CN107527075B

CN107527075B - Method and device for establishing corresponding relation between RFID (radio frequency identification) tag and personnel and tracking track

Info

Publication number: CN107527075B
Application number: CN201610457281.2A
Authority: CN
Inventors: 郑翔; 万敏
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2016-06-20
Filing date: 2016-06-20
Publication date: 2020-09-04
Anticipated expiration: 2036-06-20
Also published as: CN107527075A; WO2017219679A1

Abstract

The embodiment of the invention discloses a method and a device for establishing a corresponding relation between an RFID (radio frequency identification) tag and a person and tracking a track. According to the established corresponding relation between the personnel and the RFID labels, the personnel tracks are tracked by the RFID labels corresponding to the personnel, compared with a method for tracking the personnel tracks by only using the human face images acquired by the human face image acquisition equipment in the prior art, the human face images are not required to be acquired in the whole process, the influence of equipment and the environment is avoided, and even in the dark, low-definition equipment or scenes without the human face image acquisition equipment, the personnel tracks can be tracked according to the tracking of the RFID labels.

Description

Method and device for establishing corresponding relation between RFID (radio frequency identification) tag and personnel and tracking track

Technical Field

The invention relates to the technical field of communication, in particular to a method and a device for establishing a corresponding relation between an RFID (radio frequency identification) tag and personnel and tracking a track.

Background

In daily life, people's trajectories need to be tracked in many cases, for example, when an event such as theft or robbery occurs, the trajectories of people related to the event need to be tracked.

Currently, people trajectory is usually tracked by using a face image acquisition device: the method comprises the steps that face image acquisition equipment is arranged at various positions of roads, public places and the like, the time and the place of a specific person are determined according to data acquired by the face image acquisition equipment, and therefore the track of the specific person is tracked.

However, by applying the method, the environment and the equipment can greatly influence the data acquisition effect, and under the condition of darkness or low equipment definition, the time and the place where a specific person appears can not be accurately determined, so that the trajectory of the person can not be accurately tracked; or a human face image acquisition device cannot be arranged at some positions, so that the trajectory of the human face cannot be accurately tracked.

Disclosure of Invention

The embodiment of the invention aims to provide a method and a device for establishing a corresponding relation between an RFID tag and a person and tracking a track, so that the track of the person can be more accurately tracked.

In order to achieve the above object, an embodiment of the present invention discloses a method for establishing a correspondence between a radio frequency identification RFID tag and a person, including:

acquiring a plurality of face images, determining first acquisition time and a first acquisition position of each face image, and dividing the plurality of face images into a plurality of image groups, wherein the face images in each image group belong to the same person;

acquiring a plurality of RFID labels, and determining second acquisition time and a second acquisition position of each RFID label;

aiming at each image group, matching the first acquisition time and the first acquisition position of the face image in the image group with the second acquisition time and the second acquisition position of each RFID label, and determining a target RFID label set successfully matched with the image group;

and determining a target RFID tag from the target RFID tag set, and establishing a corresponding relation between the target RFID tag and the image group.

Optionally, the determining a target RFID tag set successfully matched with the image group may include:

and aiming at the first acquisition time and the first acquisition position of each face image in the image group, when the difference value between the second acquisition time of the RFID label and the first acquisition time is smaller than a first threshold value and the difference value between the second acquisition position of the RFID label and the first acquisition position is smaller than a second threshold value, the matching between the RFID label and the face image is successful, and the RFID label is added into a target RFID label set.

Optionally, the target RFID tag set includes at least one subset, where the subset corresponds to a face image in the image group;

the adding the RFID tag to the target set of RFID tags may include:

and adding the RFID label to a corresponding subset of the facial image.

Optionally, before the determining the target RFID tag from the target RFID tag set, the method may further include:

determining the number of face images in the image group;

the determining a target RFID tag from the target set of RFID tags includes:

when the number of the face images in the image group is one, determining any one RFID label in the target RFID label set as a target RFID label;

when the number of the face images in the image group is more than one, counting the occurrence times of each RFID label in a subset corresponding to each face image in the image group; and determining the RFID label with the occurrence number larger than the third threshold value as the target RFID label.

