An automobile mileage identification method and device, an electronic device, and a storage medium

Abstract

This application provides a method, apparatus, electronic device, and storage medium for identifying vehicle mileage. The method includes: acquiring a video frame including a vehicle odometer; identifying the video frame to determine a key field region within the video frame; and determining mileage data in the video frame centered on the key field region. Implementing the above embodiments allows for the identification of odometers in different vehicles.

Description

Technical Field

[0001] This application relates to the field of image recognition technology, and more specifically, to a method, apparatus, electronic device, and storage medium for recognizing vehicle mileage. Background Technology

[0002] Auto title loans are a common loan service offered by banks. Customers can pledge their cars to banks to obtain loans. According to relevant risk management requirements, vehicle verification is necessary to confirm vehicle information. Mileage is a key indicator in auto title loans. If odometers can be automatically scanned and the optimal mileage value identified, it can effectively assist manual verification, improve approval speed, and enhance customer service quality.

[0003] Currently, in AI-powered vehicle inspection scenarios, the automatic recognition of odometer readings is still mainly done through manual review, without the use of AI technology. This is because dashboards in the driver's cabin vary greatly, making it difficult to have a unified solution that can recognize vehicle mileage for different cars. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, electronic device and storage medium for identifying vehicle mileage, which can identify the mileage of different vehicles.

[0005] In a first aspect, embodiments of this application provide a method for identifying vehicle mileage, including:

[0006] Acquire video footage including the car's odometer;

[0007] The video frame is identified to determine the key field regions within the video frame;

[0008] Using the key field area as the center, determine the mileage data in the video frame.

[0009] In the above implementation process, there are various types of car odometers, but they are all designed under a certain standard, which has corresponding key fields. The video footage is identified to determine the key field region; mileage data in the video footage is then determined centered on the key field region. Based on the above implementation method, it is possible to identify the odometers of different cars.

[0010] Furthermore, the step of identifying the video frame and determining the key fields in the video stream includes:

[0011] The text in the video image is obtained by recognizing the text in the video image using OCR technology.

[0012] Determine whether the text in the video frame includes a mileage unit field. If so, determine the area containing the mileage unit field as the key field area.

[0013] In the above implementation process, since the car's odometer is designed according to certain standards, it must include a mileage unit field. OCR technology is used to recognize the text in the video frame. If the text in the video frame includes mileage unit segments, it means that the area near that mileage unit field must contain mileage input. Therefore, the mileage data in the video frame can be determined by centering on the area where that mileage unit field is located.

[0014] Furthermore, the step of determining the mileage data in the video frame centered on the key field region includes:

[0015] Centered on the key field area, multiple characters are determined within a preset pixel range;

[0016] The mileage data is determined based on the multiple characters.

[0017] In the above implementation process, the mileage itself has a certain range, so its length is also within a certain range. Multiple characters are determined within a preset pixel range, centered on the key field area; the mileage data is determined based on these multiple characters. This avoids repeatedly recognizing the entire video frame, increasing recognition time, and also avoids recognizing non-mileage data, which would result in non-standard mileage data.

[0018] Further, the step of determining the mileage data based on the plurality of characters includes:

[0019] By concatenating the multiple numbers, the first initial mileage data is obtained;

[0020] Determine whether to use the first initial mileage data as the mileage data based on preset conditions.

[0021] In the above implementation process, after concatenating multiple numbers, the first initial mileage data can be obtained. Since the mileage data itself has certain rules, it is determined whether to use the first initial mileage data as the mileage data based on preset conditions. Based on the above implementation method, the accuracy of mileage data recognition can be improved.

[0022] Further, the step of determining whether to use the initial mileage data as the mileage data based on preset conditions includes:

[0023] Determine whether the first initial mileage data exceeds the maximum mileage data of the vehicle, and whether the initial mileage data is negative;

[0024] If the first initial mileage data does not exceed the maximum mileage data of the vehicle and the initial mileage data is not negative, the first initial mileage data shall be used as the mileage data.

[0025] In the above implementation process, the maximum mileage of the vehicle is subject to certain limitations. Therefore, it can be determined whether the first initial mileage data is appropriate by checking if it exceeds the vehicle's maximum mileage data. Simultaneously, since the vehicle's mileage data is non-negative, it can be determined whether the first initial mileage data should be used as the final mileage data by checking if it is non-negative. Based on the above implementation method, illegal mileage data can be avoided.

[0026] Furthermore, the video frame is multiple, and the multiple video frames are parsed from a video stream including the car's odometer.

