based on the object recognition data. For example, a planogram may be extracted and compared to a target planogram, or at least one product display parameter for a product can be determined and used to assess presence of the product within the inventory environment, or to determine compliance of display of the product with a promotional objective. In yet another embodiment, comparisons may be made within a single image or between multiple images over time to detect potential conditions requiring response. In this manner, efficiency and effectiveness of many previously manually-implemented tasks may be improved.

Claims

1. A computer-implemented method, comprising:

receiving, by an image analysis server, a first image of a location within an inventory environment;

receiving, by the image analysis server, a second image, captured after the first image, of the location within the inventory environment;

performing, by the image analysis server, object recognition analysis on the first image and the second image,

comparing, by the image analysis server, at least a portion of the first image with at least a portion of the second image; and

providing, by the image analysis server, an indication of a potential condition requiring response when the object recognition analysis of the first image detects at least one recognized object instance that is not detected based on the object recognition analysis of the second image.

2. The method of claim 1, further comprising providing the indication when the portion of the first image does not substantially match the portion of the second image.

3. The method of claim 1, further comprising providing the indication when the portion of the first image substantially matches the portion of the second image.

4. A computer-implemented method, comprising:

receiving, by a image analysis server, an image of a location within an inventory environment;

comparing, by the image analysis server, at least a first portion of the image with at least a second portion of the image; and

providing, by the image analysis server, an indication of a potential condition requiring response when the first portion of the image does not compare favorably with the second portion of the image.

5. The method of claim 4, wherein the second portion of the image comprises an adjacent portion of the image.

6. The method of claim 4, further comprising providing the indication when the first portion of the image does not substantially match the second portion of the image.

7. The method of claim 4, further comprising providing the indication when the first portion of the image substantially matches the second portion of the image.

8. The method of claim 4, further comprising:

performing, by the image analysis server, object recognition analysis on the image,

wherein providing the indication further comprises providing the indication when the object recognition analysis of the first portion of the image detects at least one recognized object instance that is not detected based on the object recognition analysis of the second portion of the image.

9. An apparatus, comprising:

an image capture device configured and disposed to capture images within an inventory environment; and

an image analysis server, in communication with the image capture device, operative to receive a first image of a location within the inventory environment, receive a second image, captured after the first image, of the location within the inventory environment, perform object recognition analysis on the first image and the second image, compare at least a portion of the first image with at least a portion of the second image, and provide an indication of a potential condition requiring response when the object recognition analysis of the first image detects at least one recognized object instance that is not detected based on the object recognition analysis of the second image.

10. The apparatus of claim 9, wherein the image analysis server is further operative to provide the indication when the portion of the first image does not substantially match the portion of the second image.

11. The apparatus of claim 9, wherein the image analysis server is further operative to provide the indication when the portion of the first image substantially matches the portion of the second image.

12. An apparatus, comprising:

an image capture device configured and disposed to capture images within an inventory environment; and

an image analysis server, in communication with the image capture device, operative to receive an image of a location within the inventory environment, compare at least a first portion of the image with at least a second portion of the image, and provide an indication of a potential condition requiring response when the first portion of the image does not compare favorably with the second portion of the image.

13. The apparatus of claim 12, wherein the second portion of the image comprises an adjacent portion of the image.

14. The apparatus of claim 12, wherein the image analysis server is further operative to provide the indication when the first portion of the image does not substantially match the second portion of the image.

15. The apparatus of claim 12, wherein the image analysis server is further operative to provide the indication when the first portion of the image substantially matches the second portion of the image.

16. The apparatus of claim 12, wherein the image analysis server is further operative to perform object recognition analysis on the image and provide the indication when the object recognition analysis of the first portion of the image detects at least one recognized object instance that is not detected based on the object recognition analysis of the second portion of the image.

17. A non-transitory computer-readable medium having stored thereon executable instructions that, when executed, cause a processing device to:

receive a first image of a location within the inventory environment,

receive a second image, captured after the first image, of the location within the inventory environment,

perform object recognition analysis on the first image and the second image;

compare at least a portion of the first image with at least a portion of the second image, and

provide an indication of a potential condition requiring response when the object recognition analysis of the first image detects at least one recognized object instance that is not detected based on the object recognition analysis of the second image.

18. The non-transitory computer-readable medium of claim 17, having stored thereon executable instruction that, when executed, further cause the processing device to provide the indication when the portion of the first image does not substantially match the portion of the second image.

19. The non-transitory computer-readable medium of claim 17, having stored thereon executable instruction that, when executed, further cause the processing device to provide the indication when the portion of the first image substantially matches the portion of the second image.

20. A non-transitory computer-readable medium having stored thereon executable instructions that, when executed, cause a processing device to:

receive an image of a location within the inventory environment,

compare at least a first portion of the image with at least a second portion of the image, and

provide an indication of a potential condition requiring response when the first portion of the image does not compare favorably with the second portion of the image.

21. The non-transitory computer-readable medium of claim 20, wherein the second portion of the image comprises an adjacent portion of the image.

22. The non-transitory computer-readable medium of claim 20, having stored thereon executable instruction that, when executed, further cause the processing device to provide the indication when the first portion of the image does not substantially match the second portion of the image.

23. The non-transitory computer-readable medium of claim 20, having stored thereon executable instruction that, when executed, further cause the processing device to provide the indication when the first portion of the image substantially matches the second portion of the image.

24. The non-transitory computer-readable medium of claim 20, having stored thereon executable instruction that, when executed, further cause the processing device to:

perform object recognition analysis on the image; and

provide the indication when the object recognition analysis of the first portion of the image detects at least one recognized object instance that is not detected based on the object recognition analysis of the second portion of the image.