A method and device for vehicle speeding warning

Abstract

This application belongs to the field of vehicle speed measurement and intelligent monitoring technology, specifically disclosing a method and device for issuing vehicle speeding warnings. This application uses image processing techniques such as adaptive inverse perspective transformation and preprocessing to detect vehicle speed, avoiding the need for extensive dataset annotation and improving the real-time performance of vehicle speed detection. By accurately locating the license plate area and combining it with the centroid position of the license plate area, the accuracy of vehicle speed detection is improved. By issuing speeding warnings when a vehicle is determined to be speeding, timely intervention can be achieved to prevent traffic accidents.

Description

Technical Field

[0001] This application belongs to the field of vehicle speed measurement and intelligent monitoring technology, and more specifically, relates to a method and device for vehicle overspeed warning. Background Technology

[0002] With roads becoming smoother and wider, the problem of speeding has become increasingly serious, posing a significant threat to people's personal safety. Therefore, effective measures are needed to monitor vehicle speeds in real time to prevent traffic accidents.

[0003] Road video surveillance is characterized by its simple installation, convenient maintenance, wide monitoring range, and good compatibility. Based on these advantages, video detection technology has developed rapidly in the field of vehicle speed detection. Currently, there are two main schemes for video-based vehicle speed detection: virtual coils and target tracking-based methods. Virtual coils detect vehicle speed by placing virtual coils on the road instead of real ground induction coils. However, this method is limited by the time sampling characteristics of the camera, resulting in larger speed measurement errors and poor anti-interference capabilities. Target tracking-based methods calculate the current vehicle speed by determining the displacement from the coordinate changes of vehicle feature points after camera calibration. With the development of deep learning, there are increasingly more detection methods using neural networks. However, these methods often require large datasets, and the balance between real-time performance and accuracy needs improvement.

[0004] Solving the problem of frequent traffic accidents caused by poor real-time performance and accuracy of vehicle speed measurement is an urgent issue that needs to be addressed. Summary of the Invention

[0005] In view of the shortcomings of the prior art, the purpose of this application is to provide a vehicle speeding warning method and device, which aims to solve the problem of frequent traffic accidents caused by the poor real-time performance and accuracy of vehicle speed measurement in the prior art.

[0006] To achieve the above objectives, in a first aspect, this application provides a method for issuing a vehicle speeding warning, comprising:

[0007] Acquire consecutive frame images corresponding to the vehicle's surveillance video;

[0008] An adaptive inverse perspective transformation is performed on consecutive frames of images to obtain a corrected image set;

[0009] Preprocess the images in the corrected image set to obtain the license plate region;

[0010] Based on the centroid of the license plate area, the vehicle speed is obtained, and it is determined whether the vehicle speed exceeds a first preset value. If so, an overspeed warning is issued to the vehicle.

[0011] In some embodiments, an adaptive inverse perspective transformation is performed on consecutive frame images to obtain a corrected image set, including:

[0012] Based on the pitch angle, tilt angle, vertical field of view, horizontal field of view, width and height of consecutive frame images of the image acquisition device used to collect surveillance video, an adaptive inverse perspective transformation is performed on the consecutive frame images to obtain a corrected image set.

[0013] In some embodiments, the images in the corrected image set are preprocessed to obtain the license plate region, including:

[0014] Preprocessing is performed on the images in the corrected image set, including Gaussian filtering, opening and closing operations, and edge detection, to obtain the preprocessed images;

[0015] The license plate area is obtained based on the preprocessed image.

[0016] In some embodiments, preprocessing is performed on the images in the corrected image set, including Gaussian filtering, opening and closing operations, and edge detection, to obtain the preprocessed images, including:

[0017] Gaussian smoothing is used to remove noise from the images in the corrected image set to obtain the first image;

[0018] The first image is converted to a grayscale image using a weighted average method, and the opening operation in mathematical morphology is used to eliminate the effect of bright spots in the grayscale image to obtain the second image.

[0019] The Sobel operator is used to perform edge detection on the second image to obtain the gradient magnitude, and pixels with gradient magnitudes greater than a second preset value are set as edge points to obtain the third image;

[0020] The third image is processed using opening and closing operations to fill the closed region enclosed by the edge lines formed by the edge points, resulting in a preprocessed image.

[0021] In some embodiments, the license plate region is obtained based on the preprocessed image, including:

[0022] Based on the basic information of the vehicle's license plate, the license plate area is selected from the preprocessed image.

[0023] In some embodiments, the vehicle speed is obtained based on the centroid of the license plate region, including:

[0024] The vehicle speed is obtained based on the first centroid, the second centroid, and the time interval between adjacent frames in the corrected image set, corresponding to the license plate region.

[0025] Secondly, this application provides a vehicle overspeed warning device, comprising:

[0026] The first processing module is used to acquire continuous frame images corresponding to the vehicle's surveillance video.

[0027] The second processing module is used to perform adaptive inverse perspective transformation on consecutive frame images to obtain a corrected image set.

[0028] The third processing module is used to preprocess the images in the corrected image set to obtain the license plate area;

[0029] The alarm notification module is used to obtain the vehicle speed based on the centroid of the license plate area and determine whether the vehicle speed exceeds a first preset value. If so, an overspeed alarm notification is issued to the vehicle.

[0030] Thirdly, this application provides an electronic device, comprising: at least one memory for storing a program; and at least one processor for executing the program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to execute the vehicle overspeed warning method described in the first aspect or any of the embodiments of the first aspect.

[0031] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to execute the vehicle overspeed warning method described in the first aspect or any of the embodiments of the first aspect.

[0032] Fifthly, this application provides a computer program product that, when run on a processor, causes the processor to execute the vehicle overspeed warning notification method described in the first aspect or any of the embodiments of the first aspect.

[0033] Overall, the technical solutions conceived in this application have the following beneficial effects compared with the prior art:

[0034] This application provides a vehicle speeding warning method and apparatus. By employing image processing techniques such as adaptive inverse perspective transformation and preprocessing, it detects vehicle speed, avoiding the need for extensive dataset annotation and improving the real-time performance of vehicle speed detection. Accurately locating the license plate area and combining it with the centroid position of the license plate area allows for precise measurement of vehicle speed, further enhancing the accuracy of speed detection. By issuing speeding warnings when a vehicle is determined to be speeding, timely intervention can be achieved to prevent traffic accidents. Attached Figure Description

[0035] Figure 1This is one of the flowcharts illustrating the vehicle overspeed warning method provided in this application embodiment;

[0036] Figure 2 This is a second schematic flowchart of the vehicle overspeed warning method provided in the embodiments of this application;

[0037] Figure 3 This is a schematic diagram of the vehicle overspeed warning device provided in the embodiments of this application;

[0038] Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0040] In this article, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The symbol " / " in this article indicates that the related objects are in an "or" relationship; for example, A / B means A or B.

[0041] The terms "first" and "second," etc., used in the specification and claims herein are used to distinguish different objects, not to describe a specific order of objects. For example, "first preset value" and "second preset value," etc., are used to distinguish different preset values, not to describe a specific order of preset values.

[0042] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0043] In the description of the embodiments in this application, unless otherwise stated, "multiple" means two or more.

[0044] This application provides a method for vehicle speeding warning, which uses the center point of the license plate as a feature point and applies adaptive inverse perspective transformation to the continuous frame images corresponding to the monitoring video. It can calculate the vehicle speed and determine whether the vehicle is speeding by combining the positional relationship of the feature points in the video frame, thus realizing intervention for speeding vehicles.

[0045] The embodiments of this application are described below with reference to the accompanying drawings.

[0046] See Figure 1 This application provides a method for issuing a vehicle speeding warning, which may include steps 110 to 140.

[0047] Step 110: Obtain consecutive frame images corresponding to the vehicle's surveillance video;

[0048] Step 120 performs adaptive inverse perspective transformation on consecutive frame images to obtain the corrected image set;

[0049] Step 130 involves preprocessing the images in the corrected image set to obtain the license plate area;

[0050] Step 140: Based on the centroid of the license plate area, obtain the vehicle speed and determine whether the vehicle speed exceeds the first preset value. If so, issue an overspeed warning to the vehicle.

[0051] In practice, the vehicle's surveillance video can be collected through an imaging device, which can be a monocular camera, a high-precision camera, or the like.

[0052] By performing frame-by-frame conversion on the vehicle monitoring video captured by the imaging device, the corresponding continuous frame images are obtained.

[0053] An adaptive inverse perspective transformation is performed on the images at each frame time corresponding to the continuous frame images to correct the images at each frame time, resulting in an image set composed of the corrected images at each frame time, i.e., the corrected image set.

[0054] The images at each frame time in the obtained corrected image set are preprocessed, including noise removal, region filling and edge recognition, and the license plate region in the preprocessed image is identified.

[0055] The center position of the license plate region in each preprocessed image is identified and used as the centroid of the license plate region. Based on this centroid, the displacement of the vehicle at adjacent frame times can be calculated, and the vehicle's speed can be calculated based on this displacement.

[0056] Determine whether the vehicle's speed exceeds a first preset value, and if it is determined that the vehicle's speed exceeds the first preset value, issue an overspeed warning to the vehicle.

[0057] In this embodiment of the application, the first preset value may be a speed threshold set according to the speed limit indication on the road where the vehicle is traveling.

[0058] This application provides a vehicle speeding warning method that uses image processing techniques such as adaptive inverse perspective transformation and preprocessing to detect vehicle speed, avoiding the need for extensive dataset annotation and improving the real-time performance of vehicle speed detection. By accurately locating the license plate area and combining it with the centroid position of the license plate area, the method accurately measures the vehicle speed, further enhancing the accuracy of speed detection. By issuing speeding warnings when a vehicle is determined to be speeding, timely intervention can be achieved to prevent traffic accidents.

[0059] Furthermore, in some embodiments, step 120, performing an adaptive inverse perspective transformation on consecutive frame images to obtain a corrected image set, may include:

[0060] Based on the pitch angle, tilt angle, vertical field of view, horizontal field of view, width and height of consecutive frame images of the image acquisition device used to collect surveillance video, an adaptive inverse perspective transformation is performed on the consecutive frame images to obtain a corrected image set.

[0061] In this embodiment, the following adaptive inverse perspective transformation formula is used to perform adaptive inverse perspective transformation on the images at each frame time corresponding to the above consecutive frame images, to obtain the corrected image set:

[0062]

[0063]

[0064] In the formula, θ p θ0 is the tilt angle of the imaging device (such as a monocular camera) used to collect surveillance video, and α is the tilt angle of the imaging device. r α is half the vertical field of view of the imaging device. c The horizontal field of view of the imaging device is half of the horizontal field of view, m is the width of the continuous frame image, n is the height of the continuous frame image, X and Y are the horizontal and vertical coordinates after adaptive inverse perspective transformation, u and v are the horizontal and vertical coordinates of the pixels in the continuous frame image, and h is the height of the imaging device from the ground.

[0065] This application provides a method for vehicle speeding warning, which performs adaptive inverse perspective transformation on continuous frame images based on the internal and external parameters of the imaging device to locate the centroid of the license plate area, thereby accurately obtaining the vehicle's displacement and enabling timely intervention in the monitoring of speeding vehicles.

[0066] Furthermore, in some embodiments, the preprocessing of the images in the corrected image set in step 130 to obtain the license plate region may include:

[0067] Preprocessing is performed on the images in the corrected image set, including Gaussian filtering, opening and closing operations, and edge detection, to obtain the preprocessed images;

[0068] The license plate area is obtained based on the preprocessed image.

[0069] In the specific implementation, noise removal is achieved by applying Gaussian filtering to the images in the corrected image set. Region filling is achieved by performing opening and closing operations on the noise-removed images. Edge detection is then performed on the region-filled images to complete the preprocessing of the images in the corrected image set, resulting in the preprocessed images.

[0070] Based on the obtained preprocessed image, the license plate area is located.

[0071] Furthermore, in some embodiments, preprocessing, including Gaussian filtering, opening and closing operations, and edge detection, is performed on the images in the corrected image set to obtain preprocessed images, including:

[0072] Gaussian smoothing is used to remove noise from the images in the corrected image set to obtain the first image;

[0073] The first image is converted to a grayscale image using a weighted average method, and the opening operation in mathematical morphology is used to eliminate the effect of bright spots in the grayscale image to obtain the second image.

[0074] The Sobel operator is used to perform edge detection on the second image to obtain the gradient magnitude, and pixels with gradient magnitudes greater than a second preset value are set as edge points to obtain the third image;

[0075] The third image is processed using opening and closing operations to fill the closed region enclosed by the edge lines formed by the edge points, resulting in a preprocessed image.

[0076] In this embodiment of the application, the preprocessed image is obtained by performing noise removal, grayscale conversion, mathematical morphology processing, edge detection and connection on the images in the corrected image set.

[0077] Specifically, noise removal employs Gaussian smoothing, which is calculated based on the distance between each pixel in the corrected image set and the center point. The formula is as follows:

[0078]

[0079] In the formula, g(x,y) is the output value of the Gaussian function, x and y are the horizontal and vertical coordinates of the pixels in the corrected image set, respectively, and σ is the set standard deviation. In this embodiment, the Gaussian smoothing weight matrix corresponding to σ = 0.95 is:

[0080] After removing noise from the images in the corrected image set using Gaussian smoothing, the resulting image is the first image, which is a color image.

[0081] The first image is converted to a grayscale image using a weighted average method, as shown in the following formula:

[0082] Gray=0.299*R+0.587*G+0.144*B;

[0083] In the formula, R, G, and B are the values ​​of the red, green, and blue channels in the first image, respectively, and Gray is the calculated grayscale value.

[0084] The opening operation in mathematical morphology is used to eliminate the effect of bright spots in the grayscale image, and the resulting image is the second image.

[0085] The Sobel operator is used to perform edge detection on the second image. The convolution operator template is as follows:

[0086]

[0087]

[0088] In the formula, Δ x f and Δ y f represents the horizontal and vertical gradients of the pixels in the second image, respectively, and P represents the gradient magnitude.

[0089] The gradient magnitude P is compared with a second preset value. When the gradient magnitude is greater than the second preset value, the pixel in the second image is set as an edge point. By traversing each pixel in the second image, the edge image, i.e., the third image, is obtained.

[0090] The third processing step involves using opening and closing operations to fill the closed region enclosed by the edge lines formed by the aforementioned edge points. The resulting image is the preprocessed image.

[0091] In this embodiment, Gaussian filtering, opening and closing operations, and the Sobel operator are comprehensively applied. By calculating the centroid position of the license plate and its moving distance, the vehicle speed is calculated in real time and the overspeed alarm system is triggered. This makes vehicle overspeed detection simpler and more efficient, with strong adaptability and low deployment cost.

[0092] This application provides a vehicle speeding warning method that, by preprocessing the images in the corrected image set, can to some extent eliminate the impact of image quality degradation caused by factors such as shooting quality, vehicle speed, and lighting conditions, thereby improving the positioning accuracy of the license plate area.

[0093] Furthermore, in some embodiments, the above steps, based on the preprocessed image, to obtain the license plate region, include:

[0094] Based on the basic information of the vehicle's license plate, the license plate area is selected from the preprocessed image.

[0095] In practice, the license plate area is coarsely located and finely filtered based on the vehicle's basic license plate information to obtain the final license plate area. In this embodiment, the basic vehicle information may specifically include the license plate shape (e.g., length, width, and height) and color.

[0096] (1) Rough location of license plate:

[0097] The process involves identifying all possible rectangular regions in the preprocessed image that could be license plates. These regions are then validated based on the fixed size and aspect ratio of the license plates to filter out candidate regions. Specifically, considering that the aspect ratio of blue and yellow license plates for common motor vehicles is 3.14, and that of green license plates for new energy vehicles is 3.42, the aspect ratio of the rectangular regions suspected to be license plates should be between 2.5 and 4.5. Rectangular regions that do not meet these requirements are then excluded, resulting in the candidate regions.

[0098] (2) Fine-tuning of license plates:

[0099] The candidate areas are carefully screened, and non-license plate areas that do not meet the conditions are excluded based on the background color of the license plate (usually yellow, green and blue), thus obtaining the final license plate area.

[0100] The rough location of license plates mainly considers the shape of the license plate, and locates the rectangular area of ​​the suspected license plate based on the length and width ratio of the license plate; while the precise screening is to judge the color of the suspected area to further filter out the license plates.

[0101] Furthermore, in some embodiments, obtaining the vehicle speed based on the centroid of the license plate region in step 140 may include:

[0102] The vehicle speed is obtained based on the first centroid, the second centroid, and the time interval between adjacent frames in the corrected image set, corresponding to the license plate region.

[0103] In practice, the centroid of the license plate region in the image set after localization and correction is located. The vehicle speed can be calculated by subtracting the centroid positions of the license plate region in the previous frame and the next frame and dividing by the time interval between the two frames.

[0104] For example, assuming the centroid coordinates of the license plate region at adjacent frame times in a continuous frame image are (x1, y1) and (x2, y2) respectively, after applying adaptive inverse perspective transformation, substituting (x1, y1) and (x2, y2) into (u, v) in the above adaptive inverse perspective transformation formula yields centroid coordinates of (x1′, y1′) and (x2′, y2′) respectively. Assuming the time interval between adjacent frame times is t, the vehicle speed can be calculated based on the following formula:

[0105]

[0106] In the formula, V is the vehicle's speed, and s is the displacement of the centroid of the vehicle's license plate area at adjacent frame times.

[0107] When the vehicle speed exceeds the first preset value, it is considered that the vehicle has exceeded the speed limit, and the alarm of the work area monitoring will sound to give an alarm.

[0108] In practical applications, such as Figure 2 As shown in the embodiment of this application, a method for providing a vehicle speeding warning includes:

[0109] Step 1: Obtain consecutive frame images corresponding to the surveillance video to be detected;

[0110] Step two involves obtaining the corrected image set through adaptive inverse perspective transformation;

[0111] Step 3 involves noise removal, grayscale conversion, mathematical morphology processing, edge detection, and concatenation of the images in the corrected image set to obtain the preprocessed image.

[0112] Step four involves locating the license plate region in the preprocessed image;

[0113] Step 5: Calculate the vehicle's speed based on the centroid of the license plate area and determine if the vehicle is speeding. If it is speeding, an alarm will sound in the work area to remind the driver.

[0114] This application provides a method for issuing a vehicle speeding warning. When a vehicle's speed exceeds a preset value, it is determined that the vehicle is speeding, and an alarm is sounded to warn the speeding vehicle, thereby improving vehicle driving safety.

[0115] The vehicle overspeed warning device provided in this application is described below. The vehicle overspeed warning device described below and the vehicle overspeed warning device method described above can be referred to in correspondence.

[0116] See Figure 3This application provides a vehicle speeding warning device, which may include: a first processing module 310, a second processing module 320, a third processing module 330, and a warning module 340.

[0117] The first processing module 310 is used to acquire continuous frame images corresponding to the vehicle's monitoring video.

[0118] The second processing module 320 is used to perform adaptive inverse perspective transformation on consecutive frame images to obtain a corrected image set.

[0119] The third processing module 330 is used to preprocess the images in the corrected image set to obtain the license plate area;

[0120] The alarm module 340 is used to obtain the vehicle speed based on the centroid of the license plate area and determine whether the vehicle speed exceeds a first preset value. If so, it will issue an overspeed alarm to the vehicle.

[0121] This application provides a vehicle speeding warning device that uses adaptive inverse perspective transformation and preprocessing image processing techniques to detect vehicle speed, avoiding the need for extensive dataset annotation and improving the real-time performance of vehicle speed detection. By accurately locating the license plate area and combining it with the centroid position of the license plate area, the device accurately measures the vehicle speed, further enhancing the accuracy of speed detection. By issuing speeding warnings when a vehicle is determined to be speeding, timely intervention can be achieved to prevent traffic accidents.

[0122] It is understood that the detailed functional implementation of each of the above units / modules can be found in the description in the aforementioned method embodiments, and will not be repeated here.

[0123] It should be understood that the above-described device is used to execute the methods in the above embodiments. The implementation principle and technical effect of the corresponding program modules in the device are similar to those described in the above methods. The working process of the device can be referred to the corresponding process in the above methods, and will not be repeated here.

[0124] Based on the methods in the above embodiments, this application provides an electronic device, see [link to relevant documentation]. Figure 4 The electronic device may include a processor 410, a communications interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communications interface 420, and the memory 430 communicate with each other via the communication bus 440. The processor 410 may call logical instructions in the memory 430 to execute the methods described in the above embodiments.

[0125] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0126] Based on the methods in the above embodiments, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to execute the methods in the above embodiments.

[0127] Based on the methods in the above embodiments, this application provides a computer program product that, when run on a processor, causes the processor to execute the methods in the above embodiments.

[0128] It is understood that the processor in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0129] The method steps in this application embodiment can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can reside in an ASIC.

[0130] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0131] It is understood that the various numerical designations used in the embodiments of this application are merely for the convenience of description and are not intended to limit the scope of the embodiments of this application.

[0132] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for issuing a vehicle speeding warning, characterized in that, include: Acquire consecutive frame images corresponding to the vehicle's surveillance video; An adaptive inverse perspective transformation is performed on the consecutive frame images to obtain a corrected image set; The images in the corrected image set are preprocessed to obtain the license plate area; Based on the centroid of the license plate area, the vehicle speed is obtained, and it is determined whether the vehicle speed exceeds a first preset value. If so, an overspeed warning is issued to the vehicle. The adaptive inverse perspective transformation of the consecutive frame images to obtain the corrected image set includes: Based on the pitch angle, tilt angle, vertical field of view, horizontal field of view of the image acquisition device that acquires the surveillance video, and the width and height of the continuous frame images, an adaptive inverse perspective transformation is performed on the continuous frame images to obtain the corrected image set; The step of preprocessing the images in the corrected image set to obtain the license plate region includes: The images in the corrected image set are preprocessed, including Gaussian filtering, opening and closing operations, and edge detection, to obtain the preprocessed images. The license plate area is obtained based on the preprocessed image; The preprocessing of the images in the corrected image set, including Gaussian filtering, opening and closing operations, and edge detection, to obtain the preprocessed images includes: Gaussian smoothing is used to remove noise from the images in the corrected image set to obtain the first image; The first image is converted to a grayscale image using a weighted average method, and the opening operation in mathematical morphology is used to eliminate the influence of bright spots in the grayscale image to obtain the second image. The Sobel operator is used to perform edge detection on the second image to obtain the gradient magnitude, and pixels with gradient magnitudes greater than a second preset value are set as edge points to obtain the third image; The third image is processed using opening and closing operations to fill the closed region enclosed by the edge lines formed by the edge points, thus obtaining the preprocessed image.

2. The vehicle overspeed warning method as described in claim 1, characterized in that, The process of obtaining the license plate region based on the preprocessed image includes: Based on the vehicle's license plate information, the license plate area is selected from the preprocessed image.

3. The vehicle overspeed warning method as described in claim 1, characterized in that, The process of obtaining the vehicle speed based on the centroid of the license plate area includes: The speed of the vehicle is obtained based on the first centroid, the second centroid, and the time interval between adjacent frames in the corrected image set, corresponding to the license plate region.

4. A vehicle overspeed warning device, characterized in that, include: The first processing module is used to acquire continuous frame images corresponding to the vehicle's surveillance video. The second processing module is used to perform adaptive inverse perspective transformation on the continuous frame images to obtain a corrected image set. The third processing module is used to preprocess the images in the corrected image set to obtain the license plate area; The alarm notification module is used to obtain the vehicle speed based on the centroid of the license plate area, and determine whether the vehicle speed exceeds a first preset value. If so, an overspeed alarm notification is given to the vehicle. The second processing module is specifically used for: Based on the pitch angle, tilt angle, vertical field of view, horizontal field of view of the image acquisition device that acquires the surveillance video, and the width and height of the continuous frame images, an adaptive inverse perspective transformation is performed on the continuous frame images to obtain the corrected image set; The third processing module is specifically used for: The images in the corrected image set are preprocessed, including Gaussian filtering, opening and closing operations, and edge detection, to obtain the preprocessed images. The license plate area is obtained based on the preprocessed image; The third processing module is specifically used for: Gaussian smoothing is used to remove noise from the images in the corrected image set to obtain the first image; The first image is converted to a grayscale image using a weighted average method, and the opening operation in mathematical morphology is used to eliminate the influence of bright spots in the grayscale image to obtain the second image. The Sobel operator is used to perform edge detection on the second image to obtain the gradient magnitude, and pixels with gradient magnitudes greater than a second preset value are set as edge points to obtain the third image; The third image is processed using opening and closing operations to fill the closed region enclosed by the edge lines formed by the edge points, thus obtaining the preprocessed image.

5. An electronic device, characterized in that, include: At least one memory for storing computer programs; At least one processor is configured to execute a program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to perform the vehicle speeding warning method as described in any one of claims 1-3.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is run on the processor, the processor performs the vehicle speeding warning method as described in any one of claims 1-3.

7. A computer program product, characterized in that, When the computer program product is run on the processor, the processor performs the vehicle overspeed warning notification method as described in any one of claims 1-3.

Images