License Plate Recognition Method and Recognition Device for Construction Site Vehicles

Abstract

The present invention relates to the technical field of vehicle identification, and particularly to a license plate recognition method and a recognition device for construction site vehicles. Among them, the license plate recognition method includes: first, obtaining a license plate image to be recognized of a vehicle entering and leaving a construction site; then performing image preprocessing on the license plate image to be recognized to obtain the light intensity and soot concentration of the license plate image to be recognized; obtaining image deviation information corresponding to the light intensity and soot concentration of the license plate image to be recognized; and finally correcting the license plate number in the license plate image to be recognized according to the image deviation information to obtain the license plate number of the vehicle entering and leaving the construction site. In the present invention, by performing correction processing on the license plate number in the license plate image to be recognized, the recognized license plate number is made more accurate, and the robustness of license plate number recognition is also higher.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle identification, and particularly to a license plate recognition method and a recognition device for construction site vehicles. Background Art

[0002] At the entrance and exit positions of construction sites, vehicle identification devices are usually installed to capture, scan and recognize license plate information, so as to control and record the entry and exit of construction vehicles from the construction site and prevent unauthorized vehicles from accidentally entering the construction site. However, the current vehicle identification technology for construction sites still has the following deficiencies:

[0003] Existing recognition technologies do not have light robustness. The recognition camera is located outdoors, and there is usually a large amount of floating dust at construction sites. This results in unstable lighting factors when the camera takes pictures for recognition. Not only will the external weather affect recognition, but the dust, as an interference factor, will also affect recognition, leading to low accuracy of license plate number recognition results, which is not conducive to maintaining the stability of vehicle identification technology and thus affects the safety management of vehicle entry and exit from the construction site. Summary of the Invention

[0004] The present invention provides a license plate recognition method and a recognition device for construction site vehicles to solve the technical problem of low accuracy of license plate number recognition results in the prior art.

[0005] On the one hand, the present invention provides a license plate recognition method for construction site vehicles, including:

[0006] Obtaining a license plate image to be recognized of a vehicle entering and exiting the construction site;

[0007] Performing image preprocessing on the license plate image to be recognized to obtain the light intensity and dust concentration of the license plate image to be recognized;

[0008] Obtaining image deviation information corresponding to the light intensity and dust concentration of the license plate image to be recognized;

[0009] Correcting the license plate number in the license plate image to be recognized according to the image deviation information to obtain the license plate number of the vehicle entering and exiting the construction site.

[0010] According to the license plate recognition method for construction site vehicles provided by the present invention, the performing image preprocessing on the license plate image to be recognized to obtain the light intensity and dust concentration of the license plate image to be recognized includes:

[0011] Performing grayscale processing and binarization processing on the license plate image to be recognized to obtain the light intensity and dust concentration of the license plate image to be recognized.

[0012] According to a license plate recognition method for construction site vehicles provided by the present invention, obtaining the image deviation information corresponding to the light intensity and smoke and dust concentration of the license plate image to be recognized includes:

[0013] Obtaining the corresponding relationship between the light intensity and smoke and dust concentration and the image deviation information;

[0014] According to the corresponding relationship between the light intensity and smoke and dust concentration and the image deviation information, obtaining the image deviation information corresponding to the light intensity and smoke and dust concentration of the license plate image to be recognized.

[0015] According to a license plate recognition method for construction site vehicles provided by the present invention, obtaining the corresponding relationship between the light intensity and smoke and dust concentration and the image deviation information includes:

[0016] Respectively obtaining the reference license plate numbers of the reference license plate images under different light intensities and different smoke and dust concentrations;

[0017] Comparing and analyzing the reference license plate numbers and the correct license plate numbers under different light intensities and different smoke and dust concentrations to obtain the corresponding relationship between the light intensity and smoke and dust concentration and the image deviation information.

[0018] According to a license plate recognition method for construction site vehicles provided by the present invention, comparing and analyzing the license plate numbers of the license plate images and the correct license plate numbers under different light intensities and different smoke and dust concentrations to obtain the corresponding relationship between the light intensity and smoke and dust concentration and the image deviation information includes:

[0019] Integrating the characteristic data of the reference license plate numbers under different light intensities and different smoke and dust concentrations to obtain the characteristic data set of the reference license plate numbers;

[0020] Respectively calculating the similarity values between the reference license plate numbers and the correct license plate numbers under different light intensities and different smoke and dust concentrations to obtain the image deviation information between the reference license plate numbers and the correct license plate numbers;

[0021] Processing the similarity values using a normal distribution model to obtain the image deviation information corresponding to different light intensities and different smoke and dust concentrations.

