License plate automatic correction method and device based on big data

Abstract

The invention provides a license plate automatic correction method and device based on big data, and the method comprises the steps: carrying out the local recognition and obtaining a first license plate of a vehicle, carrying out the cloud secondary recognition and obtaining a second license plate of the vehicle, judging whether the second license plate is the same as the first license plate or not, taking the first license plate as an entrance license plate of the vehicle if yes, and taking the entrance license plate as an exit license plate of the vehicle; otherwise, acquiring first entrance times of the first license plate and the second license plate in a second time period before and after the current time point in the latest first time period of the current parking lot, and determining the entrance license plate of the vehicle according to the first entrance times. The entrance license plate of the vehicle can be determined, so that the license plate recognition accuracy is improved, and the manual confirmation frequency is reduced.

Description

Technical Field

[0001] The present invention relates to the field of parking technology, and in particular to a method and device for automatic license plate correction based on big data. Background Art

[0002] License plate recognition technology is mainly used in modern traffic management, intelligent security control and parking lot management. In the process of parking lot management, license plate recognition is mainly used for vehicle access control and parking fee charging. Therefore, it is very important to ensure the accuracy of license plate recognition.

[0003] Currently, parking lots are often unmanned on site. When a license plate is recognized incorrectly, it is necessary to go to the exit and contact remote agents for manual confirmation, which affects vehicle payment and traffic efficiency, and has high labor costs. Summary of the invention

[0004] In order to solve the above problems in the prior art, the present invention provides a method and device for automatic license plate correction based on big data, which improves the accuracy of license plate recognition and reduces the frequency of manual confirmation.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] In a first aspect, the present invention provides a method for automatic license plate correction based on big data, comprising:

[0007] Step S1, locally identify and obtain the first license plate of the vehicle, and then perform a second identification on the cloud to obtain the second license plate of the vehicle, and determine whether the second license plate is the same as the first license plate. If so, use the first license plate as the entry license plate of the vehicle, otherwise, execute step S2;

[0008] Step S2: Obtain a first number of entries of the first license plate and the second license plate in a current parking lot within a second time period before and after a current time point within a recent first time period, and determine the entry license plate of the vehicle according to the first number of entries.

[0009] The beneficial effect of the present invention is that through the two license plate recognitions locally and in the cloud, if the license plates recognized twice are the same, they are directly confirmed; if they are different, the vehicle's entry license plate is determined by the first number of entries in a second time period before and after the current time point in the most recent first time period of the current parking lot, thereby improving the accuracy of license plate recognition and reducing the frequency of manual confirmation.

[0010] Optionally, determining the entry license plate of the vehicle according to the first entry number includes:

[0011] Determine whether the first entry times of the first license plate and the second license plate are both greater than 0. If so, determine whether the difference between the first entry times of the two is greater than or equal to a first threshold. If so, take the license plate with the greater first entry times as the entry license plate of the vehicle.

[0012] Optionally, the step S2 further includes:

[0013] If one of the first number of entry of the first license plate and the second license plate is 0 and the other is not 0, the license plate whose first number of entry is not 0 is used as the entry license plate of the vehicle.

[0014] Optionally, determining the entry license plate of the vehicle according to the first entry number in step S2 further includes:

[0015] If the first entry times of the first license plate and the second license plate are both greater than 0 and the difference between the first entry times of the two is less than the first threshold, or the first entry times of the first license plate and the second license plate are both 0, then the manual correction records of the first license plate and the second license plate within the third time period of the current parking lot are obtained, and the entry license plate of the vehicle is determined based on the manual correction records of the two.

[0016] According to the above description, it can be seen that the accuracy of license plate recognition can be improved by manually correcting records.

[0017] Optionally, determining the vehicle's entry license plate according to the manual correction records of the two comprises:

[0018] Determine whether the manual correction records of both are greater than 0. If so, determine whether the corrected license plates of the first license plate and the second license plate are the same. If so, use the same corrected license plate as the entry license plate of the vehicle.

[0019] Optionally, the step S2 further includes:

[0020] If one of the manual correction records is 0 and the other is not 0, the corrected license plate corresponding to the most recently corrected license plate is used as the entry license plate of the vehicle;

[0021] If the manual correction records of both are 0, or the first license plate and the second license plate are not the same after correction, manual judgment is performed.

[0022] Optionally, the first time period and the third time period are the same.

[0023] In a second aspect, the present invention provides an automatic license plate correction device based on big data, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, an automatic license plate correction method based on big data according to the first aspect is implemented.

[0024] Among them, the technical effect corresponding to the automatic license plate correction device based on big data provided by the second aspect refers to the relevant description of the automatic license plate correction method based on big data provided by the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A schematic diagram of the main process of a method for automatic license plate correction based on big data according to an embodiment of the present invention;

[0026] Figure 2 This is a schematic diagram of a specific process of step S2 involved in an embodiment of the present invention;

[0027] Figure 3 The present invention is a schematic diagram of the framework of a device for automatic license plate correction based on big data according to an embodiment of the present invention.

