Anti-cheating method, device and equipment for automatic metering of truck scale and medium

Through machine vision algorithms and deep learning models, combined with infrared grating signals and image acquisition equipment, the vehicle status on the car scale is detected, which solves the visual cheating problem that the existing technology cannot automatically warning, and improves the accuracy of the car scale measurement process .

CN118960930APending Publication Date: 2024-11-15ANXIN TUORI INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411285014.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-13
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The existing automatic measurement system of automobile scale cannot automatically warn of visual cheating such as non-compliance in the number of people in the cab, pounds, and decks, which has affected the measurement accuracy.

Method used

The machine vision algorithm is used to detect whether the vehicle has been on the vehicle scale through infrared grating signals and image acquisition equipment, and the target vehicle image is detected and compared, and the deep learning model is used to identify cheating situations to achieve automated early warning.

Benefits of technology

Effectively avoid metrological loopholes, improve metrological accuracy, and be able to detect and warn of non-compliant cab people, pounding and decking cheating, ensuring the accuracy of the metrological process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118960930A_ABST
    Figure CN118960930A_ABST
Patent Text Reader

Abstract

The invention discloses an anti-cheating method and device for automatic metering of a truck scale, equipment and a medium, and relates to the field of information processing, and the method comprises the steps: collecting a current echelette grating signal, and determining whether a target vehicle gets on the truck scale or not according to the current echelette grating signal; if the vehicle does not get on the truck scale, performing early warning prompt, and if the vehicle already gets on the truck scale, acquiring a first vehicle image of the target vehicle through a preset image acquisition device, and performing target detection based on the first vehicle image to determine whether the current state of the target vehicle is compliant; if not, early warning prompt is carried out, and if yes, after a second vehicle image of the target vehicle is collected through preset image collection equipment, the first vehicle image and the second vehicle image are compared, and whether early warning prompt is carried out or not is determined according to the comparison result. Therefore, the vehicle can be analyzed through a machine vision algorithm, and then cheating detection and early warning in the automatic metering process of the vehicle are achieved, and metering loopholes are avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of information processing, and in particular to an anti-cheating method, device, equipment and medium for automatic measurement of a vehicle scale. Background Art

[0002] At present, when building the automatic weighing system for automobile scales, enterprises pay special attention to whether there are measurement loopholes and measurement accuracy. After searching resources and conducting research on the Internet, it was found that the existing automobile scale on-site automatic weighing system only uses infrared beaming technology to warn of cheating phenomena such as incomplete weighing, but cannot automatically warn of visual cheating phenomena such as non-compliant number of people in the cab, stepping on the scale, and using fake license plates. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide an anti-cheating method, device, equipment and medium for automatic weighing of automobile scales, which can analyze vehicles through machine vision algorithms, thereby realizing cheating detection and early warning in the process of automatic weighing of automobiles, and avoiding measurement loopholes. The specific scheme is as follows:

[0004] In a first aspect, the present application discloses an anti-cheating method for automatic weighing of a truck scale, which is applied to an automatic weighing system of a truck scale, comprising:

[0005] Collecting the current infrared grating signal, and determining whether the target vehicle has been on the vehicle scale according to the current infrared grating signal;

[0006] If the vehicle is not on the truck scale, an early warning prompt is issued; if the vehicle is on the truck scale, a first vehicle image of the target vehicle is captured by a preset image acquisition device, and target detection is performed based on the first vehicle image to determine whether the current state of the target vehicle is compliant;

[0007] If the current state of the target vehicle is not compliant, an early warning is issued; if the current state of the target vehicle is compliant, after the second vehicle image of the target vehicle is captured by the preset image acquisition device, the first vehicle image and the second vehicle image are compared, and it is determined whether to issue an early warning based on the comparison result.

[0008] Optionally, the collecting of the current infrared grating signal and determining whether the target vehicle has been on the vehicle scale according to the current infrared grating signal include:

[0009] Collecting a current infrared grating signal, and analyzing the current infrared grating signal to determine a signal type of the current infrared grating signal;

[0010] If the signal type of the current infrared grating signal is an occlusion signal, it is determined that the target vehicle is not on the vehicle scale;

[0011] If the signal type of the current infrared grating signal is an unblocked signal, it is determined that the target vehicle has been on the vehicle scale.

[0012] Optionally, if the vehicle is not on the truck scale, an early warning prompt is given; if the vehicle is on the truck scale, a first vehicle image of the target vehicle is acquired by a preset image acquisition device, and target detection is performed based on the first vehicle image to determine whether the current state of the target vehicle is compliant, including:

[0013] If the vehicle is not on the truck scale, the first warning audio stored locally is played to provide the first warning prompt;

[0014] If the vehicle has been placed on the truck scale, a first vehicle image of the target vehicle is captured by a preset image capture device, and the first vehicle image is transmitted to a first preset deep learning model so that target detection is performed on the first vehicle image through the first preset deep learning model, and whether the current status of the target vehicle is compliant is determined based on the detection results obtained.

[0015] Optionally, performing target detection on the first vehicle image by using the first preset deep learning model, and determining whether the current state of the target vehicle is compliant according to the obtained detection result, includes:

[0016] Analyze the first vehicle image by using the first preset deep learning model to determine a to-be-detected area in the first vehicle image, and determine whether there is a target object in the to-be-detected area;

[0017] If there is a target object in the area to be detected, generating a first detection result indicating that the current state of the first vehicle image is non-compliant;

[0018] If there is no target object in the area to be detected, a second detection result indicating that the current state of the first vehicle image is compliant is generated.

[0019] Optionally, if the current state of the target vehicle is not compliant, an early warning is issued; if the current state of the target vehicle is compliant, after the second vehicle image of the target vehicle is acquired by the preset image acquisition device, the first vehicle image and the second vehicle image are compared, and it is determined whether to issue an early warning according to the comparison result, including:

[0020] If the current state of the target vehicle is not in compliance, playing the second warning audio stored locally to provide a second warning prompt;

[0021] If the current state of the target vehicle is compliant, after the second vehicle image of the target vehicle is acquired by the preset image acquisition device, the first vehicle image and the second vehicle image are compared by using a target detection algorithm through a second preset deep learning model to obtain a corresponding comparison result;

[0022] If the comparison result indicates that the first vehicle image is inconsistent with the second vehicle image, a third warning audio stored locally is played to provide a third warning prompt.

[0023] Optionally, comparing the first vehicle image and the second vehicle image using a target detection algorithm through a second preset deep learning model to obtain a corresponding comparison result includes:

[0024] Performing object detection on the first vehicle image and the second vehicle image using a target detection algorithm through a second preset deep learning model to identify a first object corresponding to the first vehicle image and a second object corresponding to the second vehicle image;

[0025] Performing feature extraction on the first object and the second object respectively to obtain a first feature corresponding to the first object and a second feature corresponding to the second object;

[0026] The first feature and the second feature are compared. If the first feature is consistent with the second feature, a first comparison result indicating that no warning is needed is generated. If the first feature is inconsistent with the second feature, a second comparison result indicating that a warning is needed is generated.

[0027] Optionally, the target detection algorithm is YoloV9 algorithm.

[0028] In the second aspect, the present application discloses an anti-cheating device for automatic weighing of a truck scale, which is applied to an automatic weighing system of a truck scale, comprising:

[0029] A signal analysis module, used to collect the current infrared grating signal and determine whether the target vehicle has been on the vehicle scale according to the current infrared grating signal;

[0030] A vehicle status detection module is used to issue an early warning if the vehicle is not on the truck scale, and to collect a first vehicle image of the target vehicle through a preset image acquisition device if the vehicle is on the truck scale, and to perform target detection based on the first vehicle image to determine whether the current status of the target vehicle is compliant;

[0031] The early warning prompt module is used to issue an early warning prompt if the current state of the target vehicle is not compliant. If the current state of the target vehicle is compliant, after the second vehicle image of the target vehicle is captured by the preset image acquisition device, the first vehicle image and the second vehicle image are compared, and it is determined whether to issue an early warning prompt based on the comparison result.

[0032] In a third aspect, the present application discloses an electronic device, comprising:

[0033] Memory, used to store computer programs;

[0034] The processor is used to execute the computer program to implement the anti-cheating method for automatic measurement of vehicle scales as described above.

[0035] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the anti-cheating method for automatic measurement of a vehicle scale as described above.

[0036] In the present application, it is first necessary to collect the current infrared grating signal, and determine whether the target vehicle has been on the vehicle scale based on the current infrared grating signal. If the vehicle has not been on the vehicle scale, an early warning prompt is issued. If the vehicle has been on the vehicle scale, a first vehicle image of the target vehicle is collected by a preset image acquisition device, and target detection is performed based on the first vehicle image to determine whether the current state of the target vehicle is compliant. If the current state of the target vehicle is not compliant, an early warning prompt is issued. If the current state of the target vehicle is compliant, after the second vehicle image of the target vehicle is collected by the preset image acquisition device, the first vehicle image and the second vehicle image are compared, and it is determined whether to issue an early warning prompt based on the comparison result. It can be seen that the method of the present application needs to determine whether the target vehicle has been put on the truck scale based on the current infrared grating signal collected, and issue an early warning if the vehicle has not been put on the truck scale. If the vehicle has been put on the truck scale, the first vehicle image of the target vehicle is collected, and target detection is performed based on the collected first vehicle image to determine whether the current state of the target vehicle is compliant, and an early warning is issued if the current state is not compliant. If the current state is compliant, after the second vehicle image of the target vehicle is collected, the first vehicle image and the second vehicle image are compared to determine whether to issue an early warning based on the comparison result. In this way, the vehicle can be analyzed through a machine vision algorithm, thereby realizing cheating detection and early warning in the process of automatic vehicle measurement, plugging measurement loopholes, and improving measurement accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0038] Figure 1 A flow chart of an anti-cheating method for automatic measurement of a vehicle scale disclosed in this application;

[0039] Figure 2 This is a schematic diagram of the structure of an anti-cheating device for automatic measurement of a truck scale disclosed in the present application;

[0040] Figure 3 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. 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.

[0042] In the prior art, the on-site automatic measurement system of the truck scale only uses infrared beaming technology to warn of cheating phenomena such as incomplete weighing, but is unable to automatically warn of visual cheating phenomena such as irregular number of people in the cab, stepping on the scale, and using fake license plates.

[0043] In order to overcome the above technical problems, the present application discloses an anti-cheating method, device, equipment and medium for automatic measurement of vehicle scales, which can analyze the vehicle through a machine vision algorithm, thereby realizing cheating detection and early warning during the automatic measurement of the vehicle, and avoiding measurement loopholes.

[0044] See also Figure 1 As shown, the embodiment of the present invention discloses an anti-cheating method for automatic weighing of a truck scale, which is applied to an automatic weighing system of a truck scale, and includes:

[0045] Step S11, collecting the current infrared grating signal, and determining whether the target vehicle has been on the vehicle scale according to the current infrared grating signal.

[0046] In this embodiment, it is necessary to collect the current infrared grating signal of the vehicle scale through the infrared grating device. It should be noted that one group of infrared grating devices are installed at a distance of about 1m on both ends of the vehicle scale. Two groups of dry node signals are connected to the intelligent controller. After the current infrared grating signal of the vehicle scale is collected by the infrared grating device, the current infrared grating signal can be analyzed to determine the signal type of the current infrared grating signal. If the signal type of the current infrared grating signal is an obstruction signal, it indicates that the target vehicle has not completely boarded the vehicle scale. If the signal type of the current infrared grating signal is an unobstructed signal, it indicates that the target vehicle has completely boarded the vehicle scale, and the next step can be performed. In this way, it is possible to determine whether the vehicle has completely boarded the vehicle scale by collecting the infrared grating signal and judging the infrared grating signal, thereby avoiding the cheating phenomenon of the vehicle not being completely weighed.

[0047] Step S12: If the vehicle is not on the truck scale, an early warning prompt is issued; if the vehicle is on the truck scale, a first vehicle image of the target vehicle is captured by a preset image acquisition device, and target detection is performed based on the first vehicle image to determine whether the current status of the target vehicle is compliant.

[0048] In this embodiment, in one case, if it is determined by judging the infrared grating signal that the vehicle is not on the vehicle scale, it is necessary to play the first warning audio saved locally to provide the first warning prompt corresponding to the vehicle not being on the vehicle scale; in another case, if it is determined by judging the infrared grating signal that the vehicle is on the vehicle scale, it is necessary to collect the current image of the target vehicle on the vehicle scale as the first vehicle image through the preset image acquisition device. It should be noted that the preset image acquisition device can be any image acquisition device. In this embodiment, a high-definition camera is selected as the preset image acquisition device, and the high-definition camera is installed at a distance of about 5 meters from the left and right ends of the vehicle scale and at a height of 6 meters. The vehicle number, the cab, and both sides of the vehicle scale can be seen through the camera to ensure that the network signal is normal. Then the first preset deep learning model is required to perform target detection on the first vehicle image through the first preset deep learning model, and determine whether the current state of the target vehicle is compliant based on the obtained detection results. It should be noted that after the car is fully mounted on the vehicle scale, there may be cheating situations such as people in the cab or people standing on both sides of the scale. Therefore, it is necessary to perform target detection on the first vehicle image through the first preset deep learning model to determine whether there is cheating situation such as people in the cab or people standing on both sides of the scale. It should be noted that the first preset deep learning model is the PaddleDetection model in this application, and after the first vehicle image is collected, the first vehicle image needs to be stored for comparison with subsequently collected images.

[0049] It is further necessary to explain that the specific process of performing target detection on the first vehicle image through the first preset deep learning model and determining whether the current state of the target vehicle is compliant based on the obtained detection results is as follows: First, the first vehicle image needs to be analyzed through the first preset deep learning model to determine the area to be detected in the first vehicle image, and determine whether there is a target object in the area to be detected. For example, a preset area to be detected can be set, such as the position of the two sides of the vehicle or the cab. If there is a target object in the area to be detected, it is characterized that cheating may occur in the area to be detected when the image is collected, so it is necessary to generate a first detection result representing that the current state of the first vehicle image is not compliant. In another case, if there is no target object in the area to be detected, a second detection result representing that the current state of the first vehicle image is compliant is generated. In this way, the image can be detected through a deep learning model, and machine vision technology is used to effectively avoid the occurrence of cheating in the cab and stepping on the scale during the automatic measurement of the car.

[0050] Step S13: If the current state of the target vehicle is not compliant, an early warning is issued; if the current state of the target vehicle is compliant, after the second vehicle image of the target vehicle is captured by the preset image acquisition device, the first vehicle image and the second vehicle image are compared, and it is determined whether to issue an early warning based on the comparison result.

[0051] In this embodiment, if the result of detecting the first vehicle image of the target vehicle is the first detection result, it is characterized that the current vehicle of the target vehicle is not compliant, and the second warning audio saved locally needs to be played to provide a second warning prompt. In another case, if the current state of the target vehicle is compliant, it is necessary to capture the second vehicle image of the target vehicle through a preset image acquisition device, and then compare the first vehicle image and the second vehicle image using a target detection algorithm through a second preset deep learning model to obtain a corresponding comparison result. It should be noted that the second preset deep learning model is a Pytorch model, and the target detection algorithm is a YoloV9 algorithm. Specifically, it is necessary to perform object detection on the first vehicle image and the second vehicle image using a target detection algorithm through a second preset deep learning model to identify the first object corresponding to the first vehicle image and the second object corresponding to the second vehicle image. For example, the detection object can be set to the entire car and the license plate part, and the entire car and the license plate of the car in the two images are compared. Then, feature extraction is performed on the first object and the second object respectively to obtain the first feature corresponding to the first object and the second feature corresponding to the second object. Finally, the first feature and the second feature are compared. If the first feature is consistent with the second feature, it indicates that the first object and the second object are consistent. In the case of detecting the entire car and the license plate, it indicates that the entire car and the license plate in the two image acquisitions are consistent. Therefore, it is necessary to generate a first comparison result indicating that no warning is required. If the first feature is inconsistent with the second feature, a second comparison result indicating that a warning is required is generated. At this time, it indicates that a car with a fake license plate may appear. In this way, the image can be detected through a deep learning model, and the occurrence of cheating by using fake license plates can be effectively avoided by comparing the two acquired images.

[0052] It can be seen that the method of the present application needs to determine whether the target vehicle has been put on the truck scale based on the current infrared grating signal collected, and issue an early warning if the vehicle has not been put on the truck scale. If the vehicle has been put on the truck scale, the first vehicle image of the target vehicle is collected, and target detection is performed based on the collected first vehicle image to determine whether the current state of the target vehicle is compliant, and an early warning is issued if the current state is not compliant. If the current state is compliant, after the second vehicle image of the target vehicle is collected, the first vehicle image and the second vehicle image are compared to determine whether to issue an early warning based on the comparison result. In this way, the vehicle can be analyzed through a machine vision algorithm, thereby realizing cheating detection and early warning in the process of automatic vehicle measurement, plugging measurement loopholes, and improving measurement accuracy.

[0053] See also Figure 2 As shown, the embodiment of the present invention discloses an anti-cheating device for automatic weighing of a truck scale, which is applied to an automatic weighing system of a truck scale, and includes:

[0054] The signal analysis module 11 is used to collect the current infrared grating signal and determine whether the target vehicle has been on the vehicle scale according to the current infrared grating signal;

[0055] The vehicle status detection module 12 is used to issue an early warning if the vehicle is not on the truck scale, and to collect a first vehicle image of the target vehicle through a preset image acquisition device if the vehicle is on the truck scale, and to perform target detection based on the first vehicle image to determine whether the current status of the target vehicle is compliant;

[0056] The early warning prompt module 13 is used to issue an early warning prompt if the current state of the target vehicle is not compliant. If the current state of the target vehicle is compliant, after the second vehicle image of the target vehicle is captured by the preset image acquisition device, the first vehicle image and the second vehicle image are compared, and it is determined whether to issue an early warning prompt based on the comparison result.

[0057] In this embodiment, it is first necessary to collect the current infrared grating signal, and determine whether the target vehicle has been on the vehicle scale based on the current infrared grating signal. If the vehicle has not been on the vehicle scale, an early warning prompt is issued. If the vehicle has been on the vehicle scale, a first vehicle image of the target vehicle is collected by a preset image acquisition device, and target detection is performed based on the first vehicle image to determine whether the current state of the target vehicle is compliant. If the current state of the target vehicle is not compliant, an early warning prompt is issued. If the current state of the target vehicle is compliant, after the second vehicle image of the target vehicle is collected by the preset image acquisition device, the first vehicle image and the second vehicle image are compared, and it is determined whether to issue an early warning prompt based on the comparison result. It can be seen that the method of the present application needs to determine whether the target vehicle has been put on the truck scale based on the current infrared grating signal collected, and issue an early warning if the vehicle has not been put on the truck scale. If the vehicle has been put on the truck scale, the first vehicle image of the target vehicle is collected, and target detection is performed based on the collected first vehicle image to determine whether the current state of the target vehicle is compliant, and an early warning is issued if the current state is not compliant. If the current state is compliant, after the second vehicle image of the target vehicle is collected, the first vehicle image and the second vehicle image are compared to determine whether to issue an early warning based on the comparison result. In this way, the vehicle can be analyzed through a machine vision algorithm, thereby realizing cheating detection and early warning in the process of automatic vehicle measurement, plugging measurement loopholes, and improving measurement accuracy.

[0058] In some embodiments, the signal analysis module 11 may specifically include:

[0059] A signal type determination unit, used for collecting a current infrared grating signal and analyzing the current infrared grating signal to determine a signal type of the current infrared grating signal;

[0060] A first determination unit, configured to determine that the target vehicle is not on the vehicle scale if the signal type of the current infrared grating signal is an occlusion signal;

[0061] The second order checker is used to determine that the target vehicle has been on the truck scale if the signal type of the current infrared grating signal is an unblocked signal.

[0062] In some embodiments, the vehicle state detection module 12 may specifically include:

[0063] A first warning prompt unit, used to play a first warning audio stored locally to provide a first warning prompt if the vehicle is not on the vehicle scale;

[0064] The image analysis submodule is used to collect a first vehicle image of the target vehicle through a preset image acquisition device if the vehicle has been placed on the vehicle scale, and transmit the first vehicle image to a first preset deep learning model to perform target detection on the first vehicle image through the first preset deep learning model, and determine whether the current status of the target vehicle is compliant based on the obtained detection results.

[0065] In some embodiments, the image analysis submodule may specifically include:

[0066] A first object detection unit, configured to analyze the first vehicle image by using the first preset deep learning model to determine a to-be-detected area in the first vehicle image, and to determine whether a target object exists in the to-be-detected area;

[0067] A first detection result generating unit, configured to generate a first detection result indicating that a current state of the first vehicle image is non-compliant if a target object exists in the area to be detected;

[0068] A second detection result generating unit is configured to generate a second detection result indicating that a current state of the first vehicle image is compliant if no target object exists in the area to be detected.

[0069] In some embodiments, the early warning module 13 may specifically include:

[0070] A second warning prompt unit, configured to play a second warning audio stored locally to provide a second warning prompt if the current state of the target vehicle is not in compliance;

[0071] An image comparison submodule, for comparing the first vehicle image and the second vehicle image by using a target detection algorithm through a second preset deep learning model to obtain a corresponding comparison result after acquiring a second vehicle image of the target vehicle through the preset image acquisition device if the current state of the target vehicle is compliant;

[0072] The third warning prompt unit is used to play the third warning audio stored locally to provide a third warning prompt if the comparison result indicates that the first vehicle image and the second vehicle image are inconsistent.

[0073] In some embodiments, the image comparison submodule may specifically include:

[0074] A second object detection unit, configured to perform object detection on the first vehicle image and the second vehicle image using a target detection algorithm through a second preset deep learning model to identify a first object corresponding to the first vehicle image and a second object corresponding to the second vehicle image;

[0075] a feature extraction unit, configured to extract features from the first object and the second object respectively, so as to obtain a first feature corresponding to the first object and a second feature corresponding to the second object;

[0076] A comparison result generating unit is used to compare the first feature and the second feature, and if the first feature is consistent with the second feature, generate a first comparison result indicating that no warning is needed; if the first feature is inconsistent with the second feature, generate a second comparison result indicating that a warning is needed.

[0077] Furthermore, the present application also discloses an electronic device. Figure 3 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0078] Figure 3 A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the anti-cheating method for automatic measurement of a vehicle scale disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0079] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0080] In addition, the memory 22 as a carrier for resource storage may be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon may include an operating system 221, a computer program 222, etc., and the storage method may be temporary storage or permanent storage.

[0081] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, which can be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the anti-cheating method for automatic weighing of a vehicle scale performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include computer programs that can be used to complete other specific tasks.

[0082] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned anti-cheating method for automatic weighing of a vehicle scale disclosed above is implemented. The specific steps of the method can be referred to the corresponding contents disclosed in the aforementioned embodiments, and will not be repeated here.

[0083] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0084] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0085] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0086] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0087] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for preventing cheating in automatic weighing of a truck scale, characterized in that: Applied to the automatic measurement system of truck scales, including: Collecting the current infrared grating signal, and determining whether the target vehicle has been on the vehicle scale according to the current infrared grating signal; If the vehicle is not on the truck scale, an early warning prompt is issued; if the vehicle is on the truck scale, a first vehicle image of the target vehicle is captured by a preset image acquisition device, and target detection is performed based on the first vehicle image to determine whether the current state of the target vehicle is compliant; If the current state of the target vehicle is not compliant, an early warning is issued; if the current state of the target vehicle is compliant, after the second vehicle image of the target vehicle is captured by the preset image acquisition device, the first vehicle image and the second vehicle image are compared, and it is determined whether to issue an early warning based on the comparison result.

2. The anti-cheating method for automatic weighing of a truck scale according to claim 1 is characterized in that: The collecting of the current infrared grating signal and determining whether the target vehicle has been on the vehicle scale according to the current infrared grating signal include: Collecting a current infrared grating signal, and analyzing the current infrared grating signal to determine a signal type of the current infrared grating signal; If the signal type of the current infrared grating signal is an occlusion signal, it is determined that the target vehicle is not on the vehicle scale; If the signal type of the current infrared grating signal is an unblocked signal, it is determined that the target vehicle has been on the vehicle scale.

3. The anti-cheating method for automatic weighing of a truck scale according to claim 1 is characterized in that: If the vehicle is not on the truck scale, an early warning prompt is given; if the vehicle is on the truck scale, a first vehicle image of the target vehicle is acquired by a preset image acquisition device, and target detection is performed based on the first vehicle image to determine whether the current state of the target vehicle is compliant, including: If the vehicle is not on the truck scale, the first warning audio stored locally is played to provide the first warning prompt; If the vehicle has been placed on the truck scale, a first vehicle image of the target vehicle is captured by a preset image capture device, and the first vehicle image is transmitted to a first preset deep learning model so that target detection is performed on the first vehicle image through the first preset deep learning model, and whether the current status of the target vehicle is compliant is determined based on the detection results obtained.

4. The anti-cheating method for automatic weighing of a truck scale according to claim 3 is characterized in that: The performing target detection on the first vehicle image by using the first preset deep learning model, and determining whether the current state of the target vehicle is compliant according to the obtained detection result, includes: Analyze the first vehicle image by using the first preset deep learning model to determine a to-be-detected area in the first vehicle image, and determine whether there is a target object in the to-be-detected area; If there is a target object in the area to be detected, generating a first detection result indicating that the current state of the first vehicle image is non-compliant; If there is no target object in the area to be detected, a second detection result indicating that the current state of the first vehicle image is compliant is generated.

5. The anti-cheating method for automatic weighing of a truck scale according to any one of claims 1 to 4, characterized in that: If the current state of the target vehicle is not in compliance, an early warning is issued; if the current state of the target vehicle is in compliance, after the second vehicle image of the target vehicle is acquired by the preset image acquisition device, the first vehicle image and the second vehicle image are compared, and whether to issue an early warning is determined according to the comparison result, including: If the current state of the target vehicle is not in compliance, playing the second warning audio stored locally to provide a second warning prompt; If the current state of the target vehicle is compliant, after the second vehicle image of the target vehicle is acquired by the preset image acquisition device, the first vehicle image and the second vehicle image are compared by using a target detection algorithm through a second preset deep learning model to obtain a corresponding comparison result; If the comparison result indicates that the first vehicle image is inconsistent with the second vehicle image, a third warning audio stored locally is played to provide a third warning prompt.

6. The anti-cheating method for automatic weighing of a truck scale according to claim 5 is characterized in that: The comparing the first vehicle image and the second vehicle image by using a target detection algorithm through a second preset deep learning model to obtain a corresponding comparison result includes: Performing object detection on the first vehicle image and the second vehicle image using a target detection algorithm through a second preset deep learning model to identify a first object corresponding to the first vehicle image and a second object corresponding to the second vehicle image; Performing feature extraction on the first object and the second object respectively to obtain a first feature corresponding to the first object and a second feature corresponding to the second object; The first feature and the second feature are compared. If the first feature is consistent with the second feature, a first comparison result indicating that no warning is needed is generated. If the first feature is inconsistent with the second feature, a second comparison result indicating that a warning is needed is generated.

7. The anti-cheating method for automatic weighing of a truck scale according to claim 6 is characterized in that: The target detection algorithm is the YoloV9 algorithm. 8.An anti-cheating device for automatic weighing of a truck scale, characterized in that: Applied to the automatic measurement system of truck scales, including: A signal analysis module, used to collect the current infrared grating signal and determine whether the target vehicle has been on the vehicle scale according to the current infrared grating signal; A vehicle status detection module is used to issue an early warning if the vehicle is not on the truck scale, and to collect a first vehicle image of the target vehicle through a preset image acquisition device if the vehicle is on the truck scale, and to perform target detection based on the first vehicle image to determine whether the current status of the target vehicle is compliant; The early warning prompt module is used to issue an early warning prompt if the current state of the target vehicle is not compliant. If the current state of the target vehicle is compliant, after the second vehicle image of the target vehicle is captured by the preset image acquisition device, the first vehicle image and the second vehicle image are compared, and it is determined whether to issue an early warning prompt based on the comparison result.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the anti-cheating method for automatic measurement of a vehicle scale as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein the computer program, when executed by a processor, implements the anti-cheating method for automatic measurement of a vehicle scale as described in any one of claims 1 to 7.