Control management system of parking lot barrier gate

Abstract

The invention discloses a control management system for a parking lot barrier gate, belongs to the technical field of barrier gate management, and solves the problem that when an automobile returns to a parking lot from the outside, accumulated snow can cause that the barrier gate cannot be recognized, and finally the automobile is influenced to enter the parking lot. Comprising an image acquisition module, a heating module, a control module, a thermodynamic diagram acquisition module and a data processing module, the output end of the image acquisition module is in communication connection with the input end of the control module, the output end of the control module is coupled with the heating module, and the output end of the thermodynamic diagram acquisition module is coupled with the input end of the data processing module; the image acquisition module is used for acquiring a license plate image and feeding back the license plate image to the control module; the control module is used for identifying a part uncovered by snow on the license plate according to the license plate image fed back by the image acquisition module; whether the license plate is shielded by snow or not is judged through image recognition, if the license plate is shielded, the unshielded part is heated, the license plate thermodynamic diagram is obtained, and the license plate number is recognized.

Description

Technical Field

[0001] The present invention relates to the technical field of barrier gate management, and in particular to a control and management system for a parking lot barrier gate. Background Art

[0002] A parking lot is a special area for parking vehicles, usually with clear signs and designated parking spaces. According to the size and usage, parking lots can be divided into open-air parking lots and underground parking lots. Modern parking lots are generally equipped with intelligent management systems that can realize functions such as automatic charging, parking guidance and parking reservation to improve parking efficiency. It is an indispensable facility in urban traffic management, especially in commercial areas, residential areas and large public places, which can effectively solve parking needs and relieve traffic pressure.

[0003] The barrier used is an automated device commonly used in parking lots, toll booths, entrance and exit management, etc., mainly used to control the entry and exit of vehicles. It consists of electromechanical systems, controllers, infrared sensors and other parts, and restricts or allows vehicle passage by automatically lifting and lowering. The barrier can be equipped with different operating modes according to needs, such as card swiping, code scanning, license plate recognition, etc., to improve management efficiency and safety. With the development of intelligent technology, modern barrier systems are often equipped with remote monitoring, data analysis and other functions, and are widely used in urban transportation, property management and public facilities.

[0004] However, the barrier may encounter some rare situations in winter. For example, in winter, it rarely snows in southern cities, so it is rare for the license plate to be covered by snow and the barrier cannot recognize it. Although this phenomenon is more common in the north, in southern cities, if it snows and the snow covers the license plate of the car, especially when the car returns to the parking lot from outside, the snow will cause the barrier to be unable to recognize it, and ultimately affect the car's entry into the parking lot.

[0005] Therefore, a control and management system for a parking lot gate is proposed to solve or alleviate the above problems. Summary of the invention

[0006] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a control and management system for parking lot gates.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] A control and management system for a parking lot gate, comprising an image acquisition module, a heating module, a control module, a thermal map acquisition module, and a data processing module, wherein the output end of the image acquisition module is communicatively connected to the input end of the control module, the output end of the control module is coupled to the heating module, and the output end of the thermal map acquisition module is coupled to the input end of the data processing module;

[0009] The image acquisition module is used to acquire the license plate image and feed it back to the control module; the control module is used to identify the part of the license plate not covered by snow based on the license plate image fed back by the image acquisition module, and then control the heating module to heat the part of the license plate not covered by snow; the thermal acquisition module is used to acquire the thermal image of the heated license plate and feed it back to the data processing module; the data processing module is used to identify the specific license plate number based on the fed back thermal image.

[0010] Preferably, the image acquisition module includes a camera, and the camera is used to photograph the license plate and collect the license plate image and feed it back to the control module.

[0011] Preferably, the heating module comprises an infrared lamp and a steering gear, and the infrared lamp is fixedly connected to the movable end of the steering gear.

[0012] Preferably, the control module comprises a microcontroller, the microcontroller is coupled to the heating module via a relay, and an output end of the microcontroller is coupled to an input end of the steering gear.

[0013] Preferably, the control module is used to identify the part of the license plate not covered by snow according to the license plate image fed back by the image acquisition module, and then control the heating module to heat the part of the license plate not covered by snow, including the following steps:

[0014] Convert the license plate image to grayscale and perform Gaussian blur to complete preprocessing;

[0015] The preprocessed license plate image is subjected to the Canny edge detection algorithm to determine the edge of the entire license plate and obtain the license plate contour map;

[0016] The Otsu formula is used for adaptive segmentation to divide the license plate contour image into two parts: the snow-covered area and the license plate area. The Otsu formula is: Among them, N1(t) and N2(t) are the number of pixels of the two categories under the threshold t, μ1(t) and μ2(t) are the means of the two categories, σ b 2 (t) is the between-class variance, N is the total number of pixels;

[0017] The acquired license plate area is used as the portion of the license plate not covered by snow, Plate(x,y), and the heating module is controlled to heat the portion of the license plate not covered by snow.

[0018] Preferably, the thermal image acquisition module includes an infrared camera, which is used to collect thermal images of the heated license plate and feed them back to the data processing module.

[0019] Preferably, the data processing module is used to identify the specific license plate number according to the feedback thermal image, including the following steps:

[0020] Normalize the thermal image and convert it into a grayscale image;

[0021] By calculating the sum of pixels in each column of the grayscale image, a vertical projection of the grayscale image is obtained, and the vertical projection is used to locate the gaps between characters and segment each character;

[0022] Use a deep learning model to segment each character for character recognition;

[0023] The recognized characters are concatenated into a license plate number, and the specific license plate number is output.

[0024] Preferably, the normalization process of the thermal image to convert it into a grayscale image comprises the following steps:

[0025] Gaussian blur the thermal image.

[0026] Convert the Gaussian blurred thermal image into a grayscale image. gray (x,y)=0.2989·I r (x,y)+0.587·I g (x,y)+0.114·I b (x,y), where I r ,I g ,I b are the red, green, and blue channels of the thermal image, I gray (x,y) is a grayscale image.

[0027] Preferably, the step of obtaining a vertical projection image of the grayscale image by calculating the sum of pixels in each column of the grayscale image comprises the following steps:

[0028] Get the size of the grayscale image;

[0029] Set the threshold and binarize the grayscale image. Pixels greater than the threshold are output as 1, and pixels less than the threshold are output as 0.

[0030] The vertical projection value is calculated and the background is removed by the vertical projection formula, and the vertical projection formula is: Where w is the total number of pixels in each column;

[0031] The vertical projection image is obtained after removing the background.

[0032] Preferably, the step of using a deep learning model to perform character recognition on each segmented character comprises the following steps:

[0033] Input the vertical projection image and perform character classification and recognition through a deep learning model, wherein the deep learning model includes a convolutional neural network, and the convolutional layer calculation formula of the convolutional neural network is: Among them, I(x,y) is the vertical projection image of the input, W(i,j) is the convolution kernel, and I out (x,y) is the output image.

[0034] The present invention has the following beneficial effects:

[0035] The present invention can first perform image recognition to determine whether the license plate is blocked by snow. If not, the license plate number is directly identified. If so, the portion of the license plate not blocked by snow is found, and the heating module is controlled to work. The heating module heats the license plate not blocked by snow by infrared heating, and then obtains a thermal map of the license plate. The license plate number is identified through the image of the thermal map to avoid the situation where the license plate is covered by snow and cannot be identified. This allows the control management system to have a high license plate recognition accuracy rate, and even in such a rare situation, the license plate recognition action can still be performed. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] 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.

[0037] Figure 1 It is a structural block diagram of the present invention.

[0038] 1. Image acquisition module; 2. Control module; 3. Heating module; 4. Thermal map acquisition module; 5. Data processing module. DETAILED DESCRIPTION

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] A control and management system for parking lot gates, such as Figure 1 As shown, it includes an image acquisition module 1, a heating module 3, a control module 2, a thermal map acquisition module 4, and a data processing module 5, the output end of the image acquisition module 1 is communicatively connected to the input end of the control module 2, the output end of the control module 2 is coupled to the heating module 3, and the output end of the thermal map acquisition module 4 is coupled to the input end of the data processing module 5;

[0046] The image acquisition module 1 includes a camera, which is used to shoot the license plate and collect the license plate image and feed it back to the control module 2. The heating module 3 includes an infrared lamp and a steering gear. The infrared lamp is fixedly connected to the active end of the steering gear. The control module 2 includes a microcontroller, which is coupled to the heating module 3 through a relay, and the output end of the microcontroller is coupled to the input end of the steering gear. The thermal image acquisition module 4 includes an infrared camera, which is used to collect the thermal image of the heated license plate and feed it back to the data processing module 5.

[0047] The image acquisition module 1 is used to acquire the license plate image and feed it back to the control module 2; the control module 2 is used to identify the part of the license plate not covered by snow based on the license plate image fed back by the image acquisition module 1, and then control the heating module 3 to heat the part of the license plate not covered by snow; the thermal acquisition module is used to acquire the thermal image of the heated license plate and feed it back to the data processing module 5; the data processing module 5 is used to identify the specific license plate number based on the fed back thermal image.

[0048] The control module 2 is used to identify the part of the license plate not covered by snow according to the license plate image fed back by the image acquisition module 1, and then control the heating module 3 to heat the part of the license plate not covered by snow, including the following steps:

[0049] Convert the license plate image to grayscale and perform Gaussian blur to complete preprocessing;

[0050] The preprocessed license plate image is subjected to the Canny edge detection algorithm to determine the edge of the entire license plate and obtain the license plate contour map;

[0051] The Otsu formula is used for adaptive segmentation to divide the license plate contour into two parts: the snow-covered area and the license plate area. The Otsu formula is: Among them, N1(t) and N2(t) are the number of pixels of the two categories under the threshold t, μ1(t) and μ2(t) are the means of the two categories, σ b 2 (t) is the between-class variance, N is the total number of pixels;

[0052] The acquired license plate area is used as the portion of the license plate not covered by snow, Plate(x, y), and the heating module 3 is controlled to heat the portion of the license plate not covered by snow.

[0053] Preferably, the data processing module 5 is used to identify the specific license plate number according to the feedback thermal image, including the following steps:

[0054] Normalizing the thermal image and converting it into a grayscale image. Normalizing the thermal image and converting it into a grayscale image includes the following steps:

[0055] Gaussian blur the thermal image.

[0056] Convert the Gaussian blurred thermal image into a grayscale image. gray (x,y)=0.2989·I r (x,y)+0.587·I g (x,y)+0.114·I b (x,y), where I r ,I g ,I b are the red, green, and blue channels of the thermal image, I gray (x,y) is a grayscale image;

[0057] By calculating the sum of pixels in each column of the grayscale image, a vertical projection map of the grayscale image is obtained, and the vertical projection map is used to locate the gaps between characters and segment each character. By calculating the sum of pixels in each column of the grayscale image, a vertical projection map of the grayscale image is obtained, including the following steps:

[0058] Get the size of the grayscale image;

[0059] Set the threshold and binarize the grayscale image. Pixels greater than the threshold are output as 1, and pixels less than the threshold are output as 0.

[0060] The vertical projection value is calculated and the background is removed by the vertical projection formula. The vertical projection formula is: Where w is the total number of pixels in each column;

[0061] After removing the background, the vertical projection image is obtained;

[0062] For segmenting each character, a deep learning model is used to perform character recognition. For segmenting each character, a deep learning model is used to perform character recognition, including the following steps:

[0063] Input the vertical projection image and perform character classification and recognition through the deep learning model. The deep learning model includes a convolutional neural network. The convolutional layer calculation formula of the convolutional neural network is Among them, I(x,y) is the vertical projection image of the input, W(i,j) is the convolution kernel, and I out (x,y) is the output image;

[0064] The recognized characters are concatenated into a license plate number, and the specific license plate number is output.

[0065] Through the above system, the high accuracy of the license plate recognition system can be ensured when the vehicle's license plate is covered by snow.

[0066] First, the system processes the license plate image through image recognition technology to determine whether the license plate is blocked by snow. If the license plate is not covered by snow, the system will directly recognize the license plate number. However, if the license plate is blocked by snow, traditional recognition methods often cannot effectively recognize the license plate number. Therefore, the present invention requires subsequent steps.

[0067] In the case of snow cover, the system automatically detects the unobstructed part of the license plate and activates the heating module 3 through the control module 2. The heating module 3 heats the area not covered by snow by infrared heating, making the temperature difference in the heated area obvious. By collecting images of the heated license plate, the system can obtain a thermal map and then extract clear license plate information from the thermal map. The high temperature area on the thermal map corresponds to the part of the license plate not covered by snow. The system successfully identifies the license plate number by analyzing these image data.

[0068] This method avoids the loss of license plate information or recognition failure due to snow cover, and improves the license plate recognition capability in extreme weather conditions. Whether in the case of heavy snow or when the license plate is partially blocked, the system can still accurately complete the license plate recognition task through heating and thermal map recognition technology, thereby effectively improving the stability and reliability of the license plate recognition system.

[0069] Therefore, the present invention not only solves the special occlusion problem in license plate recognition, but also ensures that the system can maintain efficient operation in various complex environments, greatly improving the accuracy of license plate recognition and the overall performance of the system. This method can achieve fast and accurate license plate recognition under extreme weather conditions such as snowy days, providing strong technical support for practical applications.

[0070] 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 control and management system for parking lot gates, characterized in that: The invention comprises an image acquisition module (1), a heating module (3), a control module (2), a thermal map acquisition module (4), and a data processing module (5), wherein the output end of the image acquisition module (1) is communicatively connected to the input end of the control module (2), the output end of the control module (2) is coupled to the heating module (3), and the output end of the thermal map acquisition module (4) is coupled to the input end of the data processing module (5); The image acquisition module (1) is used to acquire a license plate image and feed it back to the control module (2); the control module (2) is used to identify the portion of the license plate not covered by snow based on the license plate image fed back by the image acquisition module (1), and then control the heating module (3) to heat the portion of the license plate not covered by snow; the thermal acquisition module is used to acquire a thermal image of the heated license plate and feed it back to the data processing module (5); the data processing module (5) is used to identify the specific license plate number based on the fed back thermal image.

2. A parking lot gate control and management system according to claim 1, characterized in that: The image acquisition module (1) comprises a camera, which is used to photograph the license plate and acquire the license plate image, and feed it back to the control module (2).

3. A parking lot gate control and management system according to claim 1, characterized in that: The heating module (3) comprises an infrared lamp and a steering gear, wherein the infrared lamp is fixedly connected to the movable end of the steering gear.

4. A parking lot gate control and management system according to claim 1, characterized in that: The control module (2) comprises a microcontroller, the microcontroller is coupled to the heating module (3) via a relay, and the output end of the microcontroller is coupled to the input end of the steering gear.

5. A parking lot gate control and management system according to claim 1, characterized in that: The control module (2) is used to identify the part of the license plate not covered by snow based on the license plate image fed back by the image acquisition module (1), and then control the heating module (3) to heat the part of the license plate not covered by snow, comprising the following steps: Convert the license plate image to grayscale and perform Gaussian blur to complete preprocessing; The preprocessed license plate image is subjected to the Canny edge detection algorithm to determine the edge of the entire license plate and obtain the license plate contour map; The Otsu formula is used for adaptive segmentation to divide the license plate contour image into two parts: the snow-covered area and the license plate area. The Otsu formula is: Among them, N1(t) and N2(t) are the number of pixels of the two categories under the threshold t, μ1(t) and μ2(t) are the means of the two categories, σ b 2 (t) is the between-class variance, N is the total number of pixels; The acquired license plate area is used as the portion of the license plate not covered by snow, Plate (x, y), and the heating module (3) is controlled to heat the portion of the license plate not covered by snow.

6. A parking lot gate control and management system according to claim 1, characterized in that: The thermal image acquisition module (4) comprises an infrared camera, which is used to acquire a thermal image of the heated license plate and feed it back to the data processing module (5).

7. A parking lot gate control and management system according to claim 1, characterized in that: The data processing module (5) is used to identify the specific license plate number according to the feedback thermal image, and comprises the following steps: Normalize the thermal image and convert it into a grayscale image; By calculating the sum of pixels in each column of the grayscale image, a vertical projection of the grayscale image is obtained, and the vertical projection is used to locate the gaps between characters and segment each character; Use a deep learning model to segment each character for character recognition; The recognized characters are concatenated into a license plate number, and the specific license plate number is output.

8. A parking lot gate control and management system according to claim 7, characterized in that: The normalization process of the thermal image to convert it into a grayscale image includes the following steps: Gaussian blur the thermal image. Convert the Gaussian blurred thermal image into a grayscale image. gray (x,y)=0.2989·I r (x,y)+0.587·I g (x,y)+0.114·I b (x,y), where I r ,I g ,I b are the red, green, and blue channels of the thermal image, I gray (x,y) is a grayscale image.

9. A parking lot gate control and management system according to claim 7, characterized in that: The vertical projection image of the grayscale image is obtained by calculating the sum of pixels in each column of the grayscale image, including the following steps: Get the size of the grayscale image; Set the threshold and binarize the grayscale image. Pixels greater than the threshold are output as 1, and pixels less than the threshold are output as 0. The vertical projection value is calculated and the background is removed by the vertical projection formula, and the vertical projection formula is: Where w is the total number of pixels in each column; The vertical projection image is obtained after removing the background.

10. A parking lot gate control and management system according to claim 7, characterized in that: The method of segmenting each character and using a deep learning model to perform character recognition includes the following steps: Input the vertical projection image and perform character classification and recognition through a deep learning model, wherein the deep learning model includes a convolutional neural network, and the convolutional layer calculation formula of the convolutional neural network is: Among them, I(x,y) is the vertical projection image of the input, W(i,j) is the convolution kernel, and I out (x,y) is the output image.

Images