[0027] The step of identifying key field regions in the video frame includes:

[0028] The multiple video frames are identified, and the key field regions in each video frame are determined.

[0029] The step of determining the mileage data in the video frame centered on the key field region includes:

[0030] Centered on the key field area in each video frame, the mileage data in each video frame is determined to obtain multiple second initial mileage data;

[0031] The multiple second initial mileage data are filtered to obtain the mileage data.

[0032] In the above implementation process, the user-submitted video is a video stream. To avoid inaccurate mileage data recognition, the video stream can be fully utilized. Multiple video frames containing the car's odometer are parsed from the video stream. Each of these frames is then identified to obtain key field regions. These key field regions are used to determine the mileage data in each video frame, resulting in multiple initial mileage data sets. Due to factors such as image clarity and shooting angle, the identified initial mileage data sets may not be identical. Therefore, these initial mileage data sets are filtered to obtain the final mileage data. Based on this implementation method, the video stream is fully utilized, ensuring more accurate mileage data recognition.

[0033] Further, the step of filtering the plurality of second initial mileage data to obtain the mileage data includes:

[0034] Obtain the clarity of the regions corresponding to the plurality of second initial mileage data;

[0035] The mileage data is determined based on the clarity of the regions corresponding to the plurality of second initial mileage data.

[0036] In the above implementation process, after identifying multiple second initial mileage data from multiple video frames in the video stream, since some mileage data has low clarity, the mileage data can be filtered according to clarity to obtain reliable mileage data.

[0037] Secondly, embodiments of this application provide a vehicle mileage identification device, comprising:

[0038] The acquisition module is used to acquire video footage, including the car's odometer reading.

[0039] The recognition module is used to recognize the video frame and determine the key field areas in the video frame;

[0040] The data determination module is used to determine the mileage data in the video frame, centered on the key field area.

[0041] In the above implementation process, there are various types of car odometers, but they are all designed under a certain standard, which has corresponding key fields. The video footage is identified to determine the key field region; mileage data in the video footage is then determined centered on the key field region. Based on the above implementation method, it is possible to identify the odometers of different cars.

[0042] Thirdly, an electronic device provided in this application includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method as described in any of the first aspects.

[0043] Fourthly, embodiments of this application provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method described in any of the first aspects.

[0044] Other features and advantages disclosed in this application will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the above-described technology disclosed in this application.

[0045] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 A flowchart illustrating the vehicle mileage identification method provided in this application embodiment;

[0048] Figure 2 A flowchart illustrating another method for identifying vehicle mileage provided in this application embodiment;

[0049] Figure 3 A schematic diagram of the structure of the vehicle mileage identification device provided in the embodiments of this application;

[0050] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0051] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0052] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0053] Auto title loans are a common loan service offered by banks. Customers can pledge their cars to banks to obtain loans. According to relevant risk management requirements, vehicle verification is necessary to confirm vehicle information. Mileage is a key indicator in auto title loans. If odometers can be automatically scanned and the optimal mileage value identified, it can effectively assist manual verification, improve approval speed, and enhance customer service quality.

[0054] Currently, in AI-powered vehicle inspection scenarios, the automatic recognition of odometer readings is still mainly done through manual review, without the use of AI technology. This is because dashboards in the driver's cabin vary greatly, making it difficult to have a unified solution that can recognize vehicle mileage for different cars.

[0055] In view of this, embodiments of this application provide a method, apparatus, electronic device, and storage medium for identifying vehicle mileage.

[0056] Example 1

[0057] See Figure 1 This application provides a method for identifying vehicle mileage, including:

[0058] S101: Acquire video footage including the car's odometer;

[0059] Customers and auditors upload full-vehicle videos of cars through the system, from which video footage including the car's odometer is extracted.

[0060] To make video images easier to recognize, methods such as gamma correction, sharpening algorithms, and Gaussian Unsharp can be used to preprocess the video images.

[0061] Gamma correction is used to address the problem of insufficient brightness and grayscale in display devices, and it plays a wide and significant role in real life. Car odometers use electronic displays, and gamma correction can solve the problem of unclear video footage caused by insufficient brightness on the car's electronic screen during filming.

[0062] S102: Recognize the video frame and determine the key field areas in the video frame;

[0063] S103: Determine the mileage data in the video frame, centered on the key field area.

[0064] In the above implementation process, various types of car odometers exist, but they are all designed under a certain standard, which has corresponding key fields. The video footage is identified to determine the key field regions; mileage data in the video footage is then determined centered on these key field regions. Based on this implementation method, it is possible to identify the odometers of different cars.

