Logo detection for indoor positioning

• US 8,938,257 B2
• Filed: 06/01/2012
• Issued: 01/20/2015
• Est. Priority Date: 08/19/2011
• Status: Expired due to Fees

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Chao, Hui, Hu, Nan, Das, Saumitra Mohan, Gupta, Rajarshi
• Primary Examiner(s): Shen, Qun
• Application Number:
  US13/486,359
• Publication Number:
  US 20130045751A1
• Time in Patent Office: 963 Days
• Field of Search: 455/456.1, 455/404.2
• US Class Current: 455/456.1
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• CPC Class Codes: G01C 21/3602 Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
• CPC Class Codes: G01S 5/16 using electromagnetic waves other than radio waves
• CPC Class Codes: G06F 16/24575 using context

Abstract

Example methods, apparatuses, or articles of manufacture are disclosed herein that may be utilized, in whole or in part, to facilitate or support one or more operations or techniques for logo detection for indoor positioning for use in or with a mobile device. Briefly, in accordance with one implementation, a method may include extracting, at a mobile device, visual features from one or more images captured via a camera sensor of the mobile device; and estimating a location of the mobile device based, at least in part, on a match between extracted visual features and one or more brand-specific visual signatures associated with one or more points of interest of one or more known locations. In some instances, an estimated location of a mobile device may be refined based, at least in part, on at least one additional POI of one or more POIs of one or more known locations.

Claims

1. A mobile-based method for estimating a location of a mobile device, comprising:

receiving, at said mobile device, one or more brand-specific visual signatures associated with one or more points of interest (POIs) of one or more known locations;

extracting visual features from one or more images captured via a camera sensor of said mobile device;

matching said extracted visual features and said one or more received brand-specific visual signatures; and

estimating a location of said mobile device based, at least in part, on;

a match between said extracted visual features and said one or more brand-specific visual signatures associated with said one or more POIs of one or more known locations, and

an estimation of a pose of said mobile device while said one or more images are captured via said camera sensor;

wherein said pose is estimated based, at least in part, on a line of sight angle of said mobile device relative to two or more POIs, and said line of sight angle comprises an angle formed between an optical axis extending axially from a camera lens of said mobile device to a logo observation line along which at least a portion of a logo is presented.

2. The method of claim 1, further comprising:

determining a location context identifier (LCI) identifying an area based, at least in part, on a rough location of said mobile device; and

identifying said one or more POIs within said area based, at least in part, on said determined LCI.

3. The method of claim 2, further comprising storing said one or more brand-specific visual signatures associated with said one or more identified POIs in memory.

4. The method of claim 1, wherein said location of said mobile device is estimated in connection with a map for indoor environment.

5. The method of claim 4, wherein said indoor environment comprises a venue.

6. The method of claim 1, wherein said visual features are extracted via an application of one or more visual feature extraction techniques.

7. The method of claim 1, wherein said one or more brand-specific visual signatures are associated with said one or more POIs via a database accessible by said mobile device.

8. The method of claim 7, wherein said database comprises a visual assistance database comprising at least one of:

an identifier (ID) of an indoor environment;

location information relating to said one or more POIs;

said extracted visual features of said one or more brand-specific visual signatures;

or any combination thereof.

9. The method of claim 1, wherein said one or more images comprises a series of video frames obtained via a panning sequence to view said one or more brand-specific visual signatures.

10. The method of claim 1, wherein said location is estimated based, at least in part, on said one or more POIs shown in said one or more images.

11. An apparatus comprising:

a mobile device comprising;

a wireless transceiver to receive visual assistance information;

a camera sensor to capture one or more images; and

at least one image processing module coupled to a memory to process said one or more images to;

extract visual features from said one or more images captured via said camera sensor; and

estimate a location of said mobile device based, at least in part, on;

a match between said extracted visual features and one or more brand-specific visual signatures associated with one or more POIs of one or more known locations, and

an estimation of a pose of said mobile device while said one or more images are captured via said camera sensor;

wherein said pose is estimated based, at least in part, on a line of sight angle of said mobile device relative to two or more POIs, and said line of sight angle comprises an angle formed between an optical axis extending axially from a camera lens of said mobile device to a logo observation line along which at least a portion of a logo is presented.

12. The apparatus of claim 11, wherein said pose is estimated based, at least in part, on a line of sight angle of said mobile device relative to two or more POIs.

13. The apparatus of claim 11, wherein said one or more brand-specific visual signatures are associated with said one or more POIs via an assistance database accessible by said mobile device and comprising at least one of:

an identifier (ID) of an indoor environment;

location information relating to said one or more POIs;

said extracted visual features of said one or more brand-specific visual signatures;

or any combination thereof.

14. The apparatus of claim 11, wherein said at least one image processing module further to:

determine a Location Context Identifier (“

LCI”

) identifying an area based, at least in part, on a rough location of said mobile device; and

identify said one or more POIs within said area based, at least in part, on said determined LCI.

15. An apparatus for estimating a location of a mobile device comprising:

receiving means for receiving, at a mobile device of said apparatus, one or more brand-specific visual signatures associated with one or more points of interest (POIs) of one or more known locations;

extraction means for extracting visual features from one or more images captured via a camera sensor of said mobile device;

matching means for matching said extracted visual features and said one or more received brand-specific visual signatures; and

estimation means for estimating a location of said mobile device based, at least in part, on;

a match between said extracted visual features and said one or more brand-specific visual signatures associated with said one or more POIs of one or more known locations, and

an estimation of a pose of said mobile device while said one or more images are captured via said camera sensor;

wherein said pose is estimated based, at least in part, on a line of sight angle of said mobile device relative to two or more POIs, and said line of sight angle comprises an angle formed between an optical axis extending axially from a camera lens of said mobile device to a logo observation line along which at least a portion of a logo is presented.

16. The apparatus of claim 15, wherein said pose is estimated based, at least in part, on a line of sight angle relative to two or more POIs.

17. The apparatus of claim 15, and further comprising comparison means for comparing said extracted visual features with said one or more brand-specific visual signatures to determine if there is a match between said extracted visual features and said one or more POIs.

18. The apparatus of claim 15, wherein said visual features are extracted via an application of one or more visual feature extraction techniques.

19. The apparatus of claim 15, wherein said one or more known locations are obtained via one or more maps for indoor environment.

20. The apparatus of claim 19, wherein said indoor environment comprises a venue.

21. The apparatus of claim 15, wherein said one or more brand-specific visual signatures are associated with said one or more POIs via a database accessible by said mobile device.

22. The apparatus of claim 21, wherein said database comprises a visual assistance database comprising at least one of:

an identifier (ID) of an indoor environment;

location information relating to said one or more POIs;

said extracted visual features of said one or more brand-specific visual signatures;

or any combination thereof.

23. The apparatus of claim 15, and further comprising:

determination means for determining a Location Context Identifier (“

LCI”

) identifying an area based, at least in part, on a rough location of said mobile device; and

identification means for identifying said one or more POIs within said area based, at least in part, on said determined LCI.

24. The apparatus of claim 23, and further comprising storage means for storing said one or more brand-specific visual signatures associated with said one or more identified POIs in memory.

25. An article comprising:

a non-transitory storage medium having instructions stored thereon executable by a special purpose computing platform at a mobile device to;

extract visual features from one or more images captured via a camera sensor of said mobile device; and

estimate a location of said mobile device based, at least in part, on;

a match between said extracted visual features and one or more brand-specific visual signatures associated with one or more points of interest (POIs) of one or more known locations, and

an estimation of a pose of said mobile device while said one or more images are captured via said camera sensor;

wherein said pose is estimated based, at least in part, on a line of sight angle of said mobile device relative to two or more POIs, and said line of sight angle comprises an angle formed between an optical axis extending axially from a camera lens of said mobile device to a logo observation line along which at least a portion of a logo is presented.

26. The article of claim 25, wherein said pose is estimated based, at least in part, on a line of sight angle relative to two or more POIs.

27. The article of claim 25, wherein said one or more brand-specific visual signatures are associated with said one or more POIs via an assistance database accessible by said mobile device and comprising at least one of:

an identifier (ID) of an indoor environment;

location information relating to said one or more POIs;

said extracted visual features of said one or more brand-specific visual signatures;

or any combination thereof.

28. The article of claim 25, wherein said storage medium further comprises instructions to:

determine an LCI identifying an area based, at least in part, on a rough location of said mobile device; and

identify said one or more POIs within said area based, at least in part, on said determined LCI.