Method and system for localizing spatially separated wireless transmitters

• US 10,028,148 B1
• Filed: 09/18/2017
• Issued: 07/17/2018
• Est. Priority Date: 03/06/2017
• Status: Active Grant

• Current Assignee: Wipro Limited
• Original Assignee: Wipro Limited
• Inventors: Rajendran, Surendran, Budihal, Ramachandra, Tamma, Venkata Prabhakar
• Primary Examiner(s): Arevalo, Joseph
• Application Number:
  US15/707,210
• Time in Patent Office: 302 Days
• Field of Search: 455474, 4554563, 455405, 455466, 4554561, 4554562, 455517, 455 6711, 455574, 4553435
• CPC Class Codes: G01S 1/042 Transmitters
• CPC Class Codes: G01S 5/0242 Determining the position of transmitters to be subsequently used in positioning G01S5/0289 takes precedence
• CPC Class Codes: G01S 5/02521 using a radio-map
• CPC Class Codes: G01S 5/02524 Creating or updating the radio-map
• CPC Class Codes: H04B 17/18 Monitoring during normal operation
• CPC Class Codes: H04B 17/27 for locating or positioning the transmitter
• CPC Class Codes: H04B 17/318 Received signal strength
• CPC Class Codes: H04W 16/12 Fixed resource partitioning
• CPC Class Codes: H04W 48/16 Discovering, processing access restriction or access information
• CPC Class Codes: H04W 64/00 Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Abstract

A technique is provided for localizing a plurality of wireless transmitters. The technique includes retrieving Received Signal Strength Indicator (RSSI) values measured by one or more sensors, corresponding to the plurality of wireless transmitters distributed in a region in which the sensors are located. The technique further comprises generating, a plurality of clusters based on the retrieved RSSI values. The technique further comprises generating a binary image based on the generated clusters. The binary image comprises one or more white regions and one or more black regions. The technique further comprises localizing position of each of the plurality of wireless transmitters, based on a determination of contours of the one or more white regions present in the binary image.

Claims

1. A method of localizing of wireless transmitters, the method comprising:

generating, by a localization device, a plurality of clusters based on one or more Received Signal Strength Indicator (RSSI) values corresponding to a plurality of wireless transmitters distributed in a space, wherein the generation of the plurality of clusters is based on one or more clustering algorithms performing vector quantization;

generating, by the localization device, an image comprising a plurality of regions based on the generated plurality of clusters, wherein one or more subsets of the plurality of regions indicates a location associated with corresponding one or more of the plurality of wireless transmitters;

determining, by the localization device, a location associated with the one or more of the plurality of wireless transmitters based on a determination of contours associated with the one or more subsets of the plurality of regions;

wherein a count of clusters in the plurality of clusters is based on a maximum range of transmission of the plurality of wireless transmitters and a recommended minimum distance between one or more sensors located in the region; and

wherein a difference in the maximum range of transmission of the plurality of wireless transmitters is less than a predefined threshold.

2. The method of claim 1, wherein the generation of the plurality of clusters comprises:

creating a data structure having the one or more RSSI values measured by each of the one or more sensors in the area, wherein each element of the data structure corresponds to a location of a sensor, from the one or more sensors, in the area; and

determining a plurality of centroids of the data structure having the one or more RSSI values, based on a random selection of the one or more RSSI values from the data structure, wherein each centroid in the plurality of centroids corresponds to a cluster from the plurality of clusters.

3. The method of claim 1, wherein the image comprises a binary image and the plurality of regions comprises one or more white regions and one or more black regions.

4. The method of claim 3, wherein the one or more subsets of the plurality of regions comprises one or more white regions.

5. The method of claim 4, wherein the one or more white regions in the binary image are indicative of a region in which one of the plurality of wireless transmitters are present and the one or more black regions in the binary image are indicative of a region in which one of the plurality of wireless transmitters are not present.

6. The method of claim 5, wherein the one or more clustering algorithms performing vector quantization comprises K-means clustering algorithm and wherein the determination of the contours of the one or more white regions is based on one or more image processing algorithms.