Optionally, the determining, as the target RFID tag, the RFID tag whose occurrence number is greater than the third threshold may include:

when the number of the RFID tags with the occurrence frequency larger than a third threshold value is at least two, determining the RFID tag with the maximum occurrence frequency as a first target RFID tag, and determining the RFID tags with the occurrence frequency larger than the third threshold value except the first target RFID tag as a second target RFID tag;

the establishing of the corresponding relation between the target RFID label and the image group comprises the following steps:

establishing a first corresponding relation between the first target RFID label and the image group; and establishing a second corresponding relation between the second target RFID label and the image group.

Optionally, the method may further include:

when a new face image is acquired, calculating the similarity between the new face image and the face images in the image group aiming at each image group;

when the similarity between the new face image and the face images in the image group is greater than a fourth threshold value, dividing the new face image into the image group;

and when the similarity between the new face image and the face image in each image group is not greater than a fourth threshold, dividing the new face image into new image groups.

Optionally, the method may further include:

according to a preset period, aiming at each image group, carrying out similarity calculation on the face images in the image group and the face images in other image groups;

combining two images with the similarity larger than a fifth threshold into one image group, and combining target RFID label sets of the two image groups;

counting the occurrence frequency of each RFID label in the combined target RFID label set; and determining the RFID tags with the occurrence frequency larger than the sixth threshold value as new target RFID tags, and establishing the corresponding relation between the new target RFID tags and the combined image group.

In order to achieve the above object, an embodiment of the present invention further discloses a method for tracking a person trajectory, which is applied to a computer, where a correspondence between a radio frequency identification RFID tag and an image group, a second acquisition time and a second acquisition position of a face image and the RFID tag in the image group are stored in the computer, and the method includes:

receiving a face image to be recognized sent by a user, matching the face image to be recognized with a stored face image, and determining an image group corresponding to the face image to be recognized, wherein the face image in each image group belongs to the same person;

determining the track of the RFID label according to the second acquisition time and the second acquisition position of the RFID label;

and displaying the track of the RFID label corresponding to the image group corresponding to the face image to be recognized to the user according to the stored corresponding relation between the RFID label and the image group.

In order to achieve the above object, an embodiment of the present invention further discloses a device for establishing a correspondence between a radio frequency identification RFID tag and a person, including:

the system comprises an acquisition determining and dividing module, a face image acquiring module and a face image acquiring module, wherein the acquisition determining and dividing module is used for acquiring a plurality of face images, determining the first acquisition time and the first acquisition position of each face image, and dividing the plurality of face images into a plurality of image groups, and the face images in each image group belong to the same person;

the acquisition determining module is used for acquiring a plurality of RFID labels and determining second acquisition time and second acquisition position of each RFID label;

the matching module is used for matching the first acquisition time and the first acquisition position of the face image in each image group with the second acquisition time and the second acquisition position in each RFID label aiming at each image group;

the first determining module is used for determining a target RFID label set successfully matched with the image group;

a second determining module for determining a target RFID tag from the set of target RFID tags;

and the establishing module is used for establishing the corresponding relation between the target RFID label and the image group.

Optionally, the first determining module may include:

the matching submodule is used for successfully matching the RFID tag with the face image when the difference value between the second acquisition time of the RFID tag and the first acquisition time is smaller than a first threshold value and the difference value between the second acquisition position of the RFID tag and the first acquisition position is smaller than a second threshold value aiming at the first acquisition time and the first acquisition position of each face image in the image group;

and the adding sub-module is used for adding the RFID label to the target RFID label set.

the add sub-module may be specifically configured to:

and adding the RFID label to a corresponding subset of the facial image.

Optionally, the apparatus may further include:

the third determining module is used for determining the number of the face images in the image group;

the second determining module includes:

the first determining submodule is used for determining any one RFID tag in the target RFID tag set as a target RFID tag when the number of the face images in the image group is one;

the counting submodule is used for counting the occurrence times of each RFID label in the subset corresponding to each facial image in the image group when the number of the facial images in the image group is more than one;

and the second determining submodule is used for determining the RFID label with the occurrence number larger than the third threshold value as the target RFID label.

