CN115455998A - Vehicle electronic identification recognition method and system - Google Patents
Vehicle electronic identification recognition method and system Download PDFInfo
- Publication number
- CN115455998A CN115455998A CN202210940046.6A CN202210940046A CN115455998A CN 115455998 A CN115455998 A CN 115455998A CN 202210940046 A CN202210940046 A CN 202210940046A CN 115455998 A CN115455998 A CN 115455998A
- Authority
- CN
- China
- Prior art keywords
- time slot
- tags
- signals
- preset
- labels
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/10009—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves
- G06K7/10019—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves resolving collision on the communication channels between simultaneously or concurrently interrogated record carriers.
- G06K7/10029—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves resolving collision on the communication channels between simultaneously or concurrently interrogated record carriers. the collision being resolved in the time domain, e.g. using binary tree search or RFID responses allocated to a random time slot
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/10009—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves
- G06K7/10316—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves using at least one antenna particularly designed for interrogating the wireless record carriers
- G06K7/10356—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves using at least one antenna particularly designed for interrogating the wireless record carriers using a plurality of antennas, e.g. configurations including means to resolve interference between the plurality of antennas
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a vehicle electronic identification recognition method and a system, wherein the method comprises the steps that a reader sends a Query instruction to specify the frame length, a tag in the recognition range of the reader randomly selects a time slot within the frame length range to respond to the instruction of the reader and returns an information packet; if the collision time slot exists, acquiring an observed value in the previous frame, and obtaining the number of labels according to the observed value in the previous frame and a preset label estimation algorithm; obtaining the time slot number of the next frame according to the number of the labels and the number of the antennas; and if the number of the antennas is not more than the number of the tags in the next frame time slot, separating the tag signals by adopting a second preset separation method, and identifying the vehicle according to the separated signals. And selecting a proper separation method, separating out signals and finishing identification. The accuracy of discernment has been improved, the wrong problem of discernment that has avoided the collision problem to bring has been discerned, and the recognition efficiency obtains improving.
Description
Technical Field
The present application relates to the field of vehicle identification technologies, and in particular, to a method and a system for identifying an electronic identifier of a vehicle.
Background
Radio Frequency Identification (RFID) is an abbreviation for Radio Frequency Identification. The wireless radio frequency identification technology is one of automatic identification technologies, performs non-contact bidirectional data communication in a wireless radio frequency mode, and reads and writes a recording medium (an electronic tag or a radio frequency card) in the wireless radio frequency mode so as to achieve the purposes of identification and data exchange, and is considered to be one of the information technologies with the most development potential in the 21 st century. The components of an RFID radio frequency identification system generally include at least two parts: electronic tags (Tag) and readers (Reader). Electronic data in a predetermined format is generally stored in the electronic tag, and in practical applications, the electronic tag is attached to the surface of an object to be identified. The reader is also called a reading device, and can read and identify electronic data stored in the electronic tag without contact, thereby achieving the purpose of automatically identifying an object. Further, the management functions of collecting, processing and remote transmitting the object identification information are realized through a computer and a computer network.
The multi-antenna technology is not only increased in the number of antennas, but also refers to an intelligent antenna with algorithms of tracking signals, positioning signal sources and the like, and compared with the single-antenna technology, the multi-antenna technology has the advantages of being obvious in advantages, large in communication capacity, high in transmission rate, small in signal transmitting power, capable of positioning signal sources, and further has the advantages of increasing system capacity, improving spectrum efficiency, expanding signal coverage and the like.
At present, many scholars conduct relevant research on a multi-antenna RFID system, and develop a 4-antenna ultrahigh frequency RFID reader-writer, which is not affected by the orientation of a label when the label is read, so that instantaneous reading of multiple labels is realized, and the number of the read labels is increased. However, the problem that the recognition efficiency is not high when the multi-antenna RFID system is in a scene with a large number of tags still exists, such as logistics management, warehouse management, motor vehicle management, and the like. In the multi-antenna RFID system, a large number of tags transmit signals to a plurality of antennas of a reader within the same time, and at the moment, the probability of tag signal collision at a certain time point is aggravated, so that the identification efficiency of the multi-antenna RFID system is influenced.
A schematic diagram of tag collision is shown in fig. 3, where tag collision refers to that two or more tag signals simultaneously feed back signals to a reader at the same time, so that the simultaneously returned signals collide with each other, and the collided tags cannot be identified, so that the tag collision reduces the identification efficiency of the RFID system.
