Triggering geolocation fix acquisitions on transitions between physical states

• US 9,591,456 B2
• Filed: 07/15/2014
• Issued: 03/07/2017
• Est. Priority Date: 07/15/2013
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Phan, Thomas
• Primary Examiner(s): Gelin, Jean
• Application Number:
  US14/332,177
• Publication Number:
  US 20150018014A1
• Time in Patent Office: 966 Days
• Field of Search: 455/403, 455/404.1, 455/404.2, 455/456.1, 455/456.2, 455/456.3, 455/456.5, 455/456.6
• US Class Current: 1/1
• CPC Class Codes: A61B 5/1123 Discriminating type of movement, e.g. walking or running A61B5/1116, A61B5/112 take precedence
• CPC Class Codes: A61B 5/6898 Portable consumer electronic devices, e.g. music players, telephones, tablet computers
• CPC Class Codes: G01P 13/00 Indicating or recording presence, absence, or direction, of movement electric switches H01H; counting moving objects G06M7/00
• CPC Class Codes: H04W 4/027 using movement velocity, acceleration information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services

Abstract

A method and device for triggering acquisition of geolocation fix information. The method include determining activity state information based on information from one or more sensors. It is determined if an activity state has transitioned to a particular activity state based on the activity state information. Geolocation fix information is acquired if the activity state transitioned to the particular activity state.

Claims

1. A method for triggering acquisition of geolocation fix information comprising:

obtaining sensor information from at least one sensor;

determining, using the sensor information, activity state information based on;

determining normalization information on the sensor information;

extracting a sliding window based on the normalization information; and

computing features from time-domain information and frequency-domain information based on a magnitude of a frequency response obtained based on the sliding window;

determining whether an activity state has transitioned between particular activity states based on the activity state information; and

triggering geolocation fix information based on a determination that activity state transitions between the particular activity states.

2. The method of claim 1, wherein the sensor comprises at least one accelerometer sensor, and the sensor information comprises acceleration data acquired from the at least one accelerometer sensor.

3. The method of claim 2, wherein:

the normalization information comprises tri-axis normalization information on the acceleration data; and

the sliding window is extracted based on the tri-axis normalization information.

4. The method of claim 3, further comprising:

concatenating features from the tri-axis normalization information for obtaining a feature vector; and

providing at least one of a trainer and classifier for recognizing activity states.

5. The method of claim 4, wherein the tri-axis normalization information comprises Cartesian magnitude information, true horizontal information and true vertical information.

6. The method of claim 5, wherein the trainer comprises a supervised machine learning trainer that provides offline training for providing mapping to physical activity states using a classification model, and the classifier provides classification of sensor data using information from the classification model for recognizing a plurality of activities.

7. The method of claim 6, further comprising providing information to an electronic device based on the geolocation fix information.

8. The method of claim 1, wherein the geolocation fix information comprises at least one of global positioning system information, Wi-Fi information, and triangulation information.

9. The method of claim 1, wherein acquisition of the geolocation fix information comprises controlling an active state of a global positioning system sensor.

10. The method of claim 1, wherein the activity state information comprises an indication of at least one of a moving activity and a stationary activity.

11. The method of claim 10, wherein the moving activity comprises at least one of walking, running, driving, bicycling, flying, boating, and transporting, and the stationary activity comprises at least one of sitting, standing, and idling.

12. The method of claim 11, wherein determining whether an activity state has transitioned between the particular activity states comprises determining the activity state transitions between particular pairs of activity states.

13. The method of claim 2, wherein the electronic device comprises at least one of a smart phone, a tablet device, a portable computing device, a wearable device and a camera device.

14. An electronic device comprising:

at least one sensor configured to provide sensed data;

an activity recognizer configured to determine, using the sensed data, activity state information based on;

determining normalization information on the sensed data;

extracting a sliding window based on the normalization information; and

computing features from time-domain information and frequency-domain information based on a magnitude of a frequency response obtained based on the sliding window;

a transition manager configured to determine whether an activity state has transitioned between particular activity states based on the activity state information; and

a geolocation service or geolocation sensor configured to trigger acquisition of geolocation fix information upon a determination that the activity state transitions between the particular activity states.

15. The electronic device of claim 14, wherein the at least one sensor comprises at least one accelerometer sensor that is configured to provide the sensed data.

16. The electronic device of claim 14, wherein:

the normalization information comprises tri axis normalization information; and

the sliding window is extracted based on the tri-axis normalization information.

17. The electronic device of claim 16, further comprising a smoother configured to concatenate features from the tri-axis information to obtain a feature vector, wherein the tri-axis normalization information comprises Cartesian magnitude information, true horizontal information and true vertical information.

18. The electronic device of claim 17, further comprising a supervised machine learning trainer configured to provide offline training to provide mapping to physical activity states using a classification model, and wherein the activity recognizer includes a classifier that is configured to classify the sensed data using information from the classification model to recognize a plurality of activities.

19. The electronic device of claim 18, wherein a geolocation based application is configured to provide information to the electronic device based on the geolocation fix information.

20. The electronic device of claim 14, wherein the geolocation fix information comprises at least one of global positioning system information, Wi-Fi information, and triangulation information.

21. The electronic device of claim 14, wherein the transition manager is configured to control an active state of a global positioning system sensor.

22. The electronic device of claim 14, wherein the activity state information comprises an indication of at least one of a moving activity and a stationary activity, and the moving activity comprises at least one of walking, running, driving, bicycling, flying, boating, and transporting, and the stationary activity comprises at least one of sitting, standing, and idling.

23. The electronic device of claim 14, wherein the transition manager is configured to determine whether an activity state has transitioned between the particular activity states based on a transition between particular pairs of activity states.

24. The electronic device of claim 14, further comprising at least one of a smart phone, a tablet device, a portable computing device, a wearable device and a camera device.

25. A non-transitory processor-readable medium that includes a program that when executed by a processor performs a method comprising:

obtaining sensed data from at least one sensor;

determining, using the sensed data, activity state information based on;

determining normalization information on the sensed data;

extracting a sliding window based on the normalization information; and

computing features from time-domain information and frequency-domain information based on a magnitude of a frequency response obtained based on the sliding window;

determining whether an activity state has transitioned between particular activity states based on the activity state information; and

triggering acquisition of geolocation fix information based on a determination that activity state transitions between the particular activity states.

26. The non-transitory processor-readable medium of claim 25, wherein the program that when executed by a processor performs a method further comprising providing information to an electronic device based on the geolocation fix information, and the geolocation fix information comprises at least one of global positioning system information, Wi-Fi information, and triangulation information.

27. The non-transitory processor-readable medium of claim 26, wherein the electronic device comprises at least one of a smart phone, a tablet device, a portable computing device, a wearable device and a camera device.

28. The non-transitory processor-readable medium of claim 25, wherein acquisition of the geolocation fix information comprises controlling an active state of a global positioning system sensor, and the activity state information comprises an indication of at least one of a moving activity and a stationary activity.

29. The non-transitory processor-readable medium of claim 28, wherein the moving activity comprises at least one of walking, running, driving, bicycling, flying, boating, and transporting, and the stationary activity comprises at least one of sitting, standing, and idling.

30. The non-transitory processor-readable medium of claim 29, wherein determining whether an activity state has transitioned between the particular activity states comprises determining transitions between particular pairs of activity states.