Vehicle authority identification method, device, storage medium, and electronic device

Abstract

This application proposes a vehicle authority identification method, device, storage medium and electronic device. By implementing the embodiments of this application, multiple first segmented images of the vehicle to be charged are obtained; a first image processing instruction is determined based on the multiple first segmented images and preset image compliance conditions; if the first image processing instruction is an image enhancement processing instruction, the image acquisition parameters of the target camera are adjusted to control the target camera to capture a second vehicle image of the vehicle to be charged; multiple second segmented images of the second vehicle image are obtained; the charging authority of the vehicle to be charged is detected based on the multiple second segmented images, image compliance conditions and preset character strings; if the charging authority is authorized, the charging pile is controlled to charge the vehicle to be charged. When the segmented image obtained by the first character recognition is non-compliant for a specific position of the vehicle, the character recognition process is repeated, and character segmentation and image enhancement are used in the character recognition process to improve the accuracy of the judgment of the authority of the vehicle to be charged.

Description

Technical Field

[0001] The present invention relates to the field of new energy technologies, and in particular to a vehicle authority identification method, device, storage medium and electronic equipment. Background Art

[0002] With the popularity of charging piles for electric vehicles, more and more places have installed public charging piles. In addition to public places, some specific places have also installed charging piles for specific vehicles. However, charging piles for specific vehicles are often used by vehicles other than the specific vehicles.

[0003] However, due to the possible harsh background environment and the problem of uncertain location of the vehicle identification code, the current identification of the charging authority of the vehicle to be charged still has the problem of low recognition accuracy. Summary of the Invention

[0004] The embodiments of the present application provide a vehicle authority identification method, device, storage medium and electronic device, which are conducive to improving the accuracy of vehicle identification.

[0005] In a first aspect, an embodiment of the present application provides a vehicle authority identification method, which is applied to a server of a charging pile charging system, wherein the charging pile charging system also includes a charging pile, and the method includes:

[0006] Acquire multiple first segmented images of a first vehicle image of the vehicle to be charged, where the first vehicle image is a composite image obtained by photographing the vehicle to be charged at multiple angles;

[0007] Determining a first image processing instruction based on the plurality of first segmented images and a preset image compliance condition, the first image processing instruction including an image enhancement processing instruction under a non-compliance condition and a continue processing instruction under a compliance condition, the image compliance condition being used to screen character features of the first segmented image or the segmented image obtained after the image enhancement processing instruction, the character features including a character quantity feature and a character arrangement feature;

[0008] If it is detected that the first image processing instruction is an image enhancement processing instruction, adjusting the image acquisition parameters of the target camera and controlling the target camera to capture a second vehicle image of the vehicle to be charged; and acquiring a plurality of second segmented images of the second vehicle image;

[0009] detecting the charging authority of the vehicle to be charged based on the plurality of second segmented images, the image compliance condition, and a preset character string, wherein the charging authority includes the right to charge;

[0010] If it is detected that the charging authority is authorized to charge, the charging pile is controlled to charge the vehicle to be charged.

[0011] In a second aspect, an embodiment of the present application provides a vehicle authority identification device, which is applied to a server of a charging pile charging system, wherein the charging pile charging system also includes a charging pile, and the device includes:

[0012] an acquisition module, configured to acquire a plurality of first segmented images of a first vehicle image of the vehicle to be charged, where the first vehicle image is a composite image obtained by photographing the vehicle to be charged from multiple angles;

[0013] a determination module, configured to determine a first image processing instruction based on the plurality of first segmented images and a preset image compliance condition, the first image processing instruction including an image enhancement processing instruction under a non-compliance condition and a continue processing instruction under a compliance condition, the image compliance condition being configured to screen character features of the first segmented image or the segmented image obtained after the image enhancement processing instruction, the character features including a character quantity feature and a character arrangement feature;

[0014] an adjustment module, configured to adjust image acquisition parameters of a target camera if it is detected that the first image processing instruction is an image enhancement processing instruction, and control the target camera to capture a second vehicle image of the vehicle to be charged; and obtain a plurality of second segmented images of the second vehicle image;

[0015] a detection module, configured to detect the charging authority of the vehicle to be charged based on the plurality of second segmented images, the image compliance condition, and a preset character string, wherein the charging authority includes the right to charge;

[0016] The control module is used to control the charging pile to charge the vehicle to be charged if it is detected that the charging authority is authorized to charge.

[0017] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing some or all of the steps described in the first aspect of the embodiment of the present application.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. The computer storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes some or all of the steps described in the first aspect.

[0019] In a fifth aspect, embodiments of the present application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to perform some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

[0020] In an embodiment of the present application, multiple first segmented images of a first vehicle image of a vehicle to be charged are obtained, where the first vehicle image is a composite image obtained by photographing the vehicle to be charged from multiple angles; a first image processing instruction is determined based on the multiple first segmented images and a preset image compliance condition, where the first image processing instruction includes an image enhancement processing instruction under a non-compliance condition and a continue processing instruction under a compliance condition, where the image compliance condition is used to screen character features of the first segmented image or the segmented image obtained after the image enhancement processing instruction, where the character features include character quantity features and character arrangement features; if it is detected that the first image processing instruction is an image enhancement processing instruction, the image acquisition parameters of the target camera are adjusted, and the target camera is controlled to photograph a second vehicle image of the vehicle to be charged; and multiple second segmented images of the second vehicle image are obtained; the charging authority of the vehicle to be charged is detected based on the multiple second segmented images, the image compliance condition, and the preset character string, where the charging authority includes the right to charge; if it is detected that the charging authority is the right to charge, the charging pile is controlled to charge the vehicle to be charged. In this way, if the segmented image obtained by the first character recognition is not compliant for a specific position of the vehicle, the image acquisition parameters can be changed to perform character recognition again, and the character segmentation and image enhancement processes are used in the character recognition process, so that the character recognition of the vehicle to be charged is more accurate, thereby improving the accuracy of the authority judgment of the vehicle to be charged. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0022] Figure 1 This is a system architecture diagram of a charging pile charging system provided by an embodiment of the present application;

[0023] Figure 2 This is a flow chart of a vehicle authority identification method provided in an embodiment of the present application;

[0024] Figure 3 This is a flow chart of another vehicle authority identification method provided in an embodiment of the present application;

[0025] Figure 4 This is a schematic diagram of the structure of a vehicle authority identification device proposed in an embodiment of the present application;

[0026] Figure 5 This is a structural diagram of an electronic device proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 this application.

