Match Bluetooth low energy (BLE) moving patterns

• US 10,516,982 B2
• Filed: 10/27/2017
• Issued: 12/24/2019
• Est. Priority Date: 10/27/2017
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Inventors: Jiang, Yurong, Kim, Kyu Han, Jain, Puneet, Liu, Xiaochen
• Primary Examiner(s): Liao, Hsinchun
• Application Number:
  US15/796,320
• Publication Number:
  US 20190132696A1
• Time in Patent Office: 788 Days
• 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 4/80 Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication

Abstract

An example system comprising: a processing resource; and a memory resource storing machine readable instructions executable to cause the processing resource to: receive a Bluetooth Low Energy (BLE) signal transmitted from a user device; generate, from the BLE signal, a BLE moving pattern of the user device, wherein the BLE moving pattern is generated at a different entity than an entity that transmits the BLE signal; track an object carrying the user device via visual information of the object such that a visual moving pattern of the object is generated from the tracking; determine the visual moving pattern matches the BLE moving pattern; and assign, responsive to the determination, an identity obtained from the user device to the object being tracked via the visual information.

Claims

1. A system, comprising:

a processing resource; and

a memory resource storing machine readable instructions executable to cause the processing resource to;

receive a Bluetooth Low Energy (BLE) signal transmitted from a user device;

generate, from the BLE signal, a BLE moving pattern of the user device, wherein the BLE moving pattern is generated at a different entity than an entity that transmits the BLE signal;

track an object carrying the user device via visual information of the object such that a visual moving pattern of the object is generated from the tracking;

determine the visual moving pattern matches the BLE moving pattern; and

assign, responsive to the determination, an identity obtained from the user device to the object being tracked via the visual information;

obtain a plurality of images each including the object carrying the user device transmitting the Bluetooth Low Energy (BLE) signal;

calculate a plurality of factors including a Mahalanobis distance, a deep feature distance, and an intersection-over-union (IOU) between a first object of the plurality of images and a second object of the plurality of images, each of the plurality of factors having a particular coefficient;

determine, based on each of the particular coefficients, that the object matches a different object; and

generate, responsive to visual information of the matched objects obtained from the plurality of images, a visual moving pattern such that the visual moving pattern is compared to a BLE moving pattern generated responsive to the BLE signal received from the user device.

2. The system of claim 1, wherein the user device is one of a plurality of user devices, and further comprising instructions executable to collect BLE signals from the plurality of user devices such that a BLE moving pattern corresponding to each of the plurality of user devices are generated at the system.

3. The system of claim 1, further comprising instructions executable to restrict assignment of the identity obtained from the user device to the object when the user device outside of a threshold distance from a BLE receiver that receives the BLE signal from the user device.

4. The system of claim 1, wherein the instructions executable to assign the identity to the object comprise instructions executable to assign a universal unique identifier (UUID) of the user device to the object.

5. The system of claim 1, wherein the instructions executable to generate the BLE moving pattern comprise instructions executable to generate the BLE moving pattern based on a received signal strength indication (RSSI) of the BLE signal.

6. The system of claim 1, wherein the BLE moving pattern comprises a direction of travel relative to a BLE sensor.

7. The system of claim 6, wherein the BLE moving pattern further comprises a duration of time during which the object is moving in the direction of travel relative to the BLE sensor.

8. The system of claim 1, wherein the instructions are executable to cause the processing resource to adjust, responsive to visual information of each object, a probability that the object of the first of the plurality of images matches the different object of the second of the plurality of images.

9. The system of claim 1, wherein the instructions are executable to cause the processing resource to adjust, responsive to the matched objects appearing in at least a portion of the plurality of images for more than a threshold quantity of times, the particular coefficients such that each of particular coefficients has a same value.

10. The system of claim 1, wherein the instructions are executable to cause the processing resource to adjust, responsive to the matched objects appearing in at least a portion of the plurality of images for less than a threshold quantity of times, the particular coefficient of each of the plurality of factors such that a coefficient of the deep feature distance is greater than a coefficient of the Mahalanobis distance.

11. The system of claim 10, wherein the instructions are executable to cause the processing resource to adjust a coefficient of the IOU to zero such that the IOU does not influence the matching.

12. The system of claim 1, wherein the instructions are executable to cause the processing resource to assign an initial status to an object that is newly detected and not matched to at least one of the set of objects.

13. The system of claim 1, wherein the instructions are executable to cause the processing resource to assign a confirmed status to a set of objects that is determined to be matching to each other when a quantity of the set of objects exceeds a threshold quantity of objects.

14. The system of claim 1, wherein the instructions are executable to cause a processing resource to:

obtain a plurality of images, at least one of the plurality of images including the object carrying the user device, wherein a Bluetooth Low Energy (BLE) signal is transmitted and received from the user device;

determine, responsive to the obtained plurality of images, whether a first object detected from the plurality of images matches to a second object detected from the plurality of images;

calculate a plurality of probabilities including;

a first probability that the first object matches the second object;

a second probability that the first object and the second object carry the user device; and

a third probability that a moving pattern of the matched first and second objects matches to a strength change of the BLE signals received from the user device, wherein each of the plurality of probabilities has a particular coefficient; and

determine, based on each of the particular coefficients, whether to assign an identity obtained from the user device to the matched objects.

15. The system of claim 14, wherein the first probability is calculated responsive to a comparison between:

an average speed of a set of objects determined to be matching, wherein the average speed of the set of objects is calculated from a first portion of the plurality of images having the same background; and

an imaginary speed of the set of objects, wherein the imaginary speed of the set of objects is calculated based on;

an actual distance between the first portion of the plurality of images and a second portion of the plurality of images having different background than those of the first portion of the plurality of images; and

a gap between a first time that the set of objects are lastly detected in the first portion of the plurality of images and a second time that the set of objects are first detected in the second portion of the plurality of images.

16. The system of claim 15, wherein the instructions are executable to cause the processing resource to determine a deep feature distance between the first object and the second object, wherein the deep feature distance is based on a cosine similarity between visual information of the first object and visual information of the second object.

17. The system of claim 15, wherein the instructions are executable to cause the processing resource to set a coefficient associated with the third probability to zero for a newly detected object that is not matched to other objects of the plurality of images.

18. The system of claim 15, wherein the plurality of probabilities are collectively determined such that assigning the identity is determined based on more than one of the plurality of probabilities.

19. The system of claim 15, wherein the second object is a candidate object selected from a plurality of objects included in the plurality of images, and wherein the candidate object is selected responsive to a comparison between:

an average speed of the first object that is previously determined; and

an estimated speed of the first object in relation to the second object.