[0065] In one possible implementation, the step of recognizing video frames and determining key fields in the video stream includes: recognizing the video frames using OCR technology to obtain the text in the video frames; determining whether the text in the video frames includes a mileage unit field; if so, determining the area where the mileage unit field is located as the key field area.

[0066] In other words, OCR technology is used to recognize the text in the video. If the recognized text includes a mileage unit field, such as km, miles, or kilometers, the bounding box corresponding to the text is taken as the area corresponding to the mileage unit field. A diffusion box is then generated with this area as the center. The bounding box or diffusion box is taken as the area corresponding to the mileage unit field.

[0067] In the above implementation process, since the car's odometer is designed according to certain standards, it must include a mileage unit field. OCR technology is used to recognize the text in the video footage. If the text in the video footage includes mileage unit segments, it means that the area near that mileage unit field must contain mileage input. Therefore, the mileage data in the video footage can be determined by centering on the area where that mileage unit field is located.

[0068] In one possible implementation, the step of determining mileage data in the video frame, centered on a key field region, includes:

[0069] Multiple characters are determined within a preset pixel range, centered on the key field area;

[0070] Mileage data is determined based on multiple characters.

[0071] For example, with the center point of the bounding box as the center, the preset range is set to 800 pixels, multiple characters are identified within the 800-pixel range, and mileage data is determined based on the multiple characters.

[0072] In the above implementation process, the mileage itself has a certain range, so its length is also within a certain range. Multiple characters are determined within a preset pixel range, centered on the key field area. Determining the mileage data based on these multiple characters avoids repeatedly recognizing the entire video frame, thus preventing the recognition of non-mileage data and ensuring the accuracy of the recognized mileage data.

[0073] In one possible implementation, the step of determining mileage data based on multiple characters includes: concatenating multiple numbers to obtain first initial mileage data; and determining whether to use the first initial mileage data as mileage data based on preset conditions.

[0074] For example, the text is concatenated from largest to smallest according to the distance between the characters and the key field area. This yields the first initial mileage data. Then, based on preset conditions, it is determined whether to use the first initial mileage data as the final mileage data.

[0075] In the above implementation process, multiple numbers are concatenated to obtain the first initial mileage data. Since mileage data itself has certain rules, a preset condition is used to determine whether to use the first initial mileage data as the mileage data. Based on the above implementation method, the accuracy of mileage data recognition can be improved.

[0076] In one possible implementation, the step of determining whether to use the initial mileage data as mileage data based on preset conditions includes:

[0077] Determine whether the initial mileage data exceeds the vehicle's maximum mileage data, and whether the initial mileage data is negative;

[0078] If the first initial mileage data does not exceed the maximum mileage data of the vehicle and the initial mileage data is not negative, the first initial mileage data will be used as the mileage data.

[0079] In the above implementation process, the maximum mileage of the vehicle is subject to certain limitations. Therefore, it can be determined whether the first initial mileage data is appropriate by checking if it exceeds the vehicle's maximum mileage data. Simultaneously, since the vehicle's mileage data is non-negative, it can be determined whether the first initial mileage data should be used as the final mileage data by checking if it is non-negative. Based on the above implementation method, illegal mileage data can be avoided.

[0080] Example 2

[0081] See Figure 2 This application provides a method for identifying vehicle mileage, including:

[0082] S201: Acquire the video stream, detect the video stream, and obtain multiple video frames;

[0083] S202: Recognize multiple video frames and determine the key field areas in each video frame;

[0084] S203: Using the key field area in each video frame as the center, determine the mileage data in each video frame to obtain multiple second initial mileage data;

[0085] S204: Filter multiple second initial mileage data to obtain mileage data.

[0086] In the above implementation process, the user-submitted video is a video stream. To avoid inaccurate mileage data recognition, the video stream can be fully utilized. Multiple video frames containing the car's odometer are parsed from the video stream. Each of these frames is then identified to obtain key field regions. These key field regions are used to determine the mileage data in each video frame, resulting in multiple initial mileage data sets. Due to factors such as image clarity and shooting angle, the identified initial mileage data sets may not be identical. Therefore, these initial mileage data sets are filtered to obtain the final mileage data. Based on this implementation method, the video stream is fully utilized, ensuring more accurate mileage data recognition.

[0087] This application provides a method for filtering mileage data, including:

[0088] Obtain the clarity of the regions corresponding to multiple second initial mileage data;

[0089] Mileage data is determined based on the clarity of the regions corresponding to multiple second initial mileage data.

