Device position estimates from motion and ambient light classifiers

• US 9,366,749 B2
• Filed: 01/11/2012
• Issued: 06/14/2016
• Est. Priority Date: 04/15/2011
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Grokop, Leonard Henry, Narayanan, Vidya
• Primary Examiner(s): Le, John H
• Application Number:
  US13/348,497
• Publication Number:
  US 20120265482A1
• Time in Patent Office: 1,616 Days
• Field of Search: 702/141, 702/150, 702/159, 345/156, 701/220
• US Class Current: 1/1
• CPC Class Codes: G01C 19/34 for indicating a direction in the horizontal plane, e.g. directional gyroscopes
• CPC Class Codes: G01C 19/44 for indicating the vertical
• CPC Class Codes: G01C 21/1656 with passive imaging devices, e.g. cameras
• CPC Class Codes: G01S 5/16 using electromagnetic waves other than radio waves
• CPC Class Codes: G06F 1/1686 the I/O peripheral being an integrated camera
• CPC Class Codes: G06F 1/1694 the I/O peripheral being a single or a set of motion sensors for pointer control or gesture input obtained by sensing movements of the portable computer
• CPC Class Codes: H04M 1/72403 with means for local support of applications that increase the functionality

Abstract

A position estimate for a mobile device is generated using data from motion sensors, such as accelerometers, magnetometers, and/or gyroscopes, and data from light sensors, such as an ambient light sensor, proximity sensor and/or camera intensity sensor. A plurality of proposed positions with associated likelihoods is generated by analyzing information from the motion sensors and a list of candidate positions is produced based on information from the light sensors. At least one of the plurality of proposed positions is eliminated using the list of candidate positions and a position estimate for the mobile device is determined based on the remaining proposed positions and associated likelihoods. The proposed positions may be generated by extracting features from the information from the motion sensors and using models to generate likelihoods for the proposed positions. The likelihoods may be filtered over time. Additionally, a confidence metric may be generated for the estimated position.

Claims

1. A method of determining a position estimate of a mobile device with respect to a user, comprising:

receiving signals from at least one motion sensor in the mobile device;

analyzing the signals from the at least one motion sensor in the mobile device to generate a plurality of proposed positions with respect to the user with associated likelihoods;

receiving signals from at least one light sensor in the mobile device;

processing the signals from the at least one light sensor in the mobile device to produce a list of candidate positions;

eliminating at least one of the plurality of proposed positions using the list of candidate positions; and

determining the position estimate for the mobile device with respect to the user based on remaining proposed positions and associated likelihoods.

2. The method of claim 1, wherein eliminating at least one of the plurality of proposed positions using the list of candidate positions comprises eliminating any proposed position that is not included in the list of candidate positions.

3. The method of claim 1, wherein the at least one motion sensor comprises at least one of accelerometers, magnetometers, and gyroscopes.

4. The method of claim 1, wherein the at least one light sensor comprises at least one of an ambient light sensor, proximity sensor and camera intensity sensor.

5. The method of claim 1, wherein analyzing the signals from the at least one motion sensor in the mobile device to generate the plurality of proposed positions with associated likelihoods comprises:

extracting features from the signals from the at least one motion sensor;

accessing models of features; and

using the features and the models of features to generate likelihoods for each of the plurality of proposed positions.

6. The method of claim 5, further comprising filtering the plurality of proposed positions with associated likelihoods over time.

7. The method of claim 1, further comprising generating a confidence metric associated with the position estimate.

8. The method of claim 7, wherein the confidence metric is generated based on a difference of likelihoods of two most likely proposed positions after eliminating the at least one of the plurality of proposed positions using the list of candidate positions.

9. The method of claim 1, further comprising generating likelihoods that are associated with candidate positions in the list of candidate positions, wherein eliminating at least one of the plurality of proposed positions using the list of candidate positions comprises multiplying the likelihoods associated with each of the plurality of proposed positions with the likelihoods associated with the candidate positions to determine a proposed position with a highest combined likelihood level that is used as the position estimate.

10. The method of claim 1, wherein processing the signals from the at least one light sensor to produce the list of candidate positions is performed prior to generating the plurality of proposed positions with associated likelihoods.

11. A mobile device comprising:

at least one motion sensor;

at least one light sensor;

memory; and

a processor coupled to the memory and coupled to receive signals from the at least one motion sensor and coupled to receive signals from the at least one light sensor, the processor being configured to analyze the signals from the at least one motion sensor to generate a plurality of proposed positions with respect to a user with associated likelihoods, process the signals from the at least one light sensor to produce a list of candidate positions, eliminate at least one of the plurality of proposed positions using the list of candidate positions, determine a position estimate for the mobile device with respect to the user based on remaining proposed positions and associated likelihoods, and store the position estimate in the memory.

12. The mobile device of claim 11, wherein the processor is configured to eliminate at least one of the plurality of proposed positions using the list of candidate positions by being configured to eliminate any proposed position that is not included in the list of candidate positions.

13. The mobile device of claim 11, wherein the at least one motion sensor comprises at least one of accelerometers, magnetometers, and gyroscopes.

14. The mobile device of claim 11, wherein the at least one light sensor comprises at least one of an ambient light sensor, proximity sensor and camera intensity sensor.

