Barrier gate license plate intelligent identification device

Abstract

The invention discloses intelligent identification equipment for a barrier gate license plate, belongs to the technical field of barrier gates, and solves the problem that no entrance record is caused due to the fact that a blue sticker is pasted on the license plate, then the original license plate number on the license plate is changed, and the blue sticker pasted on the license plate is uncovered when a user finally leaves a parking lot. Comprising a plurality of illumination modules, an image acquisition module and a data processing module, the plurality of illumination modules are used for irradiating license plates from different angles, the image acquisition module is used for shooting the license plates irradiated by the illumination modules and feeding back to the data processing module, and the image acquisition module is coupled with the data processing module. And the data processing module is used for receiving information from the image acquisition module, judging a license plate shielding position and estimating a real license plate number. Through illumination at different angles, the shielding position is marked by using the reflection difference, the license plate shielding condition is determined by comparing multiple images, the possible license plate number is deduced, and order evasion is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of barrier gates, and in particular to a barrier gate license plate intelligent recognition device. Background Art

[0002] The barrier is an intelligent device widely used in parking lots, residential areas, industrial parks and traffic management places. It is mainly used to control the passage of vehicles in and out. Its basic structure usually includes a control system, a transmission mechanism, a lever arm, a sensor and a power supply system. The barrier automatically starts when it senses the approach of a vehicle and controls the lifting and lowering of the lever arm, thereby achieving effective management of the vehicle. Modern barrier equipment is mostly equipped with an intelligent control system, which can be used in combination with a vehicle identification system (such as license plate recognition, card swiping, QR code scanning, etc.) to achieve unattended automatic management and improve traffic efficiency. The barrier can not only respond quickly during peak hours to avoid traffic jams, but also effectively improve the management accuracy and safety of parking lots. With the continuous development of technology, many barrier products have already been equipped with intelligent networking functions, which can monitor and analyze data in real time, providing users with more accurate management and operation decisions. In addition, modern barriers also have the characteristics of anti-collision, wind resistance, and low noise, which can adapt to various complex environments and high-frequency use needs, and are important facilities that are indispensable for modern traffic management.

[0003] However, currently when the barrier is recognizing license plates, due to the poor quality of some car owners, they are keen to evade the bill by sticking a blue sticker on the license plate, and then changing the original license plate number on the license plate. When they finally leave the parking lot, they peel off the blue sticker on the license plate, resulting in no entry record, thus completing the process of evading the bill. The current barrier does not have the function of identifying this situation.

[0004] Therefore, a barrier license plate intelligent recognition device is proposed to solve or alleviate the above problems. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a barrier license plate intelligent recognition device.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A barrier license plate intelligent recognition device includes a lighting module, an image acquisition module, and a data processing module. The number of the lighting modules is several, and the several lighting modules are used to illuminate the license plate from different angles. The image acquisition module is used to shoot the license plate illuminated by the lighting module and feed it back to the data processing module. The image acquisition module is coupled to the data processing module, and the data processing module is used to receive information from the image acquisition module, determine the license plate obstruction position, and estimate the real license plate number.

[0008] Preferably, the illumination module comprises an illumination lamp, and the illumination angles of several groups of the illumination modules are set differently.

[0009] Preferably, the image acquisition module includes a camera, and the camera is used to photograph the license plate illuminated by the illumination module, obtain the license plate image and feed it back to the data processing module.

[0010] Preferably, the data processing module is used to receive information from the image acquisition module, determine the license plate obstruction position, and estimate the real license plate number, including the following steps:

[0011] Shooting the license plate illuminated by the illumination module to obtain a license plate image;

[0012] Preprocess the license plate image to form a grayscale license plate image;

[0013] Use Sobel operator to perform edge detection to extract the license plate area;

[0014] Use the physical illumination model to detect occluders in the license plate area and locate the occluded area;

[0015] Image restoration is performed based on the characters in the occluded area and possible license plate number candidates are derived to estimate the real license plate number.

[0016] Preferably, the preprocessing of the license plate image to form a grayscale license plate image comprises the following steps:

[0017] Perform histogram equalization on the license plate image using a histogram equalization formula to obtain a histogram;

[0018] The histogram is grayed out through the cumulative distribution function, and its gray value is adjusted to obtain a grayscale license plate image.

[0019] Preferably, the histogram equalization formula includes Among them, h(x) is the license plate image, c(x) is the cumulative distribution function, and the grayscale license plate image includes Among them, c min is the minimum value of the histogram, and N is the total number of pixels.

