CN116343187A - Intelligent matching method, device, equipment and medium for license plate numbers of electric bicycles - Google Patents
Intelligent matching method, device, equipment and medium for license plate numbers of electric bicycles Download PDFInfo
- Publication number
- CN116343187A CN116343187A CN202310303214.5A CN202310303214A CN116343187A CN 116343187 A CN116343187 A CN 116343187A CN 202310303214 A CN202310303214 A CN 202310303214A CN 116343187 A CN116343187 A CN 116343187A
- Authority
- CN
- China
- Prior art keywords
- radio frequency
- time
- data
- real
- matching
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000004364 calculation method Methods 0.000 claims abstract description 106
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 9
- 238000012790 confirmation Methods 0.000 claims description 6
- 230000005059 dormancy Effects 0.000 claims description 6
- 238000013461 design Methods 0.000 description 21
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/18—Extraction of features or characteristics of the image
- G06V30/1801—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections
- G06V30/18019—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections by matching or filtering
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Vehicle Waterproofing, Decoration, And Sanitation Devices (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method, a device, equipment and a medium for intelligently matching license plates of electric bicycles, which comprise the steps of receiving video snapshot data and real-time radio frequency data reported by a radio frequency integrated machine, and respectively adding the video snapshot data and the real-time radio frequency data into a video cache queue and a radio frequency cache queue; judging whether the reporting time of each video snapshot data and each real-time radio frequency data is within the effective time, and carrying out matching calculation on the video snapshot data and the real-time radio frequency data according to a judging result and a preset matching calculation logic; and sending the result of the matching calculation to a supervision platform in real time to realize automatic identification supervision of the number of the automatic license plate of the electric vehicle. The invention greatly improves the matching rate of the radio frequency and the video license plate number; real-time matching of a large number of license plates is guaranteed, and therefore user experience is improved; the most accurate license plate matching rate in the same time domain range is ensured, and the wrong license plate number matching is greatly reduced.
Description
Technical Field
The invention belongs to the technical field of license plate number identification, and particularly relates to a method, a device, equipment and a medium for intelligently matching license plates of electric bicycles.
Background
Because electric bicycle has the license plate size is little, easily shelter from, the style is different and unordered scheduling problem of going, leads to the video snapshot discernment difficulty of license plate number, simultaneously, because a city various license plates, traffic perception crossing erect high, the distance is far away, receive illumination, dirty and shelter from etc. influence, single video discernment is more difficult. Through the radio frequency RFID technology, a radio frequency chip is embedded in the electric license plate, the license plate number is written in the chip, and the vehicle interacts with radio frequency identification equipment when passing through a radio frequency identification range, so that accurate license plate number information can be obtained. When a vehicle passes through a corresponding intersection of the all-in-one machine, the radio frequency and the camera work simultaneously, when the radio frequency reads license plate information, the license plate information can be continuously reported, meanwhile, after the camera recognizes the vehicle, the license plate number can be recognized and snap shot to report, and after the report, the license plate information reported by the radio frequency and the license plate information reported by the camera are required to be matched.
In the prior art, most of the shooting video matching algorithms are accurate matching, real-time performance of matching cannot be guaranteed, and most of the shooting video matching algorithms are used for carrying out matching logic after snapshot for a period of time, so that certain delay exists, and recognition is inaccurate.
Disclosure of Invention
The invention aims to provide a method, a device, equipment and a medium for intelligently matching license plates of electric bicycles, which are used for solving the technical problems that most of the prior art is accurate matching, real-time performance of matching cannot be guaranteed, and most of the prior art is to carry out matching logic after snapshot for a period of time, so that a certain delay exists, and recognition is inaccurate.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the first aspect provides a method for intelligently matching license plates of electric bicycles, comprising the following steps:
receiving video snapshot data and real-time radio frequency data reported by a radio frequency integrated machine, adding the video snapshot data into a video cache queue, and adding the real-time radio frequency data into the radio frequency cache queue;
judging whether the reporting time of each video snapshot data in the video cache queue and each real-time radio frequency data in the radio frequency cache queue is within the effective time, and carrying out matching calculation on the video snapshot data and the real-time radio frequency data according to a judging result and preset matching calculation logic, wherein the matching calculation comprises accurate matching calculation and fuzzy matching calculation;
and sending the result of the matching calculation to a supervision platform in real time to realize automatic identification supervision of the number of the automatic license plate of the electric vehicle.
In one possible design, after matching calculation of the video snapshot data and the real-time radio frequency data, the method further includes:
and carrying out secondary confirmation and correction on the result of the fuzzy matching calculation based on the big data matching calculation.