15. The mobile device of claim 11, wherein the processor is configured to analyze the signals from the at least one motion sensor to generate the plurality of proposed positions with associated likelihoods by being configured to:

extract features from the signals from the at least one motion sensor;

access models of features; and

use the features and the models of features to generate likelihoods for each of the plurality of proposed positions.

16. The mobile device of claim 15, wherein the processor is further configured to filter the plurality of proposed positions with associated likelihoods over time.

17. The mobile device of claim 11, wherein the processor is further configured to generate a confidence metric associated with the position estimate.

18. The mobile device of claim 17, wherein the processor is configured to generate the confidence metric based on a difference of likelihoods of two most likely proposed positions after eliminating the at least one of the plurality of proposed positions using the list of candidate positions.

19. The mobile device of claim 11, wherein the processor is further configured to generate likelihoods that are associated with candidate positions in the list of candidate positions, wherein the processor is configured to eliminate at least one of the plurality of proposed positions using the list of candidate positions by being configured to multiply the likelihoods associated with each of the plurality of proposed positions with the likelihoods associated with the candidate positions to determine a proposed position with a highest combined likelihood level that is used as the position estimate.

20. The mobile device of claim 11, wherein the processor is configured to produce the list of candidate positions before generating the plurality of proposed positions with associated likelihoods.

21. A mobile device comprising:

means for receiving signals from at least one motion sensor in the mobile device;

means for analyzing the signals from the at least one motion sensor in the mobile device to generate a plurality of proposed positions with respect to a user with associated likelihoods;

means for receiving signals from at least one light sensor in the mobile device;

means for processing the signals from the least one light sensor in the mobile device to produce a list of candidate positions;

means for eliminating at least one of the plurality of proposed positions using the list of candidate positions; and

means for determining a position estimate for the mobile device with respect to the user based on remaining proposed positions and associated likelihoods.

22. The mobile device of claim 21, wherein the means for eliminating at least one of the plurality of proposed positions using the list of candidate positions comprises means for eliminating any proposed position that is not included in the list of candidate positions.

23. The mobile device of claim 21, wherein the at least one motion sensor comprises at least one of accelerometers, magnetometers, and gyroscopes.

24. The mobile device of claim 21, wherein the at least one light sensor comprises at least one of an ambient light sensor, proximity sensor and camera intensity sensor.

25. The mobile device of claim 21, wherein the means for analyzing the signals from the at least one motion sensor in the mobile device to generate the plurality of proposed positions with associated likelihoods comprises:

means for extracting features from the signals from the at least one motion sensor;

means for accessing models of features; and

means for using the features and the models of features to generate likelihoods for each of the plurality of proposed positions.

26. The mobile device of claim 25, further comprising means for filtering the plurality of proposed positions with associated likelihoods over time.

27. The mobile device of claim 21, further comprising means for generating a confidence metric associated with the position estimate based on a difference of likelihoods of two most likely proposed positions after eliminating the at least one of the plurality of proposed positions using the list of candidate positions.

28. The mobile device of claim 21, further comprising means for generating likelihoods that are associated with candidate positions in the list of candidate positions, wherein the means for eliminating at least one of the plurality of proposed positions using the list of candidate positions comprises multiplying the likelihoods associated with each of the plurality of proposed positions with the likelihoods associated with the candidate positions to determine a proposed position with a highest combined likelihood level that is used as the position estimate.

29. A non-transitory computer-readable medium including program code stored thereon, comprising:

program code to receive signals from at least one motion sensor in a mobile device;

program code to analyze the signals from the at least one motion sensor in the mobile device to generate a plurality of proposed positions with respect to a user with associated likelihoods;

program code to receive signals from at least one light sensor in the mobile device;

program code to process the signals from the at least one light sensor in the mobile device to produce a list of candidate positions;

program code to eliminate at least one of the plurality of proposed positions using the list of candidate positions; and

program code to determine a position estimate for the mobile device with respect to the user based on remaining proposed positions and associated likelihoods.

30. The non-transitory computer-readable medium of claim 29, wherein the program code to eliminate at least one of the plurality of proposed positions using the list of candidate positions comprises program code to eliminate any proposed position that is not included in the list of candidate positions.

31. The non-transitory computer-readable medium of claim 29, wherein the program code to analyze the signals from the at least one motion sensor in the mobile device to generate the plurality of proposed positions with associated likelihoods comprises:

program code to extract features from the signals from the at least one motion sensor;

program code to access models of features; and

program code to use the features and the models of features to generate likelihoods for each of the plurality of proposed positions; and

program code to filter the plurality of proposed positions with associated likelihoods over time.

32. The non-transitory computer-readable medium of claim 29, further comprising program code to generate a confidence metric associated with the position estimate, the confidence metric being based on a difference of likelihoods of two most likely proposed positions after eliminating the at least one of the plurality of proposed positions using the list of candidate positions.

33. The non-transitory computer-readable medium of claim 29, further comprising program code to generate likelihoods that are associated with candidate positions in the list of candidate positions, wherein the program code to eliminate at least one of the plurality of proposed positions using the list of candidate positions comprises program code to multiply the likelihoods associated with each of the plurality of proposed positions with the likelihoods associated with the candidate positions to determine a proposed position with a highest combined likelihood level that is used as the position estimate.