Optionally, the second determining submodule may be specifically configured to:

the establishing module may be specifically configured to:

Optionally, the apparatus may further include:

the first calculation module is used for calculating the similarity between the new face image and the face images in the image group aiming at each image group when the new face image is obtained;

the first dividing module is used for dividing the new face image into the image group when the similarity between the new face image and the face image in the image group is greater than a fourth threshold value;

and the second dividing module is used for dividing the new face image into new image groups when the similarity between the new face image and the face image in each image group is not greater than a fourth threshold.

Optionally, the apparatus may further include:

the second calculation module is used for calculating the similarity of the face images in the image group and the face images in other image groups according to a preset period;

the merging module is used for merging two images with the similarity larger than a fifth threshold into one image group and merging the target RFID label sets of the two image groups;

the statistic determination establishing module is used for counting the occurrence frequency of each RFID label in the combined target RFID label set; and determining the RFID tags with the occurrence frequency larger than the sixth threshold value as new target RFID tags, and establishing the corresponding relation between the new target RFID tags and the combined image group.

In order to achieve the above object, an embodiment of the present invention further discloses a device for tracking a person trajectory, which is applied to a computer, wherein the computer stores a correspondence between a radio frequency identification RFID tag and an image group, and a second acquisition time and a second acquisition position of a face image and the RFID tag in the image group, and the device includes:

the receiving and determining module is used for receiving a face image to be recognized sent by a user, matching the face image to be recognized with a stored face image and determining an image group corresponding to the face image to be recognized, wherein the face image in each image group belongs to the same person;

the fourth determining module is used for determining the track of the RFID label according to the second acquisition time and the second acquisition position of the RFID label;

and the display module is used for displaying the track of the RFID label corresponding to the image group corresponding to the face image to be recognized to the user according to the stored corresponding relation between the RFID label and the image group.

According to the technical scheme, the multiple face images are divided into the multiple image groups, the face images in each image group belong to the same person, and the corresponding relation between the image groups and the RFID tags is established according to the acquisition time and the acquisition position of the face images and the acquisition time and the acquisition position of the RFID tags, namely the corresponding relation between the person and the RFID tags is established. According to the established corresponding relation between the personnel and the RFID labels, the personnel tracks are tracked by the RFID labels corresponding to the personnel, compared with a method for tracking the personnel tracks by only using the human face images acquired by the human face image acquisition equipment in the prior art, the human face images are not required to be acquired in the whole process, the influence of equipment and the environment is avoided, and even in the dark, low-definition equipment or scenes without the human face image acquisition equipment, the personnel tracks can be tracked according to the tracking of the RFID labels.

Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above-described advantages at the same time.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flow chart of a method for establishing a correspondence between a radio frequency identification RFID tag and a person according to an embodiment of the present invention;

fig. 2 is a schematic flow chart illustrating a method for tracking a person trajectory according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of a device for establishing correspondence between a radio frequency identification RFID tag and a person according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of a person trajectory tracking device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In order to solve the technical problem, embodiments of the present invention provide a method and an apparatus for establishing a correspondence between a radio frequency identification RFID tag and a person, and a method and an apparatus for tracking a person trajectory. The method may be performed by a camera, a cell phone, a tablet, a personal computer, a server, etc. First, a method for establishing a correspondence between a radio frequency identification RFID tag and a person according to an embodiment of the present invention is described in detail below.

Fig. 1 is a schematic flow chart of a method for establishing a correspondence between a radio frequency identification RFID tag and a person according to an embodiment of the present invention, including:

s101: the method comprises the steps of obtaining a plurality of face images, determining first obtaining time and first obtaining position of each face image, dividing the plurality of face images into a plurality of image groups, wherein the face images in each image group belong to the same person.