Therefore, how to improve the tag identification efficiency is a technical problem to be solved at present.
Disclosure of Invention
The invention provides a vehicle electronic identification recognition method, which is used for solving the technical problem of low identification efficiency of labels in the prior art. The method is applied to a multi-antenna RFID system, and the number of antennas is preset, and the method comprises the following steps:
the method comprises the following steps: the reader sends a Query instruction to specify the frame length, and the tags in the identification range of the reader randomly select a time slot in the frame length range to respond to the instruction of the reader and return an information packet;
step two: if collision time slots exist, after the previous frame is finished, acquiring an observed value in the previous frame, and obtaining the number of labels according to the observed value in the previous frame and a preset label estimation algorithm;
step three: obtaining the time slot number of the next frame according to the tag number and the antenna number, and judging whether the antenna number is greater than the tag number in the time slot of the next frame on the basis of the time slot number of the next frame;
step four: if the number of the antennas is larger than that of the tags in the next frame time slot, a first preset separation method is adopted to separate the tag signals, vehicle identification is carried out according to the separated signals, if the number of the antennas is not larger than that of the tags in the next frame time slot, a second preset separation method is adopted to separate the tag signals, and vehicle identification is carried out according to the separated signals;
and the collision time slot is the time slot of two or more labels returning information packets.
In some embodiments of the present application, the number of tags is obtained according to the observation value in the previous frame and a preset tag estimation algorithm, and specifically:
the observation value comprises an idle time slot number, a success time slot number and a collision time slot number, wherein the idle time slot number is the number of time slots without labels for returning the information packets, the success time slot number is the number of time slots with only one label for returning the information packets, and the collision time slot number is the number of time slots with two or more labels for returning the information packets;
calculating the probability of the collision time slot in the initial frame according to the number of the idle time slots, the number of the successful time slots and the number of the collision time slots, roughly estimating the number of the tags according to the probability to obtain the number of the first tags, and if the number of the first tags does not meet the preset requirement, finely estimating to obtain the number of the tags;
and if the first label quantity meets the preset requirement, taking the first label quantity as the label quantity.
In some embodiments of the present application, if the number of antennas is not greater than the number of tags in the next frame time slot, a second preset separation method is used to separate tag signals, specifically:
setting N tags in one time slot, wherein the return signals of the N tags are S = [ S ] 1 ，S 2 ，S 3 ......S N ]The reader is provided with M antennae, and M mixed signals of N labels randomly mixed are received by the M antennae and are X = [ X ] 1 ，X 2 ，X 3 ......X M ]Wherein, X = AS, a is an N × M-dimensional column full-rank instantaneous linear mixing matrix, a separation matrix W is obtained by an ICA method, and the separation matrix W is substituted into the following model:
Y＝WX，
wherein, Y is a signal which is close to the label signal after the M mixed signals are separated, and W is an M multiplied by N dimension instantaneous linear separation matrix.
In some embodiments of the present application, the method further comprises:
if the signals separated by the first preset separation method or the second preset separation method do not have unidentified tags, vehicle identification is carried out according to the separated signals;
and if the signals separated by the first preset separation method or the second preset separation method have unidentified labels, re-performing the first step to the fourth step.
Correspondingly, the application also provides a vehicle electronic identification recognition system, which is applied to a multi-antenna RFID system, and the number of antennas is preset, and the system comprises:
the response module is used for the reader to send a Query instruction to specify the frame length, and the tags in the identification range of the reader randomly select a time slot to respond to the instruction of the reader in the frame length range and return an information packet;
the estimation module is used for acquiring an observed value in a previous frame after the previous frame is finished if a collision time slot exists, and acquiring the number of labels according to the observed value in the previous frame and a preset label estimation algorithm;
the judging module is used for obtaining the time slot number of the next frame according to the tag number and the antenna number, and judging whether the antenna number is greater than the tag number in the time slot of the next frame on the basis of the time slot number of the next frame;
the separation module is used for separating the tag signals by adopting a first preset separation method if the number of the antennas is greater than the number of the tags in the next frame time slot, and identifying the vehicle according to the separated signals;
and the collision time slot is the time slot of two or more labels returning information packets.