In one possible design, determining whether reporting time of each video snapshot data in the video buffer queue and each real-time radio frequency data in the radio frequency buffer queue is within an effective time, and performing matching calculation on the video snapshot data and the real-time radio frequency data according to a determination result and preset matching calculation logic, where the matching calculation includes:
judging whether data exists in the video cache queue, if so, extracting video snapshot data from the video cache queue, and further judging whether the radio frequency cache queue is empty;
if the radio frequency buffer queue is not empty, extracting real-time radio frequency data from the radio frequency buffer queue, and carrying out matching calculation and matching bit number calculation on the real-time radio frequency data and video snapshot data;
judging whether the real-time radio frequency data matched at this time and the video snapshot data are accurately matched, and if so, determining that the matching is completed;
if the reporting time of the video snapshot data is within the effective time, the real-time radio frequency data matched with the video snapshot data is not precisely matched, and the real-time radio frequency data is precisely matched with or not precisely matched with the prior snapshot data, further judging whether the real-time radio frequency data exceeds the effective time, and if the effective time is not exceeded, returning to judge whether a radio frequency cache queue is empty;
if the reporting time of the video snapshot data is not within the effective time, the real-time radio frequency data matched with the video snapshot data is not precisely matched and the real-time radio frequency data is not precisely matched with the previous snapshot data or not, returning to judge whether the video cache queue has data or further judges whether the real-time radio frequency data exceeds the effective time, if the effective time is not exceeded, returning to extract the real-time radio frequency data from the radio frequency cache queue, if the effective time is exceeded, further judging whether the real-time radio frequency data is the last real-time radio frequency data, if the real-time radio frequency data is the last real-time radio frequency data, judging whether the radio frequency data with the longest matching length is obtained, and recognizing that the matching is completed, if the real-time radio frequency data is not the last real-time radio frequency data, further judging whether the number of bits is more than the last matching calculation, if the number of bits is more than the last matching calculation, recording the current longest matching radio frequency data, and if the number of bits is not more than the last matching calculation, returning to extract the real-time radio frequency data from the radio frequency cache queue.
In one possible design, after determining whether there is data in the video cache queue, the method further comprises:
traversing all real-time radio frequency data in all radio frequency cache queues, and transmitting and deleting the real-time radio frequency data exceeding the effective time.
In one possible design, after determining whether the radio frequency cache queue is empty, the method further includes:
if the radio frequency cache queue is empty and the reporting time of the video snapshot data is within the effective time, performing short dormancy, and returning to judge whether the video cache queue has data or not after dormancy;
if the radio frequency cache queue is empty and the reporting time of the video snapshot data is not within the effective time, the video snapshot data is sent, and the video snapshot data is deleted from the video cache queue.
In one possible design, after recognizing that the match is complete if it is a precise match, the method further includes:
if the reporting time of the video snapshot data is not within the effective time, transmitting the matching data, deleting the video snapshot data, judging whether the real-time radio frequency data exceeds the effective time, and if the real-time radio frequency data does not exceed the effective time, returning to judge whether the radio frequency cache queue is empty;
if the reporting time of the video snapshot data is within the effective time, the matching data is sent, the video snapshot data is deleted, whether the real-time radio frequency data exceeds the effective time is judged, if the real-time radio frequency data does not exceed the effective time, the real-time radio frequency data is returned to be extracted from the radio frequency cache queue, and if the real-time radio frequency data exceeds the effective time, the real-time radio frequency data is sent and deleted.
In one possible design, performing secondary validation and correction of the result of the fuzzy match calculation based on the big data match calculation includes:
traversing all license plate number data in fuzzy matching, and searching other video shooting all-in-one machines within a preset range based on positioning information of the video shooting all-in-one machine at the current intersection;
based on the time of the vehicle passing through the current intersection and with the preset time as a unit, retrieving the video accurate matching data of the other video all-in-one machines in a preset big data system;
and (3) performing similarity calculation on the shot video accurate matching data of other shot video all-in-one machines and the fuzzy matching data of the shot video all-in-one machine at the current intersection, and if the similarity is lower than a threshold value, considering that the fuzzy matching rate is too low, and correcting the fuzzy matching calculation result.
The second aspect provides a device for intelligent matching of license plates of electric bicycles, comprising:
the data caching module is used for receiving video snapshot data and real-time radio frequency data reported by the radio frequency integrated machine, adding the video snapshot data into a video caching queue, and adding the real-time radio frequency data into the radio frequency caching queue;
the real-time matching module is used for judging whether the reporting time of each video snapshot data in the video cache queue and each real-time radio frequency data in the radio frequency cache queue is within the effective time or not, and carrying out matching calculation on the video snapshot data and the real-time radio frequency data according to a judging result and preset matching calculation logic, wherein the matching calculation comprises accurate matching calculation and fuzzy matching calculation;
and the result transmitting module is used for transmitting the result of the matching calculation to the supervision platform in real time so as to realize automatic identification supervision of the automatic license plate number of the electric vehicle.
In a third aspect, the present invention provides a computer device comprising a memory, a processor and a transceiver in communication with each other in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to send and receive messages, and the processor is configured to read the computer program and perform the method for intelligent matching of the license plate number of the electric bicycle as described in any one of the possible designs of the first aspect.
In a fourth aspect, the present invention provides a computer readable storage medium having instructions stored thereon which, when run on a computer, perform a method of intelligent matching of electric bicycle license plates as described in any one of the possible designs of the first aspect.
In a fifth aspect, the present invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform a method of intelligent matching of electric bicycle numbers as described in any one of the possible designs of the first aspect.
Compared with the prior art, the invention has the beneficial effects that:
the method comprises the steps of adding video snapshot data into a video cache queue and adding real-time radio frequency data into the radio frequency cache queue by receiving the video snapshot data and the real-time radio frequency data reported by a radio frequency integrated machine; judging whether the reporting time of each video snapshot data in the video cache queue and each real-time radio frequency data in the radio frequency cache queue is within the effective time or not, and carrying out matching calculation on the video snapshot data and the real-time radio frequency data according to a judging result and preset matching calculation logic, wherein the matching calculation comprises accurate matching calculation and fuzzy matching calculation; the matching calculation result is sent to the supervision platform in real time, so that automatic identification and supervision of the automatic license plate number of the electric vehicle are realized, and the matching rate of the radio frequency and the video license plate number is greatly improved; real-time matching of a large number of license plates is guaranteed, and therefore user experience is improved; the most accurate license plate matching rate in the same time domain range is ensured, and the wrong license plate number matching is greatly reduced. By performing secondary confirmation and correction on the result of the fuzzy matching calculation based on the big data matching calculation, the error rate of fuzzy matching is reduced.