[0022] According to a license plate recognition method for construction site vehicles provided by the present invention, after obtaining the license plate numbers of the vehicles entering and leaving the construction site, it further includes:

[0023] Determining whether the license plate numbers of the vehicles entering and leaving the construction site have the permission to enter and leave. If so, allowing the current vehicle to enter and leave.

[0024] According to a license plate recognition method for construction site vehicles provided by the present invention, when a vehicle is allowed to enter and exit the construction site, the license plate number, entry and exit time, and entry and exit location of the vehicle are recorded.

[0025] On the other hand, the present invention also provides a license plate recognition device for construction site vehicles, including:

[0026] An acquisition unit for acquiring an image of the license plate to be recognized of a vehicle entering and exiting the construction site;

[0027] A first processing unit for performing image preprocessing on the license plate image to be recognized to obtain the illumination intensity and soot concentration of the license plate image to be recognized;

[0028] A second processing unit for obtaining image deviation information corresponding to the illumination intensity and soot concentration of the license plate image to be recognized;

[0029] A recognition unit for correcting the license plate number in the license plate image to be recognized according to the image deviation information to obtain the license plate number of the vehicle entering and exiting the construction site.

[0030] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the license plate recognition method for construction site vehicles as described in any one of the above.

[0031] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the license plate recognition method for construction site vehicles as described in any one of the above.

[0032] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the license plate recognition method for construction site vehicles as described in any one of the above.

[0033] The license plate recognition method for construction site vehicles provided by the present invention first acquires an image of the license plate to be recognized of a vehicle entering and exiting the construction site; then performs image preprocessing on the license plate image to be recognized to obtain the illumination intensity and soot concentration of the license plate image to be recognized; obtains image deviation information corresponding to the illumination intensity and soot concentration of the license plate image to be recognized; and finally corrects the license plate number in the license plate image to be recognized according to the image deviation information to obtain the license plate number of the vehicle entering and exiting the construction site. In the present invention, by performing correction processing on the license plate number in the license plate image to be recognized, the recognized license plate number is made more accurate, and the robustness of license plate number recognition is also higher. Description of the Drawings

[0034] To more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0035] Figure 1 Flowchart of the license plate recognition method for construction site vehicles provided by the embodiments of the present invention;

[0036] Figure 2 Schematic structural diagram of the license plate recognition device for construction site vehicles provided by the embodiments of the present invention;

[0037] Figure 3 Schematic diagram of the physical structure of an electronic device is illustrated. Detailed implementation manners

[0038] To make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the drawings in the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0039] The following combines Figure 1 - Figure 2 to describe the license plate recognition method and recognition device for construction site vehicles of the present invention.

[0040] Figure 1 Flowchart of the license plate recognition method for construction site vehicles provided by the embodiments of the present invention. Please refer to Figure 1 As shown, the license plate recognition method for the construction site vehicle includes:

[0041] S101. Obtain the license plate image to be recognized of the vehicle entering and leaving the construction site.

[0042] In one or more embodiments, a camera or other image acquisition device can be used to obtain the license plate image to be recognized of the vehicle entering and leaving the construction site.

[0043] S102. Perform image preprocessing on the license plate image to be recognized to obtain the light intensity and smoke and dust concentration of the license plate image to be recognized.

[0044] In one or more embodiments, the license plate image to be recognized is grayscaled and binarized to obtain the light intensity and soot concentration of the license plate image to be recognized. For example, when a construction vehicle enters or exits a construction site, the license plate image t to be recognized is captured by a camera, and the relevant information on the light intensity and soot concentration in the license plate image t to be recognized is obtained through grayscaling and binarization.

[0045] Among them, grayscaling means converting the color value of a point in the color image T1 into the color depth (i.e., gray level) of a point in a black-and-white image through the RGB model. In one embodiment, the grayscaling method can be any one of the component method, the maximum value method, the average value method, or the weighted average method.

[0046] Among them, the method used for binarization in this embodiment is the threshold method. By utilizing the difference between the target and the background in the image, the image is set to two different levels respectively, and a suitable threshold is selected to determine whether a certain pixel is the target or the background, thereby obtaining a binarized image.

[0047] Among them, the method for selecting the threshold can be any one of the bimodal method, the P-parameter method, the Otsu method, the maximum entropy threshold method, or the iterative method.

[0048] S103. Obtain the image deviation information corresponding to the light intensity and soot concentration of the license plate image to be recognized.

[0049] In one or more embodiments, obtaining the image deviation information corresponding to the light intensity and soot concentration of the license plate image to be recognized specifically includes:

[0050] Pre-obtain the correspondence between the light intensity and soot concentration and the image deviation information;

[0051] According to the correspondence between the light intensity and soot concentration and the image deviation information, obtain the image deviation information corresponding to the light intensity and soot concentration of the license plate image to be recognized.

[0052] In one or more embodiments, pre-obtaining the correspondence between the light intensity and soot concentration and the image deviation information specifically includes:

[0053] Respectively obtain the reference license plate numbers of the reference license plate images under different light intensities and different soot concentrations. For example, build an experimental site for light intensity and soot concentration, adjust different light intensities and different soot concentrations respectively to obtain multiple combinations of different light intensities and different soot concentrations, and conduct simulation tests under these multiple combinations of different light intensities and different soot concentrations.

[0054] Compare and analyze the reference license plate numbers and the correct license plate numbers under different light intensities and different soot concentrations to obtain the correspondence between the light intensity and soot concentration and the image deviation information.

[0055] In one or more embodiments, the license plate numbers of license plate images under different light intensities and different soot concentrations are compared and analyzed with the correct license plate numbers to obtain the corresponding relationship between the light intensity, the soot concentration, and the image deviation information, which specifically includes:

[0056] Integrate the characteristic data of the reference license plate numbers under different light intensities and different soot concentrations to obtain the characteristic data set of the reference license plate numbers;

[0057] Calculate the similarity values between the reference license plate numbers and the correct license plate numbers under different light intensities and different soot concentrations respectively to obtain the image deviation information between the reference license plate numbers and the correct license plate numbers;

[0058] Use the normal distribution model to process the similarity values to obtain the image deviation information corresponding to different light intensities and different soot concentrations.

[0059] In one embodiment, first, build a light simulation experimental site, use lighting equipment to simulate different lighting conditions, and use a light sensor to detect the light intensity of the experimental site in real time. Place the reference license plate in the site, and use a camera to capture the color image T1 of the reference license plate under different lighting conditions. Perform grayscale processing on the color image T1 to obtain the grayscale image T2, then perform binary processing on the grayscale image T2 to obtain the image T3, and calculate the image features of the image T3 to obtain the license plate number feature database Q2 under different light intensities. Use computer software to perform dust simulation processing on the image T3, simulate different concentrations of soot by overlaying a dust simulation layer on the image T3, synthesize the image T4 under different soot concentrations, perform grayscale processing and binary processing on the image T4 in sequence to obtain the new image T5, and calculate the image features of the image T5 to obtain the license plate number feature database Q3 under different soot concentrations. Classify and match the data in the license plate number feature databases Q1, Q2, and Q3 according to the numerical values of the license plate numbers, integrate the characteristic data of the same license plate number under different light intensities and different soot concentrations to obtain the characteristic data set An of the same license plate number, then use similarity calculation to calculate the similarity S between the characteristic data and the template characteristic data under different light intensities and different soot concentrations respectively, and use the normal distribution model to process the similarity values to obtain the influence relationship of the light intensity and the soot concentration on the license plate number recognition degree, and accordingly obtain the image deviation situation of the license plate number under different light intensities and different soot concentrations. Repeat the above operations to obtain the image deviation situations of all license plate numbers under light and soot interference.

[0060] Among them, each pixel in the grayscale image T2 only needs one byte to store the grayscale value, and the grayscale range is 0 - 255.

[0061] S104. Correct the license plate number in the license plate image to be recognized according to the image deviation information, so as to obtain the license plate number of the vehicle entering and leaving the construction site.

[0062] In one or more embodiments, for example, for a digit 9 in a license plate number, under different light intensities and different soot concentrations, the display state and clarity of the digit 9 will be affected. By comparing the display state of the license plate number in different situations obtained in advance with the correct display state of the license plate number, the image deviation information can be obtained. For example, the image deviation information of the digit 9 can be obtained. Subsequently, when recognizing the license plate number of the vehicle entering and leaving the construction site, the image deviation information of the digit 9 can be used to correct the digit 9 in the collected license plate number, which is equivalent to the compensation of the recognition result, making the recognition result more accurate and the recognition stability higher.

[0063] For example, in this embodiment, when a construction vehicle enters and leaves the construction site, the license plate image t is captured by a camera. The light intensity and soot concentration in the image t are obtained through grayscale processing and binarization processing, and are matched with the image deviation situation recorded in the system. The license plate digital image is locked through similarity analysis, and the corresponding correct license plate number is tracked to realize the correction of the content of the image t.

[0064] Among them, the image similarity is inversely proportional to the image deviation. The higher the similarity, the smaller the image deviation and the lighter the image deviation situation. On the contrary, the lower the similarity, the larger the image deviation and the more serious the image deviation situation.

[0065] In one or more embodiments, after obtaining the license plate number of the vehicle entering and leaving the construction site, it further includes:

[0066] Determine whether the license plate number of the vehicle entering and leaving the construction site has the access permission. If so, allow the current vehicle to enter and leave; otherwise, refuse the current vehicle to enter and leave the construction site.

[0067] In one or more embodiments, when the vehicle is allowed to enter and leave the construction site, record the license plate number, entry and exit time, and entry and exit location of the vehicle; which is equivalent to generating a log of the vehicle entering and leaving the construction site for storage, facilitating subsequent viewing.

[0068] It can be seen that adopting the license plate recognition method for construction site vehicles provided in this embodiment has light robustness, can reduce the interference degree of outdoor light on the license plate number recognition work, avoid the influence of the difference in the captured image caused by unstable light on the recognition result, and is beneficial to improving the vehicle recognition accuracy under different light conditions; at the same time, it reduces the influence of the interference factor of soot on the recognition, enables the recognition technology to better apply to the vehicle recognition work on the construction site, is beneficial to maintaining the stability of the recognition technology, and improves the recognition effect.

[0069] The license plate recognition device for construction site vehicles provided by the present invention will be described below. The license plate recognition device for construction site vehicles described below can be referred to correspondingly with the license plate recognition method for construction site vehicles described above.

[0070] Figure 2 For the structural schematic diagram of the license plate recognition device for construction site vehicles provided by an embodiment of the present invention, please refer to Figure 2 As shown, the license plate recognition device includes:

[0071] An acquisition unit 201, configured to acquire the license plate image to be recognized of the vehicle entering and leaving the construction site.

[0072] A first processing unit 202, configured to perform image preprocessing on the license plate image to be recognized, and obtain the light intensity and soot concentration of the license plate image to be recognized.

[0073] A second processing unit 203, configured to obtain the image deviation information corresponding to the light intensity and soot concentration of the license plate image to be recognized.

[0074] A recognition unit 204, configured to correct the license plate number in the license plate image to be recognized according to the image deviation information, and obtain the license plate number of the vehicle entering and leaving the construction site.

[0075] In one or more embodiments, the first processing unit 202 is further specifically configured to:

[0076] Perform grayscale processing and binarization processing on the license plate image to be recognized, and obtain the light intensity and soot concentration of the license plate image to be recognized.

[0077] In one or more embodiments, the second processing unit 203 is further specifically configured to:

[0078] Obtain the correspondence between the light intensity and soot concentration and the image deviation information;

[0079] According to the correspondence between the light intensity and soot concentration and the image deviation information, obtain the image deviation information corresponding to the light intensity and soot concentration of the license plate image to be recognized.

[0080] In one or more embodiments, the second processing unit 203 is further specifically configured to:

[0081] Respectively obtain the reference license plate numbers of the reference license plate images under different light intensities and different soot concentrations;

[0082] Compare and analyze the reference license plate numbers and the correct license plate numbers under different light intensities and different soot concentrations, and obtain the correspondence between the light intensity and soot concentration and the image deviation information.

[0083] In one or more embodiments, the second processing unit 203 is further specifically configured to:

[0084] Integrate the feature data of the reference license plate numbers under different light intensities and different soot concentrations to obtain a feature data set of the reference license plate numbers;

[0085] Calculate the similarity values between the reference license plate numbers and the correct license plate numbers under different light intensities and different soot concentrations respectively to obtain the image deviation information between the reference license plate numbers and the correct license plate numbers;

[0086] Process the similarity values by using a normal distribution model to obtain the image deviation information corresponding to different light intensities and different soot concentrations.

[0087] Figure 3 An example of the physical structure diagram of an electronic device is shown as Figure 3 shown. The electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call the logical instructions in the memory 330 to execute the license plate recognition method for construction site vehicles, and the method includes: obtaining the license plate image to be recognized of the vehicle entering and leaving the construction site; performing image preprocessing on the license plate image to be recognized to obtain the light intensity and soot concentration of the license plate image to be recognized; obtaining the image deviation information corresponding to the light intensity and soot concentration of the license plate image to be recognized; correcting the license plate number in the license plate image to be recognized according to the image deviation information to obtain the license plate number of the vehicle entering and leaving the construction site.

[0088] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software function units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. And the aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0089] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the license plate recognition method for construction site vehicles provided by the above-mentioned various methods. The method includes: obtaining an image of the license plate to be recognized of a vehicle entering and leaving the construction site; performing image preprocessing on the image of the license plate to be recognized to obtain the light intensity and smoke and dust concentration of the image of the license plate to be recognized; obtaining image deviation information corresponding to the light intensity and smoke and dust concentration of the image of the license plate to be recognized; and correcting the license plate number in the image of the license plate to be recognized according to the image deviation information to obtain the license plate number of the vehicle entering and leaving the construction site.

[0090] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the license plate recognition method for construction site vehicles provided by the above-mentioned various methods. The method includes: obtaining an image of the license plate to be recognized of a vehicle entering and leaving the construction site; performing image preprocessing on the image of the license plate to be recognized to obtain the light intensity and smoke and dust concentration of the image of the license plate to be recognized; obtaining image deviation information corresponding to the light intensity and smoke and dust concentration of the image of the license plate to be recognized; and correcting the license plate number in the image of the license plate to be recognized according to the image deviation information to obtain the license plate number of the vehicle entering and leaving the construction site.

[0091] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0092] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A license plate recognition method for construction vehicles at a construction site, characterized in that, Including: Obtaining a license plate image to be recognized of a vehicle entering and leaving a construction site; Performing image preprocessing on the license plate image to be recognized to obtain the light intensity and soot concentration of the license plate image to be recognized; Respectively obtaining the reference license plate numbers of reference license plate images under different light intensities and different soot concentrations, integrating the feature data of the reference license plate numbers under different light intensities and different soot concentrations to obtain a feature data set of the reference license plate numbers, and respectively calculating the similarity values between the reference license plate numbers and the correct license plate numbers under different light intensities and different soot concentrations to obtain image deviation information between the reference license plate numbers and the correct license plate numbers; Processing the similarity values using a normal distribution model to obtain image deviation information corresponding to different light intensities and different soot concentrations; according to the corresponding relationship between the light intensity and soot concentration and the image deviation information, obtaining the image deviation information corresponding to the light intensity and soot concentration of the license plate image to be recognized; Correcting the license plate number in the license plate image to be recognized according to the image deviation information to obtain the license plate number of the vehicle entering and leaving the construction site.

2. The license plate recognition method for construction site vehicles according to claim 1, characterized in that, The performing image preprocessing on the license plate image to be recognized to obtain the light intensity and soot concentration of the license plate image to be recognized includes: Performing grayscale processing and binary processing on the license plate image to be recognized to obtain the light intensity and soot concentration of the license plate image to be recognized.

3. The license plate recognition method for construction site vehicles according to claim 1, wherein After obtaining the license plate number of the vehicle entering and leaving the construction site, it further includes: Determining whether the license plate number of the vehicle entering and leaving the construction site has the permission to enter and leave. If so, allowing the current vehicle to enter and leave.

4. The license plate recognition method for construction site vehicles according to claim 1, characterized in that, When the vehicle is allowed to enter and leave the construction site, recording the license plate number, entry and exit time, and entry and exit location of the vehicle.

5. A license plate recognition device for a construction vehicle at a construction site, characterized in that, Including: An obtaining unit for obtaining a license plate image to be recognized of a vehicle entering and leaving a construction site; A first processing unit for performing image preprocessing on the license plate image to be recognized to obtain the light intensity and soot concentration of the license plate image to be recognized; A second processing unit for obtaining the image deviation information corresponding to the light intensity and soot concentration of the license plate image to be recognized; An identifying unit for correcting the license plate number in the license plate image to be recognized according to the image deviation information to obtain the license plate number of the vehicle entering and leaving the construction site; Among them, obtaining the image deviation information corresponding to the illumination intensity and soot concentration of the license plate image to be recognized includes: respectively obtaining the reference license plate numbers of the reference license plate images under different illumination intensities and different soot concentrations, integrating the characteristic data of the reference license plate numbers under different illumination intensities and different soot concentrations, obtaining the characteristic data set of the reference license plate numbers, respectively calculating the similarity values between the reference license plate numbers and the correct license plate numbers under different illumination intensities and different soot concentrations, obtaining the image deviation information between the reference license plate numbers and the correct license plate numbers; processing the similarity values by using a normal distribution model to obtain the image deviation information corresponding to different illumination intensities and different soot concentrations; and obtaining the image deviation information corresponding to the illumination intensity and soot concentration of the license plate image to be recognized according to the corresponding relationship between the illumination intensity and soot concentration and the image deviation information.

6. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the license plate recognition method for construction site vehicles according to any one of claims 1 to 4.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the license plate recognition method for construction site vehicles according to any one of claims 1 to 4.

Images