Step detection and step length estimation

• US 8,831,909 B2
• Filed: 09/22/2011
• Issued: 09/09/2014
• Est. Priority Date: 09/22/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Li, Fan, Zhao, Chunshui, Zhao, Feng
• Primary Examiner(s): Le, John H
• Application Number:
  US13/240,743
• Publication Number:
  US 20130080255A1
• Time in Patent Office: 1,083 Days
• Field of Search: 702/75, 702/97, 702/104, 702/141, 702/149, 702/150, 702/160, 701/220, 701/409, 701/410, 701/446, 701/469, 701/472, 701/500, 705/14.58
• US Class Current: 702/160
• CPC Class Codes: G01C 22/006 Pedometers
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Step detection and step length estimation techniques include detecting salient points in sensor data of one or more sensors. A step frequency is estimated based on a time interval between the detected salient points. A step length of the step may then be computed based on a nonlinear combination of the estimated step frequency and a function of the sensor data, and/or a step model. Alternatively, the step length of the step may be computed based on a combination of a nonlinear function of the estimated step frequency and a (linear or nonlinear) function of the sensor data, and/or a step model.

Claims

1. A method of estimating a step length, comprising:

under control of one or more processors configured with executable instructions;

receiving sensor data from a sensor;

detecting salient points of a same type from the sensor data;

estimating a step frequency from the sensor data based on a time interval between the salient points of the same type in the sensor data; and

calculating a step length of a step based at least in part on a nonlinear combination of the estimated step frequency and a predetermined function of the sensor data.

2. The method of claim 1, further comprising:

determining a type of movement of a user that the sensor measures, the type of movement being selected from a group consisting of walking, jogging and running; and

selecting a step model based on the determined type of movement of the user.

3. The method of claim 2, wherein selecting the step model is further based on one or more of personal information of the user, a position of the sensor, a type of shoes that the user wears or a type of surface on which the user moves, wherein the personal information of the user comprises one or more of an age of the user, a height of the user, a weight of the user or a gender of the user, and the position of the sensor comprises a position close to a body part of the user, a pocket of the user'"'"'s clothes or a bag of the user.

4. The method of claim 2, wherein determining the type of movement of the user is based at least in part on the estimated step frequency and the calculated step length.

5. The method of claim 2, wherein calculating the step length comprises calculating the step length based on the selected step model.

6. The method of claim 2, further comprising:

detecting a change in the type of movement to a new type of movement; and

selecting a new step model based on the new type of movement.

7. The method of claim 1, further comprising filtering the sensor data using a low-pass filter prior to detecting the salient points in the sensor data.

8. The method of claim 7, wherein the low-pass filter comprises at least one of a Finite Impulse Response (FIR) filter or a Biorthogonal Spline Wavelet (BSW) filter.

9. The method of claim 1, wherein estimating the step frequency comprises:

determining that the time interval between the detected salient points is less than a predetermined threshold; and

in response to determining that the time interval between the detected salient points is less than the predetermined threshold, detecting a new salient point that is located outside the time interval between the detected turned points, and estimating the step frequency based on a new time interval between the new salient point and one of the detected salient points.

10. The method of claim 1, wherein estimating the frequency comprises:

determining that the time interval between the detected salient points is greater than a predetermined threshold; and

in response to determining that the time interval between the detected salient points is greater than the predetermined threshold, detecting a new salient point that is located within the time interval between the detected salient points, and estimating the step frequency based on a new time interval between the new salient point and one of the detected salient points.

11. The method of claim 1, further comprising:

determining a condition associated with a first computing device that receives the sensor data from the sensor;

performing at least one of the estimating or the calculating at the first computing device or a second computing device communicatively connected to the first computing device based on the determining.

12. The method of claim 11, wherein the condition associated with the first computing device comprises one or more of an application response latency, a power reserve, a processor speed, a CPU occupancy rate, a network bandwidth or a network speed between the first computing device and the second computing device.

13. One or more computer-readable media configured with computer-executable instructions that, when executed by one or more processors, configure the one or more processors to perform acts comprising:

determining an area of interest in which a user intends to navigate;

obtaining a map covering at least a portion of the determined area of interest;

receiving sensor data from a sensor associated with the user;

detecting salient points of a same type from the sensor data;

estimating a step frequency from the sensor data based on a time interval between the salient points of the same type in the sensor data;

calculating a step length of a step based at least in part on the estimated step frequency; and

determining a location of the user on the obtained map based on a detection of a plurality of steps of the user, the estimated step frequency and the calculated step lengths of the plurality of steps.

14. The one or more computer-readable media of claim 13, further comprising providing a recommendation to the user through a computing device based on the determined location, the recommendation comprising an advertisement related to the determined location.

15. The one or more computer-readable media of claim 13, wherein the determined area of interest comprises an indoor area with little or no signal of a Global Positioning System (GPS), and determining the location of the user within the determined area of interest is performed using local sensors without using GPS data.

16. The one or more computer-readable media of claim 13, further comprising:

receiving location information from one or more devices; and

updating the determined location based on the received location information.

17. The one or more computer-readable media of claim 16, further comprising updating a step model that is used for the detection of the plurality of steps the user has made and the estimation of respective step lengths for the plurality of steps in response to determining that a difference between the determined location and the updated location is greater than a predetermined threshold.

18. The one or more computer-readable media of claim 13, wherein determining the location of the user comprises, for each step of the plurality of steps:

receiving acceleration readings from an accelerometer;

estimating a step frequency from the received acceleration readings; and

calculating a step length of the respective step based at least in part on a combination of a nonlinear function of the estimated step frequency and a linear or nonlinear function of the acceleration readings.

19. A system comprising:

one or more processors;

memory, communicatively coupled to the one or more processors, storing instructions that, when executed by the one or more processors, configure the one or more processors to perform acts comprising;

displaying a map representing a predetermined scope of an area that covers a current location of a user;

receiving an indication of a destination location on the displayed map from the user; and

providing live instructions to the user to route the user to the destination location without using a Global Positioning System (GPS), providing the live instructions comprising;

receiving sensor data from a sensor associated with the user;

detecting salient points of a same type from the sensor data;

estimating a step frequency from the sensor data based on a time interval between the salient points of the same type in the sensor data;

calculating a step length of a step based at least in part on the estimated step frequency; and

updating a new location of the user based on a detection of a plurality of steps, the estimated step frequency of the user and the calculated step lengths of the plurality of steps made by the user.

20. The system as recited in claim 19, wherein the salient point types further comprise one of zero crossing points, valleys of a magnitude trajectory of the sensor data, or peaks of a magnitude trajectory of the sensor data.