Drawings
FIG. 1 is a flow chart diagram of a method for intelligent matching of license plates of electric bicycles in the embodiment of the present application;
FIG. 2 is a flow chart of part A of a method for intelligent matching of license plates of electric bicycles in the embodiment of the present application;
FIG. 3 is a flow chart of part B of a method for intelligent matching of license plates of electric bicycles in the embodiment of the present application;
fig. 4 is a flow chart of part C of a method for intelligently matching license plates of electric bicycles in the embodiment of the present application.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be briefly described below with reference to the accompanying drawings and the description of the embodiments or the prior art, and it is obvious that the following description of the structure of the drawings is only some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art. It should be noted that the description of these examples is for aiding in understanding the present invention, but is not intended to limit the present invention.
Examples
In order to solve the technical problems that most of the prior art is accurate matching and real-time matching cannot be guaranteed, most of the prior art is to carry out matching logic after snapshot for a period of time, so that a certain time delay exists, and the identification is inaccurate. The embodiment of the application provides a method for intelligently matching license plates of electric bicycles, which comprises the steps of receiving video snapshot data and real-time radio frequency data reported by a radio frequency integrated machine, adding the video snapshot data into a video cache queue, and adding the real-time radio frequency data into the radio frequency cache queue; judging whether the reporting time of each video snapshot data in the video cache queue and each real-time radio frequency data in the radio frequency cache queue is within the effective time or not, and carrying out matching calculation on the video snapshot data and the real-time radio frequency data according to a judging result and preset matching calculation logic, wherein the matching calculation comprises accurate matching calculation and fuzzy matching calculation; the matching calculation result is sent to the supervision platform in real time, so that automatic identification and supervision of the automatic license plate number of the electric vehicle are realized, and the matching rate of the radio frequency and the video license plate number is greatly improved; real-time matching of a large number of license plates is guaranteed, and therefore user experience is improved; the most accurate license plate matching rate in the same time domain range is ensured, and the wrong license plate number matching is greatly reduced.
The method for intelligently matching the license plate numbers of the electric bicycle provided by the embodiment of the application will be described in detail below.
It should be noted that, the method for intelligently matching the license plate number of the electric bicycle provided by the embodiment of the application can be applied to any terminal device, wherein the operating system includes, but is not limited to, a Windows system, a Mac system, a Linux system, a Chrome OS system, a UNIX operating system, an IOS system, an android system, and the like, and is not limited herein; the terminal device includes, but is not limited to, a server, an IPAD tablet computer, a personal mobile computer, an industrial computer, a personal computer, etc., which are not limited herein. For convenience of description, the embodiments of the present application will be described with reference to a server as an execution body, except for specific descriptions. It will be appreciated that the execution subject is not limited to the embodiments of the present application, and in other embodiments, other types of terminal devices may be used as the execution subject.
1-4, a flowchart of an intelligent electric bicycle license plate number matching method provided by an embodiment of the present application includes, but is not limited to, implementation by steps S1-S3:
s1, receiving video snapshot data and real-time radio frequency data reported by a radio frequency integrated machine, adding the video snapshot data into a video cache queue, and adding the real-time radio frequency data into the radio frequency cache queue;
the method is characterized in that in the process that vehicles pass through intersections, video information is uploaded to a large data platform, and the large data platform contains images and radio frequency information when all vehicles pass through the intersections. When the vehicle passes through the effective radio frequency identification area, the vehicle continuously reports license plate data to the main control after the radio frequency reads the license plate data, the license plate data is reported for multiple times within 1 second, and if the time from the last report of the radio frequency data exceeds the effective time, for example, 120 seconds, the vehicle corresponding to the radio frequency data is judged to have left the radio frequency identification range. In this process, the camera recognizes the license plate number and takes a snapshot of the vehicle at 4 possible times:
1) Snapshot time 1: the camera recognizes and captures the vehicle before the radio frequency 1 st time is reported to the main control;
2) Snapshot time 2: in the radio frequency continuous reporting process, a camera captures a vehicle;
3) Snapshot time 3: the camera captures a vehicle within 120 seconds after the last report of the radio frequency;
4) Snapshot time 4: after 120 seconds after the last report of the radio frequency, the camera captures a photograph of the vehicle;
the snapshot time 2 and the snapshot time 3 are in the radio frequency effective time range, and after the camera snapshot data are reported to the main control, the main control can directly match vehicle data. When a vehicle normally runs through an intersection, if the intersection has traffic lights, the traffic lights are generally at most 90 seconds long, so the time for the vehicle to pass through the intersection is not more than 120 seconds. The radio frequency data is valid data within 120 seconds from the last recognition, so there is no camera snapshot time 4 under normal conditions. And (3) for the snapshot time 1 of the camera, after the snapshot is finished and the vehicle information is reported to the main control, the main control sets the validity period to 120 seconds, namely, the main control can be matched with radio frequency data within 120 seconds, and the vehicle is considered to be away after the period exceeds 120 seconds.