[0028] Description of reference numerals:

[0029] 1. A license plate automatic correction device based on big data;

[0030] 2. Processor;

[0031] 3. Memory. DETAILED DESCRIPTION

[0032] In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a clearer and more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0033] Embodiment 1

[0034] This embodiment is suitable for application scenarios that require license plate recognition. Especially license plate recognition during off-street parking. Affected by ambient light, license plate position and angle, and obstructions, the license plate will be recognized incorrectly. If it is a parking lot with no on-site staff, it is necessary to contact remote agents for manual confirmation, which affects vehicle payment and traffic efficiency, and the labor cost is high. This embodiment reconfirms license plates with low credibility through secondary pre-judgment and the first number of entries in the second time period before and after the current time point in the most recent first time period of the current parking lot, so as to improve the accuracy of license plate recognition and reduce the frequency of manual confirmation. See the following description for details.

[0035] Please refer to Figure 1 , a license plate automatic correction method based on big data, comprising the steps of:

[0036] Step S1, locally identify and obtain the first license plate of the vehicle, and then perform a second identification in the cloud to obtain the second license plate of the vehicle, and determine whether the second license plate is the same as the first license plate. If so, the first license plate is used as the vehicle's entry license plate, otherwise, execute step S2;

[0037] Among them, after the first license plate is recognized locally, the photo will be pushed to the cloud for secondary recognition. If the results of the two recognitions are consistent, the recognition is considered accurate and the entry license plate will not be adjusted. The first license plate will be used as the vehicle's entry license plate.

[0038] Step S2, obtaining the first entry times of the first license plate and the second license plate in the current parking lot in a second time period before and after the current time point in the most recent first time period, and determining the entry license plate of the vehicle based on the first entry times of the two.

[0039] In this embodiment, the first time period is 30 days, and the second time period is 1 hour, that is, the first entry times of the two license plates in the current parking lot within the last 30 days within 1 hour before and after the current time point are compared. In other embodiments, the first time period can be 15 days, 7 days, or more than 3 days. The value range of the second time period is 30-180 minutes, such as 30 minutes, 45 minutes, etc.

[0040] Specifically, determining the vehicle's entry license plate according to the first entry times of the two in step S2 includes:

[0041] Step S21, determine whether the first entry times of the first license plate and the second license plate are both greater than 0. If so, determine whether the difference between the first entry times of the two is greater than or equal to a first threshold. If so, take the license plate with the greater first entry times as the vehicle's entry license plate.

[0042] In this embodiment, the first threshold is 3. In other embodiments, the first threshold may be 2 or 4.

[0043] Step S22: If one of the first number of entry of the first license plate and the second license plate is 0 and the other is not 0, the license plate whose first number of entry is not 0 is used as the entry license plate of the vehicle.

[0044] At this time, an example is given below:

[0045] a. The first license plate A has made 5 first entries into the current parking lot within 1 hour before and after the current time point in the past 30 days, and the second license plate B has made 1 first entry. The difference between the two entries is 4, which is greater than the first threshold of 3. In this case, the first license plate A will be used as the vehicle's entry license plate.

[0046] b. If the first license plate A has entered the current parking lot twice within 1 hour before and after the current time point in the past 30 days, and the second license plate B has entered the parking lot 0 times, then the first license plate A will be used as the vehicle's entry license plate.

[0047] In this embodiment, if the first number of entries of the first license plate A and the first license plate B are both 0 or both are not 0 but the difference is less than 3, for example, the first number of entries of the first license plate A and the second license plate B are 5 and 3 respectively, and the difference between the two is 2, which is less than the first threshold of 3, then it is necessary to combine other rules for judgment or to make a manual judgment. However, this embodiment has been able to reduce the number of manual judgments required through secondary recognition and judgment of the first number of entries, thereby ensuring the accuracy of license plate recognition and reducing the frequency of manual confirmation.

[0048] Embodiment 2

[0049] This embodiment adds manual correction records to the above embodiment 1 for judgment, thereby further improving the accuracy of license plate recognition and reducing the frequency of manual confirmation. See the following description for details.

[0050] Please refer to Figure 1 to Figure 2 , a license plate automatic correction method based on big data, in step S2, determining the vehicle's entry license plate according to the first entry times of the two comprises:

[0051] Step S23: If the first entry times of the first license plate and the second license plate are both greater than 0 and the difference between the first entry times of the two is less than the first threshold, or the first entry times of the first license plate and the second license plate are both 0, then obtain the manual correction records of the first license plate and the second license plate in the third time period of the current parking lot, and determine the entry license plate of the vehicle based on the manual correction records of the two.

[0052] In this embodiment, the third time period is the same as the first time period, and in this embodiment, the manual correction records of the first license plate A and the second license plate B in the current parking lot within the last 30 days are obtained.

[0053] In this embodiment, determining the vehicle's entry license plate based on the manual correction records of the two includes:

[0054] Step S231, determine whether the manual correction records of both are greater than 0, if so, determine whether the corrected license plate of the first license plate and the second license plate are the same, if so, use the same corrected license plate as the vehicle's entry license plate.

[0055] Specifically, when the first number of entries cannot determine which license plate is more accurate, manual correction records are introduced to see whether there are records of manual correction. If both the first license plate A and the second license plate B have records of manual correction and are still the same after correction, the same corrected license plate will be used as the vehicle's entry license plate. For example, if the first license plate A is Min D·XXBXX and the second license plate B is Min D·XXDXX, and both are corrected to Min D·XX6XX, Min D·XX6XX will be used as the vehicle's entry license plate.

[0056] Step S232: If one of the manual correction records is 0 and the other is not 0, the corrected license plate corresponding to the most recently corrected license plate is used as the vehicle's entry license plate.

[0057] Specifically, if the first license plate A has a manual correction record, but the second license plate B has no manual correction record, the license plate of the first license plate A that was corrected most recently will be used as the vehicle's entry license plate.

[0058] Step S233: If the manual correction records of both are 0, or the first license plate and the second license plate are not the same after correction, manual judgment is performed.

[0059] Specifically, when the first license plate A and the second license plate B are both 0, or the corrected license plates are not the same, the system cannot identify which license plate is more accurate, so manual judgment is required.

[0060] The specific flow chart of step S2 in this embodiment is shown in FIG. Figure 2 .

[0061] It can be seen that after a license plate recognition error, this embodiment can significantly reduce the number of times manual judgment is required through a comprehensive judgment of secondary recognition, first entry times and manual correction records, further ensuring the accuracy of license plate recognition and reducing the frequency of manual confirmation.

[0062] Embodiment 3

[0063] Please refer to Figure 3A license plate automatic correction device 1 based on big data includes a memory 3, a processor 2, and a computer program stored in the memory 3 and executable on the processor 2. When the processor 2 executes the computer program, the steps in the above-mentioned embodiment 1 or 2 are implemented.

[0064] Since the system / device described in the above embodiments of the present invention is a system / device used to implement the method of the above embodiments of the present invention, a person skilled in the art can understand the specific structure and deformation of the system / device based on the method described in the above embodiments of the present invention, and thus will not be described in detail here. All systems / devices used in the method of the above embodiments of the present invention belong to the scope of protection of the present invention.

[0065] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0066] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (apparatus) and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions.

[0067] It should be noted that in the claims, any reference numerals placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In the claims enumerating several means, several of these means may be embodied by the same hardware. The use of the words first, second, third, etc., is for convenience of expression only and does not indicate any order. These words may be understood as part of the component name.

[0068] In addition, it should be noted that, in the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0069] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments after knowing the basic creative concept. Therefore, the claims should be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0070] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention should also include these modifications and variations.

Claims

1. A license plate automatic correction method based on big data, characterized in that: include: Step S1, locally identify and obtain the first license plate of the vehicle, and then perform a second identification on the cloud to obtain the second license plate of the vehicle, and determine whether the second license plate is the same as the first license plate. If so, use the first license plate as the entry license plate of the vehicle, otherwise, execute step S2; Step S2: Obtain a first number of entries of the first license plate and the second license plate in a current parking lot within a second time period before and after a current time point within a recent first time period, and determine the entry license plate of the vehicle according to the first number of entries.

2. The method for automatic license plate correction based on big data according to claim 1 is characterized in that: Determining the entry license plate of the vehicle according to the first entry number includes: Determine whether the first entry times of the first license plate and the second license plate are both greater than 0. If so, determine whether the difference between the first entry times of the two is greater than or equal to a first threshold. If so, take the license plate with the greater first entry times as the entry license plate of the vehicle.

3. The method for automatic license plate correction based on big data according to claim 2 is characterized in that: The step S2 further comprises: If one of the first license plate and the second license plate's first entry times is 0 and the other is not 0, the license plate whose first entry times is not 0 is used as the entry license plate of the vehicle.

4. The method for automatic license plate correction based on big data according to claim 2 is characterized in that: Determining the vehicle's entry license plate according to the first entry number in step S2 further includes: If the first entry times of the first license plate and the second license plate are both greater than 0 and the difference between the first entry times of the two is less than the first threshold, or the first entry times of the first license plate and the second license plate are both 0, then the manual correction records of the first license plate and the second license plate within the third time period of the current parking lot are obtained, and the entry license plate of the vehicle is determined based on the manual correction records of the two.

5. The method for automatic license plate correction based on big data according to claim 4 is characterized in that: Determining the vehicle's entry license plate based on the two manual correction records includes: Determine whether the manual correction records of both are greater than 0. If so, determine whether the corrected license plates of the first license plate and the second license plate are the same. If so, use the same corrected license plate as the entry license plate of the vehicle.

6. The method for automatic license plate correction based on big data according to claim 5 is characterized in that: The step S2 further comprises: If one of the manual correction records is 0 and the other is not 0, the corrected license plate corresponding to the most recently corrected license plate is used as the entry license plate of the vehicle; If the manual correction records of both are 0, or the first license plate and the second license plate are not the same after correction, manual judgment is performed.

7. The method for automatic license plate correction based on big data according to claim 4 is characterized in that: The first time period and the third time period are the same.

8. A license plate automatic correction device based on big data, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for automatic license plate correction based on big data as described in any one of claims 1 to 7 is implemented.

Images