As an embodiment of the present invention, a face image may be acquired by a face image acquisition device, and the face image acquisition device stores the acquired face image in a database. In addition, the database also correspondingly stores the first acquisition time and the first acquisition position of the face image. Specifically, the database may be stored in an electronic device such as a computer, and the electronic device may use the time when the face image is received as the first acquisition time of the face image. In addition, if the position of the face image acquisition device is fixed, the position of the face image acquisition device acquiring the face image can be acquired in advance as the acquisition position of the face image. If the face image acquisition device is mobile, the geographical position of the face image acquisition device when the face image is acquired can be used as the acquisition position, and the geographical position of a person in the face image can also be used as the acquisition position.

And matching the face images to obtain the face images belonging to the same person. Specifically, the two face images are matched, the face images can be converted into binary models through a deep learning algorithm, similarity calculation is carried out on the binary models of the two face images, and if the similarity is higher than a set value, successful matching of the two face images is indicated. And dividing the successfully matched face images into an image group, wherein the face images in each image group belong to the same person.

S102: and acquiring a plurality of RFID labels, and determining a second acquisition time and a second acquisition position of each RFID label.

As an embodiment of the present invention, the RFID tag may be collected by an RFID collection device, and the RFID collection device stores the collected RFID tag in a database. The RFID tag can be arranged on articles carried by people, such as a notebook, a case and the like; can also be arranged on vehicles used by people, such as bicycles, electric vehicles and the like; or on public transport means, such as buses and the like; of course, other objects that can move with the person are also possible. In addition, the database correspondingly stores the second acquisition time and the second acquisition position of the RFID tag. Specifically, the database may be stored in an electronic device such as a computer, and the electronic device takes the time when the RFID tag is received as the second acquisition time of the RFID tag; in addition, if the position of the RFID acquisition device is fixed, the position of the RFID acquisition device acquiring the RFID information may be acquired in advance as the acquisition position of the RFID information.

In order to ensure that the matching degree between the first acquisition position of the acquired face image and the second acquisition position of the acquired RFID tag is high, in one embodiment of the present invention, the RFID acquisition device and the face image acquisition device may be arranged in the same or similar geographical areas. Therefore, when the face image acquisition equipment acquires the face image, the RFID acquisition equipment correspondingly acquires the RFID label.

S103: and aiming at each image group, matching the first acquisition time and the first acquisition position of the face image in the image group with the second acquisition time and the second acquisition position of each RFID tag, and determining a target RFID tag set successfully matched with the image group.

As an embodiment of the present invention, determining a target RFID tag set successfully matched with the image group may include:

Assume that the image group M includes 3 face images: the first acquisition time and the first acquisition position of the face image a, the face image B and the face image C, and 3 face images are shown in table 1:

face image	First acquisition time of face image	First acquisition position of face image
			Face image A	4 month, 26 days, 10:10	X1
Face image B	4 month, 27 days, 11:10	X2
			Face image C	4 month, 28 days, 9:10	X3

Assume that the following RFID tags are obtained, as shown in Table 2:

TABLE 2

RFID tag numbering	Second acquisition time of RFID tag	Second acquisition location of RFID tag
			1	4 month, 26 days, 10:06	X1+10m
2	4 month, 26 days, 10:14	X1+20m
			3	12:07 in 26 days 4 and 26 months	X1+200m
4	4 month, 26 days, 22:05	X1+100m
			1	4 month, 27 days, 11:14	X2+20m
3	4 month, 27 days 11:06	X2+10m
			1	4 month, 28 days, 9:07	X3+10m
2	4 month, 28 days, 9:11	X3+20m
			4	4 month, 28 days, 10:10	X4+40m

Assume that the first threshold is 5min and the second threshold is 30 m. As can be seen from table 1, for the face image a: the difference between the second acquisition time (10: 06 on 26/4 month) of the RFID tag numbered 1 and the first acquisition time (10: 10 on 26/4 month) of the face image a is less than the first threshold value for 5min, and the difference between the second acquisition position (X1+10M) of the RFID tag numbered 1 and the first acquisition position (X1) of the face image a is less than the second threshold value of 30M, that is, the RFID tag numbered 1 is successfully matched with the face image a, and the RFID tag numbered 1 is added to the target RFID tag set of the image group M.