S2, judging whether reporting time of each video snapshot data in the video cache queue and each real-time radio frequency data in the radio frequency cache queue is within effective time, and carrying out matching calculation on the video snapshot data and the real-time radio frequency data according to a judging result and preset matching calculation logic, wherein the matching calculation comprises accurate matching calculation and fuzzy matching calculation;
based on step S1, the basic logic for matching the correlation video data in the embodiment of the present application is as follows:
1) In the process of passing a vehicle, a plurality of illegal behaviors can exist in the vehicle, and a camera can report data for each violation, so that radio frequency data in the passing vehicle cannot be deleted immediately even if the radio frequency data are accurately matched;
2) The radio frequency data can be deleted only after the effective time is exceeded;
3) The camera data can be deleted only after the valid time is precisely matched or overtime;
4) The matching data can be sent out immediately after the radio frequency is precisely matched with the video, otherwise, the matching data can be sent out only after the matching is performed for the last time after the timeout is equal;
5) The radio frequency and video are provided with a data queue, and the matching logic is based on the data queue.
Based on the logic, the embodiment of the present application provides a specific implementation manner of step S2, as follows:
judging whether data exists in the video cache queue, if so, extracting video snapshot data from the video cache queue, and further judging whether the radio frequency cache queue is empty;
in one possible design, after determining whether there is data in the video cache queue, the method further comprises:
traversing all real-time radio frequency data in all radio frequency cache queues, and transmitting and deleting the real-time radio frequency data exceeding the effective time.
If the radio frequency buffer queue is not empty, extracting real-time radio frequency data from the radio frequency buffer queue, and carrying out matching calculation and matching bit number calculation on the real-time radio frequency data and video snapshot data;
in one possible design, after determining whether the radio frequency cache queue is empty, the method further includes:
if the radio frequency cache queue is empty and the reporting time of the video snapshot data is within the effective time, performing short dormancy, and returning to judge whether the video cache queue has data or not after dormancy;
if the radio frequency cache queue is empty and the reporting time of the video snapshot data is not within the effective time, the video snapshot data is sent, and the video snapshot data is deleted from the video cache queue.
Judging whether the real-time radio frequency data matched at this time and the video snapshot data are accurately matched, and if so, determining that the matching is completed;
in one possible design, after recognizing that the match is complete if it is a precise match, the method further includes:
if the reporting time of the video snapshot data is not within the effective time, transmitting the matching data, deleting the video snapshot data, judging whether the real-time radio frequency data exceeds the effective time, and if the real-time radio frequency data does not exceed the effective time, returning to judge whether the radio frequency cache queue is empty;
if the reporting time of the video snapshot data is within the effective time, the matching data is sent, the video snapshot data is deleted, whether the real-time radio frequency data exceeds the effective time is judged, if the real-time radio frequency data does not exceed the effective time, the real-time radio frequency data is returned to be extracted from the radio frequency cache queue, and if the real-time radio frequency data exceeds the effective time, the real-time radio frequency data is sent and deleted.
If the reporting time of the video snapshot data is within the effective time, the real-time radio frequency data matched with the video snapshot data is not precisely matched, and the real-time radio frequency data is precisely matched with or not precisely matched with the prior snapshot data, further judging whether the real-time radio frequency data exceeds the effective time, and if the effective time is not exceeded, returning to judge whether a radio frequency cache queue is empty;
if the reporting time of the video snapshot data is not within the effective time, the real-time radio frequency data matched with the video snapshot data is not precisely matched and the real-time radio frequency data is not precisely matched with the previous snapshot data or not, returning to judge whether the video cache queue has data or further judges whether the real-time radio frequency data exceeds the effective time, if the effective time is not exceeded, returning to extract the real-time radio frequency data from the radio frequency cache queue, if the effective time is exceeded, further judging whether the real-time radio frequency data is the last real-time radio frequency data, if the real-time radio frequency data is the last real-time radio frequency data, judging whether the radio frequency data with the longest matching length is obtained, and recognizing that the matching is completed, if the real-time radio frequency data is not the last real-time radio frequency data, further judging whether the number of bits is more than the last matching calculation, if the number of bits is more than the last matching calculation, recording the current longest matching radio frequency data, and if the number of bits is not more than the last matching calculation, returning to extract the real-time radio frequency data from the radio frequency cache queue.
It should be noted that, a complete license plate number includes the province abbreviation, the affiliated city and the license plate number, for example, "Ji A123456", and the recognition rate of the camera to the province abbreviation and the affiliated city is lower in the actual running process, so the matching algorithm is to match the license plate number by taking the following 6 digits as the reference.
The matching algorithm is based on the radio frequency license plate number, the last 6 bits of the license plate number given by the camera license plate number camera are matched with the radio frequency license plate number, the radio frequency video matching is divided into accurate matching and fuzzy matching, the 6 bits of the matching are accurate matching, and the 5 bits of the matching, the 4 bits of the matching and the 3 bits of the matching are fuzzy matching.
The following needs to be considered in the design of the matching algorithm for passing: firstly, the license plate number is incomplete; secondly, the camera may recognize some digits and letters in the license plate number as erroneous, such as g as 6, s as 8, etc. Based on the above considerations, a specific matching method is as follows:
assuming the radio frequency license plate number 123456, the letter # represents any number or letter from 0 to 1 in the following example process, the radio frequency video matching method is as follows:
(one) 6-bit matching
Each position of the video license plate number corresponds to the radio frequency license plate number one by one, i.e. the video license plate number must be 123456.
(two) 5-bit matching
When the video license plate number is the following license plate number, namely 5-bit matching comprises the following steps: #23456, 1#3456, 12#456, 123#56, 1234#6 and 12345#, wherein # represents 0 or 1 letter or number, each possibility includes 10 numbers from 0 to 9, 26 letters from a to z and 0, so the above one possibility includes the number calculation method: number of letters + number of digits +1 = 26+10+1 = 37; the number of all matched license plates is 222, and the calculation method is as follows:
6*37＝222；(1)
(III) 4-bit matching
If a 4-bit match where two bits are random # does not consider whether there is a continuation, the probability that a completely different license plate number will match during the actual test is found to be 10%, for example: 123456 may be successfully matched with 221356 and 221256 license plate numbers in actual license plate numbers, and because this situation has a high probability of occurrence, 4-bit matching is designed such that 3 bits are consecutive, and there are a total of the following cases: (1) the 1 st bit is fixed to be random#, and the other 1 st bit is shifted, including #3456, #2#456, #23#56- > disagreement, #234#6 and #2345#; (2) the 2 nd bit is fixed to be random#, and the other 1 st bit is shifted, including 1# #456, 1#3#56- > non-conforming, 1#34#6- > non-conforming and 1#345#; (3) the 3 rd bit is fixed as random#, and the other 1 st bit is shifted, including 12# #56- >, 12# -4# -6- >, and 12# -45# >; (4) bit 4 is fixed to random # and bit 1 is shifted, including 123# 6 and 123#5#; (5) bit 5 is fixed to random#, and bit 1 is shifted, including 1234#. From this, it is inferred that there are 9 possibilities for 4-bit matching, and that 1# of each possibility has 37 possibilities, so the number of license plates that can be matched at two # is: 37 x 37 = 1,369; all the matable quantities are: 1369×9= 12,321.
(IV) 3-bit matching
Since the matching rate is too high if the matching is skipped at the time of 3-bit matching, the following two cases are classified: if the length of the license plate number given by the video is 6 bits, the position requiring 3-bit matching in 3-bit matching must be consistent with the radio frequency number; if the license plate number given by the video is less than 6 bits, 3 bits are required to be continuous 3 bits to calculate the matching; for easier analysis, let @ represent at least 1 letter or number, and the possible case when the video gives a license plate number of 6 bits in length is as follows: 123@ @4@ 12@ 5@ 12@ 6 @ 1@3@5@ 1@34 @5@, 1@3@ 6 @ 1@ 45@, 1@ 4@6, 1@ 56 @2@45@, @2@4@6, @234@ 23@ 6, @2@ 56, @345@ 34@6, @3@56, @456. And when the video gives a license plate number of less than 6 bits, the possible cases are as follows: # #456, #345, #234, # and 123 #.
The analysis shows that the possible quantity is too large in the matching process, all the possibilities cannot be listed one by one and then matched, and the matching calculation amount is large, so that the low-level language c is adopted for coding, and the matching digit number is calculated by using a regular expression method.
And S3, sending the result of the matching calculation to a supervision platform in real time, and realizing automatic identification supervision of the automatic license plate number of the electric vehicle.
After the real-time passing matching analysis is implemented, a matching error exists, and because the probability of a certain error exists in fuzzy matching, the probability is generally within 10%, and in order to further improve the matching rate, big data matching is performed, which comprises:
and S4, carrying out secondary confirmation and correction on the fuzzy matching calculation result based on big data matching calculation.
In one possible design, performing secondary validation and correction of the result of the fuzzy match calculation based on the big data match calculation includes:
traversing all license plate number data in fuzzy matching, and searching other video shooting all-in-one machines within a preset range based on positioning information of the video shooting all-in-one machine at the current intersection;
the large data platform stores the panoramic view, the special police view, the license plate view and the radio frequency information when vehicles at all intersections pass, and stores the GPS and the intersection information of all radio frequency video all-in-one machines. And searching all the radio-frequency video all-in-one machines in a nearby preset range, for example, a range of 5 to 10 km by taking the GPS of the position of the radio-frequency video all-in-one machine at the intersection as a reference.
Based on the time of the vehicle passing through the current intersection and with the preset time as a unit, retrieving the video accurate matching data of the other video all-in-one machines in a preset big data system;
for example, in 10 minutes, license plate matching data in the data of all the searched all-in-one machines is searched in a big data system, precisely matched data is found, and if the data cannot be found, the time range is gradually expanded (data within the range of 3 hours can be searched at most).
And (3) performing similarity calculation on the shot video accurate matching data of other shot video all-in-one machines and the fuzzy matching data of the shot video all-in-one machine at the current intersection, and if the similarity is lower than a threshold value, considering that the fuzzy matching rate is too low, and correcting the fuzzy matching calculation result.
Specifically, the special police chart in accurate matching is taken out to carry out similarity calculation with the special police chart in fuzzy matching, the ncc algorithm of opencv is adopted to calculate the similarity, if the similarity is lower than 50%, the fuzzy matching rate is too low, the fuzzy matching is wrong, and correction is needed; and (3) further extracting all the feature images of the fuzzy matching records within a certain time range (within 1 minute) from the matching data with the similarity lower than 50%, and carrying out fuzzy matching calculation to find out the video data with the similarity higher than 60% and the highest similarity as the matching data with the radio frequency in the process of passing the vehicle.
Based on the above disclosure, in the embodiment of the present application, by receiving video snapshot data and real-time radio frequency data reported by a radio frequency integrated machine, adding the video snapshot data to a video cache queue, and adding the real-time radio frequency data to a radio frequency cache queue; judging whether the reporting time of each video snapshot data in the video cache queue and each real-time radio frequency data in the radio frequency cache queue is within the effective time or not, and carrying out matching calculation on the video snapshot data and the real-time radio frequency data according to a judging result and preset matching calculation logic, wherein the matching calculation comprises accurate matching calculation and fuzzy matching calculation; the matching calculation result is sent to the supervision platform in real time, so that automatic identification and supervision of the automatic license plate number of the electric vehicle are realized, and the matching rate of the radio frequency and the video license plate number is greatly improved; real-time matching of a large number of license plates is guaranteed, and therefore user experience is improved; the most accurate license plate matching rate in the same time domain range is ensured, and the wrong license plate number matching is greatly reduced. By performing secondary confirmation and correction on the result of the fuzzy matching calculation based on the big data matching calculation, the error rate of fuzzy matching is reduced.
The second aspect provides a device for intelligent matching of license plates of electric bicycles, comprising:
the data caching module is used for receiving video snapshot data and real-time radio frequency data reported by the radio frequency integrated machine, adding the video snapshot data into a video caching queue, and adding the real-time radio frequency data into the radio frequency caching queue;
the real-time matching module is used for judging whether the reporting time of each video snapshot data in the video cache queue and each real-time radio frequency data in the radio frequency cache queue is within the effective time or not, and carrying out matching calculation on the video snapshot data and the real-time radio frequency data according to a judging result and preset matching calculation logic, wherein the matching calculation comprises accurate matching calculation and fuzzy matching calculation;
and the result transmitting module is used for transmitting the result of the matching calculation to the supervision platform in real time so as to realize automatic identification supervision of the automatic license plate number of the electric vehicle.
The working process, working details and technical effects of the foregoing apparatus provided in the second aspect of the present embodiment may be referred to as the method described in the foregoing first aspect or any one of the possible designs of the first aspect, which are not described herein again.
In a third aspect, the present invention provides a computer device comprising a memory, a processor and a transceiver in communication with each other in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to send and receive messages, and the processor is configured to read the computer program and perform the method for intelligent matching of the license plate number of the electric bicycle as described in any one of the possible designs of the first aspect.
By way of specific example, the Memory may include, but is not limited to, random-Access Memory (RAM), read-Only Memory (ROM), flash Memory (Flash Memory), first-in first-out Memory (First Input First Output, FIFO), and/or first-in last-out Memory (First Input Last Output, FILO), etc.; the processor may not be limited to use with a microprocessor of the STM32F105 family; the transceiver may be, but is not limited to, a WiFi (wireless fidelity) wireless transceiver, a bluetooth wireless transceiver, a GPRS (General Packet Radio Service, general packet radio service technology) wireless transceiver, and/or a ZigBee (ZigBee protocol, low power local area network protocol based on the ieee802.15.4 standard), etc. In addition, the computer device may include, but is not limited to, a power module, a display screen, and other necessary components.
The working process, working details and technical effects of the foregoing computer device provided in the third aspect of the present embodiment may be referred to the above first aspect or any one of the possible designs of the first aspect, which are not described herein.
In a fourth aspect, the present invention provides a computer readable storage medium having instructions stored thereon which, when run on a computer, perform a method of intelligent matching of electric bicycle license plates as described in any one of the possible designs of the first aspect.
The computer readable storage medium refers to a carrier for storing data, and may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash Memory, and/or a Memory Stick (Memory Stick), etc., where the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable devices.
The working process, working details and technical effects of the foregoing computer readable storage medium provided in the fourth aspect of the present embodiment may refer to the method as described in the foregoing first aspect or any one of the possible designs of the first aspect, which are not repeated herein.
In a fifth aspect, the present invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform a method of intelligent matching of electric bicycle numbers as described in any one of the possible designs of the first aspect.
The working process, working details and technical effects of the foregoing computer program product containing instructions provided in the fifth aspect of the present embodiment may be referred to as the method described in the foregoing first aspect or any one of the possible designs of the first aspect, which are not repeated herein.
Finally, it should be noted that: the foregoing description is only of the preferred embodiments of the invention and is not intended to limit the scope of the invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The intelligent matching method for the license plate numbers of the electric bicycles is characterized by comprising the following steps:
receiving video snapshot data and real-time radio frequency data reported by a radio frequency integrated machine, adding the video snapshot data into a video cache queue, and adding the real-time radio frequency data into the radio frequency cache queue;
judging whether the reporting time of each video snapshot data in the video cache queue and each real-time radio frequency data in the radio frequency cache queue is within the effective time, and carrying out matching calculation on the video snapshot data and the real-time radio frequency data according to a judging result and preset matching calculation logic, wherein the matching calculation comprises accurate matching calculation and fuzzy matching calculation;
and sending the result of the matching calculation to a supervision platform in real time to realize automatic identification supervision of the number of the automatic license plate of the electric vehicle.
2. The method for intelligently matching the license plate numbers of the electric bicycles according to claim 1, wherein after the matching calculation is performed on the video snapshot data and the real-time radio frequency data, the method further comprises:
and carrying out secondary confirmation and correction on the result of the fuzzy matching calculation based on the big data matching calculation.