In some embodiments of the present application, the estimation module is specifically configured to:
the observation value comprises an idle time slot number, a success time slot number and a collision time slot number, wherein the idle time slot number is the number of time slots without labels for returning the information packets, the success time slot number is the number of time slots with only one label for returning the information packets, and the collision time slot number is the number of time slots with two or more labels for returning the information packets;
calculating the probability of the collision time slot in the initial frame according to the number of the idle time slots, the number of the successful time slots and the number of the collision time slots, roughly estimating the number of the tags according to the probability to obtain the number of the first tags, and if the number of the first tags does not meet the preset requirement, finely estimating to obtain the number of the tags;
and if the first label quantity meets the preset requirement, taking the first label quantity as the label quantity.
In some embodiments of the present application, the separation module is specifically configured to:
setting N tags in one time slot, wherein the return signals of the N tags are S = [ S ] 1 ，S 2 ，S 3 ......S N ]The reader is provided with M antennae, and M mixed signals of N labels which are randomly mixed are received by the M antennae and are X = [ X ] 1 ，X 2 ，X 3 ......X M ]Wherein, X = AS, A is N × M dimension full rank instantaneous linear mixing matrix, then separating matrix W is obtained by ICA method, and separating matrix W is processedSubstituted into the following model:
Y＝WX，
wherein, Y is a signal which is close to the label signal after the M mixed signals are separated, and W is an M multiplied by N dimension instantaneous linear separation matrix.
In some embodiments of the present application, the system further comprises a verification module, the verification module being configured to:
if the signals separated by the first preset separation method or the second preset separation method do not have unidentified tags, vehicle identification is carried out according to the separated signals;
and if the signals separated by the first preset separation method or the second preset separation method have unidentified labels, re-performing the first step to the fourth step.
By applying the technical scheme, the first step is as follows: the reader sends a Query instruction to specify the frame length, and a time slot is randomly selected in the range of the frame length for the tags in the range of the reader identification to respond to the instruction of the reader and return an information packet; step two: if collision time slots exist, after the previous frame is finished, obtaining an observed value in the previous frame, and obtaining the number of labels according to the observed value in the previous frame and a preset label estimation algorithm; step three: obtaining the time slot number of the next frame according to the tag number and the antenna number, and judging whether the antenna number is greater than the tag number in the time slot of the next frame on the basis of the time slot number of the next frame; step four: if the number of the antennas is larger than that of the tags in the next frame time slot, a first preset separation method is adopted to separate the tag signals, vehicle identification is carried out according to the separated signals, if the number of the antennas is not larger than that of the tags in the next frame time slot, a second preset separation method is adopted to separate the tag signals, and vehicle identification is carried out according to the separated signals. According to the method and the device, the estimated frame length of the next frame is obtained according to the number of the antennas and the number of the tags, and a proper separation method is selected according to the relation between the number of the antennas and the number of the tags in the time slot, so that signals are separated, and the identification is completed. The accuracy of discernment is improved, the problem of the wrong discernment that has avoided the collision problem to bring is discerned, and recognition efficiency obtains improving.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for identifying an electronic identifier of a vehicle according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a vehicle electronic identification recognition system according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating the principle of tag collision in the background of the invention;
FIG. 4 shows a mathematical model diagram that sets forth blind primitive separation according to another embodiment of the present invention;
fig. 5 shows a mathematical model diagram based on the ICA method according to another embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
The embodiment of the application provides a vehicle electronic identification recognition method, which is applied to a multi-antenna RFID system, and the number of antennas is preset, as shown in FIG. 1, the method comprises the following steps:
the method comprises the following steps: s101, the reader sends a Query instruction to specify the frame length, and tags in the identification range of the reader randomly select a time slot to respond to the instruction of the reader in the frame length range and return an information packet.
In the embodiment, a time slot ALOHA algorithm is improved, and the basic working process of the time slot ALOHA algorithm is that a reader firstly sends a Query instruction to specify the frame length, namely the number of frame time slots; the tags in the identification range randomly select a time slot in the frame length range to respond to the instruction of the reader-writer and return information packets, the time slot in which only one tag returns the information packet is called a success time slot, the time slot in which no tag returns the information packet is called an empty time slot, the time slots in which 2 or more tags return the information packet are called collision time slots, and the tags which collide continue to try to identify in the next frame; the algorithm firstly adopts a certain label estimation method to estimate the number of labels in the field according to the feedback of the previous frame (namely the observed value: the number of collision time slots, the number of empty time slots and the number of successful time slots), then adopts a frame time slot estimation algorithm according to the conditions of the number of labels and the like to estimate the frame length of the next frame, and so on until the labels in the working field of the reader-writer are completely identified. The improvement point is that the length of the frame is changed according to the number of the current tags and the number of the antennas, so that the proper time slot number is selected.