Similarly, the RFID tag numbered 2 is successfully matched with the face image a, and the RFID tag numbered 2 is added to the target RFID tag set of the image group M.

Similarly, for the face image B, the RFID tags numbered 1 and 3 are successfully matched with the face image B, and the RFID tags numbered 1 and 3 are added to the target RFID tag set of the image group M.

For the face image C, the RFID tags numbered 1 and 2 are successfully matched with the face image C, and the RFID tags numbered 1 and 2 are added to the target RFID tag set of the image group M.

As an embodiment of the present invention, the target RFID tag set includes at least one subset, and the subset corresponds to a face image in the image group. In this case, the RFID tag is added to a target RFID tag set, that is, the RFID tag is added to a corresponding subset of the face image.

Also explained with the above example, that is, 3 subsets are included in the target RFID tag set, and the 3 subsets correspond to 3 face images respectively. In this case, RFID tags numbered 1 and 2 are added to the subset corresponding to face image a, RFID tags numbered 1 and 3 are added to the subset corresponding to face image B, and RFID tags numbered 1 and 2 are added to the subset corresponding to face image C.

S104: determining a target RFID tag from the set of target RFID tags.

In the illustrated embodiment of the present invention, before S104, the number of face images in the image group may be determined.

When the image group includes only one face image, that is, the target RFID tag set includes only one subset, any one RFID tag in the subset is determined as the target RFID tag.

In the above example, the image group M includes 3 face images, and the target RFID tag set includes 3 subsets: the set corresponding to the face image A comprises RFID tags numbered 1 and 2, the sub-set corresponding to the face image B comprises RFID tags numbered 1 and 3, and the sub-set corresponding to the face image C comprises RFID tags numbered 1 and 2. In this case, the number of times of occurrence of each RFID tag in the subset corresponding to each face image in the image group M is counted: the RFID tag numbered 1 appears 3 times, the RFID tag numbered 2 appears 2 times, and the RFID tag numbered 3 appears 1 time.

Assuming that the third threshold value is 1, the RFID tags whose number of occurrences is greater than 1 are determined as the target RFID tags, that is, the RFID tags numbered 1 and 2 are determined as the target RFID tags.

S105: and establishing a corresponding relation between the target RFID label and the image group.

As one embodiment of the present invention, when the number of RFID tags whose number of occurrences is greater than the third threshold value includes at least two, the RFID tag whose number of occurrences is the largest is determined as a first target RFID tag, and the RFID tags whose number of occurrences is greater than the third threshold value other than the first target RFID tag are determined as a second target RFID tag.

That is, the RFID tag numbered 1 is determined as a first target RFID tag, and the RFID tag numbered 2 is determined as a second target RFID tag.

The establishing of the corresponding relationship between the target RFID tag and the image group may include:

That is, a first correspondence relationship between the RFID tag numbered 1 and the image group is established; and establishing a second corresponding relation between the RFID label with the number of 2 and the image group.

As will be appreciated by those skilled in the art, as one embodiment of the present invention, an RFID acquisition device is provided in the vicinity of the face image acquisition device. When the facial image acquisition device acquires a facial image, the RFID acquisition device may acquire RFID tags of a plurality of people nearby at the same time. However, through long-time statistics, the number of times that the RFID tag of the person appears together with the face image of the person is large, so that the RFID tag with the largest number of times of appearance is determined as a first target RFID tag, namely the RFID tag which is determined as the person; a first correspondence between the personal RFID tag and a personal image group is established.

In addition, the RFID tags of other people who appear together with the face images frequently are the RFID tags of the same personnel, and have important significance. Thus, the RFID tags other than the first target RFID tag among the RFID tags whose number of occurrences is greater than the third threshold value are determined as the second target RFID tag; and establishing a second corresponding relation between the second target RFID label and the image group.

In the embodiment of the invention, when a new face image is acquired, for each image group, similarity calculation is carried out on the new face image and the face images in the image group;

As an embodiment of the invention, the face image acquisition device stores the acquired face image into the database, and the RFID acquisition device also stores the acquired RFID label into the database.

In the embodiment of the invention, when the face image acquisition device stores the newly acquired face image into the database, the two situations of addition and update are included: when the similarity between the new face image and the face images in the image group is greater than a fourth threshold value, the face image of the person corresponding to the new face image is already in the database, and in this case, the new face image is divided into the image group and belongs to updating; and when the similarity between the new face image and the face image in each image group is not greater than the fourth threshold, the face image of the person corresponding to the new face image does not exist in the database, and under the condition, the new face image is divided into new image groups and belongs to new addition.

In the embodiment of the present invention, according to a preset period, for each image group, similarity calculation may be performed on a face image in the image group and a face image in another image group;

That is, in the illustrated embodiment of the present invention, the human merger may be performed periodically.

For example, after calculating the similarity between the face image in the image group and the face images in other image groups for each image group, if it is found that the person Y and the person Z are the same person, the person Y and the person Z are merged, before merging:

	person Y	Person Z
			Human face record	E1、E2	D1，D2，D3
RFID tag numbering	1、2、3	1、4、5
			Corresponding number of occurrences of radio frequency number	2、1、1	3、2、1

After merging:

	person Y
		Human face record	E1、E2、D1、D2、D3
Radio frequency numbering	1、2、3、4、5
		Corresponding number of occurrences of radio frequency number	5、1、1、2、1

And personnel merging is carried out regularly, so that the accuracy of the data is further improved.

By applying the embodiment of the invention shown in fig. 1, a plurality of face images are divided into a plurality of image groups, the face images in each image group belong to the same person, and the corresponding relation between the image groups and the RFID tags is established according to the acquisition time and the acquisition position of the face images and the acquisition time and the acquisition position of the RFID tags, namely the corresponding relation between the person and the RFID tags is established. According to the established corresponding relation between the personnel and the RFID labels, the personnel tracks are tracked by the RFID labels corresponding to the personnel, compared with a method for tracking the personnel tracks by only using the human face images acquired by the human face image acquisition equipment in the prior art, the human face images are not required to be acquired in the whole process, the influence of equipment and the environment is avoided, and even in the dark, low-definition equipment or scenes without the human face image acquisition equipment, the personnel tracks can be tracked according to the tracking of the RFID labels.

Fig. 2 is a schematic flow chart of a person trajectory tracking method according to an embodiment of the present invention, which is applied to a computer, where a correspondence between a radio frequency identification RFID tag and an image group, a second acquisition time and a second acquisition position of a face image and the RFID tag in the image group are stored in the computer, and the method includes:

s201: receiving a face image to be recognized sent by a user, matching the face image to be recognized with a stored face image, and determining an image group corresponding to the face image to be recognized. And the face images in each image group belong to the same person.

S202: and determining the track of the RFID label according to the second acquisition time and the second acquisition position of the RFID label.

S203: and displaying the track of the RFID label corresponding to the image group corresponding to the face image to be recognized to the user according to the stored corresponding relation between the RFID label and the image group.

By applying the embodiment of the invention shown in fig. 1, the corresponding relation between the radio frequency identification RFID tag and the image group is established and stored, and the face image in each image group belongs to the same person, that is, the corresponding relation between the RFID tag and the person is established. In addition, the computer also stores a second acquisition time and a second acquisition position of the face image and the RFID tag in the image group. And determining the track of the RFID label according to the second acquisition time and the second acquisition position of the RFID label.

It can be understood that the RFID tags are installed on objects such as electric vehicles and bicycles, the RFID acquisition equipment is arranged in the active area of the objects, the RFID tags of the objects with the RFID tags can be acquired by using the plurality of RFID acquisition equipment, and the tracks of the RFID tags can be obtained according to the acquired different positions of the RFID tags appearing at different times.

Receiving a face image to be recognized sent by a user, matching the face image to be recognized with a stored face image, and determining an image group corresponding to the face image to be recognized, wherein the process is to determine a person to be inquired by the user. The computer stores the corresponding relation between the RFID tags and the personnel, so that the RFID tags corresponding to the personnel to be inquired by the user can be determined. The computer also stores a second acquisition time and a second acquisition location of the RFID tag, so that the trajectory of the RFID tag can be determined. Therefore, by applying the scheme, the track of the RFID label corresponding to the person is displayed to the user according to the determined person to be inquired, and the tracking of the track of the person can be realized.