[0020] Preferably, the Sobel operator performs edge detection to extract the license plate area, comprising the following steps:

[0021] The gradient intensity of the grayscale license plate image is calculated using the calculation formula of the Sobel operator. The calculation formula of the Sobel operator is: Among them, I is the grayscale license plate image, * is the convolution operation;

[0022] The license plate area is extracted using the region growing algorithm.

[0023] Preferably, the use of a physical illumination model to detect obstructions in the license plate area and locate the obstructed area comprises the following steps:

[0024] According to the physical illumination model, the occluder is detected by the reflection characteristics of the license plate. The physical illumination model is I = I0 × (k d (N×L)+k s (R×V) n ), where I is the reflected light intensity, I0 is the light source intensity, k d is the diffuse reflectance, k s is the specular reflection coefficient, N is the surface normal, L is the light source direction vector, R is the reflected light direction, V is the line of sight of the image acquisition module, and n is the reverse gloss index;

[0025] Based on the difference in reflection intensity under different lighting conditions, the image difference method is used to detect the boundary of the occlusion. If the gradient value of a certain area changes significantly, it can be inferred that the area is an occlusion area.

[0026] Preferably, the image restoration based on the characters in the blocked area and the derivation of possible license plate number candidates as the estimated real license plate number comprises the following steps:

[0027] Define the width w of each character, the character spacing s, the coordinates of the previous and next characters as x1 and x2, and determine the position of the characters in the occluded area as

[0028] Match characters by calculating the correlation of images through template matching, Corr(I1,I2)=∑ x,y I1(x,y)·I2(x,y), where I1 is the character template to be matched and I2 is the candidate region in the image;

[0029] For characters in the occluded area, an image restoration algorithm is used to restore the characters and obtain the license plate number candidate as an estimate of the real license plate number.

[0030] The present invention has the following beneficial effects:

[0031] The present invention illuminates at different angles. Since the materials of the obstructions covered by tape and the like and the license plate are different, the reflection conditions are different. Different marks are made at different reflective positions, and the marked positions of multiple pictures are compared to determine the marked positions. It is judged whether the license plate is obstructed, and the possible license plate number is deduced based on the existing characters at the obstructed position. In this way, the correct license plate number can be obtained to avoid the situation where the vehicle is escaped through the barrier. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 It is a structural block diagram of the present invention.

[0034] 1. Illumination module; 2. Image acquisition module; 3. Data processing module. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0036] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0038] In the description of the present invention, it should be understood that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or are the orientations or positional relationships in which the product of the invention is conventionally placed when in use, or are the orientations or positional relationships conventionally understood by those skilled in the art. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0039] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0040] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0041] A barrier license plate intelligent recognition device, such as Figure 1 As shown, it includes an illumination module 1, an image acquisition module 2, and a data processing module 3. There are several illumination modules 1, and the several illumination modules 1 are used to illuminate the license plate from different angles. The image acquisition module 2 is used to shoot the license plate illuminated by the illumination module 1 and feed it back to the data processing module 3. The image acquisition module 2 is coupled to the data processing module 3. The data processing module 3 is used to receive information from the image acquisition module 2, determine the license plate occlusion position, and estimate the real license plate number.

[0042] The present invention uses the characteristics of light reflection on the license plate to identify the license plate information by illuminating the license plate from multiple different angles. Since the material of the license plate and the possible covering obstructions (such as tape, etc.) are different, their reflection of light will also be different. By analyzing the reflection intensity and distribution of different positions of the license plate, the present invention can accurately calibrate the reflection difference and then identify the reflection position. By comparing the reflective mark information in multiple images, the specific position of the reflective area and the obstruction can be effectively confirmed. Through this process, the system can determine whether the license plate has partial obstruction, and infer the possible license plate number based on the existing characters in the obstruction area.

[0043] This method can solve the problem that traditional license plate recognition systems cannot accurately identify license plate numbers under obstruction conditions, especially when the obstruction is obvious or the reflection is uneven. The license plate number can still be effectively identified. In addition, by comparing the positions of reflective marks at different angles, the system can further improve the recognition accuracy and avoid recognition failure or bill escape due to partial obstruction of the license plate. Ultimately, this technology ensures that the parking lot gate system can accurately record and identify license plate numbers, effectively preventing the occurrence of bill escape and missed orders, and improving the efficiency and safety of parking management.

[0044] Preferably, the illumination module 1 comprises an illumination lamp, and the illumination angles of several groups of illumination modules 1 are set differently.

[0045] The different illumination angles of the plurality of illumination modules 1 can illuminate the license plate at multiple angles, so that the portion of the license plate with tape and the portion without tape can be distinguished by the reflection, which is convenient for the recognition device to recognize.

[0046] Preferably, the image acquisition module 2 includes a camera, which is used to photograph the license plate illuminated by the illumination module 1 , obtain the license plate image and feed it back to the data processing module 3 .

[0047] By setting a camera, the license plate illuminated by the illumination module 1 can be photographed, so as to obtain an image of the license plate where reflection occurs.

[0048] Preferably, the data processing module 3 is used to receive information from the image acquisition module 2, determine the license plate occlusion position, and estimate the real license plate number, including the following steps:

[0049] Shooting the license plate illuminated by the illumination module 1 to obtain a license plate image;

[0050] Preprocess the license plate image to form a grayscale license plate image;

[0051] Use Sobel operator to perform edge detection to extract the license plate area;

[0052] Use the physical illumination model to detect occluders in the license plate area and locate the occluded area;

[0053] Image restoration is performed based on the characters in the occluded area and possible license plate number candidates are derived to estimate the real license plate number.

[0054] Through the above steps, after the data processing module 3 receives the license plate illuminated by the shooting illumination module 1 and obtains the license plate image, the license plate image can be processed, and then the license plate area in the license plate image is extracted, and the part where the reflection occurs in the license plate area is detected, and then the characters at that place are repaired, and multiple real license plate numbers are estimated. If a license plate of a vehicle that has escaped the bill appears, the vehicle with that license plate can be required to pay.

[0055] Preferably, preprocessing the license plate image to form a grayscale license plate image includes the following steps:

[0056] Perform histogram equalization on the license plate image using a histogram equalization formula to obtain a histogram;

[0057] The histogram is grayed out through the cumulative distribution function, and its gray value is adjusted to obtain a grayscale license plate image.

[0058] Through the above steps, the preprocessing of the license plate image can be achieved, and a grayscale license plate image can be formed, so that the grayscale license plate image can be suitable for subsequent recognition actions.

[0059] Preferably, the histogram equalization formula includes Among them, h(x) is the license plate image, c(x) is the cumulative distribution function, and the grayscale license plate image includes Among them, c min is the minimum value of the histogram, and N is the total number of pixels.

[0060] Through the above algorithm formula, the histogram equalization processing of the license plate image can be achieved, which is convenient for subsequent recognition actions.

[0061] Preferably, the Sobel operator performs edge detection to extract the license plate area, including the following steps: calculating the gradient intensity of the grayscale license plate image by the calculation formula of the Sobel operator, and the calculation formula of the Sobel operator is: Among them, I is the grayscale license plate image, * is the convolution operation;

[0062] The license plate area is extracted using the region growing algorithm.

[0063] In the above steps, the license plate area is extracted by performing edge detection using the Sobel operator, so that the license plate area can be extracted from the license plate image.

[0064] Preferably, a physical illumination model is used to detect the occluder in the license plate area and locate the occluded area, including the following steps:

[0065] According to the physical illumination model, the occluder is detected by the reflection characteristics of the license plate. The physical illumination model is I = I0 × (k d (N×L)+k s (R×V) n ), where I is the reflected light intensity, I0 is the light source intensity, k d is the diffuse reflectance, k s is the specular reflection coefficient, N is the surface normal, L is the light source direction vector, R is the reflected light direction, V is the sight direction of the image acquisition module 2, and n is the reverse gloss index;

[0066] Based on the difference in reflection intensity under different lighting conditions, the image difference method is used to detect the boundary of the occlusion. If the gradient value of a certain area changes significantly, it can be inferred that the area is an occlusion area.

[0067] Through the above steps, the physical illumination model is used to detect the occluders in the license plate area, thereby determining the position of the characters on the license plate where the tape is pasted to modify the characters as the occluded area, so that the characters in the occluded area can be repaired later.

[0068] Preferably, performing image restoration based on the characters in the blocked area and deriving possible license plate number candidates as estimated real license plate numbers includes the following steps:

[0069] Define the width w of each character, the character spacing s, the coordinates of the previous and next characters as x1 and x2, and determine the position of the characters in the occluded area as

[0070] Match characters by calculating the correlation of images through template matching, Corr(I1,I2)=∑ x,y I1(x,y)·I2(x,y), where I1 is the character template to be matched and I2 is the candidate region in the image;

[0071] For characters in the occluded area, an image restoration algorithm is used to restore the characters and obtain the license plate number candidate as an estimate of the real license plate number.

[0072] Through the above steps, the characters on the license plate modified by the tape can be repaired by the image repair algorithm, and multiple estimated real license plate numbers can be derived for verification when the subsequent vehicle leaves.

[0073] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A barrier license plate intelligent recognition device, characterized in that: The invention comprises an illumination module (1), an image acquisition module (2), and a data processing module (3); the illumination modules (1) are provided in a plurality, the plurality of illumination modules (1) being used to illuminate a license plate from different angles; the image acquisition module (2) being used to photograph the license plate illuminated by the illumination module (1) and feed the photographs back to the data processing module (3); the image acquisition module (2) being coupled to the data processing module (3); and the data processing module (3) being used to receive information from the image acquisition module (2), determine the occlusion position of the license plate, and estimate the real license plate number.

2. The intelligent license plate recognition device for a barrier gate according to claim 1 is characterized in that: The illumination module (1) comprises an illumination lamp, and the illumination angles of a plurality of groups of the illumination modules (1) are set differently.

3. The intelligent license plate recognition device for a barrier gate according to claim 1 is characterized in that: The image acquisition module (2) comprises a camera, which is used to photograph the license plate illuminated by the illumination module (1), obtain a license plate image and feed it back to the data processing module (3).

4. The intelligent license plate recognition device for a barrier gate according to claim 1 is characterized in that: The data processing module (3) is used to receive information from the image acquisition module (2), determine the license plate obstruction position, and estimate the real license plate number, including the following steps: photographing the license plate illuminated by the illumination module (1) to obtain a license plate image; Preprocess the license plate image to form a grayscale license plate image; Use the Sobel operator to perform edge detection to extract the license plate area; Use the physical illumination model to detect occluders in the license plate area and locate the occluded area; Image restoration is performed based on the characters in the occluded area and possible license plate number candidates are derived to estimate the real license plate number.

5. The intelligent license plate recognition device for a barrier gate according to claim 4 is characterized in that: The method of preprocessing the license plate image to form a grayscale license plate image comprises the following steps: Perform histogram equalization on the license plate image using a histogram equalization formula to obtain a histogram; The histogram is grayed out through the cumulative distribution function, and its gray value is adjusted to obtain a grayscale license plate image.

6. The intelligent license plate recognition device for a barrier gate according to claim 5 is characterized in that: The histogram equalization formula includes Among them, h(x) is the license plate image, c(x) is the cumulative distribution function, and the grayscale license plate image includes Among them, c min is the minimum value of the histogram, and N is the total number of pixels.

7. The intelligent license plate recognition device for a barrier gate according to claim 4 is characterized in that: The Sobel operator performs edge detection to extract the license plate area, including the following steps: The gradient intensity of the grayscale license plate image is calculated using the calculation formula of the Sobel operator. The calculation formula of the Sobel operator is: Among them, I is the grayscale license plate image, * is the convolution operation; The license plate area is extracted using the region growing algorithm.

8. The intelligent license plate recognition device for a barrier gate according to claim 4 is characterized in that: The method of using a physical illumination model to detect an obstruction in the license plate area and locate the obstruction area includes the following steps: According to the physical illumination model, the occluder is detected by the reflection characteristics of the license plate. The physical illumination model is I = I0 × (k d (N×L)+k s (R×V) n ), where I is the reflected light intensity, I0 is the light source intensity, k d is the diffuse reflectance, k s is the specular reflection coefficient, N is the surface normal, L is the light source direction vector, R is the reflected light direction, V is the sight direction of the image acquisition module (2), and n is the reverse gloss index; Based on the difference in reflection intensity under different lighting conditions, the image difference method is used to detect the boundary of the occlusion. If the gradient value of a certain area changes significantly, it can be inferred that the area is an occlusion area.

9. The intelligent license plate recognition device for a barrier gate according to claim 4 is characterized in that: The method of performing image restoration based on the characters in the blocked area and deriving possible license plate number candidates as estimated real license plate numbers includes the following steps: Define the width w of each character, the character spacing s, the coordinates of the previous and next characters as x1 and x2, and determine the position of the characters in the occluded area as Match characters by calculating the correlation of images through template matching, Corr(I1,I2)=∑ x,y I1(x,y)·I2(x,y), where I1 is the character template to be matched and I2 is the candidate region in the image; For characters in the occluded area, an image restoration algorithm is used to restore the characters and obtain the license plate number candidate as an estimate of the real license plate number.

Images