7. A localization device, comprising at least one processor and a memory having stored thereon instructions that, when executed by the at least one processor, cause the at least one processor to perform steps comprising:

generating a plurality of clusters based on one or more Received Signal Strength Indicator (RSSI) values corresponding to a plurality of wireless transmitters distributed in a space, wherein the generation of the plurality of clusters is based on one or more clustering algorithms performing vector quantization;

generating an image comprising a plurality of regions based on the generated plurality of clusters, wherein one or more subsets of the plurality of regions indicates a location associated with corresponding one or more of the plurality of wireless transmitters;

determining a location associated with the one or more of the plurality of wireless transmitters based on a determination of contours associated with the one or more subsets of the plurality of regions;

wherein a count of clusters in the plurality of clusters is based on a maximum range of transmission of the plurality of wireless transmitters and a recommended minimum distance between one or more sensors located in the region; and

wherein a difference in the maximum range of transmission of the plurality of wireless transmitters is less than a predefined threshold.

8. The localization device of claim 7, wherein the generation of the plurality of clusters comprises:

creating a data structure having the one or more RSSI values measured by each of the one or more sensors in the area, wherein each element of the data structure corresponds to a location of a sensor, from the one or more sensors, in the area; and

determining a plurality of centroids of the data structure having the one or more RSSI values, based on a random selection of the one or more RSSI values from the data structure, wherein each centroid in the plurality of centroids corresponds to a cluster from the plurality of clusters.

9. The localization device of claim 7, wherein the image comprises a binary image and the plurality of regions comprises one or more white regions and one or more black regions.

10. The localization device of claim 9, wherein the one or more subsets of the plurality of regions comprises one or more white regions.

11. The localization device of claim 10, wherein the one or more white regions in the binary image are indicative of a region in which one of the plurality of wireless transmitters are present and the one or more black regions in the binary image are indicative of a region in which one of the plurality of wireless transmitters are not present.

12. The localization device of claim 11, wherein the one or more clustering algorithms performing vector quantization comprises K-means clustering algorithm and wherein the determination of the contours of the one or more white regions is based on one or more image processing algorithms.

13. A non-transitory computer-readable medium storing instructions for localizing of wireless transmitters, wherein upon execution of the instructions by one or more processors, the processors perform operations comprising

generating a plurality of clusters based on one or more Received Signal Strength Indicator (RSSI) values corresponding to a plurality of wireless transmitters distributed in a space, wherein the generation of the plurality of clusters is based on one or more clustering algorithms performing vector quantization;

generating an image comprising a plurality of regions based on the generated plurality of clusters, wherein one or more subsets of the plurality of regions indicates a location associated with corresponding one or more of the plurality of wireless transmitters;

determining a location associated with the one or more of the plurality of wireless transmitters based on a determination of contours associated with the one or more subsets of the plurality of regions;

wherein a count of clusters in the plurality of clusters is based on a maximum range of transmission of the plurality of wireless transmitters and a recommended minimum distance between one or more sensors located in the region; and

wherein a difference in the maximum range of transmission of the plurality of wireless transmitters is less than a predefined threshold.

14. The non-transitory computer-readable medium of claim 13, wherein the generation of the plurality of clusters comprises:

creating a data structure having the one or more RSSI values measured by each of the one or more sensors in the area, wherein each element of the data structure corresponds to a location of a sensor, from the one or more sensors, in the area; and

determining a plurality of centroids of the data structure having the one or more RSSI values, based on a random selection of the one or more RSSI values from the data structure, wherein each centroid in the plurality of centroids corresponds to a cluster from the plurality of clusters.

15. The non-transitory computer-readable medium of claim 13, wherein the image comprises a binary image and the plurality of regions comprises one or more white regions and one or more black regions.

16. The non-transitory computer-readable medium of claim 15, wherein the one or more subsets of the plurality of regions comprises the one or more white regions.

17. The non-transitory computer-readable medium of claim 16, wherein the one or more white regions in the binary image are indicative of a region in which one of the plurality of wireless transmitters are present and the one or more black regions in the binary image are indicative of a region in which one of the plurality of wireless transmitters are not present.

18. The non-transitory computer-readable medium of claim 17, wherein the one or more clustering algorithms performing vector quantization comprises K-means clustering algorithm and wherein the determination of the contours of the one or more white regions is based on one or more image processing algorithms.