Methods and systems for improving accuracy of indoor positioning

• US 10,028,100 B2
• Filed: 06/27/2016
• Issued: 07/17/2018
• Est. Priority Date: 06/27/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Abadi, Aharon, Melamed, Roie, Packer, Eli, Shapira, Natalie
• Primary Examiner(s): MIZRAHI, DIANE D
• Application Number:
  US15/193,153
• Publication Number:
  US 20170374525A1
• Time in Patent Office: 750 Days
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/023 using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
• CPC Class Codes: H04W 4/027 using movement velocity, acceleration information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/33 for indoor environments, e.g. buildings

Abstract

A computerized method of improving position measurement of an indoor positioning system (IPS), comprising: gathering a plurality of position samples of a mobile device measured by an indoor wireless device, each of the position samples is indicative of a measured position and a measurement time; receiving a current position sample of the mobile device; for each of the plurality of position samples and the current position sample, determining a time weight, the time weight is higher for samples measured at a later time; for each of the plurality of position samples and the current position sample, determining a signal weight, the signal weight is higher for measured with stronger signal; and estimating a current position of the mobile device by weighting at least some of the position samples with the respective weights.

Claims

1. A computerized method of improving position measurement of an indoor positioning system (IPS), comprising:

gathering, at a server, indoor position data of a mobile device by;

gathering from an indoor wireless device a plurality of position samples of the mobile device, the plurality of position samples are measured at the indoor wireless device, each of said plurality of position samples is indicative of a measured position and a measurement time;

receiving a current position sample of said mobile device;

for each of said plurality of position samples and said current position sample, using at least one processor of the server for determining a time weight, said time weight is higher for samples measured at a later time;

for each of said plurality of position samples and said current position sample, using the at least one processor of the server for determining a signal weight, said signal weight is higher for samples measured with stronger signal; and

adding a current position of said mobile device to the indoor position data, the current position of said mobile device is estimated by weighting at least some of said position samples with said respective weights to improve an accuracy of the indoor position data.

2. The method of claim 1, further comprising:

receiving a next position sample of said mobile device;

estimating a movement velocity of said mobile device from said estimated current position and said next position sample;

when said movement velocity is lower than a predetermined maximal velocity, adding said next position sample to a dataset.

3. The method of claim 1, wherein said indoor wireless device is a Wi-Fi access point device.

4. The method of claim 1, wherein said estimating is done for a time earlier than measurement time of at least one of said position samples.

5. The method of claim 1, wherein said time weight is the difference between the measurement time of each position sample and a window start time.

6. The method of claim 5, wherein said time weight is normalized by subtracting said difference by the sum of the time weight of at least some of said plurality of position samples.

7. The method of claim 1, wherein said signal weight is a linear function of a received signal strengths indication (RSSI) of each sample.

8. The method of claim 7, wherein said signal weight is normalized by subtracting said RSSI by the sum of the RSSIs of at least some of said plurality of position samples.

9. A computerized method of improving position measurement of an indoor positioning system (IPS), comprising:

gathering indoor position data of a mobile device by;

gathering at least one position sample of the mobile device from an indoor wireless device, the at least one position sample is measured at the an indoor wireless device, indicative of a measured position and a measurement time,

receiving, at a server, a current position sample of said mobile device,

using at least one processor of the server for estimating a movement velocity of said mobile device from said at least one position sample and said current position sample, and

wherein when said movement velocity is higher than a predetermined maximal velocity, marking said current position sample as noise to improve an accuracy of the indoor position data.

10. The method of claim 9, further comprising:

when said movement velocity is lower than a predetermined maximal velocity, adding said current position sample to a dataset.

11. The method of claim 9, wherein said estimating is based on an inaccuracy radius of said indoor wireless device.

12. The method of claim 9, wherein said maximal velocity is determined based on an average walking speed of a person.

13. The method of claim 9, wherein said at least one position sample includes a weighted average position calculated by:

for each of a plurality of position samples, determining a time weight, said time weight is higher for samples measured at a later time;

for each of said plurality of position samples, determining a signal weight, said signal weight is higher for samples measured with stronger signal; and

estimating a weighted position of said mobile device by weighting as least some of said position samples with said respective weights.

14. A system of improving position measurement of an indoor positioning system (IPS), comprising:

an indoor wireless device for measuring a plurality of position samples of a mobile device, each of said position samples is indicative of a measured position and a measurement time;

a dataset for storing indoor position data of the mobile device and said plurality of position samples; and

a processor for;

for each of said plurality of position samples and said current position sample, determining a time weight, said time weight is higher for samples measured at a later time;

for each of said plurality of position samples and said current position sample, determining a signal weight, said signal weight is higher for samples measured with stronger signal; and

adding a current position of said mobile device to the indoor position data, the current position is estimated by weighting at least some of said position samples with said respective weights to improve an accuracy of the indoor position data.