[0028] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or electronic device comprising a series of steps or units is not limited to the listed steps or units, but may, in an optional example, also include steps or units not listed, or may, in an optional example, include other steps or units inherent to the process, method, product, or electronic device.

[0029] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] The data analysis method, apparatus, device and storage medium provided in the embodiments of the present application can be applied to Figure 1 In the data analysis system shown. Figure 1 , Figure 1 This is a system architecture diagram of a charging pile charging system provided by an embodiment of the present application, such as Figure 1 As shown, the charging pile charging system 100 includes: a server 110 , a charging pile 120 and a mobile terminal 130 .

[0031] Among them, the mobile terminal 130 can communicate with the server 110 through the network. The mobile terminal 130 refers to a device used by the staff, such as a smartphone, computer, etc. In this solution, the mobile terminal 130 is provided with a user interface, which is mainly responsible for interacting with the server 110, so that the staff can easily view images or letters transmitted by the server, input instructions, and perform other operations. The server 110 refers to a remote computer used to process large amounts of computing tasks and store data. In this solution, one or more of the following models are deployed on the server 110: a feature extraction model, a convolutional neural network feature extraction model, a character recognition network model, an image enhancement sub-model, a character segmentation sub-model, and a character classification sub-model for analyzing vehicle permissions. The server 110 can also be used to collect data from the use of the above models to facilitate subsequent optimization of the above. The server 110 can transmit data to the mobile terminal 130, including but not limited to images or information. The server 110 can send control instructions to the charging pile 120, such as instructions to control whether the charging pile 120 charges or not.

[0032] Based on this, the present application provides a vehicle authority identification method, device, storage medium and electronic device, and the present application is described in detail below with reference to the accompanying drawings.

[0033] See also Figure 2 , Figure 2 This is a flow chart of a vehicle authority identification method provided by an embodiment of the present application. The method is applied to a server of a charging pile charging system. The charging pile charging system also includes a charging pile, such as Figure 2 As shown, the method includes:

[0034] S210 , obtaining a plurality of first segmented images of a first vehicle image of a vehicle to be charged, where the first vehicle image is a composite image obtained by photographing the vehicle to be charged at multiple angles.

[0035] The vehicle to be charged may be a vehicle parked at a charging station, ready for charging. The charging station may be equipped with multiple cameras for capturing images of the vehicle to be charged, including a first vehicle image. The server obtains multi-angle images captured by the multiple cameras, then synthesizes the multi-angle images into a complete image of the target area of ​​the vehicle to be charged, i.e., the first vehicle image, and then obtains a first segmented image based on the first vehicle image. The target area may include a VIN code, and in some cases, may also include a license plate number.

[0036] In a possible embodiment, obtaining multiple first segmented images of a first vehicle image of a vehicle to be charged includes: obtaining multiple first segmented images based on a sliding window method, a trained feature extraction model, a trained character recognition network model, and a first vehicle image, wherein the trained feature extraction model includes a trained convolutional neural network feature extraction model; including: obtaining multiple first window images in sequence based on the sliding window method and the first vehicle image; performing feature extraction on the multiple first window images based on the trained convolutional neural network feature extraction model to obtain first window image feature probabilities; performing judgment based on the first window image feature probabilities and a preset probability threshold to obtain a first region image; and obtaining N first segmented images based on the first region image and the trained character recognition network model, where N is an integer greater than or equal to 0.

[0037] Among them, after obtaining the first vehicle image, the server performs image processing based on the sliding window method, the trained feature extraction model, and the trained character recognition network model to obtain the first segmented image, wherein the sliding window method is to slide a window of a specific size (which can be fixed or dynamically changed) on the first vehicle image to obtain multiple first window images in sequence. The above-mentioned window of a specific size can be set according to a preset size. For example, if the target area is an area that may contain a VIN code, the size of the window can be set to the size of each character in the vehicle VIN code. The trained feature extraction model is a model for extracting features from each first window image to obtain a window image that may contain characters. The trained character recognition network model is used to perform further character recognition on the window image that may contain characters to obtain accurate characters.

[0038] The trained feature extraction model may be a trained convolutional neural network feature extraction model or a support vector machine feature extraction model, wherein the convolutional neural network feature extraction model is a model for feature extraction based on a convolutional neural network. The character recognition network model may be a network model based on a long short-term memory (LSTM) model.

[0039] Specifically, based on the sliding window method, multiple first window images are obtained with a fixed step size in the first vehicle image. The fixed step size can be determined by the window size. For example, the step size is set to be equal to the length or width of the window, that is, there is no gap in the middle of each window movement. The first window image is then input into a trained data neural network feature extraction model. The trained data neural network feature extraction model includes a convolution layer, a pooling layer, and a fully connected layer. The convolution layer is used to perform a convolution operation based on the input multiple first window images to obtain a feature map. The pooling layer is then used to reduce the spatial dimension of the feature map output by the convolution layer. The pooling layer is then used to flatten the feature map after the spatial dimension is reduced and output a probability value, namely the first window image feature probability. The first window image feature probability is the value output by the final trained data neural network feature extraction model. Each input first window image corresponds to a first window image feature probability. The first window image feature probability represents the probability value that the corresponding first window image may contain a character. The first window image feature probability is then compared with a preset probability threshold. If the first window image feature probability is greater than the preset probability threshold, the first window image is used as part of the first region image. After all first window images have been evaluated, all first window images corresponding to first window image feature probabilities greater than the preset probability threshold are aggregated to obtain a first region image. This first region image represents the region most likely to contain a VIN code. A trained character recognition network model is then input into the first region image. The trained character recognition network model then performs specific character classification and recognition on the first region image, obtaining N first segmented images, each representing a character, where N is an integer greater than or equal to 0.

[0040] Specifically, the process of extracting features from multiple first window images based on the trained convolutional neural network feature extraction model to obtain the feature probability of the first window image can be: applying multiple convolution kernels K in the convolution layer to perform a convolution operation on each first window image. The specific formula can be Where I is the first window image of the input, K is the convolution kernel, O ij Or the pixel value of the feature map at position (i, j), I (i+m)(j+n) represents the pixel value of the input image, i.e. the first window image, at position (i+m, j+n), K mn : represents the value (weight) of the convolution kernel at position (m, n). Then the pooling layer is based on O ij The pixel value of the first window image after reducing the spatial dimension of the feature map is obtained by the following formula, P ij =max m,n O (i+m)(j+n) , where P ij Represents the pixel value of the output image (or feature map) at position (i, j) after pooling, O(i+m)(j+n) Represents the pixel value at position (i+m, j+n) of the intermediate output image (or feature map) obtained after the convolution operation. Then the fully connected layer converts P ij Perform vector expansion to obtain a vector V, which is a one-dimensional vector. Then, perform at least one of weighted summation and nonlinear transformation based on these vectors V to obtain and output the first window image feature probability P(VIN). The specific formula can be: P(VIN) = σ(W·V+b), where W is the weight matrix of the fully connected layer, each row represents the weight of an output node (usually a category) to the input feature, b is a bias term used to offset after the weighted summation, and σ is an activation function, which converts the linear combination of the input into a probability value.

[0041] It can be seen that in this embodiment, the area in the first vehicle image that is most likely to contain the identification code is obtained through the sliding window method, the trained feature extraction model, the trained character recognition network model and the first vehicle image, which lays the foundation for subsequent character recognition and can make subsequent character recognition more accurate.

[0042] In a possible embodiment, the trained character recognition network model includes at least one of an image enhancement sub-model, a character segmentation sub-model, and a character classification sub-model. Obtaining N first segmented images based on the first region image and the trained character recognition network model includes: performing an image preprocessing operation based on the first region image and the image enhancement sub-model to obtain a second region image, and the image preprocessing operation is used to clarify the first region image; performing a character segmentation operation based on the second region image and the character segmentation sub-model to obtain a third region image, and the third region image includes multiple segmented character image blocks; and inputting the third region image into the character classification sub-model to obtain N first segmented images.

[0043] Among them, the character network model can include one or more of an image enhancement sub-model, a character segmentation sub-model and a character classification sub-model, and can be combined together to obtain a character network model. When the character network model contains an image enhancement sub-model, a character segmentation sub-model and a character classification sub-model, the first area image is input into the image enhancement sub-model for image preprocessing operations to make the first area image clearer and better for subsequent processing, thereby obtaining a second area image. The second area image is then input into the character segmentation sub-model to perform character cutting so that each character is accurately cut out, and an image including only the character part is obtained, i.e., a third area image. The third area image is then input into the character classification sub-model, and the character classification sub-model performs detailed classification of the characters, excludes characters that may be confused, and outputs accurate character types, which include each type of number and each type of letter.

[0044] Specifically, the image enhancement sub-model is used to pre-process the input image, including but not limited to grayscale, binarization, and image enhancement. Among them, the grayscale process includes converting a color image into a grayscale image, so that the computational complexity of the image is reduced, but important edge information is retained. Among them, the binarization process includes converting the grayscale image into a black and white image through threshold processing. The specific method can be to use the maximum inter-class variance method to automatically calculate the threshold and then convert it into a binary image. Other methods can also be used, which are not limited here. Among them, the image enhancement process can include performing image enhancement by using image enhancement methods such as histogram equalization or Laplace sharpening to improve the contrast and clarity of the image.

[0045] Specifically, the character segmentation sub-model can be implemented by a projection method or the like, so that the characters are cut out at the edge line to obtain a third region image.

[0046] Specifically, the character sub-classification model may include an input layer, a feature extraction layer, an LSTM layer, a fully connected layer, and an output layer, wherein the input layer is used to flatten the input third region image into a one-dimensional vector, the feature extraction layer is used to perform feature extraction on the one-dimensional vector through a convolutional layer to obtain a feature vector corresponding to each character, and then the feature vector corresponding to each character is input into the LSTM layer, the LSTM layer processes the input character image features in the input order to obtain hidden state parameters, and then the hidden state parameters are input into the fully connected layer, and the fully connected layer maps the hidden state parameters to a specific classification result, and then the output layer obtains a sequence including N characters according to the specific classification result, that is, N first segmented images.

[0047] Specifically, the LSTM layer has a forget gate, an input gate, a memory cell state update, and an output gate. The forget gate: f t =σ(W f ·[h t-1 ,x t ]+b f ), where f t Represents the output of the forget gate, W f is the weight matrix, b f is the bias term, [h t-1 ,x t ] is the hidden state h at the previous moment t-1 and the current input x t σ is the activation function that limits the output to between 0 and 1. Input gate: i t =σ(W i ·[h t-1 ,x t ]+b i ), where i t represents the output of the input gate, W i and bi is the weight matrix and bias term of the input gate. Candidate memory unit: in Represents the value of the candidate memory unit, W c and b c is the weight matrix and bias term of the input gate. Update the memory unit Among them C t is the current state of the memory unit, C t-1 Is the memory cell state at the previous moment. Output gate o t =σ(W o ·[h t-1 ,x t ]+b o ), where o t Represents the output of the output gate. Hidden state update h t =o t tanh(C t ), h t is the hidden state at the current moment, that is, the above hidden state parameters.

[0048] It can be seen that in this embodiment, through multi-model collaborative processing, the process of character segmentation and image enhancement is used in the character recognition process, which makes the character recognition of the vehicle to be charged more accurate, thereby improving the accuracy of the authority judgment of the vehicle to be charged.

[0049] S220, determining a first image processing instruction based on multiple first segmented images and preset image compliance conditions, the first image processing instruction including an image enhancement processing instruction under non-compliance conditions and a continue processing instruction under compliance conditions, the image compliance conditions being used to screen character features of the first segmented image or the segmented image obtained after the image enhancement processing instruction, the character features including character quantity features and character arrangement features.

[0050] Among them, the image compliance condition can be used to determine whether the first segmented image can comply with the character feature rules of the identification code. The character features include character quantity features and character arrangement features. Specifically, it can be the number of characters recognized by the first segmented image and the arrangement of the recognized characters, such as the order of numbers and letters. The first image processing instruction can be an image enhancement instruction issued when it is determined that the first segmented image is not compliant. It can be understood that if the recognized first segmented image does not comply with the arrangement and combination rules of the identification code, the recognized first segmented image is considered to be non-compliant, that is, the identification code cannot be compared, and then an image enhancement instruction is issued. The first image processing instruction also includes a continue processing instruction under the compliance condition, indicating that if the first segmented image is compliant, the next step is performed.

[0051] In a possible embodiment, the image compliance condition includes a quantity compliance condition and an arrangement compliance condition. The quantity compliance condition includes that the number N of the first segmented images is equal to the preset number of characters, and the arrangement compliance condition includes that the arrangement order of the first segmented images conforms to the preset arrangement order. Determining the first image processing instruction based on multiple first segmented images and the preset image compliance condition includes: judging whether the number N of the first segmented images conforms to the quantity compliance condition; if it is detected that the number N of the first segmented images does not conform to the quantity compliance condition, the first image processing instruction is an image enhancement processing instruction; if it is detected that the number N of the first segmented images conforms to the quantity compliance condition, and the arrangement order of the first segmented images conforms to the arrangement compliance condition, the first image processing instruction is a continue processing instruction, and the continue processing instruction is used to enable the server to detect the charging authority of the vehicle to be charged to determine whether the vehicle to be charged has the right to charge.

[0052] Among them, the image compliance conditions include quantity compliance conditions and arrangement compliance conditions. The quantity compliance conditions are used to limit whether the quantity of the first segmented image or the second segmented image is compliant, and the arrangement compliance conditions are used to limit whether the arrangement between multiple first segmented images or multiple second segmented images meets the arrangement standards. For example, the quantity compliance condition can be whether the number of constrained characters is equal to a quantity value, and the arrangement compliance condition can be whether the constrained characters are arranged according to AAABBBBB, where A is an alphabetic character and B is a numeric character. The specific restrictions of the above quantity compliance conditions and arrangement compliance conditions are pre-set.

[0053] Among them, the number of multiple first segmented images can be N. After obtaining N first segmented images, the number N of the first segmented images is judged according to the quantity compliance condition to determine whether N meets the quantity compliance condition. If N meets the quantity compliance condition, then it is determined whether the arrangement of the first segmented images meets the arrangement compliance condition. If it meets the arrangement compliance condition, then it is considered that the first segmented image meets the image compliance condition, and then it is confirmed that the image processing instruction at this time is a continue processing instruction, that is, it is detected whether the first segmented image has charging permission and no image processing is required. If N meets the quantity compliance condition but the first segmented image does not meet the arrangement compliance condition, or if N does not meet the quantity compliance condition, then it is considered that the first segmented image does not meet the image compliance condition, and then it is confirmed that the image processing instruction at this time is an image enhancement processing instruction.

[0054] Specifically, if it is detected that the first image processing instruction is a continue processing instruction, a match is performed based on the second segmented image and a preset string in the database. The preset string is an identification code that has been entered for charging at a charging pile, specifically a VIN code or a license plate number; if a matching preset string is detected, the charging permission of the vehicle to be charged is determined to be authorized to charge; if no matching preset string is detected, the charging permission of the vehicle to be charged is determined to be unauthorized to charge.

[0055] For example, if the number of detected first segmented images is 17, specifically 1HGCM82633A004352, the number compliance condition in the image compliance condition includes the number being 17, and the number arrangement condition includes ABBBBAAAAABAAAAAA, where A represents a number and B represents an uppercase letter. Then, after determination, the first segmented images are deemed to meet the image compliance condition.

[0056] It can be seen that in this embodiment, by performing image compliance judgment on multiple first segmented images obtained after segmentation and character recognition, compliance judgment is performed in advance, so that correct, clear and accurate character strings can be matched when performing subsequent permission judgment, thereby improving the accuracy of permission judgment.

[0057] S230: If it is detected that the first image processing instruction is an image enhancement processing instruction, adjust the image acquisition parameters of the target camera, control the target camera to capture a second vehicle image of the vehicle to be charged, and obtain multiple second segmented images of the second vehicle image.

[0058] If the first segmented image is determined not to meet the image compliance condition, the first image processing instruction is confirmed to be an image enhancement processing instruction. The image enhancement processing instruction is then sent to the target camera, controlling the target camera to capture a second vehicle image of the vehicle to be charged. The image enhancement processing instruction is used to control the target camera to adjust parameters, including but not limited to adjusting autofocus parameters, auto-exposure parameters, and auto-white balance parameters, so that the current target camera can capture a clearer image, i.e., the second vehicle image, under the current circumstances.

[0059] The second segmented image is obtained by performing multi-model processing based on the second vehicle image through a process similar to the method of obtaining the first segmented image.

[0060] Among them, the autofocus parameter adjustment can use the image edge or contrast information to adjust the focal length through the autofocus algorithm. The goal of focusing is to maximize the sharpness or contrast of the edges in the image. The autofocus algorithm usually calculates the Laplace operator of the image to measure the clarity of the image. When the calculation result of the Laplace operator reaches the maximum value, it means that the image is in the best focus state. The adjustment of the automatic exposure parameters can ensure that the brightness of the image is moderate by adjusting the exposure time or aperture of the camera to avoid overexposure or underexposure. The adjustment of the automatic white balance parameters can adjust the balance of the RGB channels according to the color temperature of the image to ensure the accuracy of the image color, especially the color difference problem of characters.

[0061] In a possible embodiment, the image acquisition parameters include at least one of an autofocus parameter, an auto-exposure parameter, and an auto-white balance parameter, and acquiring multiple second segmented images of the second vehicle image includes: sequentially acquiring multiple second window images based on a sliding window method and the second vehicle image; performing feature extraction on the multiple second window images based on a trained convolutional neural network feature extraction model to obtain second window image feature probabilities; performing judgment based on the second window image feature probabilities and a preset probability threshold to obtain a second area image; and obtaining M second segmented images based on the second area image and a trained character recognition network model, where M is an integer greater than or equal to 0.

[0062] After obtaining the second vehicle image, the server performs image processing based on the sliding window method, the trained feature extraction model, and the trained character recognition network model to obtain a second segmented image. The sliding window method is to slide a window of a specific size (which can be fixed or dynamically changed) on the second vehicle image to obtain multiple second window images in sequence. The above-mentioned window of a specific size can be set according to a preset size. For example, if the target area is an area that may contain a VIN code, the size of the window can be set to the size of each character in the vehicle VIN code. The trained feature extraction model is a model for extracting features from each second window image to obtain a window image that may contain characters. The trained character recognition network model is used to perform further character recognition on the window image that may contain characters to obtain accurate characters.

[0063] The trained feature extraction model may be a trained convolutional neural network feature extraction model or a support vector machine feature extraction model, wherein the convolutional neural network feature extraction model is a model for feature extraction based on a convolutional neural network. The character recognition network model may be a network model based on a long short-term memory (LSTM) model.

[0064] It should be noted that the detailed explanation of the above-mentioned convolutional neural network feature extraction model, sliding window method, and character recognition network model is referred to the description of step S210 and will not be repeated here. M and N can be the same or different.

[0065] It can be seen that in this embodiment, after the target camera is adjusted, the second vehicle image is obtained again, and then the area in the second vehicle image that is most likely to contain the identification code is obtained through the sliding window method, the trained feature extraction model, the trained character recognition network model and the second vehicle image. This can reduce the impact of the external environment on the vehicle recognition accuracy, lay the foundation for subsequent character recognition, and make subsequent character recognition more accurate.

[0066] S240 , detecting the charging authority of the vehicle to be charged based on the plurality of second segmented images, the image compliance condition, and a preset character string, where the charging authority includes the right to charge.

[0067] Among them, the image compliance condition can be used to determine whether the second segmented image can meet the character feature rules of the identification code. The character features include character quantity features and character arrangement features. Specifically, it can be the number of characters recognized by the second segmented image and the arrangement of the recognized characters, such as the order of numbers and letters.

[0068] Among them, similar to the first segmented image and image compliance condition judgment method, a second image processing instruction can be obtained based on the image compliance condition. The second image processing instruction may include a continue processing instruction under the compliance condition, indicating that if the second segmented image is compliant, the next operation is performed. The next operation may be to detect the charging authority of the second segmented image, that is, to determine whether there is charging authority. The above-mentioned charging authority includes the right to charge.

[0069] In a possible embodiment, the segmented image also includes a second segmented image, the quantity compliance condition also includes that the number M of the second segmented images is equal to the preset number of characters, the arrangement compliance condition also includes that the arrangement order of multiple second segmented images complies with the preset arrangement order, the second image processing instruction includes an image enhancement processing instruction under the non-compliance condition and a continue processing instruction under the compliance condition, and the charging permission also includes unauthorized charging; detecting the charging permission of the vehicle to be charged based on the multiple second segmented images, image compliance conditions and permission determination conditions includes: determining whether the number M of the second segmented images complies with the quantity compliance condition; if it is detected that the number M of the second segmented images complies with the quantity compliance condition, and the arrangement order of the multiple second segmented images complies with the arrangement compliance condition, then the second image processing instruction is a continue processing instruction; if it is detected that the second image processing instruction is a continue processing instruction, then matching is performed based on the second segmented image and a preset character string in the database; if a matching preset character string is detected, then the charging permission of the vehicle to be charged is determined to be authorized charging; if no matching preset character string is detected, then the charging permission of the vehicle to be charged is determined to be unauthorized charging.

[0070] The second image processing instruction may be an image enhancement instruction issued when the second segmented image is determined to be non-compliant. This instruction can be understood as follows: if the identified second segmented image does not conform to the permutation and combination rules of the identification code, the identified second segmented image is considered non-compliant, i.e., the identification code cannot be compared, and an image enhancement instruction is issued. The second image processing instruction also includes a continue processing instruction under the compliance condition, indicating that if the second segmented image conforms, the next step is performed.

[0071] For the description of the image compliance conditions, please refer to the description of step S220 and will not be repeated here.

[0072] The number of the plurality of second segmented images may be M. After obtaining the M second segmented images, the number M of the second segmented images is judged according to the quantity compliance condition to determine whether M meets the quantity compliance condition. If M meets the quantity compliance condition, then the arrangement of the second segmented images is determined to determine whether it meets the arrangement compliance condition. If it meets the arrangement compliance condition, then the second segmented image is considered to meet the image compliance condition, and the image processing instruction is confirmed to be a continue processing instruction, i.e., whether the second segmented image has charging permission. If M meets the quantity compliance condition but the second segmented image does not meet the arrangement compliance condition, or if M does not meet the quantity compliance condition, then the second segmented image is considered to not meet the image compliance condition.

[0073] It can be seen that in this embodiment, after obtaining the second vehicle image, the second vehicle image is processed to obtain a second segmented image, and then the compliance of the second segmented image is judged, so that when performing subsequent authority judgment, there are correct, clear and accurate character strings to match, thereby improving the accuracy of the authority judgment.

[0074] In a possible embodiment, the charging pile charging system also includes a mobile terminal, which is used for manual processing by staff. After the step of detecting the charging permission of the vehicle to be charged based on multiple second segmented images, image compliance conditions and preset character strings, the method also includes: if it is detected that the second segmented image does not meet the image compliance conditions, sending the vehicle image and / or the first segmented image and / or the second segmented image to the mobile terminal; obtaining charging permission information from the mobile terminal, the charging permission information including charging permission.

[0075] Among them, after the image enhancement is performed and the second segmented image is obtained, if the server still cannot obtain a compliant second segmented image, it will send one or more of the first vehicle image, the second vehicle image, the first segmented image, and the second segmented image to the mobile terminal, or it can send the image of the entire vehicle to the mobile terminal. The mobile terminal is an electronic device held by the staff and can be used to view images, receive or send data, etc. The staff will make a manual judgment based on one or more of the above-mentioned first vehicle image, the second vehicle image, the first segmented image, the second segmented image, and the image of the entire vehicle. The server then obtains the charging permission information of the vehicle to be charged from the mobile terminal and controls whether the charging pile is charging based on the charging permission information.

[0076] It can be seen that in this embodiment, when the server is unable to perform accurate recognition, the image is transmitted to the staff's mobile terminal, and the staff performs recognition and authority judgment, which to a certain extent improves the accuracy of the charging authority judgment of the charging vehicle and increases flexibility.

[0077] S250: If it is detected that the charging authority is authorized to charge, the charging pile is controlled to charge the vehicle to be charged.

[0078] In a possible embodiment, if the server directly determines that the charging permission is unauthorized charging, the vehicle image and / or the first segmented image and / or the second segmented image are sent to the mobile terminal; and charging permission information is obtained from the mobile terminal, where the charging permission information includes charging permission.

[0079] The case where the server directly determines that charging is unauthorized includes the case where the server directly determines that charging is unauthorized based on the first segmented image and the preset character string, and also includes the case where the server directly determines that charging is unauthorized based on the second segmented image and the preset character string.

[0080] Among them, when it is determined that the second segmented image meets the image compliance conditions, but is not matched according to the preset character string in the database, that is, the charging permission is unauthorized charging, one or more of the first vehicle image, the second vehicle image, the first segmented image, and the second segmented image are sent to the mobile terminal, or the image of the entire vehicle can be sent to the mobile terminal. The mobile terminal is an electronic device held by the staff and can be used to view images, receive or send data, etc. The staff makes a manual judgment based on one or more of the above-mentioned first vehicle image, the second vehicle image, the first segmented image, the second segmented image, and the image of the entire vehicle. The server then obtains the charging permission information of the vehicle to be charged from the mobile terminal and controls whether the charging pile is charging based on the charging permission information.

[0081] It can be seen that in this embodiment, after it is determined that the vehicle is not authorized to charge, manual judgment can also be performed, which increases the flexibility and accuracy of vehicle charging authority identification.

[0082] It can be seen that according to this embodiment, multiple first segmented images of the first vehicle image of the vehicle to be charged are obtained, and the first vehicle image is a composite image obtained by shooting the vehicle to be charged from multiple angles; a first image processing instruction is determined based on the multiple first segmented images and the preset image compliance condition, and the first image processing instruction includes an image enhancement processing instruction under non-compliance conditions and a continue processing instruction under compliance conditions. The image compliance condition is used to screen the character features of the first segmented image or the segmented image obtained after the image enhancement processing instruction, and the character features include character quantity features and character arrangement features; if it is detected that the first image processing instruction is an image enhancement processing instruction, the image acquisition parameters of the target camera are adjusted, and the target camera is controlled to shoot the second vehicle image of the vehicle to be charged; and multiple second segmented images of the second vehicle image are obtained; based on the multiple second segmented images, the image compliance condition and the preset character string, the charging authority of the vehicle to be charged is detected, and the charging authority includes the right to charge; if it is detected that the charging authority is the right to charge, the charging pile is controlled to charge the vehicle to be charged. In this way, when the segmented image obtained by the first character recognition is not compliant for a specific position of the vehicle, the image acquisition parameters can be changed to perform character recognition again, and the character segmentation and image enhancement processes are used in the character recognition process to make the character recognition of the vehicle to be charged more accurate, thereby improving the accuracy of the authority judgment of the vehicle to be charged.

[0083] In one possible embodiment, see Figure 3 , Figure 3 This is a flow chart of another vehicle authority identification method proposed in an embodiment of the present application. Figure 3As shown, after a vehicle to be charged reaches a preset charging area or is plugged into a charging gun, a vehicle image is captured. This vehicle image includes a first vehicle image during the first cycle and a second vehicle image during other cycles. Multiple segmented images are then generated based on a sliding window method, a trained feature extraction model, and a trained character recognition network model. These segmented images include the first segmented image during the first cycle and the second segmented image during other cycles. The segmented images are then judged to determine whether they meet image compliance conditions, and image processing instructions are generated. These image processing instructions include the first image processing instruction during the first cycle and the second image processing instruction during other cycles. If it does not comply with the rules, determine whether it is the first cycle. If it is the first cycle, the image processing instruction is an image enhancement processing instruction, adjust the image acquisition parameters of the target camera, the image acquisition parameters automatic focus parameters, automatic exposure parameters, and automatic white balance parameters, re-acquire the vehicle image, and then perform a second cycle. If it is not the first cycle, perform manual judgment; if it complies, the image processing instruction is a continue processing instruction, and determine the charging authority of the vehicle to be charged corresponding to the segmented image according to the preset character string. If there is charging authority, the charging pile is controlled to start charging. If there is no charging authority, manual judgment is performed.

[0084] It can be seen that according to this embodiment, when the segmented image obtained by the first character recognition is not compliant for a specific position of the vehicle, the image acquisition parameters can be changed to perform character recognition again, and the character segmentation and image enhancement processes are used in the character recognition process, so that the character recognition of the vehicle to be charged is more accurate, thereby improving the accuracy of the authority judgment of the vehicle to be charged.

[0085] See Figure 4 , Figure 4 This is a structural diagram of a vehicle authority identification device proposed in an embodiment of the present application. The device is applied to a server of a charging pile charging system. The charging pile charging system also includes a charging pile. The vehicle authority identification device 400 includes: an acquisition module 410, a determination module 420, an adjustment module 430, a detection module 440, and a control module 450, wherein,

[0086] An acquisition module 410 is configured to acquire a plurality of first segmented images of a first vehicle image of a vehicle to be charged, where the first vehicle image is a composite image obtained by photographing the vehicle to be charged from multiple angles;

[0087] Determination module 420, configured to determine a first image processing instruction based on the plurality of first segmented images and a preset image compliance condition, wherein the first image processing instruction includes an image enhancement processing instruction under a non-compliance condition and a continue processing instruction under a compliance condition, wherein the image compliance condition is configured to screen character features of the first segmented image or the segmented image obtained after the image enhancement processing instruction, wherein the character features include a character quantity feature and a character arrangement feature;

[0088] An adjustment module 430 is configured to adjust image acquisition parameters of a target camera if it is detected that the first image processing instruction is an image enhancement processing instruction, and control the target camera to capture a second vehicle image of the vehicle to be charged; and obtain a plurality of second segmented images of the second vehicle image;

[0089] A detection module 440 is configured to detect the charging authority of the vehicle to be charged based on the plurality of second segmented images, the image compliance condition, and a preset character string, wherein the charging authority includes the right to charge;

[0090] The control module 450 is configured to control the charging pile to charge the vehicle to be charged if it is detected that the charging authority is authorized to charge.

[0091] In a possible embodiment, the acquisition module 410 is specifically configured to acquire a plurality of first segmented images of the first vehicle image of the vehicle to be charged by:

[0092] Acquiring a plurality of first segmented images based on a sliding window method, a trained feature extraction model, a trained character recognition network model, and a first vehicle image, wherein the trained feature extraction model includes a trained convolutional neural network feature extraction model; including:

[0093] sequentially acquiring a plurality of first window images based on a sliding window method and the first vehicle image;

[0094] Performing feature extraction on the plurality of first window images based on the trained convolutional neural network feature extraction model to obtain first window image feature probabilities;

[0095] A first region image is obtained by performing a judgment based on the first window image feature probability and a preset probability threshold;

[0096] N first segmented images are obtained based on the first region image and the trained character recognition network model, where N is an integer greater than or equal to 0.

[0097] In a possible embodiment, the acquisition module 410 is specifically configured to obtain N first segmented images based on the first region image and the trained character recognition network model:

[0098] performing an image preprocessing operation based on the first region image and the image enhancement sub-model to obtain a second region image, wherein the image preprocessing operation is used to make the first region image clearer;

[0099] Performing a character segmentation operation based on the second region image and the character segmentation sub-model to obtain a third region image, wherein the third region image includes a plurality of segmented character image blocks;

[0100] The third region image is input into the character classification sub-model to obtain N first segmented images.

[0101] In a possible embodiment, the determination module 420, in determining the first image processing instruction based on the plurality of first segmented images and a preset image compliance condition, is specifically configured to:

[0102] Determine whether the number N of the first segmented images meets the quantity compliance condition;

[0103] If it is detected that the number N of the first segmented images does not meet the quantity compliance condition, then the first image processing instruction is an image enhancement processing instruction;

[0104] If it is detected that the number N of the first segmented images meets the quantity compliance condition, and the arrangement order of the first segmented images meets the arrangement compliance condition, then the first image processing instruction is a continue processing instruction, which is used to enable the server to detect the charging authority of the vehicle to be charged to determine whether the vehicle to be charged has the right to charge.

[0105] In a possible embodiment, the acquisition module 410 is specifically configured to:

[0106] sequentially acquiring a plurality of second window images based on a sliding window method and a second vehicle image;

[0107] Performing feature extraction on the plurality of second window images based on the trained convolutional neural network feature extraction model to obtain feature probabilities of the second window images;

[0108] A second region image is obtained by performing a judgment based on the second window image feature probability and a preset probability threshold;

[0109] M second segmented images are obtained based on the second region image and the trained character recognition network model, where M is an integer greater than or equal to 0.

[0110] In a possible embodiment, the detection module 440 is specifically configured to detect the charging authority of the vehicle to be charged based on the plurality of second segmented images, the image compliance conditions, and the authority determination conditions:

[0111] Determining whether the number M of the second segmented images meets a quantity compliance condition;

[0112] If it is detected that the number M of the second segmented images meets the number compliance condition, and the arrangement order of the plurality of second segmented images meets the arrangement compliance condition, then the second image processing instruction is a continue processing instruction;

[0113] If the second image processing instruction is detected as a continue processing instruction, a match is performed based on the second segmented image and a preset character string in the database; if a matching preset character string is detected, the charging permission of the vehicle to be charged is determined to be authorized to charge; if no matching preset character string is detected, the charging permission of the vehicle to be charged is determined to be unauthorized to charge.

[0114] In a possible embodiment, the detection module 440 is further configured to detect the charging authority of the vehicle to be charged based on the plurality of second segmented images, the image compliance conditions, and the authority determination conditions:

[0115] If it is detected that the second segmented image does not meet the image compliance condition, sending the vehicle image and / or the first segmented image and / or the second segmented image to the mobile terminal;

[0116] Charging authority information is acquired from the mobile terminal, where the charging authority information includes charging authority.

[0117] It is worth noting that the specific functional implementation of the vehicle authority identification device can be found in the above Figure 2 The description of the vehicle authority identification method shown, such as the acquisition module 410 is used to implement the relevant content of executing S210. The various units or modules in the vehicle authority identification device 400 can be individually or completely merged into one or several other units or modules to form a structure, or one (some) of the units or modules can be further divided into multiple functionally smaller units or modules to form a structure, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present invention. The above-mentioned units or modules are divided based on logical functions. In actual applications, the functions of one unit (or module) are implemented by multiple units (or modules), or the functions of multiple units (or modules) are implemented by one unit (or module).

[0118] It can be seen that the vehicle authority identification device described in the embodiment of the present application obtains multiple first segmented images of the first vehicle image of the vehicle to be charged, and the first vehicle image is a composite image obtained by shooting the vehicle to be charged from multiple angles; a first image processing instruction is determined based on the multiple first segmented images and the preset image compliance condition, and the first image processing instruction includes an image enhancement processing instruction under non-compliance conditions and a continue processing instruction under compliance conditions. The image compliance condition is used to screen the character features of the first segmented image or the segmented image obtained after the image enhancement processing instruction, and the character features include character quantity features and character arrangement features; if it is detected that the first image processing instruction is an image enhancement processing instruction, the image acquisition parameters of the target camera are adjusted, and the target camera is controlled to shoot the second vehicle image of the vehicle to be charged; and multiple second segmented images of the second vehicle image are obtained; based on the multiple second segmented images, the image compliance condition and the preset character string, the charging authority of the vehicle to be charged is detected, and the charging authority includes the right to charge; if the charging authority is detected to be the right to charge, the charging pile is controlled to charge the vehicle to be charged. In this way, if the segmented image obtained by the first character recognition is not compliant for a specific position of the vehicle, the image acquisition parameters can be changed to perform character recognition again, and the character segmentation and image enhancement processes are used in the character recognition process, so that the character recognition of the vehicle to be charged is more accurate, thereby improving the accuracy of the authority judgment of the vehicle to be charged.

[0119] See also Figure 5 , Figure 5 This is a structural diagram of an electronic device proposed in an embodiment of the present application. As shown in the figure, the electronic device 500 includes a processor 510, a memory 520, a communication interface 530 and one or more programs 521. The one or more programs 521 are stored in the memory 520 and are configured to be executed by the processor 510.

[0120] The processor 510, the memory 520, and the communication interface 530 are interconnected and perform communication between them.

[0121] The memory 520 can be a volatile memory such as a dynamic random access memory DRAM, or a non-volatile memory such as a mechanical hard disk. The memory 520 is used to store a set of executable program codes, and the processor 510 is used to call one or more programs 521 stored in the memory 520, and can execute the above-mentioned Figure 2 Part or all of the steps of any vehicle authority identification method recorded in the embodiments.

[0122] Among them, the electronic device 500 may include smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, driving recorders, vehicle-mounted electronic devices, servers, laptops, mobile Internet electronic devices (MID, Mobile Internet Devices) or wearable electronic devices (such as smart watches, Bluetooth headsets), etc. The above are only examples and not exhaustive, including but not limited to the above electronic devices.

[0123] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.

[0124] The present application also provides a computer program product comprising a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may comprise an electronic device.

[0125] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0126] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0127] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0128] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0129] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0130] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions for enabling a computer electronic device (which can be a personal computer, electronic device or network electronic device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0131] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0132] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein 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 and core idea of ​​the present application. At the same time, for those skilled in the art, based on the ideas of the present application, there may 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 vehicle authority identification method, characterized in that: A server applied to a charging pile charging system, wherein the charging pile charging system further includes a charging pile, and the method includes: Obtaining multiple first segmented images based on a sliding window method, a trained feature extraction model, a trained character recognition network model, and a first vehicle image, including: sequentially obtaining multiple first window images based on the sliding window method and the first vehicle image, performing feature extraction on the multiple first window images based on the trained convolutional neural network feature extraction model to obtain first window image feature probabilities, performing a judgment based on the first window image feature probabilities and a preset probability threshold to obtain a first region image, and obtaining N first segmented images based on the first region image and the trained character recognition network model, where N is an integer greater than or equal to 0, the trained feature extraction model includes a trained convolutional neural network feature extraction model, and the first vehicle image is a composite image obtained by photographing the vehicle to be charged from multiple angles; Determining a first image processing instruction based on the multiple first segmented images and a preset image compliance condition, the first image processing instruction including an image enhancement processing instruction under a non-compliance condition and a continue processing instruction under a compliance condition, the image compliance condition being used to screen character features of the first segmented image or the segmented image obtained after the image enhancement processing instruction, the character features including a character quantity feature and a character arrangement feature; If it is detected that the first image processing instruction is the image enhancement processing instruction, adjusting the image acquisition parameters of the target camera and controlling the target camera to capture a second vehicle image of the vehicle to be charged; and acquiring a plurality of second segmented images of the second vehicle image; detecting the charging authority of the vehicle to be charged based on the plurality of second segmented images, the image compliance condition, and a preset character string, wherein the charging authority includes the right to charge; If it is detected that the charging authority is the authorized charging, the charging pile is controlled to charge the vehicle to be charged.

2. The method according to claim 1, characterized in that The trained character recognition network model includes at least one of an image enhancement sub-model, a character segmentation sub-model, and a character classification sub-model, and obtaining the N first segmented images based on the first region image and the trained character recognition network model includes: performing an image preprocessing operation based on the first region image and the image enhancement sub-model to obtain a second region image, wherein the image preprocessing operation is used to sharpen the first region image; Performing a character segmentation operation based on the second region image and the character segmentation sub-model to obtain a third region image, wherein the third region image includes a plurality of segmented character image blocks; The third region image is input into the character classification sub-model to obtain N first segmented images.

3. The method according to claim 1 or 2, characterized in that The image compliance condition includes a quantity compliance condition and an arrangement compliance condition, wherein the quantity compliance condition includes that the number N of the first segmented images is equal to the number of preset characters, and the arrangement compliance condition includes that the arrangement order of the first segmented images complies with the preset arrangement order. Determining the first image processing instruction based on the multiple first segmented images and the preset image compliance conditions includes: Determining whether the number N of the first segmented images meets the number compliance condition; If it is detected that the number N of the first segmented images does not meet the number compliance condition, the first image processing instruction is the image enhancement processing instruction; If it is detected that the number N of the first segmented images meets the quantity compliance condition, and the arrangement order of the first segmented images meets the arrangement compliance condition, then the first image processing instruction is the continue processing instruction, and the continue processing instruction is used to enable the server to detect the charging authority of the vehicle to be charged to determine whether the vehicle to be charged has the right to charge.

4. The method according to claim 3, characterized in that The image acquisition parameter includes at least one of an auto-focus parameter, an auto-exposure parameter, and an auto-white balance parameter, and acquiring a plurality of second segmented images of the second vehicle image includes: sequentially acquiring a plurality of second window images based on the sliding window method and the second vehicle image; Performing feature extraction on the plurality of second window images based on the trained convolutional neural network feature extraction model to obtain second window image feature probabilities; Obtaining a second region image by performing a judgment based on the second window image feature probability and a preset probability threshold; M second segmented images are obtained based on the second region image and the trained character recognition network model, where M is an integer greater than or equal to 0.

5. The method according to claim 4, characterized in that The segmented image also includes the second segmented image, the quantity compliance condition further includes that the number M of the second segmented images is equal to a preset number of characters, the arrangement compliance condition further includes that the arrangement order of the plurality of second segmented images complies with a preset arrangement order, the second image processing instruction includes an image enhancement processing instruction under a non-compliance condition and a continue processing instruction under a compliance condition, and the charging permission also includes unauthorized charging; detecting the charging permission of the vehicle to be charged based on the plurality of second segmented images, the image compliance condition, and the permission determination condition includes: Determining whether the number M of the second segmented images meets the number compliance condition; If it is detected that the number M of the second segmented images meets the number compliance condition, and the arrangement order of the plurality of second segmented images meets the arrangement compliance condition, then the second image processing instruction is the continue processing instruction; If it is detected that the second image processing instruction is the continue processing instruction, a match is performed based on the second segmented image and a preset character string in the database; if a matching preset character string is detected, the charging permission of the vehicle to be charged is determined to be the authorized charging; if no matching preset character string is detected, the charging permission of the vehicle to be charged is determined to be the unauthorized charging.

6. The method according to claim 5, characterized in that The charging pile charging system further includes a mobile terminal, which is used for manual processing by staff. After the step of detecting the charging permission of the to-be-charged vehicle based on the multiple second segmented images, the image compliance condition, and the preset character string, the method further includes: If it is detected that the second segmented image does not meet the image compliance condition, sending the vehicle image and / or the first segmented image and / or the second segmented image to the mobile terminal; Charging authority information is acquired from the mobile terminal, where the charging authority information includes the charging authority.

7. A vehicle authority identification device, characterized in that: The vehicle authority identification method according to claim 1 is applied to a server of a charging pile charging system, wherein the charging pile charging system further includes a charging pile, and the device includes: an acquisition module, configured to acquire multiple first segmented images based on a sliding window method, a trained feature extraction model, a trained character recognition network model, and a first vehicle image, comprising: sequentially acquiring multiple first window images based on the sliding window method and the first vehicle image, performing feature extraction on the multiple first window images based on the trained convolutional neural network feature extraction model to obtain first window image feature probabilities, performing a judgment based on the first window image feature probabilities and a preset probability threshold to obtain a first region image, and obtaining N first segmented images based on the first region image and the trained character recognition network model, wherein N is an integer greater than or equal to 0, the trained feature extraction model includes a trained convolutional neural network feature extraction model, and the first vehicle image is a composite image obtained by photographing the vehicle to be charged from multiple angles; a determination module, configured to determine a first image processing instruction based on the plurality of first segmented images and a preset image compliance condition, wherein the first image processing instruction includes an image enhancement processing instruction under a non-compliance condition and a continue processing instruction under a compliance condition, wherein the image compliance condition is used to screen character features of the first segmented image or the segmented image obtained after the image enhancement processing instruction, wherein the character features include a character quantity feature and a character arrangement feature; an adjustment module, configured to, if detecting that the first image processing instruction is the image enhancement processing instruction, adjust image acquisition parameters of a target camera, control the target camera to capture a second vehicle image of the vehicle to be charged, and acquire a plurality of second segmented images of the second vehicle image; a detection module, configured to detect the charging authority of the vehicle to be charged based on the plurality of second segmented images, the image compliance condition, and a preset character string, wherein the charging authority includes the right to charge; The control module is used to control the charging pile to charge the vehicle to be charged if it is detected that the charging authority is authorized to charge.

8. A computer-readable storage medium, characterized in that A vehicle authority identification program is stored, including an execution instruction. When a processor of an electronic device executes the execution instruction, the processor executes the method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: The method comprises a processor and a memory storing execution instructions, wherein the memory stores one or more programs; when the processor executes the execution instructions stored in the memory, the processor executes the method according to any one of claims 1 to 6.

Images