Ad collateral detection

• US 9,245,192 B2
• Filed: 09/20/2013
• Issued: 01/26/2016
• Est. Priority Date: 09/20/2013
• Status: Active Grant

• Current Assignee: HERE Global B.V. (Nokia Corporation)
• Original Assignee: HERE Global B.V. (Nokia Corporation)
• Inventors: Bamidele, Adetokunbo
• Primary Examiner(s): MOE, AUNG SOE
• Application Number:
  US14/032,399
• Publication Number:
  US 20150085154A1
• Time in Patent Office: 858 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 20/62 Text, e.g. of license plates, overlay texts or captions on TV images
• CPC Class Codes: H04N 23/63 by using electronic viewfinders

Abstract

A method including transmitting an image from a camera of an apparatus, where the image includes one or more Ad collateral; and automatically detecting by the apparatus at least one of the Ad collateral in the image. An apparatus including at least one processor; and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to automatically discern at least one Ad collateral in a camera image.

Claims

1. A method comprising:

transmitting an image from a camera of an apparatus, where the image comprises at least one Ad collateral; and

automatically detecting by the apparatus the at least one Ad collateral in the image, where detecting the at least one Ad collateral comprises

generating a visual attention map based upon the image,

generating an edge map based upon the image,

fusing the visual attention map and the edge map,

deriving connected edges from the fusing to form one or more lines, and

tracing the one or more lines based on the fused edge and visual attention maps, and a thresholding scheme.

2. The method as in claim 1 further comprising drawing at least one recticule based upon the detecting of the at least one Ad collateral.

3. The method as in claim 2 further comprising providing the at least one recticule on a display or a view finder of the apparatus.

4. The method as in claim 3 further comprising aligning the at least one recticule relative to an Ad collateral of the at least one Ad collateral.

5. The method as in claim 1 further comprising comparing the at least one Ad collateral to Ad collaterals stored in a memory.

6. The method as in claim 1 where the fusing comprises fusing known heuristics of the visual attention map and the edge map with a biologically inspired algorithm which uses a visual attention model.

7. The method as in claim 1 further comprising, based at least partially upon the detecting of the at least one Ad collateral, identifying the at least one Ad collateral to a user of the apparatus.

8. The method as in claim 1 further comprising, based at least partially upon the detecting of the at least one Ad collateral, receiving information by the apparatus relating to the at least one Ad collateral.

9. The method as in claim 1 further comprising, based upon the detecting of the at least one Ad collateral, performing at least one function by the apparatus based, at least partially, upon coordinates of at least one of the camera and the at least one Ad collateral.

10. An apparatus comprising

at least one processor;

and

at least one memory including computer program code,

the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to;

automatically discern at least one Ad collateral in a camera image, where discerning the at least one Ad collateral comprises

generating a visual attention map based upon the camera image,

generating an edge map based upon the camera image,

fusing the visual attention map and the edge map,

deriving connected edges from the fusing to form one or more lines, and

tracing the one or more lines based on the fused edge and visual attention maps, and a thresholding.

11. The apparatus as in claim 10 where the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to at least partially identify the at least one Ad collateral.

12. The apparatus as in claim 10 where the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to automatically detect the at least one Ad collateral in the camera image.

13. The apparatus as in claim 10 where the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to draw at least one recticule based upon the discerning of the at least one Ad collateral.

14. The apparatus as in claim 13 where the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to provide the at least one recticule on a display or a view finder of the apparatus.

15. The apparatus as in claim 13 where the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to align the at least one recticule relative to an Ad collateral of the at least one Ad collateral.

16. The apparatus as in claim 10 where the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to compare the at least one Ad collateral to Ad collaterals stored in a memory.

17. The apparatus as in claim 10 where the fusing comprises fusing known heuristics of the visual attention map and the edge map with a biologically inspired algorithm which uses a visual attention model.

18. The apparatus as in claim 10 where the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to, based upon the discerning of the at least one Ad collateral, perform at least one function by the apparatus based, at least partially, upon coordinates of at lest one of the apparatus and the at least one Ad collateral.

19. The apparatus as in claim 10 comprising means for automatically detecting by the apparatus the at least one of the at least one Ad collateral in the camera image.

20. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations comprising:

analyze an image from a camera, where the image comprises one or more Ad collateral; and

automatically discern at least one of the Ad collateral in the image, where discerning the at least one Ad collateral comprises

generating a visual attention map based upon the camera image,

generating an edge map based upon the camera image,

fusing the visual attention map and the edge map,

deriving connected edges from the fusing to form one or more lines, and

tracing the one or more lines based on the fused edge and visual attention maps, and a thresholding.