Communication system architecture and method of processing data therein

Patent metadata

Field	Value
Publication number	US-10951580-B2
Application number	US-201815971759-A
Country	US
Kind code	B2
Filing date	May 4, 2018
Priority date	May 4, 2017
Publication date	Mar 16, 2021
Grant date	Mar 16, 2021

Abstract

A method includes identifying a plurality of local tracklets from a plurality of targets, creating a plurality of global tracklets from the plurality of local tracklets, wherein each global tracklet comprises a set of local tracklet of the plurality of local tracklets, wherein the set of local tracklet corresponds to a target of the plurality of targets; extracting motion features of the target from the each global tracklet of the plurality of global tracklets, wherein the motion features of each target of the plurality of targets from each global tracklet of the plurality of global tracklets are distinguishable from the motion features of remaining targets of the plurality of targets from remaining global tracklets; transforming the motion features into an address code by using a hashing process; and transmitting a plurality of address codes and a transformation parameter of the hashing process to a communication device.

First claim

The invention claimed is:

1. A non-transitory computer-readable medium encoded with a computer-readable program which, when executed by a second processor, will cause a computer to execute a second processing method, the second processing method comprising:
receiving a plurality of address codes, a hash process, and a transformation parameter of the hash process from a server;
extracting motion features of a user, wherein the user is in physical possession of the second processor;
transforming the motion features into a second address code by using the hash process;
validating the second address code with a validating address code of the plurality of address codes; and
receiving a message from the server, wherein the message is concocted with the validating address code of the plurality of address codes.

2. The method of claim 1 , wherein the validating the second address code with the validating address code of the plurality of address codes comprises comparing the second address code with the validating address code to ensure that the second address code is substantially equal to the validating address code.

3. The method of claim 1 , wherein the transforming the motion features into the second address code by using the hash process comprises transforming the motion features into the second address code by using the transformation parameter comprising:
transforming a first motion feature of the motion features into a first motion code by using the transformation parameters;
transforming a second motion feature of the motion features into a second motion code by using the transformation parameters; and
stitching a plurality of motion codes into the second address code, wherein the plurality of motion codes comprises the first motion code and the second motion code.

4. The method of claim 1 , wherein the motion features comprises at least one of movement, absolute direction, or relative direction.

5. A non-transitory computer-readable medium encoded with a computer-readable program which, when executed by a first processor, will cause a computer to execute an image processing method, the processing method comprising:
identifying a plurality of local tracklets from a plurality of targets;
creating a plurality of global tracklets from the plurality of local tracklets, wherein each global tracklet comprises a set of local tracklet of the plurality of local tracklets, wherein the set of local tracklet corresponds to a target of the plurality of targets;
extracting motion features of the target from the each global tracklet of the plurality of global tracklets, wherein the motion features of each target of the plurality of targets from each global tracklet of the plurality of global tracklets are distinguishable from the motion features of remaining targets of the plurality of targets from remaining global tracklets;
transforming the motion features into an address code by using a hashing process; and
transmitting a plurality of address codes and a transformation parameter of the hashing process to a communication device.

6. The image processing method of claim 5 , wherein the identifying the plurality of local tracklets from the plurality of targets comprises:
using multiple cameras to identify the plurality of local tracklets from the plurality of targets.

7. The image processing method of claim 5 , wherein the creating the plurality of global tracklets from the plurality of local tracklets comprises:
stitching multiple local tracklets of the plurality of local tracklets from multiple cameras.

8. The image processing method of claim 7 , wherein the stitching the multiple local tracklets of the plurality of local tracklets from the multiple cameras comprises:
stitching the multiple local tracklets of the plurality of local tracklets from the multiple cameras in spatial space and temporal space.

9. The image processing method of claim 5 , wherein the extracting the motion features of the target comprises the motion features comprising at least one of a movement vector, an absolute direction vector, or a relative direction vector.

10. The image processing method of claim 5 , wherein each motion feature of the motion features comprises a vector, wherein the vector comprises information on a category of motion feature.

11. The image processing method of claim 5 , wherein the transforming the motion features into the address code by using the hashing process comprises transforming the motion features into the address code by using principal component analysis.

12. The image processing method of claim 5 , wherein the transmitting the plurality of address codes and the transformation parameter to the communication device comprises:
transmitting each address code of the plurality of address codes, wherein the each address code is concocted with a message.

13. The image processing method of claim 11 , wherein the transforming the motion features into the address code by using the principal component analysis comprises:
transforming a first motion feature of the motion features of the target into a first motion code by using the principal component analysis, wherein the first motion feature is a first category of motion feature;
transforming a second motion feature of the motion features of the target into a second motion code by using the principal component analysis, wherein the second motion feature is a second category of motion feature; and
stitching a plurality of motion codes into the address code, wherein the plurality of motion codes comprise the first motion code and the second motion code.

14. The image processing method of claim 13 , wherein the transforming the first motion feature of the motion features of the target into the first motion code comprises:
adding multiple noise vectors to each vector of a set of vectors, thereby generating a first concatenated set of vectors, wherein the each of the set of vectors comprises information on the first category of motion feature of the plurality of targets;
applying the principal component analysis to the first concatenated set of vectors to calculate a transformation coefficient matrix; and
using the transformation coefficient matrix and a first vector to calculate the first motion code, wherein the first vector comprises information of the first motion feature.

15. The image processing method of claim 13 , wherein the first category of motion feature comprises a movement vector category, an absolute direction vector category, or a relative direction vector category.

16. The image processing method of claim 13 , wherein the second category of motion feature comprises a movement vector category, an absolute direction vector category, or a relative direction vector category.

17. The image processing method of claim 14 , further comprising selecting, by a user, a number of principal components for the principal component analysis.

18. The image processing method of claim 1 , wherein an entirety of the each global tracklet comprises the motion features of a single target.

19. A method comprising:
identifying, using a server, a plurality of local tracklets from a plurality of targets;
creating, using a server, a plurality of global tracklets from the plurality of local tracklets, wherein each global tracklet comprises a set of local tracklet of the plurality of local tracklets, wherein the set of local tracklet corresponds to a target of the plurality of targets;
extracting, using a server, motion features of the each global tracklet of the plurality of global trackl

Assignees

• Purdue Research Foundation

Inventors

• Wang He
• Cao Siyuan

Classifications

• H04W4/029 Primary

  Location-based management or tracking services · CPC title

• H04L2101/69

  using geographic information, e.g. room number · CPC title

• H04L61/2503 Primary

  Translation of Internet protocol [IP] addresses · CPC title

• G06T7/292

  Multi-camera tracking · CPC title

• G06T7/246

  using feature-based methods, e.g. the tracking of corners or segments · CPC title