Image-Based Indoor Position Determination

• US 20140153773A1
• Filed: 02/01/2013
• Published: 06/05/2014
• Est. Priority Date: 11/30/2012
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: GUPTA, Rajarshi, DAS, Saumitra Mohan, CHAO, Hui, NAGUIB, Ayman Fawzy
• Granted Patent: US 9,020,191 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 7/75 involving models
• 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

In one implementation, a method may comprise: determining a topological representation of an indoor portion of a building based, at least in part, on positions or number of lines in an image of the indoor portion of the building; and comparing the topological representation to one or more stored topological representations, for example in a digital map of the building, to determine a potential position of the indoor portion of the building.

Claims

1. A method comprising:

extracting linear features from an image of an indoor portion of a building, said image captured by a camera at a mobile station;

determining a topological representation of said indoor portion based, at least in part, on positions or quantity of said linear features in said image; and

comparing said topological representation to stored topological representations of said building to determine a candidate position of said mobile station.

2. The method of claim 1, wherein said indoor portion of said building comprises a hallway or corridor.

3. The method of claim 2, wherein said linear features comprise four or more lines converging to a vanishing point in said image.

4. The method of claim 3, wherein said linear features further comprise one or more paired lines between two of said converging lines, and further comprising associating said one or more paired lines to one or more doorways, respectively, wherein said determined representation is based, at least in part, on said one or more doorways.

5. The method of claim 1, further comprising:

resolving multiple candidate positions of said mobile station based, at least in part, on a signal strength or a travel time of a wireless signal received at said mobile station.

6. The method of claim 1, further comprising:

annotating said image with a rotation vector based, at least in part, on an inertial sensor or gravitometer.

7. The method of claim 1, wherein said topological representation corresponds to said linear features in three-dimensions.

8. The method of claim 1, further comprising:

initializing a particle filter based, at least in part, on said candidate position or additional candidate positions.

9. The method of claim 1, further comprising:

determining a heading of said mobile station, wherein said comparing is further based, at least in part, on said heading.

10. The method of claim 1, further comprising:

correcting an estimated position of said mobile station based, at least in part, on said candidate position.

11. An apparatus comprising:

means for extracting linear features from an image of an indoor portion of a building, said image captured by a camera at a mobile station;

means for determining a topological representation of said indoor portion based, at least in part, on positions or quantity of said linear features in said image; and

means for comparing said topological representation to stored topological representations of said building to determine a candidate position of said mobile station.

12. The apparatus of claim 11, wherein said indoor portion of said building comprises a hallway or corridor.

13. The apparatus of claim 12, wherein said linear features comprise four or more lines converging to a vanishing point in said image.

14. The apparatus of claim 13, wherein said linear features further comprise one or more paired lines between two of said converging lines, and further comprising means for associating said one or more paired lines to one or more doorways, respectively, wherein said determined representation is based, at least in part, on said one or more doorways.

15. The apparatus of claim 11, further comprising:

means for resolving multiple candidate positions of said mobile station based, at least in part, on a signal strength or a travel time of a wireless signal received at said mobile station.

16. The apparatus of claim 11, further comprising:

means for annotating said image with a rotation vector based, at least in part, on an inertial sensor or gravitometer.

17. The apparatus of claim 11, wherein said topological representation corresponds to said linear features in three-dimensions.

18. The apparatus of claim 11, further comprising:

means for initializing a particle filter based, at least in part, on said candidate position or additional candidate positions.

19. The apparatus of claim 11, further comprising:

means for determining a heading of said mobile station, wherein said comparing is further based, at least in part, on said heading.

20. The apparatus of claim 11, further comprising:

means for correcting an estimated position of said mobile station based, at least in part, on said candidate position.

21. An apparatus comprising:

one or more processing units configured to;

extract linear features from an image of an indoor portion of a building, said image captured by a camera at a mobile station;

determine a topological representation of said indoor portion based, at least in part, on positions or quantity of said linear features in said image; and

compare said topological representation to stored topological representations of said building to determine a candidate position of said mobile station.

22. The apparatus of claim 21, wherein said indoor portion of said building comprises a hallway or corridor.

23. The apparatus of claim 22, wherein said linear features comprise four or more lines converging to a vanishing point in said image.

24. The apparatus of claim 23, wherein said linear features further comprise one or more paired lines between two of said converging lines, wherein said one or more processing units are further configured to associate said one or more paired lines to one or more doorways, respectively, and wherein said determined representation is based, at least in part, on said one or more doorways.

25. The apparatus of claim 21, wherein said one or more processing units are further configured to resolve multiple candidate positions of said mobile station based, at least in part, on a signal strength or a travel time of a wireless signal received at said mobile station.

26. The apparatus of claim 21, wherein said one or more processing units are further configured to annotate said image with a rotation vector based, at least in part, on an inertial sensor or gravitometer.

27. The apparatus of claim 21, wherein said topological representation corresponds to said linear features in three-dimensions.

28. The apparatus of claim 21, wherein said one or more processing units are further configured to initialize a particle filter based, at least in part, on said candidate position or additional candidate positions.

29. The apparatus of claim 21, wherein said one or more processing units are further configured to determine a heading of said mobile station, wherein said comparing is further based, at least in part, on said heading.

30. The apparatus of claim 21, wherein said one or more processing units are further configured to correct an estimated position of said mobile station based, at least in part, on said candidate position.

31. A non-transitory storage medium comprising machine-readable instructions stored thereon that are executable by a special purpose computing device to:

extract linear features from an image of an indoor portion of a building, said image captured by a camera at a mobile station;

determine a topological representation of said indoor portion based, at least in part, on positions or quantity of said linear features in said image; and

compare said topological representation to stored topological representations of said building to determine a candidate position of said mobile station.