[0090] In the above implementation process, after identifying multiple second initial mileage data from multiple video frames in the video stream, since some mileage data has low clarity, the mileage data can be filtered according to clarity to obtain reliable mileage data.

[0091] This application provides another method for filtering mileage data, including:

[0092] Obtain the number and proportion of identical second initial mileage data in multiple second initial mileage data sets;

[0093] Mileage data is determined from multiple second initial mileage data based on the proportion.

[0094] For example, if three of the multiple second initial mileage data are 700 and four of the second initial mileage data are 800, then 700 will be used as the final mileage data.

[0095] This application provides another method for determining final mileage data from a plurality of second initial mileage data, the method comprising:

[0096] First, obtain the clarity of multiple second initial mileage data;

[0097] Select the preset number of third initial mileage data with the highest clarity from multiple second initial mileage data;

[0098] Obtain the number and proportion of identical third initial mileage data in multiple third initial mileage data sets;

[0099] Mileage data is determined from multiple third initial mileage data based on proportions.

[0100] For example, among multiple second initial mileage data, the thirty third initial mileage data with the highest clarity are selected; among the thirty third initial mileage data, 26 have a value of 700, 2 have a value of 100, and 2 have a value of 10, and the final mileage data is determined to be 700.

[0101] It should be noted that the various implementation methods in Example 1 are applicable to Example 2, and will not be repeated here.

[0102] Example 3

[0103] See Figure 3 This application provides a vehicle mileage identification device, comprising:

[0104] Module 1 is used to acquire video footage including the car's odometer.

[0105] Recognition module 2 is used to recognize video frames and determine key field areas in the video frames;

[0106] Data determination module 3 is used to determine the mileage data in the video frame, centered on the key field area.

[0107] In the above implementation process, various types of car odometers exist, but they are all designed under a certain standard, which has corresponding key fields. The video footage is identified to determine the key field regions; mileage data in the video footage is then determined centered on these key field regions. Based on this implementation method, it is possible to identify the odometers of different cars.

[0108] In one possible implementation, the recognition module 2 is further used to recognize the video frame using OCR technology to obtain the text in the video frame;

[0109] Determine if the text in the video frame includes a mileage unit field. If so, identify the area containing the mileage unit field as the critical field area.

[0110] In the above implementation process, since the car's odometer is designed according to certain standards, it must include a mileage unit field. OCR technology is used to recognize the text in the video footage. If the text in the video footage includes mileage unit segments, it means that the area near that mileage unit field must contain mileage input. Therefore, the mileage data in the video footage can be determined by centering on the area where that mileage unit field is located.

[0111] In one possible implementation, the data determination module 3 is also used to determine multiple characters within a preset pixel range, centered on the key field area;

[0112] Mileage data is determined based on multiple characters.

[0113] In one possible implementation, the data determination module 3 is further configured to concatenate multiple numbers to obtain first initial mileage data;

[0114] Determine whether to use the initial mileage data as mileage data based on preset conditions.

[0115] In one possible implementation, the data determination module 3 is further used to determine whether the first initial mileage data exceeds the maximum mileage data of the vehicle, and whether the initial mileage data is negative.

[0116] If the first initial mileage data does not exceed the maximum mileage data of the vehicle and the initial mileage data is not negative, the first initial mileage data will be used as the mileage data.

[0117] In one possible implementation, there are multiple video frames, which are parsed from a video stream including a car odometer; the recognition module 2 is further configured to recognize the multiple video frames and determine the key field regions in each video frame; the data determination module 3 is further configured to determine the mileage data in each video frame, centered on the key field regions in each video frame, to obtain multiple second initial mileage data; and to filter the multiple second initial mileage data to obtain mileage data.

[0118] In one possible implementation, the data determination module 3 is also used to obtain the clarity of the area corresponding to multiple second initial mileage data;

[0119] Mileage data is determined based on the clarity of the regions corresponding to multiple second initial mileage data.

[0120] This application also provides an electronic device, please refer to [link to application]. Figure 4 , Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of this application. The electronic device may include a processor 41, a communication interface 42, a memory 34, and at least one communication bus 34. The communication bus 34 is used to enable direct communication between these components. In this embodiment, the communication interface 42 of the electronic device is used for signaling or data communication with other node devices. The processor 41 may be an integrated circuit chip with signal processing capabilities.

[0121] The processor 41 described above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor, or the processor 41 can be any conventional processor.

[0122] The memory 34 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc. The memory 34 stores computer-readable instructions, which, when executed by the processor 41, allow the electronic device to perform the various steps involved in the above method embodiments.

[0123] Alternatively, the electronic device may also include a storage controller and an input / output unit.

[0124] The memory 34, memory controller, processor 41, peripheral interface, and input / output unit are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses 34. The processor 41 is used to execute executable modules stored in the memory 34, such as software function modules or computer programs included in electronic devices.

[0125] Input / output units are used to enable users to create tasks and set optional start periods or preset execution times for those tasks, facilitating user-server interaction. Input / output units can be, but are not limited to, a mouse and keyboard.

[0126] Understandable. Figure 4 The structure shown is for illustrative purposes only; the electronic device may also include components that are more advanced than those shown. Figure 4 The more or fewer components shown, or having the same Figure 4 The different configurations shown. Figure 4 The components shown can be implemented using hardware, software, or a combination thereof.

[0127] This application also provides a computer-readable storage medium storing instructions. When the instructions are executed on a computer, the computer program is executed by a processor to implement the method of the method embodiment. To avoid repetition, the details will not be repeated here.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0129] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0130] If a function is implemented as a software module and sold or used as an independent product, it 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 of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0131] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0132] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0133] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

Claims

1. A method of identifying the mileage of a vehicle, characterized by, include: Acquire video footage including the car's odometer; The video frame is multiple, and the multiple video frames are obtained by parsing from a video stream including the car's odometer; The video frame is identified to determine the key field regions within the video frame; Using the key field area as the center, determine the mileage data in the video frame; The step of identifying the video frame and determining the key field regions in the video frame includes: The multiple video frames are identified, and the key field regions in each video frame are determined. The step of determining the mileage data in the video frame, centered on the key field region, includes: Centered on the key field area in each video frame, the mileage data in each video frame is determined to obtain multiple second initial mileage data; The mileage data is obtained by filtering the plurality of second initial mileage data; The step of filtering the plurality of second initial mileage data to obtain the mileage data includes: Obtain the clarity of the regions corresponding to the plurality of second initial mileage data; The mileage data is determined based on the clarity of the regions corresponding to the plurality of second initial mileage data; The determination of the mileage data based on the clarity of the regions corresponding to the plurality of second initial mileage data includes: Clarity of multiple second initial mileage data; Select the preset number of third initial mileage data with the highest clarity from multiple second initial mileage data; Obtain the number and proportion of identical third initial mileage data in multiple third initial mileage data sets; Mileage data is determined from multiple third initial mileage data based on proportions.

2. The method of claim 1, wherein The step of recognizing the video frame and determining key fields in the video stream includes: The text in the video image is obtained by recognizing the text in the video image using OCR technology. Determine whether the text in the video frame includes a mileage unit field. If so, determine the area containing the mileage unit field as the key field area.

3. The method of claim 2, wherein The step of determining the mileage data in the video frame centered on the key field region includes: Centered on the key field area, multiple characters are determined within a preset pixel range; The mileage data is determined based on the multiple characters.

4. The method of claim 3, wherein The step of determining the mileage data based on the plurality of characters includes: The multiple characters are concatenated to obtain the first initial mileage data; Determine whether to use the first initial mileage data as the mileage data based on preset conditions.

5. The method of claim 4, wherein The step of determining whether to use the initial mileage data as the mileage data based on preset conditions includes: Determine whether the first initial mileage data exceeds the maximum mileage data of the vehicle, and whether the initial mileage data is negative; If the first initial mileage data does not exceed the maximum mileage data of the vehicle and the initial mileage data is not negative, the first initial mileage data shall be used as the mileage data.

6. An automobile mileage recognition device characterized by comprising: include: The acquisition module is used to acquire video footage, including the car's odometer reading. The recognition module is used to recognize the video frame and determine the key field areas in the video frame; The data determination module is used to determine the mileage data in the video frame, centered on the key field area; The system comprises multiple video frames, which are parsed from a video stream including a car odometer. The recognition module is also used to recognize the multiple video frames and determine the key field regions in each video frame. The data determination module is also used to determine the mileage data in each video frame, centered on the key field regions, to obtain multiple second initial mileage data. The multiple second initial mileage data are then filtered to obtain the mileage data. The data determination module is also used to obtain the clarity of the regions corresponding to multiple second initial mileage data; and to determine the mileage data based on the clarity of the regions corresponding to multiple second initial mileage data. Specifically, the data determination module is used to obtain the clarity of multiple second initial mileage data; select the preset number of third initial mileage data with the highest clarity from the multiple second initial mileage data; obtain the number and proportion of identical third initial mileage data in the multiple third initial mileage data; and determine the mileage data in the multiple third initial mileage data according to the proportion.

7. An electronic device, comprising: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1-5.

Images