As an embodiment of the present invention, the method may further include receiving an RFID tag sent by a user, querying a face image of a person corresponding to the RFID tag according to a stored correspondence between the RFID tag and the image group and the face image in the image group, and displaying the queried face image to the user.

In addition, after the RFID tag sent by the user is received, the track of the RFID tag can be determined according to the stored second acquisition time and the second acquisition position of the RFID tag, and the determined track of the RFID tag is displayed to the user.

By applying the embodiment of the invention shown in fig. 2, the personnel track is tracked by using the RFID tag corresponding to the personnel according to the stored corresponding relationship between the personnel and the RFID tag, compared with the method for tracking the personnel track by using the human face image acquired by the human face image acquisition equipment in the prior art, the method does not need to acquire the human face image in the whole process, avoids the influence of equipment and environment, and can realize the tracking of the personnel track according to the tracking of the RFID tag even in dark scenes with low equipment definition or scenes without the human face image acquisition equipment.

Corresponding to the method embodiment, the embodiment of the invention also provides a device for establishing the corresponding relation between the radio frequency identification RFID tag and the personnel and a personnel track tracking device.

Fig. 3 is a schematic structural diagram of a device for establishing correspondence between a radio frequency identification RFID tag and a person according to an embodiment of the present invention, including:

the acquisition determining and dividing module 301 is configured to acquire a plurality of face images, determine a first acquisition time and a first acquisition position of each face image, and divide the plurality of face images into a plurality of image groups, where the face images in each image group belong to the same person;

an obtaining and determining module 302, configured to obtain a plurality of RFID tags, and determine a second obtaining time and a second obtaining location of each RFID tag;

the matching module 303 is configured to match, for each image group, the first acquisition time and the first acquisition position of the face image in the image group with the second acquisition time and the second acquisition position in each RFID tag;

a first determining module 304, configured to determine a target RFID tag set successfully matched with the image group;

a second determining module 305 for determining a target RFID tag from the target RFID tag set;

an establishing module 306, configured to establish a correspondence between the target RFID tag and the image group.

In the illustrated embodiment of the present invention, the first determining module 304 may include: a matching sub-module and an adding sub-module (not shown), wherein,

In the embodiment of the invention, the target RFID label set comprises at least one sub-set, and the sub-set corresponds to a face image in the image group;

the add sub-module may be specifically configured to:

and adding the RFID label to a corresponding subset of the facial image.

In the embodiment of the present invention, a third determining module may be further included, configured to determine the number of face images in the image group;

the second determining module 305 may include: a first determination submodule, a statistics submodule and a second determination submodule (not shown in the figure), wherein,

In the embodiment of the present invention, the second determining submodule may be specifically configured to:

the establishing module 306 may specifically be configured to:

In the embodiment of the present invention, the method may further include: a first calculation module, a first division module, and a second division module (not shown), wherein,

In the embodiment of the present invention, the method may further include: a second calculation module, a merging module, and a statistical determination establishing module (not shown in the figure), wherein,

By applying the embodiment of the invention shown in fig. 3, a plurality of face images are divided into a plurality of image groups, the face images in each image group belong to the same person, and the corresponding relation between the image groups and the RFID tags is established according to the acquisition time and the acquisition position of the face images and the acquisition time and the acquisition position of the RFID tags, that is, the corresponding relation between the person and the RFID tags is established. According to the established corresponding relation between the personnel and the RFID labels, the personnel tracks are tracked by the RFID labels corresponding to the personnel, compared with a method for tracking the personnel tracks by only using the human face images acquired by the human face image acquisition equipment in the prior art, the human face images are not required to be acquired in the whole process, the influence of equipment and the environment is avoided, and even in the dark, low-definition equipment or scenes without the human face image acquisition equipment, the personnel tracks can be tracked according to the tracking of the RFID labels.

Fig. 4 is a schematic structural diagram of a person trajectory tracking device according to an embodiment of the present invention, which is applied to a computer, where a correspondence between a radio frequency identification RFID tag and an image group, a second acquisition time and a second acquisition position of a face image and the RFID tag in the image group are stored in the computer, and the device includes:

the receiving and determining module 401 is configured to receive a facial image to be recognized sent by a user, match the facial image to be recognized with a stored facial image, and determine an image group corresponding to the facial image to be recognized, where the facial image in each image group belongs to the same person;

a fourth determining module 402, configured to determine a track of the RFID tag according to the second obtaining time and the second obtaining location of the RFID tag;

and the displaying module 403 is configured to display, according to the stored correspondence between the RFID tag and the image group, a track of the RFID tag corresponding to the image group corresponding to the face image to be recognized to the user.

By applying the embodiment of the invention shown in fig. 4, the personnel track is tracked by using the RFID tag corresponding to the personnel according to the stored corresponding relationship between the personnel and the RFID tag, compared with the method for tracking the personnel track by using the human face image acquired by the human face image acquisition equipment in the prior art, the method does not need to acquire the human face image in the whole process, avoids the influence of equipment and environment, and can realize the tracking of the personnel track according to the tracking of the RFID tag even in dark scenes with low equipment definition or scenes without the human face image acquisition equipment.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

Those skilled in the art will appreciate that all or part of the steps in the above method embodiments may be implemented by a program to instruct relevant hardware to perform the steps, and the program may be stored in a computer-readable storage medium, which is referred to herein as a storage medium, such as: ROM/RAM, magnetic disk, optical disk, etc.

The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims

1. A method for establishing a corresponding relationship between a Radio Frequency Identification (RFID) tag and a person is characterized by comprising the following steps:

determining a target RFID tag from the target RFID tag set, and establishing a corresponding relation between the target RFID tag and the image group;

prior to said determining a target RFID tag from said set of target RFID tags, further comprising:

determining the number of face images in the image group;

the determining a target RFID tag from the target set of RFID tags includes:

when the number of the face images in the image group is more than one, counting the occurrence frequency of each RFID label in a subset corresponding to each face image in the image group, wherein the subset is an RFID label set successfully matched with the face image; determining the RFID tags with the occurrence times larger than a third threshold value as target RFID tags;

the method further comprises the following steps:

2. The method of claim 1, wherein determining the set of target RFID tags that successfully match the set of images comprises:

3. The method of claim 1, wherein determining the RFID tag with the occurrence number greater than the third threshold as the target RFID tag comprises:

4. The method of claim 1, further comprising:

5. A person trajectory tracking method, applied to a computer, wherein a correspondence relationship between a radio frequency identification RFID tag and an image group, a second acquisition time and a second acquisition position of a face image and the RFID tag in the image group are stored in the computer, and the correspondence relationship is established by the method for establishing a correspondence relationship between a radio frequency identification RFID tag and a person according to any one of claims 1 to 4, the method comprising:

6. A device for establishing correspondence between Radio Frequency Identification (RFID) tags and persons is characterized by comprising:

the establishing module is used for establishing the corresponding relation between the target RFID label and the image group;

the second determining module includes:

the counting submodule is used for counting the occurrence frequency of each RFID label in a subset corresponding to the face image aiming at each face image in the image group when the number of the face images in the image group is more than one, and the subset is combined into an RFID label set successfully matched with the face image;

the second determining submodule is used for determining the RFID label with the occurrence frequency larger than a third threshold value as a target RFID label;

7. The apparatus of claim 6, wherein the first determining module comprises:

8. The apparatus of claim 6, wherein the second determining submodule is specifically configured to:

the establishing module is specifically configured to:

9. The apparatus of claim 6, further comprising:

10. A person trajectory tracking device, applied to a computer, wherein a correspondence relationship between a radio frequency identification RFID tag and an image group, a second acquisition time and a second acquisition position of a face image and the RFID tag in the image group are stored in the computer, and the correspondence relationship is established by the method for establishing a correspondence relationship between a radio frequency identification RFID tag and a person according to any one of claims 1 to 4, the device comprising: