Vehicle management method and system for intelligent construction site

Abstract

The invention relates to an image processing technology, in particular to a vehicle management method and system for an intelligent construction site, and the method comprises the steps: obtaining a data set containing a vehicle cleaning image; taking the environment images of different weathers as style images; calculating a content weighting coefficient and a style weighting coefficient according to the vehicle cleaning image and the style image; setting a pre-training convolutional neural network, inputting a vehicle cleaning image and a style image, adding the product of the style weighting coefficient and the style loss and the product of the content weighting coefficient and the content loss to serve as a loss function, iterating the vehicle cleaning image by minimizing the loss function, and obtaining a style migration image after iteration is completed. And expanding a data set for training a vehicle cleanliness recognition model according to the style migration image. The method has the effect of improving the expansion data and quality.

Description

Technical Field

[0001] The present application relates to image processing technology, and specifically to a vehicle management method and system for smart construction sites. Background Art

[0002] In order to prevent construction vehicles from bringing mud and sand from the construction site into urban roads, it is necessary to supervise and manage the construction vehicles entering and leaving the construction site to ensure that the construction vehicles are effectively washed before leaving the construction site, thereby reducing the impact of construction on air quality. In order to reduce labor costs, when supervising and managing vehicles, a vehicle unwashed capture system is usually used to supervise and manage whether the vehicle has been washed.

[0003] In order to improve the efficiency of vehicle supervision and management, it is usually determined whether the vehicle is cleaned during the cleaning process, and the image is identified through a neural network to determine whether the vehicle is clean. For example, the patent application document with the publication number CN116758521A discloses a vehicle cleanliness detection method and device, which includes the steps of: obtaining a vehicle image to be detected; inputting the vehicle image to be detected into a batch linear mapping module in a pre-built vehicle cleanliness detection model, dividing the vehicle image to be detected into multiple image blocks, the vehicle cleanliness detection model is obtained by training the model with sample images marked with cleanliness labels, and inputting multiple image blocks in sequence; determining whether the vehicle cleanliness is qualified according to the output result of the vehicle cleanliness detection model.

[0004] Due to the limited number of training samples, there may be insufficient recognition accuracy, so the dataset needs to be expanded. The style transfer algorithm can apply the style of one image to another while retaining the content characteristics of the target image. The style transfer algorithm can be used to generate images under different weather conditions to expand the dataset.

[0005] However, the style transfer algorithm has the problem of how to balance content loss and style loss. Assigning unreasonable weights to content loss and style loss may affect the quality of the generated vehicle washing images in multiple environments and affect the recognition of vehicle washing effects. Summary of the invention

[0006] In order to solve the problem of how to balance content loss and style loss, the present application provides a vehicle management method and system for a smart construction site.

[0007] In a first aspect, the present application provides a vehicle management method for a smart construction site, which adopts the following technical solution: A vehicle management method for a smart construction site comprises the following steps: obtaining a data set including a vehicle washing image, calculating the content complexity and style feature vector of the vehicle washing image; using environmental images of different weather conditions as style images, calculating the content complexity and style feature vector of the style image; calculating a content weighting coefficient; the content weighting coefficient is proportional to the content complexity of the vehicle washing image and inversely proportional to the content complexity of the style image; calculating a style weighting coefficient; wherein the similarity between the style image vector and the style feature vector is obtained, the style weighting coefficient is inversely proportional to the similarity and inversely proportional to the content complexity of the vehicle washing image; setting a pre-trained convolutional neural network, inputting the vehicle washing image and the style image, adding the product of the style weighting coefficient and the style loss and the product of the content weighting coefficient and the content loss as a loss function, iterating the vehicle washing image by minimizing the loss function, obtaining a style transfer image after iteration, and expanding a data set for training a vehicle cleanliness recognition model according to the style transfer image.

[0008] The beneficial effects are as follows: content complexity indicates the amount of information contained in an image, the feature vector quantifies the degree of similarity between images, the style loss weight and the content loss weight are calculated based on the content complexity and style feature vector of the image, and the weight ratio of content loss to style loss is dynamically adjusted for each pair of images used for style transfer based on the characteristics of the vehicle washing image and the style image in the original data set, thereby ensuring that the image obtained by style transfer can not only retain the details and structure of the original image, but also accurately integrate the target's lighting scene and weather scene into the generated image, and finally generate a natural, delicate style transfer image that meets the requirements of specific scenarios. Expanding the data set based on the style transfer image is conducive to improving the accuracy of subsequent vehicle washing recognition and the accuracy of vehicle washing management.

[0009] Optionally, the calculation formula for the vehicle washing image content complexity is: ,in, Indicates The content complexity of the vehicle washing image, Indicates The maximum value of the pixel gradient value in the vehicle washing image. Indicates The mean value of the pixel gradient in the vehicle washing image, Indicates In the vehicle cleaning image, the gradient value is greater than The number of pixels; Indicates The number of pixels in the vehicle washing image, For the The number of grayscale value types that appear in the vehicle washing image; the content complexity of the style image is obtained in the same way as the calculation formula of the vehicle washing image content complexity.

[0010] The beneficial effects are: is the difference between the overall gradient size of the image and the maximum gradient value; is the relative size of the number of pixels with prominent gradients in the image; It is the relative size of the number of grayscale values ​​appearing in the image; it comprehensively quantifies the complexity of the content by multiplying the characteristic factors of different dimensions.

[0011] Optionally, the content complexity of the vehicle washing image is: the inverse of the variance of the grayscale histogram column height of the vehicle washing image.

[0012] The beneficial effect is that the height of each column of the grayscale histogram represents the number of pixels with the corresponding grayscale value, and the variance reflects the degree of deviation of these grayscale values ​​from their mean. The larger the value, the more dispersed the distribution of pixel grayscale values ​​in the image, that is, the richer the texture of the image, the higher the contrast, and the more obvious the image details. The smaller the value, the more concentrated the distribution of pixel grayscale values ​​in the image, that is, the smoother the texture of the image, the lower the contrast, and the less obvious the image details.

[0013] Optionally, the mathematical expression of the style feature vector is: , For the The style feature vector of the style image, For the The style image The number of pixels corresponding to the eigenvalues, , is the total number of pixel feature values ​​obtained by the local binary pattern. The number of pixel feature values ​​obtained by using local binary patterns with different parameters is different. The style feature vector of the vehicle washing image is constructed in the same way as the method for constructing the style feature vector of the style image.

[0014] The beneficial effect is that since the local binary pattern can well extract the texture features in the image, the texture features in images with different style features also have different manifestations. The difference in style between images can be reflected in the distribution of the feature values ​​of all pixels in the image. The distribution of feature values ​​in some style images is relatively even, while the distribution of feature values ​​in some style images is relatively concentrated. It can reflect the style characteristics of images with different styles.

[0015] Optionally, the style weighting coefficient is calculated as: , Indicates The vehicle cleaning image The style weighting coefficient used when performing style transfer on the style image. Indicates The exponential function with base , represents the style feature vector of the vehicle washing image in the dataset, The style feature vector representing the style image, Indicates The content complexity of the vehicle washing image, represents the cosine similarity function, express and degree of similarity.

[0016] The beneficial effects are: is the style similarity between the vehicle cleaning image and the style image. Normalized to get , The larger the value of , the greater the style similarity between the two images, and the closer the weather scenes or lighting conditions corresponding to the two images are. At this time, there is no need to make too many adjustments to the image generation based on the style features. At this time, the style loss weight should be reduced so that the content information in the original vehicle washing image can be more retained in the new image.

[0017] Optionally, the style weighting coefficient is calculated as: , Indicates The vehicle cleaning image The style weighting coefficient used when performing style transfer on the style image. represents the normalization function, represents the Euclidean distance, Indicates The exponential function with base , represents the style feature vector of the vehicle washing image in the dataset, The style feature vector representing the style image, Indicates The content complexity of the vehicle washing image, express and degree of similarity.

[0018] The beneficial effects are: represents the normalization function, represents the Euclidean distance, express and The purpose of normalization is to scale the data proportionally and to quantify the style similarity between images by calculating the Euclidean distance between vectors.

[0019] Optionally, the content weighting coefficient is calculated as: ,in, Indicates The vehicle cleaning image The content weighting coefficient used when performing style transfer on the style image. Indicates The exponential function with base , Indicates The content complexity of the vehicle washing image, Indicates The content complexity of the style image.

[0020] In the second aspect, the present application provides a vehicle management system for a smart construction site, which adopts the following technical solutions: A vehicle management system for a smart construction site comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the vehicle management method for a smart construction site described above is implemented.

[0021] The beneficial effect is: the above-mentioned vehicle management method for smart construction sites is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a system based on the memory and the processor for easy use.

[0022] This application has the following technical effects: 1. Content complexity indicates the amount of information contained in the image, and the feature vector quantifies the similarity between images. The style loss weight and content loss weight are calculated based on the content complexity and style feature vector of the image. The weight ratio of content loss and style loss is dynamically adjusted for each pair of images used for style transfer based on the characteristics of the vehicle washing image and the style image in the original dataset, thereby ensuring that the image obtained by style transfer can not only retain the details and structure of the original image, but also accurately integrate the target's lighting scene and weather scene into the generated image, and finally generate a natural, delicate style transfer image that meets the requirements of specific scenarios. Expanding the dataset based on the style transfer image is conducive to improving the accuracy of subsequent vehicle washing recognition and the accuracy of vehicle washing management.

[0023] 2. The greater the content complexity of the vehicle washing image, the more details it contains. The higher the content complexity of the vehicle washing image, the more accurate it is necessary to retain these complex details to avoid losing the structural information of the engineering vehicle washing image during the style transfer process. The greater the content loss weight used in the style transfer of the vehicle washing image, the smaller the content complexity of the vehicle washing image, because the simple content is already clearer and less prone to distortion, the content loss weight can be appropriately reduced, so that more weight can be placed on the style loss, so as to achieve more lighting conditions and weather scene migration effects; Since style transfer emphasizes the style of the style image rather than the content, the greater the content complexity of the style image, the more details, structures, and complex visual elements the image contains. In this process, if the content complexity of the style image is high, the details and structure of the original vehicle wash image are easily affected by the details of the style image. If the weight of the content loss is too large at this time, it will limit the effective transfer of the style features of the style image. Therefore, the weight of the content loss needs to be reduced so that the generated image can better integrate the complex structure and details of the style image; When the content complexity of the style image is small, the style image itself is relatively simple and may present relatively blurred and single image features (such as foggy days or dark days). At this time, if the content loss weight is too low, the generated image may lack the basic structure of the source image, resulting in the lack of recognition of the generated image as a vehicle washing image. Therefore, in order to ensure that the structure of the source image, object morphology and other contents are not erased too much and the generated image retains the essence of the source image, it is necessary to increase the weight of the content loss so that the generated image can better retain the content characteristics of the source image, thereby achieving a more natural and coherent style transfer effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-restrictive manner, and the same or corresponding numbers represent the same or corresponding parts.

[0025] Figure 1 This is a method flow chart of a vehicle management method for a smart construction site according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0027] It should be understood that when the terms "first", "second", etc. are used in the claims, specification and drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0028] The present application embodiment discloses a vehicle management method for a smart construction site, referring to Figure 1 , including the steps of: S1: Obtain a data set containing vehicle washing images, calculate the content complexity and style feature vector of the vehicle washing images; use environmental images of different weather conditions as style images, and calculate the content complexity and style feature vector of the style images.

[0029] Obtain an existing dataset of vehicle washing images, and collect style images under different lighting conditions and weather conditions to generate vehicle images under different weather and lighting scenes. Exemplarily, both the vehicle washing image and the style image are grayscale images. Use the Sobel operator to calculate the gradient of each pixel in the image, and count the number of grayscale values ​​that appear in the image. Exemplarily, if only pixels with a grayscale value of 0 appear in the image, then this value is 1, and if pixels with grayscale values ​​of 0, 3, 4, and 5 appear, then this value is 4.

[0030] Since different images have different detail information, when using the style transfer algorithm to perform image style transfer, the generated new image will retain different degrees of image details in the vehicle washing image. In order to avoid the image details in the vehicle washing image being lost or blurred in the new image, this application calculates the content complexity of the image based on the pixels in the dataset image.

[0031] In one embodiment, the calculation formula for the complexity of the vehicle washing image content is: ,in, Indicates The content complexity of the vehicle washing image, Indicates The maximum value of the pixel gradient value in the vehicle cleaning image. Indicates The mean value of the pixel gradient in the vehicle washing image, Indicates In the vehicle cleaning image, the gradient value is greater than The number of pixels; Indicates The number of pixels in the vehicle washing image, For the The number of grayscale value types that appear in the vehicle washing image, For the The difference between the overall gradient size of the vehicle washing image and the maximum gradient value. The larger the value, the smaller the overall gradient of the image, the less detailed information in the image, and the smaller the content complexity of the image. The smaller the value, the larger the overall gradient of the image, the more detailed information in the image, and the greater the content complexity of the image.

[0032] It is the relative size of the number of pixels with prominent gradients in the image. The larger the value, the more pixels with prominent gradients in the image, the more detailed information in the image, and the greater the content complexity of the image. The smaller the value, the fewer pixels with prominent gradients in the image, the less detailed information in the image, and the smaller the content complexity of the image.

[0033] It is the relative size of the number of grayscale values ​​appearing in the image. The larger the value, the more colors appearing in the image, the more detailed information in the image, and the greater the content complexity of the image. The smaller the value, the fewer colors appearing in the image, the less detailed information in the image, and the smaller the content complexity of the image.

[0034] In other embodiments, the content complexity of the vehicle washing image is: the inverse of the variance of the grayscale histogram column height of the vehicle washing image. The larger the variance, the smaller the inverse of the variance, that is, the smaller the content complexity, and vice versa.

[0035] The height of each column of the grayscale histogram represents the number of pixels with the corresponding grayscale value, and the variance reflects the degree of deviation of these grayscale values ​​from their mean. The larger the value, the more dispersed the distribution of pixel grayscale values ​​in the image, that is, the richer the texture of the image, the higher the contrast, and the more obvious the image details. The smaller the value, the more concentrated the distribution of pixel grayscale values ​​in the image, that is, the smoother the texture of the image, the lower the contrast, and the less obvious the image details.

[0036] The content complexity of the style image is obtained in the same way as the calculation formula of the content complexity of the vehicle washing image. I will not go into details here.

[0037] In one embodiment, taking the style feature vector of a style image as an example, the mathematical expression of the style feature vector is: , For the The style feature vector of the style image, For the The style image The number of pixels corresponding to the eigenvalues, , is the total number of pixel feature values ​​obtained by the local binary pattern. The number of pixel feature values ​​obtained by using local binary patterns with different parameters is different.

[0038] For example, using a radius of 1 and a local binary pattern based on 8 sampling points, , if the radius is 1 and the local binary pattern based on 4 sampling points is used, then .

[0039] Since local binary patterns can be used to extract texture features in images, the texture features in images with different style features also have different manifestations. The difference in style between images can be reflected in the distribution of eigenvalues ​​of all pixels in the image. The distribution of eigenvalues ​​in some style images is relatively even, while the distribution of eigenvalues ​​in some style images is relatively concentrated. It can reflect the style characteristics of images with different styles.

[0040] The method for constructing the style feature vector of the vehicle washing image is similar to the method for constructing the style feature vector of the style image, which will not be described in detail here.

[0041] S2: Calculate the content weighting coefficient; the content weighting coefficient is directly proportional to the content complexity of the vehicle washing image and inversely proportional to the content complexity of the style image.

[0042] The calculation formula of content weight coefficient is: ,in, Indicates The vehicle cleaning image The content weighting coefficient used when performing style transfer on the style image. Indicates The exponential function with base , Indicates The content complexity of the vehicle washing image, Indicates The content complexity of the style image.

[0043] S3: Calculate the style weighting coefficient; wherein, the similarity between the style image vector and the style feature vector is obtained, and the style weighting coefficient is inversely proportional to the similarity and inversely proportional to the content complexity of the vehicle washing image.

[0044] The calculation formula of style weighting coefficient is: , Indicates The vehicle cleaning image The style weighting coefficient used when performing style transfer on the style image. Indicates The exponential function with base , represents the style feature vector of the vehicle washing image in the dataset, The style feature vector representing the style image, Indicates The content complexity of the vehicle washing image, Cosine similarity function, express and degree of similarity.

[0045] The greater the content complexity of the vehicle washing image, the more details it contains. The higher the content complexity of the vehicle washing image, the more these complex details need to be retained more accurately to avoid losing the structural information of the engineering vehicle washing image during the style transfer process. The larger the content loss weight used in the style transfer of a vehicle washing image, the smaller the content complexity of the vehicle washing image, because the simple content is already clearer and less likely to be distorted, the weight of the content loss can be appropriately reduced, so that more weight can be placed on the style loss, so as to achieve the effect of more lighting conditions and weather scene transfer.

[0046] Since style transfer emphasizes the style of the style image rather than the content, the greater the content complexity of the style image, the more details, structures, and complex visual elements the image contains. In this process, if the content complexity of the style image is high, the details and structure of the original vehicle wash image are easily affected by the details of the style image. If the weight of the content loss is too large at this time, it will limit the effective transfer of the style features of the style image. Therefore, the weight of the content loss needs to be reduced so that the generated image can better integrate the complex structure and details of the style image.

[0047] When the content complexity of the style image is small, the style image itself is relatively simple and may present relatively blurred and single image features (such as foggy days or dark days). At this time, if the content loss weight is too low, the generated image may lack the basic structure of the source image, resulting in the lack of recognition of the generated image as a vehicle washing image. Therefore, in order to ensure that the structure of the source image, object morphology and other contents are not erased too much and the generated image retains the essence of the source image, it is necessary to increase the weight of the content loss so that the generated image can better retain the content characteristics of the source image, thereby achieving a more natural and coherent style transfer effect.

[0048] is the style similarity between the vehicle cleaning image and the style image. Since the value range of cosine similarity is from -1 to 1, for the convenience of calculation, the formula is added by 1 and divided by 2. Normalize.

[0049] The bigger, The larger the value, the greater the style similarity between the two images, and the closer the weather scenes or lighting conditions corresponding to the two images are. At this time, there is no need to make too many adjustments to the image generation in terms of style features. At this time, the style loss weight should be reduced so that the content information in the original vehicle washing image can be more retained in the new image. The smaller the value, the greater the style gap between the two images, and the greater the difference in weather scenes or lighting conditions corresponding to the two images. At this time, more adjustments need to be made to the image generation in terms of style features. At this time, the style loss weight should be increased so that the style information in the target style image can be more reflected in the new image.

[0050] At the same time, the content complexity of the vehicle washing image The larger the value, the more details the image has. If too much style loss is applied during style transfer, details may be lost or unnatural transitions may occur in the new image. Therefore, the weight of style loss should be reduced to avoid excessive changes in image style. The smaller the value, the less detailed information the image has, and it is not easy to lose too much content during the style transfer process. Therefore, a larger style loss weight can be used to allow the generated image to better absorb the lighting conditions or weather scene style information in the target style image.

[0051] In other embodiments, the calculation formula of the style weighting coefficient may also be: , Indicates The vehicle cleaning image The style weighting coefficient used when performing style transfer on a style image. Indicates The exponential function with base , represents the style feature vector of the vehicle washing image in the dataset, The style feature vector representing the style image, Indicates Content complexity of the vehicle washing image.

[0052] represents the normalization function, represents the Euclidean distance, express and The purpose of normalization is to scale the data so that it falls into a small specific interval, such as [0,1]. With the above The effect is similar and will not be described here.

[0053] S4: Set up a pre-trained convolutional neural network, input the vehicle cleaning image and the style image, add the product of the style weighting coefficient and the style loss and the product of the content weighting coefficient and the content loss as the loss function, iterate the vehicle cleaning image by minimizing the loss function, and obtain the style transfer image after the iteration. According to the style transfer image, expand the data set used to train the vehicle cleanliness recognition model.

[0054] It is an existing technology to generate images using a style transfer algorithm (VGG19 network, Inception network or other feature extraction networks can be used), which will not be described in detail here. In this process, style loss and content loss are continuously calculated, and the style loss weight is multiplied by the style loss, and the content loss weight is multiplied by the content loss, and subsequent training iterations are performed, so that the generated image can not only well retain the content of the vehicle washing process in the original image, but also enable the image to integrate different lighting and different weather conditions. The style transfer of the image by this method can generate a higher quality and richer vehicle washing recognition data set. The training of the vehicle washing recognition neural network through the expanded data set can improve the accuracy of vehicle washing recognition. The training and use of the vehicle washing recognition neural network are existing technologies and will not be described in detail here.

[0055] An embodiment of the present application also discloses a vehicle management system for a smart construction site, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a vehicle management method for a smart construction site according to the present application is implemented.

[0056] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0057] In the present application, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high bandwidth memory HBM (High Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0058] Although this specification has shown and described a plurality of embodiments of the present application, it is obvious to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, modifications and alternatives without departing from the thought and spirit of the present application. It should be understood that in the process of practicing the present application, various alternatives to the embodiments of the present application described herein may be adopted.

[0059] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A vehicle management method for a smart construction site, characterized in that: Includes steps: Obtain a data set containing vehicle washing images, calculate the content complexity and style feature vector of the vehicle washing images; use environmental images of different weather conditions as style images, and calculate the content complexity and style feature vector of the style images; Calculate the content weighting coefficient; the content weighting coefficient is directly proportional to the content complexity of the vehicle washing image and inversely proportional to the content complexity of the style image; Calculate the style weighting coefficient; wherein, the similarity between the style image vector and the style feature vector is obtained, and the style weighting coefficient is inversely proportional to the similarity and inversely proportional to the content complexity of the vehicle washing image; A pre-trained convolutional neural network is set up, and the vehicle cleaning image and style image are input. The product of the style weighting coefficient and the style loss is added to the product of the content weighting coefficient and the content loss as the loss function. The vehicle cleaning image is iterated by minimizing the loss function. After the iteration, the style transfer image is obtained. According to the style transfer image, the data set used to train the vehicle cleanliness recognition model is expanded.

2. The vehicle management method for a smart construction site according to claim 1, characterized in that: The calculation formula for the content complexity of the vehicle washing image is: ,in, Indicates The content complexity of the vehicle washing image, Indicates The maximum value of the pixel gradient value in the vehicle washing image. Indicates The mean value of the pixel gradient in the vehicle washing image, Indicates In the vehicle cleaning image, the gradient value is greater than The number of pixels; Indicates The number of pixels in the vehicle washing image, For the The number of grayscale value types that appear in a vehicle washing image; The content complexity of the style image is obtained in the same way as the calculation formula of the content complexity of the vehicle washing image.

3. The vehicle management method for a smart construction site according to claim 1, characterized in that: The content complexity of the vehicle washing image is: the inverse of the variance of the grayscale histogram column height of the vehicle washing image.

4. The vehicle management method for a smart construction site according to any one of claims 1 to 3, characterized in that: The mathematical expression of the style feature vector is: , For the The style feature vector of the style image, For the The style image The number of pixels corresponding to the eigenvalues, , is the total number of pixel feature values ​​obtained by the local binary pattern. The number of pixel feature values ​​obtained by using local binary patterns with different parameters is different. The style feature vector of the vehicle washing image is constructed in the same way as the method for constructing the style feature vector of the style image.

5. The vehicle management method for a smart construction site according to claim 4, characterized in that: The calculation formula of style weighting coefficient is: , Indicates The vehicle cleaning image The style weighting coefficient used when performing style transfer on the style image. Indicates The exponential function with base , represents the style feature vector of the vehicle washing image in the dataset, The style feature vector representing the style image, Indicates The content complexity of the vehicle washing image, represents the cosine similarity function, express and degree of similarity.

6. The vehicle management method for a smart construction site according to claim 4, characterized in that: The calculation formula of style weighting coefficient is: , Indicates The vehicle cleaning image The style weighting coefficient used when performing style transfer on the style image. represents the normalization function, represents the Euclidean distance, Indicates The exponential function with base , represents the style feature vector of the vehicle washing image in the dataset, The style feature vector representing the style image, Indicates The content complexity of the vehicle washing image, express and degree of similarity.

7. The vehicle management method for a smart construction site according to claim 1, characterized in that: The calculation formula of content weight coefficient is: ,in, Indicates The vehicle cleaning image The content weighting coefficient used when performing style transfer on the style image. Indicates The exponential function with base , Indicates The content complexity of the vehicle washing image, Indicates The content complexity of the style image.

8. A vehicle management system for a smart construction site, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a vehicle management method for a smart construction site according to any one of claims 1 to 7 is implemented.

Images