Step two: s102, if a collision time slot exists, after the previous frame is finished, obtaining an observed value in the previous frame, and obtaining the number of labels according to the observed value in the previous frame and a preset label estimation algorithm.
In some embodiments of the present application, the number of tags is obtained according to the observation value in the previous frame and a preset tag estimation algorithm, and specifically: the observation values comprise an idle time slot number, a success time slot number and a collision time slot number, wherein the idle time slot number is the number of time slots without labels for returning the information packets, the success time slot number is the number of time slots with only one label for returning the information packets, and the collision time slot number is the number of time slots with two or more labels for returning the information packets; calculating the probability of the collision time slot in the initial frame according to the number of the idle time slots, the number of the successful time slots and the number of the collision time slots, roughly estimating the number of the tags according to the probability to obtain the number of the first tags, and if the number of the first tags does not meet the preset requirement, finely estimating to obtain the number of the tags; and if the first label quantity meets the preset requirement, taking the first label quantity as the label quantity.
In this embodiment, the initial frame size is set to be F, and after the previous frame identification is finished, the number of idle slots C0, the number of successful slots C1, and the number of collision slots CK are counted. Then, the probability P = CK/F that the collision slot occurs in the initial frame is calculated. The number of tags N at the first calculation (first number of tags) is estimated by modeling analysis P against the average number of tags in the collision time slot nk. And then, evaluating the number of the labels estimated for the first time, if the number of the labels is in accordance with the requirement, finishing the algorithm, otherwise, carrying out fine estimation, namely estimating the number of the labels for the second time. Wherein, the precise estimation algorithm adopts a maximum posterior probability estimation algorithm based on prior knowledge. And taking the number N of the labels estimated in the rough estimation as an estimated starting point value of the fine estimation, determining the searching direction in the rough estimation through the posterior probability, then, searching the maximum posterior probability until the requirement is met, and stopping the searching, wherein the N is the final estimated value of the number of the labels.
As shown in fig. 3, blind signal separation refers to: the process of finding Source signal data by obtaining observation signal data only, i.e. Blind Source Separation, is based on some statistical properties of the Source signal, when the parameters of the Source signal and the transmission channel are not known. The idea of blind source separation is applied to the processing of tag signals of a multi-antenna RFID system, and a mathematical model of blind source separation is similar to a mathematical model of receiving a plurality of tag signals by a plurality of antennas in the RFID system. On the left side of the figure are M source signals S, analogous to the multiple tag signals of a certain time slot in a multi-antenna RFID system, a referring to the mixing matrix, both the mixing matrix and the source signals being unknown. In the middle are N observation signals X, which are known and whose signal lengths are the same, in analogy to the signals received by the antennas of a multi-antenna RFID system in a certain time slot. The mathematical model of blind source separation can be written as formula:
X＝AS，Y＝WX。
y is the output signal through the separation matrix. The blind source separation method is to make the output signal approach the real source signal as much as possible by finding the separation matrix w. The mixing matrix A is an N multiplied by M dimension column full rank instantaneous linear mixing matrix; the separation matrix W is an M × N dimensional instantaneous linear separation matrix.
Step three: s103, obtaining the time slot number of the next frame according to the tag number and the antenna number, and judging whether the antenna number is larger than the tag number in the time slot of the next frame on the basis of the time slot number of the next frame.
In this embodiment, here, the number of tags in the next frame slot is the number of tags that need to be identified. When the first frame is finished, the number of empty time slots, successful time slots and failed time slots in the frame can be known, the total number n of the tags can be estimated according to the existing tag estimation algorithm, and then the number of the tags to be identified in the next frame can be calculated according to n and the number of the tags already identified in the frame. The optimal number of slots for the next frame can be estimated. The time slot number N1 of the next frame is determined by the number of antennas, the number of tags and the time slot number of the initial frame. And judging whether the number of the antennas is greater than the number of the tags in the next frame time slot, wherein the number of the tags in the next frame time slot is N, the number of the antennas is M, judging the sizes of M and N, and selecting a separation method according to the relationship between the M and the N.
Step four: and S104, if the number of the antennas is larger than that of the tags in the next frame time slot, separating the tag signals by adopting a first preset separation method, and identifying the vehicle according to the separated signals, and if the number of the antennas is not larger than that of the tags in the next frame time slot, separating the tag signals by adopting a second preset separation method, and identifying the vehicle according to the separated signals.
In some embodiments of the present application, if the number of antennas is not greater than the number of tags in the next frame time slot, a second preset separation method is used to separate tag signals, specifically: setting N tags in one time slot, wherein the return signals of the N tags are S = [ S ] 1 ，S 2 ，S 3 ......S N ]The reader is provided with M antennae, and M mixed signals of N labels randomly mixed are received by the M antennae and are X = [ X ] 1 ，X 2 ，X 3 ......X M ]Wherein, X = AS, a is an N × M-dimensional column full-rank instantaneous linear mixing matrix, a separation matrix W is obtained by an ICA method, and the separation matrix W is substituted into the following model: y = WX, wherein Y is a signal in which M mixed signals are separated and then close to the tag signal, and W is an M × N-dimensional instantaneous linear componentAnd (4) an off-matrix.
In this embodiment, the ICA method is based on independent component analysis, and the number of observed signals is equal to or greater than the number of source signals; in the two cases, which can be regarded as a case, in blind source separation, the mixing matrix a is a square matrix, the matrix a is reversible, and a unique solution of the source signal can be obtained.
As shown in fig. 4, there are N tags in one slot, where N tag return signals are denoted as S = [ S ] 1 ，S 2 ，S 3 ......S N ]For the source signal, the reader has M antennas (generally not more than 8 due to other factors), and the M antennas receive M mixed signals in which N tag signals are randomly mixed, and the M mixed signals are denoted as X = [ X ] 1 ，X 2 ，X 3 ......X M ]For the observed signals, the M mixed signals are processed by the ICA method of the reader, and then signals close to the tag signal are separated, and are marked as Y = [ Y = 1 ，Y 2 ，Y 3 ......Y N ]. In the ICA method, where the number of observed signals is less than or equal to the number of source signals, i.e., M ≦ N, the mathematical model for blind source separation is, X = AS. With the ICA method, the separation matrix W can be found such that Y = [ Y ] output after the mixed signal X received by the antenna passes through it 1 ，Y 2 ，Y 3 ......Y N ]An optimal approximation to the source signal S. I.e. Y = WX. The key of the blind source separation idea is to obtain a separation matrix W, then separate the received mixed signals through matrix transformation to obtain a separation signal Y closest to the source signal X, and successfully identify the label signal collided in the time slot. However, the ICA method is also used in relation to the number of slots in the frame, and only the optimal number of slots can improve the recognition efficiency of the system better. If the number of the time slots is too small, the number of the tags in each time slot is increased, and when the number of the tags in the time slots is more than the number of the antennas, the collision tags cannot be identified by adopting an ICA (independent component analysis) method; if the number of the time slots is too large, the number of the idle time slots is more, and the system time is wasted; therefore, the size of the time slot number affects the identification efficiency of the system.
If M > N, the number of observed signals is greater than the number of source signals (N < M); at this time, the number of columns in the hybrid matrix a is more than the number of rows, the matrix is irreversible, and there is no unique solution of the source signal. The ICA method cannot be used to separate signals. The signals are generally separated by a two-step method of Sparse Component Analysis (SCA), which is a conventional technique in the art and will not be described herein.
In some embodiments of the present application, the method further comprises: if the signals separated by the first preset separation method or the second preset separation method do not have unidentified tags, vehicle identification is carried out according to the separated signals; and if the signals separated by the first preset separation method or the second preset separation method have unidentified labels, re-performing the first step to the fourth step.
By applying the technical scheme, the first step is as follows: the reader sends a Query instruction to specify the frame length, and the tags in the identification range of the reader randomly select a time slot in the frame length range to respond to the instruction of the reader and return an information packet; step two: if collision time slots exist, after the previous frame is finished, acquiring an observed value in the previous frame, and obtaining the number of labels according to the observed value in the previous frame and a preset label estimation algorithm; step three: obtaining the time slot number of the next frame according to the tag number and the antenna number, and judging whether the antenna number is greater than the tag number in the time slot of the next frame on the basis of the time slot number of the next frame; step four: if the number of the antennas is larger than that of the tags in the next frame time slot, a first preset separation method is adopted to separate the tag signals, vehicle identification is carried out according to the separated signals, if the number of the antennas is not larger than that of the tags in the next frame time slot, a second preset separation method is adopted to separate the tag signals, and vehicle identification is carried out according to the separated signals. According to the method and the device, the estimated frame length of the next frame is obtained according to the number of the antennas and the number of the tags, and a proper separation method is selected according to the relation between the number of the antennas and the number of the tags in the time slot, so that signals are separated, and the identification is completed. The accuracy of discernment has been improved, the wrong problem of discernment that has avoided the collision problem to bring has been discerned, and the recognition efficiency obtains improving.
Through the above description of the embodiments, those skilled in the art will clearly understand that the present invention may be implemented by hardware, or by software plus a necessary general hardware platform. Based on such understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.), and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method according to the implementation scenarios of the present invention.
In order to further illustrate the technical idea of the present invention, the technical solution of the present invention will now be described with reference to specific application scenarios.
Correspondingly, the application also provides a vehicle electronic identification recognition system, which is applied to a multi-antenna RFID system, and the number of antennas is preset, and the system comprises:
a response module 201, configured to send a Query instruction to specify a frame length by a reader, randomly select a time slot within a range identified by the reader to respond to the instruction of the reader within the range of the frame length by a tag within the range identified by the reader, and return an information packet;
the estimation module 202 is configured to, if there is a collision time slot, obtain an observation value in a previous frame after the previous frame is finished, and obtain the number of tags according to the observation value in the previous frame and a preset tag estimation algorithm;
a judging module 203, configured to obtain the time slot number of the next frame according to the tag number and the antenna number, and judge, on the basis of the time slot number of the next frame, whether the antenna number is greater than the tag number in the time slot of the next frame;
a separation module 204, configured to separate the tag signals by using a first preset separation method if the number of antennas is greater than the number of tags in the next frame time slot, perform vehicle identification according to the separated signals, and separate the tag signals by using a second preset separation method if the number of antennas is not greater than the number of tags in the next frame time slot, and perform vehicle identification according to the separated signals;
and the collision time slot is the time slot of two or more labels returning information packets.
In some embodiments of the present application, the estimation module 202 is specifically configured to:
the observation value comprises an idle time slot number, a success time slot number and a collision time slot number, wherein the idle time slot number is the number of time slots without labels for returning the information packets, the success time slot number is the number of time slots with only one label for returning the information packets, and the collision time slot number is the number of time slots with two or more labels for returning the information packets;
calculating the probability of the collision time slot in the initial frame according to the number of the idle time slots, the number of the successful time slots and the number of the collision time slots, roughly estimating the number of the tags according to the probability to obtain the number of the first tags, and if the number of the first tags does not meet the preset requirement, finely estimating to obtain the number of the tags;
and if the first label quantity meets the preset requirement, taking the first label quantity as the label quantity.
In some embodiments of the present application, the separation module 204 is specifically configured to:
setting N tags in one time slot, wherein the return signals of the N tags are S = [ S ] 1 ，S 2 ，S 3 ......S N ]The reader is provided with M antennae, and M mixed signals of N labels randomly mixed are received by the M antennae and are X = [ X ] 1 ，X 2 ，X 3 ......X M ]Wherein, X = AS, a is an N × M-dimensional column full-rank instantaneous linear mixing matrix, and then a separation matrix W is obtained by an ICA method, and the separation matrix W is substituted into the following model:
Y＝WX，
wherein, Y is a signal which is close to the label signal after the M mixed signals are separated, and W is an M multiplied by N dimension instantaneous linear separation matrix.
In some embodiments of the present application, the system further comprises a verification module, the verification module being configured to:
if the signals separated by the first preset separation method or the second preset separation method do not have unidentified tags, vehicle identification is carried out according to the separated signals;
and if the signals separated by the first preset separation method or the second preset separation method have unidentified labels, re-performing the first step to the fourth step.
Those skilled in the art will appreciate that the modules in the system implementing the scenario may be distributed in the system implementing the scenario according to the description of the implementation scenario, or may be correspondingly changed in one or more systems different from the present implementation scenario. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not necessarily depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (8)
1. A vehicle electronic identification recognition method is applied to a multi-antenna RFID system, and the number of antennas is preset, and the method comprises the following steps:
the method comprises the following steps: the reader sends a Query instruction to specify the frame length, and a time slot is randomly selected in the range of the frame length for the tags in the range of the reader identification to respond to the instruction of the reader and return an information packet;
step two: if collision time slots exist, after the previous frame is finished, acquiring an observed value in the previous frame, and obtaining the number of labels according to the observed value in the previous frame and a preset label estimation algorithm;
step three: obtaining the time slot number of the next frame according to the tag number and the antenna number, and judging whether the antenna number is greater than the tag number in the time slot of the next frame on the basis of the time slot number of the next frame;
step four: if the number of the antennas is larger than that of the tags in the next frame time slot, a first preset separation method is adopted to separate the tag signals, and vehicle identification is carried out according to the separated signals;
and the collision time slot is the time slot of two or more labels returning information packets.
2. The method of claim 1, wherein the number of tags is obtained according to the observation value in the previous frame and a preset tag estimation algorithm, and specifically comprises:
the observation value comprises an idle time slot number, a success time slot number and a collision time slot number, wherein the idle time slot number is the number of time slots without labels for returning the information packets, the success time slot number is the number of time slots with only one label for returning the information packets, and the collision time slot number is the number of time slots with two or more labels for returning the information packets;
calculating the probability of the collision time slot in the initial frame according to the number of the idle time slots, the number of the successful time slots and the number of the collision time slots, roughly estimating the number of the tags according to the probability to obtain the number of the first tags, and if the number of the first tags does not meet the preset requirement, finely estimating to obtain the number of the tags;
and if the first label quantity meets the preset requirement, taking the first label quantity as the label quantity.
3. The method of claim 1, wherein if the number of antennas is not greater than the number of tags in the next frame slot, then separating the tag signals by a second preset separation method, specifically:
setting N tags in one time slot, wherein the return signals of the N tags are S = [ S ] 1 ，S 2 ，S 3 ......S N ]The reader is provided with M antennae, and M mixed signals of N labels randomly mixed are received by the M antennae and are X = [ X ] 1 ，X 2 ，X 3 ......X M ]Wherein, X = AS, A is N × M dimension instantaneous linear mixing matrix with full rank, and obtained by ICA methodAnd (3) a separation matrix W, which is substituted into the following model:
Y＝WX，
wherein, Y is a signal which is close to the label signal after the M mixed signals are separated, and W is an M multiplied by N dimension instantaneous linear separation matrix.
4. The method of claim 1, wherein the method further comprises:
if the signals separated by the first preset separation method or the second preset separation method do not have unidentified tags, vehicle identification is carried out according to the separated signals;
and if the signals separated by the first preset separation method or the second preset separation method have unidentified tags, re-performing the first step to the fourth step.
5. A vehicle electronic identification recognition system is applied to a multi-antenna RFID system, and the number of antennas is preset, and the system comprises:
the response module is used for the reader to send a Query instruction to specify the frame length, and the tags in the identification range of the reader randomly select a time slot to respond to the instruction of the reader in the frame length range and return an information packet;
the estimation module is used for acquiring an observed value in a previous frame after the previous frame is finished if a collision time slot exists, and acquiring the number of labels according to the observed value in the previous frame and a preset label estimation algorithm;
the judging module is used for obtaining the time slot number of the next frame according to the tag number and the antenna number, and judging whether the antenna number is greater than the tag number in the time slot of the next frame on the basis of the time slot number of the next frame;
the separation module is used for separating the tag signals by adopting a first preset separation method if the number of the antennas is greater than the number of the tags in the next frame time slot, and identifying the vehicle according to the separated signals;
and the collision time slot is the time slot of two or more labels returning information packets.
6. The system of claim 5, wherein the estimation module is specifically configured to:
the observation value comprises an idle time slot number, a success time slot number and a collision time slot number, wherein the idle time slot number is the number of time slots without labels for returning the information packets, the success time slot number is the number of time slots with only one label for returning the information packets, and the collision time slot number is the number of time slots with two or more labels for returning the information packets;
calculating the probability of the collision time slot in the initial frame according to the number of the idle time slots, the number of the successful time slots and the number of the collision time slots, roughly estimating the number of the tags according to the probability to obtain the number of the first tags, and if the number of the first tags does not meet the preset requirement, finely estimating to obtain the number of the tags;
and if the first label quantity meets the preset requirement, taking the first label quantity as the label quantity.
7. The system of claim 6, wherein the separation module is specifically configured to:
setting N tags in one time slot, wherein the return signals of the N tags are S = [ S ] 1 ，S 2 ，S 3 ......S N ]The reader is provided with M antennae, and M mixed signals of N labels randomly mixed are received by the M antennae and are X = [ X ] 1 ，X 2 ，X 3 ......X M ]Wherein, X = AS, a is an N × M-dimensional column full-rank instantaneous linear mixing matrix, and then a separation matrix W is obtained by an ICA method, and the separation matrix W is substituted into the following model:
Y＝WX，
wherein, Y is a signal which is close to the label signal after the M mixed signals are separated, and W is an M multiplied by N dimension instantaneous linear separation matrix.
8. The system of claim 6, further comprising a verification module to:
if the signals separated by the first preset separation method or the second preset separation method do not have unidentified tags, vehicle identification is carried out according to the separated signals;
and if the signals separated by the first preset separation method or the second preset separation method have unidentified tags, re-performing the first step to the fourth step.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210940046.6A CN115455998A (en) | 2022-08-05 | 2022-08-05 | Vehicle electronic identification recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210940046.6A CN115455998A (en) | 2022-08-05 | 2022-08-05 | Vehicle electronic identification recognition method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115455998A true CN115455998A (en) | 2022-12-09 |
Family
ID=84296065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210940046.6A Pending CN115455998A (en) | 2022-08-05 | 2022-08-05 | Vehicle electronic identification recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115455998A (en) |
-
2022
- 2022-08-05 CN CN202210940046.6A patent/CN115455998A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8085131B2 (en) | System for tag estimation and anti-collision and method thereof | |
| KR100717877B1 (en) | Tag Number Estimation Method in Sloted Aloha based RFID Systems | |
| US9773132B2 (en) | Tag anti-collision method, reader apparatus and system for RFID systems with multi-packet reception capability | |
| US8610544B2 (en) | Method for determining optimal frame size for tag collision prevention in RFID system | |
| CN101359358B (en) | Label recognizing system, label accessing device and label sposition determining method | |
| US7612672B2 (en) | Query tree based tag identification method in RFID systems | |
| CN107506676B (en) | RFID anti-collision method based on dynamic detection point and label estimation | |
| CN104881693B (en) | A Dynamic Frame Slot ALOHA Anti-collision Algorithm Based on Subframe Observation | |
| CN101499119A (en) | Label recognition method, system and apparatus based on radio frequency recognition | |
| Deng et al. | Optimal dynamic framed slotted ALOHA based anti-collision algorithm for RFID systems | |
| CN110414286A (en) | A kind of RFID label tag collision-proof method | |
| CN115455998A (en) | Vehicle electronic identification recognition method and system | |
| Nguyen et al. | Tag cardinality estimation using expectation-maximization in ALOHA-based RFID systems with capture effect and detection error | |
| Yoon et al. | ISS-TCA: An identified slot scan-based tag collection algorithm for performance improvement in active RFID systems | |
| CN105160373B (en) | A kind of dynamic frame Slot-aloha algorithm independently recognized based on collision time slot | |
| Zahran et al. | Enhanced aloha-based anti-collision algorithm for efficien rfid tags identification | |
| CN110852129B (en) | Dynamic label estimation method | |
| Cho et al. | LDFSA: A learning-based dynamic framed slotted ALOHA for collision arbitration in active RFID systems | |
| CN118519969B (en) | Digital storage management system and device for positioning type entity files | |
| US20050176414A1 (en) | Communications device identification methods, communications methods, wireless communications readers, wireless communications systems, and articles of manufacture | |
| CN101751539A (en) | Method for estimating number of tags and reader | |
| Yoon et al. | An efficient tag collection algorithm utilizing empty time slots in active RFID systems | |
| Pudasaini et al. | Optimum Tag Reading Efficiency of Multi-Packet Reception Capable RFID Readers | |
| CN106250794A (en) | Multi-label anti-collision algorithm in a kind of ultrahigh-frequency radio-frequency identification system | |
| CN121217302A (en) | Information processing method, apparatus, device, readable storage medium, and program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |