CN111860590A - License plate voting method and device, computer equipment and storage medium - Google Patents
License plate voting method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111860590A CN111860590A CN202010543233.1A CN202010543233A CN111860590A CN 111860590 A CN111860590 A CN 111860590A CN 202010543233 A CN202010543233 A CN 202010543233A CN 111860590 A CN111860590 A CN 111860590A
- Authority
- CN
- China
- Prior art keywords
- license plate
- voting
- queue
- voted
- recognition result
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000004590 computer program Methods 0.000 claims description 18
- 230000007613 environmental effect Effects 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- 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
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/259—Fusion by voting
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to a license plate voting method, a license plate voting device, computer equipment and a storage medium, wherein a first recognition result is put into a queue to be voted under the condition that the frame difference between a first image frame and a second image frame is smaller than a preset frame difference threshold value, wherein the second image frame is in front of the first image frame, the first image frame corresponds to the first recognition result, the second image frame corresponds to a second recognition result, and the second recognition result and the first recognition result are recognition results adjacent to a target license plate; voting is carried out according to the recognition results in the queue to be voted, the license plate voting result is determined, the recognition results in the queue to be voted are screened, and the stable recognition result is selected for license plate voting, so that the license plate voting result is more accurate and reliable.
Description
Technical Field
The present application relates to the field of license plate recognition technologies, and in particular, to a license plate voting method and apparatus, a computer device, and a storage medium.
Background
With the development of image recognition technology, the application of license plate recognition equipment on the market is wide, and in order to improve the accuracy of license plate recognition results, license plate voting is a common post-processing mode, namely, in a continuous video sequence, aiming at the same target license plate, the obtained license plate recognition results are placed in a queue with a fixed length, and then the recognition results in the queue are synthesized to obtain a voting result which is output as the license plate. However, in the related art, in the case of a local license plate occlusion, for example, a part of the lower edge of the license plate is occluded, the recognition effect of the license plate recognition algorithm is unstable, and on one hand, the license plate recognition result is sometimes not present, and on the other hand, the license plate recognition results are uneven and have low accuracy. Even if the license plate voting is adopted, the wrong license plate is still output.
Aiming at the problem of low accuracy of the license plate voting result in the related technology, no effective solution is provided at present.
Disclosure of Invention
In view of the above, it is necessary to provide a license plate voting method, apparatus, computer device and storage medium.
According to one aspect of the invention, a license plate voting method is provided, which comprises the following steps:
putting a first recognition result into a queue to be voted under the condition that the frame difference between a first image frame and a second image frame is smaller than a preset frame difference threshold value, wherein the first image frame is corresponding to the first recognition result before the second image frame, the second image frame is corresponding to a second recognition result, and the second recognition result and the first recognition result are adjacent recognition results of a target license plate;
and voting according to the recognition result in the queue to be voted, and determining a license plate voting result.
In one embodiment, the method further comprises:
and when the frame difference between the first image frame and the second image frame is greater than or equal to the frame difference threshold value, emptying the queue to be voted and recording the frame number of the first image frame.
In one embodiment, after the first recognition result is placed in a queue to be voted, the method includes:
increasing the number of times of the license plate recognition result once;
and under the condition that the number of times of the license plate identification result is greater than a voting threshold value, voting is carried out according to the queue to be voted, and a license plate voting result is determined.
In one embodiment, the placing the first recognition result into a queue to be voted includes:
and under the condition that the queue to be voted is full, putting the first identification result into the queue to be voted, and removing the identification result which has the longest time interval with the acquisition time of the first identification result from the queue to be voted out of the queue to be voted.
In one embodiment, the frame difference threshold is selected based on environmental factors, wherein the environmental factors include at least one of ambient brightness or vehicle travel speed.
According to another aspect of the invention, the invention also provides a license plate voting device, which comprises a screening module and a voting module,
the screening module is used for putting a first recognition result into a queue to be voted under the condition that the frame difference between a first image frame and a second image frame is smaller than a preset frame difference threshold value, wherein the first image frame is corresponding to the first recognition result before the second image frame, the second image frame is corresponding to a second recognition result, and the second recognition result and the first recognition result are adjacent recognition results of the same target license plate;
And the voting module is used for voting according to the identification result in the queue to be voted and determining the license plate voting result.
In one embodiment, the screening module is further configured to empty the queue to be voted and record a frame number of the first image frame when a frame difference between the first image frame and the second image frame is greater than or equal to the frame difference threshold.
In one embodiment, the voting module is further configured to increase the number of times of the license plate recognition result once after the first recognition result is placed in a queue to be voted; and under the condition that the number of times of the license plate identification result is greater than a voting threshold value, voting is carried out according to the queue to be voted, and a license plate voting result is determined.
According to another aspect of the present invention, there is also provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
putting a first recognition result into a queue to be voted under the condition that the frame difference between the first recognition result and a second recognition result is smaller than a preset frame difference threshold value, wherein the second recognition result and the first recognition result are the same recognition results of target license plates which are adjacent in sequence;
And voting according to the queue to be voted, and determining a license plate voting result.
According to another aspect of the present invention, there is also provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
putting a first recognition result into a queue to be voted under the condition that the frame difference between the first recognition result and a second recognition result is smaller than a preset frame difference threshold value, wherein the second recognition result and the first recognition result are the same recognition results of target license plates which are adjacent in sequence;
and voting according to the queue to be voted, and determining a license plate voting result.
According to the license plate voting method, the license plate voting device, the computer equipment and the storage medium, under the condition that the frame difference between a first image frame and a second image frame is smaller than a preset frame difference threshold value, a first recognition result is put into a queue to be voted, wherein the second image frame is in front of the first image frame, the first image frame corresponds to the first recognition result, the second image frame corresponds to a second recognition result, and the second recognition result and the first recognition result are recognition results of adjacent target license plates; voting is carried out according to the recognition results in the queue to be voted, the license plate voting result is determined, the recognition results in the queue to be voted are screened, and the stable recognition result is selected for license plate voting, so that the license plate voting result is more accurate and reliable.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a diagram illustrating an application scenario of a license plate voting method according to an embodiment of the present invention;
FIG. 2 is a first flowchart of a license plate voting method according to an embodiment of the present invention;
FIG. 3 is a flowchart of a license plate voting method according to an embodiment of the present invention;
FIG. 4 is a flowchart of a license plate voting method according to an embodiment of the present invention;
FIG. 5 is a flow chart of license plate voting according to an embodiment of the present invention;
fig. 6 is a structural view of a license plate voting device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.
It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
Fig. 1 is an application scenario diagram of a license plate voting method according to an embodiment of the present invention, and the license plate voting method provided in the present application may be applied to the application environment shown in fig. 1. Wherein the image capture device 102 communicates with the computer device 104 over a network. The image acquisition device 102 acquires a vehicle license plate picture in a visual field range and sends the vehicle license plate picture to the computer device 104, the computer device 104 identifies license plate information in the image through an image identification algorithm, under the condition that a frame difference between a first identification result and a second identification result of the same target license plate is smaller than a preset frame difference threshold value, the first identification result is put into a queue to be voted, wherein the second identification result and the first identification result are sequentially adjacent identification results, and the computer device 104 votes according to the queue to be voted to determine a license plate voting result. The computer device 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and may also be an independent server or a server cluster composed of a plurality of servers.
In an embodiment, fig. 2 is a flowchart of a license plate voting method according to an embodiment of the present invention, and as shown in fig. 2, a license plate voting method is provided, which is described by taking the example that the method is applied to the computer device 104 in fig. 1, and includes the following steps:
Step S210, placing the first recognition result into a queue to be voted when a frame difference between the first image frame and the second image frame is smaller than a preset frame difference threshold. When acquiring an image of a license plate of a vehicle, a frame of image is generally acquired at preset time intervals, and the acquired frame of image generally has a timestamp or a frame number. In step S210, the second recognition result and the first recognition result are recognition results of two frames of images of the same target license plate that are sequentially adjacent in the acquisition time. Optionally, different license plate identifiers may be generated for license plate recognition of image frames corresponding to different license plates, and in this embodiment, the first recognition result and the second recognition result are recognition results of adjacent image frames containing the same license plate identifier. For example, the recognition results in the queue to be voted are stored in time sequence, and the second recognition result stored in the queue at last corresponds to the A frame image; and B frames are collected, an effective first identification result is also obtained from the B frame image, the A frame image and the B frame sequence number are compared, and if the difference between the frame sequence numbers is smaller than a preset frame difference threshold value, the first identification result is placed into a queue to be voted.
And step S220, voting according to the recognition result in the queue to be voted, and determining the license plate voting result. And executing a voting algorithm by using the identification result in the queue to be voted, which is obtained in the step S210, to obtain a voting result. In the license plate recognition process, after image frames acquired by image acquisition equipment are generally acquired, the license plate in the images is positioned, characters in the license plate are segmented, the characters are recognized, and finally a license plate number is formed. In the process of character recognition, the voting algorithm is used, and because a certain recognition error rate exists in the character recognition, the voting is carried out on each character by using a plurality of groups of recognition results in a queue to be voted, so that the recognition misjudgment rate can be reduced. Various types of voting algorithms provided in the related art can be used for implementation of the present embodiment.
According to the license plate voting method, under the condition that the frame difference between a first recognition result and a second recognition result is smaller than a preset frame difference threshold value, the first recognition result is placed in a queue to be voted, wherein the second recognition result and the first recognition result are the same recognition results of the adjacent target license plates in sequence; voting is carried out according to the recognition results in the queue to be voted, the license plate voting result is determined, the recognition results in the queue to be voted are screened, and the stable recognition result is selected for license plate voting, so that the license plate voting result is more accurate and reliable.
In an embodiment, fig. 3 is a flowchart illustrating a license plate voting method according to an embodiment of the present invention, as shown in fig. 3, the method further includes:
step 300, determining whether a frame difference between the first image frame and the second image frame is smaller than a preset frame difference threshold.
Step S310, emptying the queue to be voted and recording the frame number of the first image frame under the condition that the frame difference between the first image frame and the second image frame is greater than or equal to the frame difference threshold value.
In step S310, the recognition result stored in the queue to be voted finally corresponds to the a-frame image; and (3) acquiring a frame B, obtaining an effective identification result from the frame B image, comparing the frame A image with the frame B sequence number, and if the difference between the frame sequence numbers is greater than or equal to a preset frame difference threshold value, determining that the license plate identification results of the two times before and after are unstable or the reliability of the previous identification result is poor, emptying the previous queue to be voted, and putting the identification result corresponding to the frame B into the queue to be voted. For example, when a vehicle stops at a position where a license plate is partially blocked, the probability of acquiring a recognition result from an image frame is low, license plate recognition is unstable, so that the recognition result is sometimes not obtained, the recognition result cannot be acquired in each image frame, and the frame difference of the image frames corresponding to adjacent recognition results is large. The obtained result has a high error rate, and if the license plate recognition results are put into a queue to be voted, the voting result is further influenced. And after the vehicle leaves the position, the license plate is not shielded, so that the recognition result can be obtained from each frame of image under the normal condition, the license plate recognition is relatively stable, and the reliability of the recognition result is higher. Under the condition, the recognition results in the queue to be voted before the license plate is emptied are stored, the recognition results after the license plate is stably recognized are stored, and the recognition results stored in the queue to be voted are further screened, so that the license plate voting result is more accurate and reliable.
In an embodiment, fig. 4 is a flowchart of a license plate voting method according to an embodiment of the present invention, and as shown in fig. 4, after the first recognition result is placed in a queue to be voted, the method further includes:
step S410, increasing the number of times of the license plate recognition result once;
and step S420, voting according to the queue to be voted under the condition that the number of times of the license plate recognition result is greater than the voting threshold value, and determining the license plate voting result.
In this embodiment, a counting parameter of the recognition result, that is, the number of times of license plate recognition, is added. And under the condition that the identification result is put into the queue to be voted, the number of times of license plate identification is increased. And comparing the license plate identification times with a preset voting threshold, and triggering a voting process under the condition that the license plate identification times are greater than the license plate voting threshold. It should be noted that the number of license plate identification times is not affected by the length of the queue to be voted, and the license plate voting threshold value may be larger than the length value of the queue to be voted. The voting threshold may be obtained by empirical values, and optionally, the voting threshold is set to 8-10.
In one embodiment, placing the first recognition result in a queue to be voted comprises: and under the condition that the queue to be voted is full, putting the first identification result into the queue to be voted, and removing the identification result which has the longest time interval with the acquisition time of the first identification result from the queue to be voted out of the queue to be voted. In this embodiment, the queue to be voted is set to be of a fixed length, and a first-in first-out principle is adopted for the recognition result entering the queue to be voted, that is, in the case that the total length of the queue is 10, when the 11 th license plate recognition result satisfying the foregoing condition comes, the recognition result entering the queue for the 1 st time is replaced. Because the length of the queue to be voted affects the calculation speed of the voting result, the length of the queue to be voted can be properly reduced under the condition that the recognition result in the queue to be voted is pre-screened and has higher stability, the voting efficiency of the license plate is further improved, and the efficiency of the license plate recognition process is further improved.
In one embodiment, the frame difference threshold is selected based on environmental factors. In the process of collecting the vehicle image by the image collecting device, the quality of the collected image is influenced by factors such as light, vehicle running speed and angle when the vehicle passes through the image collecting device, and the identification result is also influenced. Therefore, in the present embodiment, the environmental factors, which may be the brightness of light, the vehicle running speed, etc., are added, and then the corresponding frame difference threshold is selected according to the environmental factors according to the history data. For example, in the case that the brightness of the light is lower than the brightness threshold, the frame difference threshold is increased, so that a higher fault tolerance rate is given to the system, and an effective voting result is obtained.
In an embodiment, fig. 5 is a flowchart illustrating a license plate voting process according to an embodiment of the present invention, as shown in fig. 5, the method includes the following steps:
step S510, obtaining a target license plate recognition result;
step S520, judging whether the first recognition result is the first recognition result of the target license plate; jumping to step S540 if the recognition result is the first recognition result of the target license plate;
step S530, under the condition that the identification result is not the first identification result of the target license plate; judging whether the frame difference between the current identification result last _ index and the previous identification result last _ index is smaller than a frame difference threshold Th 2; under the condition that the frame difference is smaller than a frame difference threshold Th2, the license plate recognition results of the two times of the previous and next times are considered to be stable, and the step S540 is skipped; in the case where the frame difference is greater than or equal to the frame difference threshold Th2, the flow proceeds to step S550.
Step S540, storing the identification result into a queue to be voted, recording the last _ index of the current frame number and adding one to the number count of the license plate identification result;
step S550, emptying the queue to be voted, recording that the current frame number is last _ index, and emptying the license plate identification result times count;
step S560, judging whether the number of times count of the license plate recognition result is greater than a voting threshold Th 1;
and step S570, voting the license plate and outputting a voting result under the condition that the number of times count of the license plate recognition result is greater than the voting threshold Th 1.
The voting threshold Th1 and the frame difference threshold Th2 are adjusted according to different application scenarios, optionally, Th1 is 10, and Th2 is 3. The method can avoid the problem that the license plate is wrongly voted due to the fact that the license plate is partially shielded or stained and the license plate identification result is sometimes existed as far as possible, and in addition, the situation that the unlicensed vehicle is occasionally identified as the licensed vehicle within the normal error range of the license plate identification algorithm can be effectively avoided through the scheme; in addition, whether the license plate recognition result is really stable or not is judged by judging whether the frame difference of the license plate recognition results of the two times before and after the license plate recognition is smaller than a preset threshold value or not, and the license plate voting is triggered only when the license plate recognition result is stable and reaches a certain threshold value, so that the license plate result is prevented from being thrown out by mistake when the license plate recognition is not stable.
It should be understood that although the various steps in the flow charts of fig. 2-5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, fig. 6 is a block diagram of a license plate voting device according to one embodiment of the present invention, and as shown in fig. 6, there is provided a license plate recognition device 60, which includes a screening module 62 and a voting module 64,
the screening module 62 is configured to place the first recognition result in a queue to be voted when a frame difference between the first image frame and the second image frame is smaller than a preset frame difference threshold, where the first image frame is before the second image frame, the first image frame corresponds to the first recognition result, the second image frame corresponds to the second recognition result, and the second recognition result and the first recognition result are adjacent recognition results of the target license plate;
The voting module 64 is used for voting according to the recognition result in the queue to be voted, and determining the license plate voting result.
In one embodiment, the screening module 62 is further configured to empty the queue to be voted and record the frame number of the first image frame when the frame difference between the first image frame and the second image frame is greater than or equal to the frame difference threshold.
In one embodiment, the voting module 64 is further configured to increase the number of times of the license plate recognition result once after the first recognition result is placed in the queue to be voted; and under the condition that the number of times of the license plate identification result is greater than the voting threshold value, carrying out bitwise voting according to the queue to be voted, and determining the license plate voting result.
For specific limitations of the license plate voting device, reference may be made to the above limitations of the license plate voting method, which are not described herein again. All modules in the license plate voting device can be completely or partially realized through software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
The license plate voting device puts the first recognition result into a queue to be voted under the condition that the frame difference between the first recognition result and the second recognition result is smaller than a preset frame difference threshold value, wherein the second recognition result and the first recognition result are the same recognition results of the target license plates which are adjacent in sequence; voting is carried out according to the recognition results in the queue to be voted, the license plate voting result is determined, the recognition results in the queue to be voted are screened, and the stable recognition result is selected for license plate voting, so that the license plate voting result is more accurate and reliable.
According to another aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
putting the first recognition result into a queue to be voted under the condition that the frame difference between the first recognition result and the second recognition result is smaller than a preset frame difference threshold value, wherein the second recognition result and the first recognition result are the same recognition results of the adjacent target license plates in sequence;
and voting according to the recognition result in the queue to be voted, and determining the license plate voting result.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and when the frame difference between the first identification result and the second identification result is greater than or equal to the frame difference threshold value, emptying the queue to be voted and recording the frame sequence number corresponding to the first identification result.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
increasing the number of times of the license plate recognition result once;
and under the condition that the number of times of the license plate recognition result is greater than the voting threshold value, voting is carried out according to the queue to be voted, and the license plate voting result is determined.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and under the condition that the queue to be voted is full, putting the first identification result into the queue to be voted, and removing the identification result which has the longest time interval with the acquisition time of the first identification result from the queue to be voted out of the queue to be voted.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
the frame difference threshold is selected based on environmental factors, including ambient brightness and vehicle travel speed.
The license plate voting computer equipment puts the first recognition result into a queue to be voted under the condition that the frame difference between the first recognition result and the second recognition result is smaller than a preset frame difference threshold value, wherein the second recognition result and the first recognition result are the same recognition results of the adjacent target license plates in sequence; voting is carried out according to the recognition results in the queue to be voted, the license plate voting result is determined, the recognition results in the queue to be voted are screened, and the stable recognition result is selected for license plate voting, so that the license plate voting result is more accurate and reliable.
According to another aspect of the present invention, there is also provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
Putting the first recognition result into a queue to be voted under the condition that the frame difference between the first recognition result and the second recognition result is smaller than a preset frame difference threshold value, wherein the second recognition result and the first recognition result are the same recognition results of the adjacent target license plates in sequence;
and voting according to the recognition result in the queue to be voted, and determining the license plate voting result.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and when the frame difference between the first identification result and the second identification result is greater than or equal to the frame difference threshold value, emptying the queue to be voted and recording the frame sequence number corresponding to the first identification result.
In one embodiment, the computer program when executed by the processor further performs the steps of:
increasing the number of times of the license plate recognition result once;
and under the condition that the number of times of the license plate identification result is greater than a voting threshold value, voting is carried out according to the queue to be voted, and a license plate voting result is determined.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and under the condition that the queue to be voted is full, putting the first identification result into the queue to be voted, and removing the identification result which has the longest time interval with the acquisition time of the first identification result from the queue to be voted out of the queue to be voted.
In one embodiment, the computer program when executed by the processor further performs the steps of:
the frame difference threshold is selected based on environmental factors, wherein the environmental factors include ambient brightness and vehicle travel speed.
The license plate voting computer storage medium puts a first recognition result into a queue to be voted under the condition that the frame difference between the first recognition result and a second recognition result is smaller than a preset frame difference threshold value, wherein the second recognition result and the first recognition result are the same recognition results of the adjacent target license plates in sequence; voting is carried out according to the recognition results in the queue to be voted, the license plate voting result is determined, the recognition results in the queue to be voted are screened, and the stable recognition result is selected for license plate voting, so that the license plate voting result is more accurate and reliable.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A license plate voting method, comprising:
putting a first recognition result into a queue to be voted under the condition that the frame difference between a first image frame and a second image frame is smaller than a preset frame difference threshold value, wherein the first image frame is corresponding to the first recognition result before the second image frame, the second image frame is corresponding to a second recognition result, and the second recognition result and the first recognition result are adjacent recognition results of a target license plate;
And voting according to the recognition result in the queue to be voted, and determining a license plate voting result.
2. The method of claim 1, further comprising:
and when the frame difference between the first image frame and the second image frame is greater than or equal to the frame difference threshold value, emptying the queue to be voted and recording the frame number of the first image frame.
3. The method according to claim 1 or 2, wherein after the first recognition result is placed in a queue to be voted, the method comprises:
increasing the number of times of the license plate recognition result once;
and under the condition that the number of times of the license plate identification result is greater than a voting threshold value, voting is carried out according to the queue to be voted, and a license plate voting result is determined.
4. The method of claim 1, wherein the placing the first recognition result into a queue to be voted comprises:
and under the condition that the queue to be voted is full, putting the first identification result into the queue to be voted, and removing the identification result which has the longest time interval with the acquisition time of the first identification result from the queue to be voted out of the queue to be voted.
5. The method of claim 1, further comprising:
the frame difference threshold is selected based on an environmental factor, wherein the environmental factor includes at least one of ambient brightness or vehicle travel speed.
6. The license plate voting device is characterized by comprising a screening module and a voting module,
the screening module is used for putting a first recognition result into a queue to be voted under the condition that the frame difference between a first image frame and a second image frame is smaller than a preset frame difference threshold value, wherein the first image frame is corresponding to the first recognition result before the second image frame, the second image frame is corresponding to a second recognition result, and the second recognition result and the first recognition result are adjacent recognition results of a target license plate;
and the voting module is used for voting according to the identification result in the queue to be voted and determining the license plate voting result.
7. The apparatus of claim 6,
the screening module is further configured to empty the queue to be voted and record a frame number of the first image frame when a frame difference between the first image frame and the second image frame is greater than or equal to the frame difference threshold.
8. The apparatus of claim 6,
the voting module is further used for increasing the number of times of the license plate recognition result once after the first recognition result is placed in a queue to be voted; and under the condition that the number of times of the license plate identification result is greater than a voting threshold value, carrying out bitwise voting according to the queue to be voted, and determining a license plate voting result.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the license plate voting method according to any one of claims 1 to 5.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the license plate voting method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010543233.1A CN111860590A (en) | 2020-06-15 | 2020-06-15 | License plate voting method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010543233.1A CN111860590A (en) | 2020-06-15 | 2020-06-15 | License plate voting method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111860590A true CN111860590A (en) | 2020-10-30 |
Family
ID=72986640
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010543233.1A Pending CN111860590A (en) | 2020-06-15 | 2020-06-15 | License plate voting method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111860590A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112507827A (en) * | 2020-11-30 | 2021-03-16 | 之江实验室 | Intelligent video target shooting real-time detection method |
| CN113191343A (en) * | 2021-03-31 | 2021-07-30 | 成都飞机工业（集团）有限责任公司 | Aviation wire identification code automatic identification method based on convolutional neural network |
| CN114677774A (en) * | 2022-03-30 | 2022-06-28 | 深圳市捷顺科技实业股份有限公司 | Barrier gate control method and related equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824066A (en) * | 2014-03-18 | 2014-05-28 | 厦门翼歌软件科技有限公司 | Video stream-based license plate recognition method |
| US20160004922A1 (en) * | 2013-03-15 | 2016-01-07 | Kabushiki Kaisha Toshiba | Image pickup device, vehicle number image pickup device, and image pickup method |
| CN107545563A (en) * | 2017-07-13 | 2018-01-05 | 上海造币有限公司 | A kind of silver punching number system and method for counting |
| CN107798297A (en) * | 2017-09-28 | 2018-03-13 | 成都大熊智能科技有限责任公司 | A kind of method that stabilizer frame is automatically extracted based on inter-frame difference |
| CN108197621A (en) * | 2017-12-28 | 2018-06-22 | 北京金堤科技有限公司 | Company information acquisition methods and system and information processing method and system |
| CN108399349A (en) * | 2018-03-22 | 2018-08-14 | 腾讯科技（深圳）有限公司 | Image-recognizing method and device |
| CN110059686A (en) * | 2019-04-26 | 2019-07-26 | 腾讯科技（深圳）有限公司 | Character identifying method, device, equipment and readable storage medium storing program for executing |
-
2020
- 2020-06-15 CN CN202010543233.1A patent/CN111860590A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160004922A1 (en) * | 2013-03-15 | 2016-01-07 | Kabushiki Kaisha Toshiba | Image pickup device, vehicle number image pickup device, and image pickup method |
| CN103824066A (en) * | 2014-03-18 | 2014-05-28 | 厦门翼歌软件科技有限公司 | Video stream-based license plate recognition method |
| CN107545563A (en) * | 2017-07-13 | 2018-01-05 | 上海造币有限公司 | A kind of silver punching number system and method for counting |
| CN107798297A (en) * | 2017-09-28 | 2018-03-13 | 成都大熊智能科技有限责任公司 | A kind of method that stabilizer frame is automatically extracted based on inter-frame difference |
| CN108197621A (en) * | 2017-12-28 | 2018-06-22 | 北京金堤科技有限公司 | Company information acquisition methods and system and information processing method and system |
| CN108399349A (en) * | 2018-03-22 | 2018-08-14 | 腾讯科技（深圳）有限公司 | Image-recognizing method and device |
| CN110059686A (en) * | 2019-04-26 | 2019-07-26 | 腾讯科技（深圳）有限公司 | Character identifying method, device, equipment and readable storage medium storing program for executing |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112507827A (en) * | 2020-11-30 | 2021-03-16 | 之江实验室 | Intelligent video target shooting real-time detection method |
| CN112507827B (en) * | 2020-11-30 | 2022-05-13 | 之江实验室 | Intelligent video target shooting real-time detection method |
| CN113191343A (en) * | 2021-03-31 | 2021-07-30 | 成都飞机工业（集团）有限责任公司 | Aviation wire identification code automatic identification method based on convolutional neural network |
| CN114677774A (en) * | 2022-03-30 | 2022-06-28 | 深圳市捷顺科技实业股份有限公司 | Barrier gate control method and related equipment |
| CN114677774B (en) * | 2022-03-30 | 2023-10-17 | 深圳市捷顺科技实业股份有限公司 | Barrier gate control method and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111860590A (en) | License plate voting method and device, computer equipment and storage medium | |
| CN111046959A (en) | Model training method, device, equipment and storage medium | |
| CN108229260B (en) | Identity information verification method and system | |
| CN109816200B (en) | Task pushing method, device, computer equipment and storage medium | |
| CN110750670B (en) | Stranger monitoring method, device and system and storage medium | |
| CN110489415B (en) | Data updating method and related equipment | |
| US8842889B1 (en) | System and method for automatic face recognition | |
| CN109784316B (en) | Method, device and storage medium for tracing subway gate ticket evasion | |
| CN111191568A (en) | Method, device, equipment and medium for identifying copied image | |
| CN109800318A (en) | A kind of archiving method and device | |
| CN111191506A (en) | Personnel flow statistical method and device, computer equipment and storage medium | |
| CN109308704B (en) | Background eliminating method, device, computer equipment and storage medium | |
| CN109740003A (en) | A kind of archiving method and device | |
| CN110991231A (en) | Living body detection method and device, server and face recognition equipment | |
| CN112232140A (en) | Crowd counting method and device, electronic equipment and computer storage medium | |
| CN109800675A (en) | A kind of method and device of the identification image of determining face object | |
| CN108647106A (en) | Using abnormality eliminating method, storage medium and computer equipment | |
| CN109359689B (en) | Data identification method and device | |
| CN109828715B (en) | Screen recording method and device | |
| CN111611821B (en) | Two-dimensional code identification method and device, computer equipment and readable storage medium | |
| CN116612498A (en) | Bird recognition model training method, bird recognition method, device and equipment | |
| CN111985438A (en) | Static face processing method, device and equipment | |
| CN112330967B (en) | Identification method, device and system of fake-licensed vehicle and computer equipment | |
| CN113421241B (en) | Abnormal event reporting method and device, computer equipment and storage medium | |
| CN111597979B (en) | Target object clustering method and device |
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 |