3. The method for intelligently matching the license plate number of the electric bicycle according to claim 1, wherein the steps of judging whether the reporting time of each video snapshot data in the video cache queue and each real-time radio frequency data in the radio frequency cache queue is within the effective time, and performing matching calculation on the video snapshot data and the real-time radio frequency data according to a judgment result and preset matching calculation logic comprise the following steps:
judging whether data exists in the video cache queue, if so, extracting video snapshot data from the video cache queue, and further judging whether the radio frequency cache queue is empty;
if the radio frequency buffer queue is not empty, extracting real-time radio frequency data from the radio frequency buffer queue, and carrying out matching calculation and matching bit number calculation on the real-time radio frequency data and video snapshot data;
judging whether the real-time radio frequency data matched at this time and the video snapshot data are accurately matched, and if so, determining that the matching is completed;
if the reporting time of the video snapshot data is within the effective time, the real-time radio frequency data matched with the video snapshot data is not precisely matched, and the real-time radio frequency data is precisely matched with or not precisely matched with the prior snapshot data, further judging whether the real-time radio frequency data exceeds the effective time, and if the effective time is not exceeded, returning to judge whether a radio frequency cache queue is empty;
if the reporting time of the video snapshot data is not within the effective time, the real-time radio frequency data matched with the video snapshot data is not precisely matched and the real-time radio frequency data is not precisely matched with the previous snapshot data or not, returning to judge whether the video cache queue has data or further judges whether the real-time radio frequency data exceeds the effective time, if the effective time is not exceeded, returning to extract the real-time radio frequency data from the radio frequency cache queue, if the effective time is exceeded, further judging whether the real-time radio frequency data is the last real-time radio frequency data, if the real-time radio frequency data is the last real-time radio frequency data, judging whether the radio frequency data with the longest matching length is obtained, and recognizing that the matching is completed, if the real-time radio frequency data is not the last real-time radio frequency data, further judging whether the number of bits is more than the last matching calculation, if the number of bits is more than the last matching calculation, recording the current longest matching radio frequency data, and if the number of bits is not more than the last matching calculation, returning to extract the real-time radio frequency data from the radio frequency cache queue.
4. The method for intelligent matching of electric bicycle license plates of claim 3, further comprising, after determining whether there is data in the video buffer queue:
traversing all real-time radio frequency data in all radio frequency cache queues, and transmitting and deleting the real-time radio frequency data exceeding the effective time.
5. The method for intelligent matching of electric bicycle license plates of claim 3, further comprising, after determining whether the radio frequency buffer queue is empty:
if the radio frequency cache queue is empty and the reporting time of the video snapshot data is within the effective time, performing short dormancy, and returning to judge whether the video cache queue has data or not after dormancy;
if the radio frequency cache queue is empty and the reporting time of the video snapshot data is not within the effective time, the video snapshot data is sent, and the video snapshot data is deleted from the video cache queue.
6. The method for intelligently matching license plates of electric bicycles according to claim 3, wherein after the completion of the matching is determined if the matching is accurate, the method further comprises:
if the reporting time of the video snapshot data is not within the effective time, transmitting the matching data, deleting the video snapshot data, judging whether the real-time radio frequency data exceeds the effective time, and if the real-time radio frequency data does not exceed the effective time, returning to judge whether the radio frequency cache queue is empty;
if the reporting time of the video snapshot data is within the effective time, the matching data is sent, the video snapshot data is deleted, whether the real-time radio frequency data exceeds the effective time is judged, if the real-time radio frequency data does not exceed the effective time, the real-time radio frequency data is returned to be extracted from the radio frequency cache queue, and if the real-time radio frequency data exceeds the effective time, the real-time radio frequency data is sent and deleted.
7. The method for intelligent matching of electric bicycle license plates according to claim 2, wherein the performing of the secondary confirmation and correction of the result of the fuzzy matching calculation based on the big data matching calculation includes:
traversing all license plate number data in fuzzy matching, and searching other video shooting all-in-one machines within a preset range based on positioning information of the video shooting all-in-one machine at the current intersection;
based on the time of the vehicle passing through the current intersection and with the preset time as a unit, retrieving the video accurate matching data of the other video all-in-one machines in a preset big data system;
and (3) performing similarity calculation on the shot video accurate matching data of other shot video all-in-one machines and the fuzzy matching data of the shot video all-in-one machine at the current intersection, and if the similarity is lower than a threshold value, considering that the fuzzy matching rate is too low, and correcting the fuzzy matching calculation result.
8. An electric bicycle license plate number intelligent matching device, which is characterized by comprising:
the data caching module is used for receiving video snapshot data and real-time radio frequency data reported by the radio frequency integrated machine, adding the video snapshot data into a video caching queue, and adding the real-time radio frequency data into the radio frequency caching queue;
the real-time matching module is used for judging whether the reporting time of each video snapshot data in the video cache queue and each real-time radio frequency data in the radio frequency cache queue is within the effective time or not, and carrying out matching calculation on the video snapshot data and the real-time radio frequency data according to a judging result and preset matching calculation logic, wherein the matching calculation comprises accurate matching calculation and fuzzy matching calculation;
and the result transmitting module is used for transmitting the result of the matching calculation to the supervision platform in real time so as to realize automatic identification supervision of the automatic license plate number of the electric vehicle.
9. A computer device comprising a memory, a processor and a transceiver connected in sequence, wherein the memory is used for storing a computer program, the transceiver is used for receiving and transmitting messages, and the processor is used for reading the computer program and executing the intelligent matching method of the license plate numbers of the electric bicycles.
10. A storage medium having instructions stored thereon that, when executed on a computer, perform the method of intelligent matching of electric bicycle license plates of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310303214.5A CN116343187B (en) | 2023-03-23 | 2023-03-23 | Intelligent matching method, device, equipment and medium for license plate numbers of electric bicycles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310303214.5A CN116343187B (en) | 2023-03-23 | 2023-03-23 | Intelligent matching method, device, equipment and medium for license plate numbers of electric bicycles |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116343187A true CN116343187A (en) | 2023-06-27 |
| CN116343187B CN116343187B (en) | 2023-11-28 |
Family
ID=86894493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310303214.5A Active CN116343187B (en) | 2023-03-23 | 2023-03-23 | Intelligent matching method, device, equipment and medium for license plate numbers of electric bicycles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116343187B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004042673A2 (en) * | 2002-11-04 | 2004-05-21 | Imperial Vision Ltd. | Automatic, real time and complete identification of vehicles |
| US20130266190A1 (en) * | 2012-04-06 | 2013-10-10 | Xerox Corporation | System and method for street-parking-vehicle identification through license plate capturing |
| CN107452209A (en) * | 2017-07-26 | 2017-12-08 | 江苏本能科技有限公司 | Radio frequency identification and video identification integration method and system, equipment, storage medium |
| CN108596119A (en) * | 2018-04-28 | 2018-09-28 | 江苏本能科技有限公司 | Radio frequency identification and video identification matching process and system, equipment, storage medium |
| CN111583431A (en) * | 2020-05-09 | 2020-08-25 | 广西信路威科技发展有限公司 | Result matching method for RSU antenna and video image joint detection |
| CN112668642A (en) * | 2020-12-28 | 2021-04-16 | 高新兴智联科技有限公司 | System and method for combining electronic identification and video of motor vehicle |
| CN112712620A (en) * | 2020-12-23 | 2021-04-27 | 高新兴智联科技有限公司 | Access control vehicle recognition device and method based on positioning function and storage medium |
| CN115100610A (en) * | 2021-10-18 | 2022-09-23 | 公安部交通管理科学研究所 | Method for identifying digital identity information of electric bicycle |
-
2023
- 2023-03-23 CN CN202310303214.5A patent/CN116343187B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004042673A2 (en) * | 2002-11-04 | 2004-05-21 | Imperial Vision Ltd. | Automatic, real time and complete identification of vehicles |
| US20130266190A1 (en) * | 2012-04-06 | 2013-10-10 | Xerox Corporation | System and method for street-parking-vehicle identification through license plate capturing |
| CN107452209A (en) * | 2017-07-26 | 2017-12-08 | 江苏本能科技有限公司 | Radio frequency identification and video identification integration method and system, equipment, storage medium |
| CN108596119A (en) * | 2018-04-28 | 2018-09-28 | 江苏本能科技有限公司 | Radio frequency identification and video identification matching process and system, equipment, storage medium |
| CN111583431A (en) * | 2020-05-09 | 2020-08-25 | 广西信路威科技发展有限公司 | Result matching method for RSU antenna and video image joint detection |
| CN112712620A (en) * | 2020-12-23 | 2021-04-27 | 高新兴智联科技有限公司 | Access control vehicle recognition device and method based on positioning function and storage medium |
| CN112668642A (en) * | 2020-12-28 | 2021-04-16 | 高新兴智联科技有限公司 | System and method for combining electronic identification and video of motor vehicle |
| CN115100610A (en) * | 2021-10-18 | 2022-09-23 | 公安部交通管理科学研究所 | Method for identifying digital identity information of electric bicycle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116343187B (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115223100A (en) | Intelligent park abnormal person identification method, system, equipment and storage medium | |
| CN111382808A (en) | Vehicle detection processing method and device | |
| CN107395252B (en) | Frequency-hopping method, frequency-hopping arrangement, terminal and baseband chip | |
| CN112562330A (en) | Method and device for evaluating road operation index, electronic equipment and storage medium | |
| CN111723772B (en) | Perishable garbage identification method and device based on image identification and computer equipment | |
| CN111523527A (en) | Special transport vehicle monitoring method and device, medium and electronic equipment | |
| CN108320255A (en) | A kind of information processing method and device | |
| CN111078973B (en) | Fake-licensed car identification method, equipment and storage medium based on big data | |
| CN116343187B (en) | Intelligent matching method, device, equipment and medium for license plate numbers of electric bicycles | |
| CN110796240A (en) | Training method, feature extraction method, device and electronic equipment | |
| CN108198433B (en) | Parking identification method and device and electronic equipment | |
| CN112631333B (en) | Target tracking method and device of unmanned aerial vehicle and image processing chip | |
| CN109255283A (en) | A kind of license plate number based on multiframe determines method, apparatus and electronic equipment | |
| CN109743362B (en) | Data storage method applied to full-format data structure | |
| CN115495498B (en) | Data association method, system, electronic equipment and storage medium | |
| CN116708511A (en) | Method, equipment and medium based on microcontroller integrated vehicle-machine interconnection technology | |
| CN112468965B (en) | Method and device for verifying authenticity of field visit and computer equipment | |
| CN114724128A (en) | License plate recognition method, device, equipment and medium | |
| CN114780304A (en) | Smart city operation and maintenance management method based on big data and cloud platform | |
| CN114554179A (en) | Automatic shooting method, system, terminal and storage medium based on target model | |
| CN111898475A (en) | Method and device for estimating state of non-motor vehicle, storage medium, and electronic device | |
| CN207460317U (en) | Vehicle-mounted shooting device | |
| CN112364683A (en) | Case evidence fixing method and device | |
| CN110110676A (en) | Automatic error correction method and device based on Car license recognition | |
| CN111354205A (en) | ETC-based road condition information acquisition method and system, storage medium and intelligent terminal |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |