Artificial Intelligence-Based Intelligent Connected Vehicle Safety Enhancement Method and System

Abstract

The present invention relates to the technical field of intelligent connected vehicle data security, and particularly relates to a method and system for enhancing the security of intelligent connected vehicles based on artificial intelligence. The present invention obtains vehicle external environment image data and vehicle operation data, divides the security enhancement tendency categories, optionally adds layers to several clustering clusters, obtains the contour positions, and adjusts the sizes of the remaining clustering clusters to obtain disguised vehicle external environment image data. All the data is encrypted to obtain encrypted ciphertext and then all is sent to the data receiving end. The data receiving end obtains the encrypted ciphertext, decrypts the encrypted ciphertext, and restores the disguised vehicle external environment image data to vehicle external environment image data. The present invention screens out the vehicle external environment image data with more information content for processing, so that while reducing the computing power and improving the data processing efficiency, the security of important data can be ensured, and the present invention encrypts all the data to further enhance the security of all the data.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent connected vehicle data security, and particularly to an intelligent connected vehicle security enhancement method and system based on artificial intelligence. Background Art

[0002] With the rapid development of intelligent connected vehicle technology, these vehicles contain a large amount of important information, such as vehicle status, driving behavior, environmental perception data, etc. These information are crucial for the research and development of the intelligent driving system of the vehicle. However, the sensitivity and value of these data also make them potential security risk points. Therefore, it becomes particularly important to protect the security of this information.

[0003] The prior art discloses a method for enhancing the intelligent connected vehicle channel based on spatial scanning technology, including: configuring a spatial beam scanning system on the intelligent connected vehicle and infrastructure equipment, and the intelligent connected vehicle transmits data information to the spatial beam scanning system; the beam scanning system calculates the weights for beamforming, and uses the obtained channel estimation to calculate the phase and amplitude weights of each antenna element in the beamforming network; the calculated weights are used to control the shape and direction of the beam; the spatial beam scanning system is a Butler spatial beam scanning system, which is obtained by designing a Butler matrix and connecting it to an antenna array, and is verified, analyzed and performance-adjusted in HFSS and CST simulation software. The present invention ensures that only legitimate recipients receive the data information, and eavesdroppers cannot intercept the effective transmitted data, and can be applied to fields such as intelligent transportation systems and autonomous driving vehicles.

[0004] However, the prior art still has the following problems:

[0005] It does not screen according to the importance of the information, and encrypts all the information after processing the important information, resulting in a low level of security for the important information, as well as consuming a large amount of computing power and resources, causing the problem of low data processing efficiency Summary of the Invention

[0006] Therefore, the present invention provides an intelligent connected vehicle security enhancement method and system based on artificial intelligence to overcome the problems in the prior art that it does not screen according to the importance of the information, encrypts all the information after processing the important information, resulting in a low level of security for the important information, as well as consuming a large amount of computing power and resources, causing the problem of low data processing efficiency.

[0007] To achieve the above object, on the one hand, the present invention provides an intelligent connected vehicle security enhancement method based on artificial intelligence, including:

[0008] Step S1: Obtain the external vehicle environment image data and vehicle operation data, where the vehicle operation data includes vehicle driving speed, engine speed, vehicle acceleration, and vehicle steering angle;

[0009] Step S2: Automatically extract the image features of the external vehicle environment image data through a convolutional neural network, perform clustering analysis on the image features based on shape and size, and obtain the number of clustering clusters;

[0010] Step S3: Classify the safety enhancement tendency categories by combining the number of clustering clusters with the change value of vehicle operation data;

[0011] Step S4: In response to a preset category, select several clustering clusters, add a layer to the clustering clusters, obtain the contour positions of the clustering clusters, and adjust the sizes of the remaining clustering clusters in the external vehicle environment image data to obtain a disguised external vehicle environment image data;

[0012] Step S5: Encrypt the disguised external vehicle environment image data, the contour positions of the clustering clusters, and the non-disguised external vehicle environment image data, and send all the obtained encrypted ciphertexts to the data receiving end;

[0013] Step S6: The data receiving end obtains the encrypted ciphertext, the encrypted disguised external vehicle environment image data, the contour positions of the clustering clusters, and the non-disguised external vehicle environment image data, decrypts the encrypted ciphertext, and obtains the non-disguised external vehicle environment image data;

[0014] Also, remove the layer of the disguised external vehicle environment image data according to the contour positions of the clustering clusters for the disguised external vehicle environment image data, and adjust the sizes of the remaining clustering clusters in the disguised external vehicle environment image data to obtain all the external vehicle environment image data.

[0015] As a preferred technical solution of the intelligent networked vehicle safety enhancement method based on artificial intelligence, in step S3, it further includes calculating a safety enhancement tendency characterization value according to the number of clustering clusters and the change value of vehicle operation data,

[0016] Denote the ratio of the number of clustering clusters to the preset number threshold of clustering clusters as the first weight influence quantity;

[0017] Obtain the ratio of the vehicle driving speed change value to the preset vehicle driving speed change value threshold, the sum of the ratios of the engine speed change value to the preset engine speed change value threshold, the vehicle acceleration change value to the preset vehicle acceleration change value threshold, and the vehicle steering angle change value to the preset vehicle steering angle change value threshold as the second weight influence quantity;

[0018] Weighted sum the first weight influence quantity and the second weight influence quantity to obtain the safety enhancement tendency characterization value.

[0019] As a preferred technical solution of the artificial intelligence-based intelligent connected vehicle safety enhancement method, in step S3, it further includes classifying the safety enhancement tendency categories according to the safety enhancement tendency characterization value. The process of classifying the safety enhancement tendency categories includes,

[0020] comparing the safety enhancement tendency characterization value with a preset safety enhancement tendency characterization value comparison threshold,

[0021] if the safety enhancement tendency characterization value is greater than the preset safety enhancement tendency characterization value comparison threshold, then classify the safety enhancement tendency category as a strong safety enhancement tendency category;

[0022] if the safety enhancement tendency characterization value is less than or equal to the preset safety enhancement tendency characterization value comparison threshold, then classify the safety enhancement tendency category as a weak safety enhancement tendency category.

[0023] As a preferred technical solution of the artificial intelligence-based intelligent connected vehicle safety enhancement method, in step S4, in response to a preset category, where the preset category is a strong safety enhancement tendency category.

[0024] As a preferred technical solution of the artificial intelligence-based intelligent connected vehicle safety enhancement method, in step S4, select several clustering clusters optionally, where the number of selected clustering clusters is positively correlated with the number of clustering clusters in the out-of-vehicle environment image data.

[0025] As a preferred technical solution of the artificial intelligence-based intelligent connected vehicle safety enhancement method, in step S4, adjust the size of the remaining clustering clusters in the out-of-vehicle environment image data, where there is an adjustment ratio corresponding to the number of the remaining clustering clusters.

[0026] As a preferred technical solution of the artificial intelligence-based intelligent connected vehicle safety enhancement method, in step S5, the out-of-vehicle environment image data without camouflage is the out-of-vehicle environment image data of the weak safety enhancement tendency category.

[0027] As a preferred technical solution of the artificial intelligence-based intelligent connected vehicle safety enhancement method, in step S6, the process of adjusting the size of the remaining clustering clusters in the camouflaged out-of-vehicle environment image data includes,

[0028] determine the number of the remaining clustering clusters;

[0029] determine the adjustment ratio according to the number of the remaining clustering clusters;

[0030] adjust the size of the remaining clustering clusters in the camouflaged out-of-vehicle environment image data according to the adjustment ratio.

[0031] On the other hand, the present invention also provides an artificial intelligence-based intelligent connected vehicle safety enhancement system, including:

[0032] A data acquisition module for acquiring external vehicle environment image data and vehicle operation data, where the vehicle operation data includes vehicle driving speed, engine speed, vehicle acceleration, and vehicle steering angle;

[0033] An image analysis module, connected to the data acquisition module, for automatically extracting image features of the external vehicle environment image data through a convolutional neural network, performing clustering analysis on the image features based on shape and size, and obtaining the number of clustering clusters;

[0034] A data processing module, connected to each of the data acquisition modules and the image analysis module, includes an image classification unit, an image encryption unit, and a data sending unit,

[0035] The image classification unit is used to divide the safety enhancement tendency category by combining the number of clustering clusters with the change value of vehicle operation data;

[0036] The image encryption unit is used to respond to a preset category, select several clustering clusters at random, add a layer to the clustering clusters, obtain the contour positions of the clustering clusters, and adjust the sizes of the remaining clustering clusters in the external vehicle environment image data to obtain a disguised external vehicle environment image data;

[0037] The data sending unit is used to encrypt the disguised external vehicle environment image data, the contour positions of the clustering clusters, and the non-disguised external vehicle environment image data, and after obtaining the encrypted ciphertext, send all of them to the data receiving end;

[0038] An image decryption module, connected to the data processing module, for the data receiving end to obtain the encrypted ciphertext, the encrypted disguised external vehicle environment image data, the contour positions of the clustering clusters, and the non-disguised external vehicle environment image data, decrypt the encrypted ciphertext, and obtain the non-disguised external vehicle environment image data;

[0039] And, for the disguised external vehicle environment image data, remove the layer of the disguised external vehicle environment image data according to the contour positions of the clustering clusters, and adjust the sizes of the remaining clustering clusters in the disguised external vehicle environment image data to obtain all the external vehicle environment image data.

[0040] As a preferred technical solution of the intelligent networked vehicle safety enhancement system based on artificial intelligence, it further includes a display module for displaying the external vehicle environment image data.

[0041] Compared with the prior art, the present invention obtains the number of clustering clusters and combines the change value of vehicle operation data to divide the safety enhancement tendency categories by acquiring the vehicle external environment image data and the vehicle operation data. In response to a preset category, several clustering clusters are optionally added with layers, the contour positions are obtained, and the sizes of the remaining clustering clusters are adjusted to obtain the disguised vehicle external environment image data. The disguised vehicle external environment image data, the contour positions of the clustering clusters, and the vehicle external environment image data that has not been disguised are encrypted to obtain encrypted ciphertexts, which are all sent to the data receiving end. The data receiving end obtains the encrypted ciphertexts, the encrypted disguised vehicle external environment image data, the contour positions of the clustering clusters, and the vehicle external environment image data that has not been disguised, decrypts the encrypted ciphertexts to obtain the vehicle external environment image data that has not been disguised, and restores the disguised vehicle external environment image data to the vehicle external environment image data. The present invention screens out the vehicle external environment image data with more information for processing, so that while reducing the computing power and improving the efficiency of data processing, the security of important data can be ensured, and the present invention encrypts all data to further improve the security of all data.

[0042] In particular, the present invention divides the safety enhancement tendency categories by combining the number of clustering clusters with the change value of vehicle operation data. In actual situations, the vehicle external environment image data includes information such as road infrastructure, road conditions, and traffic congestion. These information are crucial for the research and development of vehicle intelligent driving systems and can be used to achieve intelligent navigation and path planning, improving driving safety and traffic efficiency. Therefore, during the uploading process, this vehicle external environment image data should be processed to ensure data security and compliance and prevent data leakage. However, processing all the vehicle external environment image data will cause a problem of excessive computing power. Therefore, the vehicle external environment image data with more information is screened out for processing, so that while reducing the computing power, the security of important data can be ensured. The number of clustering clusters and the change value of vehicle operation data are important influencing parameters for judging whether the vehicle external environment image data includes more information. Based on these parameters, the amount of information contained in the vehicle external environment image data can be characterized, so as to screen the vehicle external environment image data, effectively protect the data security, and significantly improve the efficiency of data processing.

[0043] In particular, the present invention optionally adds layers to several clustering clusters, obtains the contour positions of the clustering clusters, and adjusts the sizes of the remaining clustering clusters in the vehicle external environment image data to obtain the disguised vehicle external environment image data. After processing the vehicle external environment image data with more information by blocking arbitrary clustering clusters in the image and adjusting the sizes of the remaining clustering clusters in the image, it will increase the difficulty of obtaining the original vehicle external environment image data, thereby improving the data security.

[0044] In particular, the present invention encrypts the disguised external vehicle environment image data, the contour positions of the clustering clusters, and the undisguised external vehicle environment image data. After processing the external vehicle environment image data with more information and encrypting it together with the unprocessed external vehicle environment image data, the security of all data can be further enhanced after the security of important data is pre-enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a step diagram of the intelligent networked vehicle security enhancement method based on artificial intelligence according to an embodiment of the present invention;

[0046] Figure 2 It is a logical decision diagram for classifying security enhancement tendencies according to an embodiment of the present invention;

[0047] Figure 3 It is a structural block diagram of the intelligent networked vehicle security enhancement system based on artificial intelligence according to an embodiment of the present invention;

[0048] Figure 4 It is a structural block diagram of the data processing module according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] In order to make the objectives and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0050] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0051] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0052] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0053] Please refer toFigure 1-2 As shown in the figure, the present invention provides a method for enhancing the safety of intelligent networked vehicles with artificial intelligence, including:

[0054] Step S1, obtaining vehicle external environment image data and vehicle operation data, where the vehicle operation data includes vehicle driving speed, engine speed, vehicle acceleration, and vehicle steering angle;

[0055] Step S2, automatically extracting image features of the vehicle external environment image data through a convolutional neural network, performing clustering analysis on the image features based on shape and size, and obtaining the number of clustering clusters;

[0056] Step S3, dividing the safety enhancement tendency categories by combining the number of clustering clusters with the change value of vehicle operation data;

[0057] Step S4, in response to a preset category, optionally selecting several clustering clusters, adding a layer to the clustering clusters, obtaining the contour positions of the clustering clusters, and adjusting the sizes of the remaining clustering clusters in the vehicle external environment image data to obtain a disguised vehicle external environment image data;

[0058] Step S5, encrypting the disguised vehicle external environment image data, the contour positions of the clustering clusters, and the vehicle external environment image data that has not been disguised, and sending all of them to the data receiving end after obtaining the encrypted ciphertext;

[0059] Step S6, the data receiving end obtains the encrypted ciphertext, the encrypted disguised vehicle external environment image data, the contour positions of the clustering clusters, and the vehicle external environment image data that has not been disguised, decrypts the encrypted ciphertext, and obtains the vehicle external environment image data that has not been disguised;

[0060] And, removing the layer of the disguised vehicle external environment image data according to the contour positions of the clustering clusters for the disguised vehicle external environment image data, and adjusting the sizes of the remaining clustering clusters in the disguised vehicle external environment image data to obtain all the vehicle external environment image data.

[0061] Specifically, the present invention divides the safety enhancement tendency categories by combining the number of clustering clusters with the change value of vehicle operation data. In actual situations, the out-of-vehicle environment image data includes information such as road infrastructure, road conditions, and traffic congestion. These information are crucial for the research and development of vehicle intelligent driving systems and can be used to achieve intelligent navigation and path planning, improving driving safety and traffic efficiency. Therefore, during the uploading process, this out-of-vehicle environment image data should be processed to ensure data security and compliance and prevent data leakage. However, processing all out-of-vehicle environment image data will cause excessive computing power problems. Thus, out-of-vehicle environment image data containing more information is screened for processing, enabling the guarantee of important data security while reducing computing power. The number of clustering clusters and the change value of vehicle operation data are important influencing parameters for determining whether the out-of-vehicle environment image data contains more information. Based on these parameters, the amount of information contained in the out-of-vehicle environment image data can be characterized, thereby screening the out-of-vehicle environment image data, effectively protecting data security, and significantly improving the efficiency of data processing.

[0062] In this embodiment, the out-of-vehicle environment image data is obtained through an in-vehicle camera equipped on the intelligent connected vehicle, and the vehicle operation data is obtained through in-vehicle sensors, including a wheel speed sensor, a rotational speed sensor, an acceleration sensor, and a steering wheel angle sensor.

[0063] In this embodiment, a convolutional neural network is used to automatically extract image features. The convolutional neural network can automatically extract local features in the image and combine low-level features into high-level feature representations through a layer-by-layer transmission method. Optionally, a pre-trained model VGG16 is used to extract features. The K-means clustering algorithm is used to perform clustering analysis on the extracted features. The elbow method is used to determine the number of clustering clusters.

[0064] Specifically, in step S3, it further includes calculating a safety enhancement tendency characterization value based on the number of clustering clusters and the change value of vehicle operation data.

[0065] The ratio of the number of clustering clusters to the preset number of clustering cluster thresholds is denoted as the first weight influence amount;

[0066] The ratio of the vehicle driving speed change value to the preset vehicle driving speed change value threshold, the ratio of the engine rotational speed change value to the preset engine rotational speed change value threshold, the ratio of the vehicle acceleration change value to the preset vehicle acceleration change value threshold, and the sum of the ratio of the vehicle steering angle change value to the preset vehicle steering angle change value threshold are denoted as the second weight influence amount;

[0067] The first weight influence amount and the second weight influence amount are weighted and summed to obtain the safety enhancement tendency characterization value.

[0068] In this embodiment, the preset clustering cluster quantity threshold C0, the preset vehicle driving speed change value threshold v0, the ratio r0 of the preset engine speed change value threshold, the preset vehicle acceleration change value threshold a0, and the preset vehicle steering angle change value threshold θ0 are all obtained in advance through experiments. By calling historical data, the number of clustering clusters of several out-of-vehicle environment image data is obtained, and the average value Ce of the number of clustering clusters is calculated. Let C0 = k × Ce, where k is the clustering cluster quantity coefficient and 0.9 < k < 1.1. The vehicle operation data within several time periods is obtained, and the average value ve of the vehicle driving speed change value, the average value re of the engine speed change value, the average value ae of the vehicle acceleration change value, and the average value θe of the vehicle steering angle change value are calculated. Let v0 = g × ve, where g is the vehicle driving speed change value coefficient and 0.9 < g < 1.1. Let r0 = m × re, where m is the engine speed change value coefficient and 0.9 < m < 1.1. Let a0 = n × ae, where n is the vehicle acceleration change value coefficient and 0.9 < n < 1.1. Let θ0 = j × θe, where j is the vehicle steering angle change value coefficient and 0.9 < j < 1.1.

[0069] In this embodiment, the weight coefficient of the first weight influence amount is 0.7, and the weight coefficient of the second weight influence amount is 0.3.

[0070] Specifically, in step S3, it further includes dividing the safety enhancement tendency category according to the safety enhancement tendency characterization value. The process of dividing the safety enhancement tendency category includes

[0071] comparing the safety enhancement tendency characterization value with the preset safety enhancement tendency characterization value comparison threshold.

[0072] If the safety enhancement tendency characterization value is greater than the preset safety enhancement tendency characterization value comparison threshold, then the safety enhancement tendency category is divided into a strong safety enhancement tendency category;

[0073] If the safety enhancement tendency characterization value is less than or equal to the preset safety enhancement tendency characterization value comparison threshold, then the safety enhancement tendency category is divided into a weak safety enhancement tendency category.

[0074] In this embodiment, the preset safety enhancement tendency characterization value comparison threshold is selected within the range of [1.8, 2.0].

[0075] Specifically, in step S4, in response to the preset category, where the preset category is a strong safety enhancement tendency category.

[0076] Specifically, in step S4, several clustering clusters are randomly selected, where the number of selected clustering clusters has a positive correlation with the number of clustering clusters in the out-of-vehicle environment image data.

[0077] It can be understood that the more the number of clustering clusters in the out-of-vehicle environment image data, the more the number of selected clustering clusters.

[0078] Specifically, in step S4, the size of the remaining clustering clusters in the vehicle exterior environment image data is adjusted, and there is an adjustment ratio corresponding to the number of the remaining clustering clusters.

[0079] In this embodiment,

[0080] If 1 ≤ the number of the remaining clustering clusters < 3, the adjustment ratio is to reduce by 0.8 times;

[0081] If 3 ≤ the number of the remaining clustering clusters < 5, the adjustment ratio is to reduce by 0.6 times;

[0082] If 5 ≤ the number of the remaining clustering clusters, the adjustment ratio is to enlarge by 1.2 times.

[0083] In this embodiment, adding a layer on the clustering clusters can be achieved by programmatically adding a layer on the vehicle exterior environment image data through PIL in Python.

[0084] In this embodiment, the findContours function in OpenCV is used to obtain the contour positions.

[0085] Specifically, the present invention obtains the camouflaged vehicle exterior environment image data by optionally adding layers to several clustering clusters, obtaining the contour positions of the clustering clusters, and adjusting the size of the remaining clustering clusters in the vehicle exterior environment image data. After processing the vehicle exterior environment image data with more information by occluding arbitrary clustering clusters in the image and adjusting the size of the remaining clustering clusters in the image, the difficulty of obtaining the original vehicle exterior environment image data will be increased, thereby improving the security of the data.

[0086] Specifically, in step S5, the vehicle exterior environment image data without camouflage is the vehicle exterior environment image data with a weak security enhancement tendency category.

[0087] Specifically, in step S6, the process of adjusting the size of the remaining clustering clusters in the camouflaged vehicle exterior environment image data includes,

[0088] Determining the number of the remaining clustering clusters;

[0089] Determining the adjustment ratio according to the number of the remaining clustering clusters;

[0090] Adjusting the size of the remaining clustering clusters in the camouflaged vehicle exterior environment image data according to the adjustment ratio.

[0091] For example, in this embodiment, if the number of weak remaining clustering clusters is 3, it is determined that the camouflaged vehicle exterior environment image data is obtained after reducing the vehicle exterior environment image data by 0.8 times, and then the camouflaged vehicle exterior environment image data needs to be restored according to the ratio.

[0092] Specifically, the present invention encrypts the disguised vehicle exterior environment image data, the contour positions of the clustering clusters, and the undisguised vehicle exterior environment image data. After processing the vehicle exterior environment image data with more information and encrypting it together with the unprocessed vehicle exterior environment image data, the security of all data can be further enhanced after initially enhancing the security of important data.

[0093] Please refer to Figure 3-4 As shown, the present invention also provides an intelligent networked vehicle security enhancement system based on artificial intelligence, including:

[0094] A data acquisition module for acquiring vehicle exterior environment image data and vehicle operation data, where the vehicle operation data includes vehicle driving speed, engine speed, vehicle acceleration, and vehicle steering angle;

[0095] An image analysis module connected to the data acquisition module for automatically extracting image features of the vehicle exterior environment image data through a convolutional neural network, performing clustering analysis on the image features based on shape and size, and obtaining the number of clustering clusters;

[0096] A data processing module connected to each of the data acquisition module and the image analysis module, including an image classification unit, an image encryption unit, and a data sending unit.

[0097] The image classification unit is used to divide the security enhancement tendency categories by combining the number of clustering clusters with the change value of vehicle operation data;

[0098] The image encryption unit is used to, in response to a preset category, select several clustering clusters at random, add a layer to the clustering clusters, and obtain the contour positions of the clustering clusters, and, adjust the sizes of the remaining clustering clusters in the vehicle exterior environment image data to obtain disguised vehicle exterior environment image data;

[0099] The data sending unit is used to encrypt the disguised vehicle exterior environment image data, the contour positions of the clustering clusters, and the undisguised vehicle exterior environment image data, and send all of them to the data receiving end after obtaining the encrypted ciphertext;

[0100] An image decryption module connected to the data processing module for the data receiving end to obtain the encrypted ciphertext, the encrypted disguised vehicle exterior environment image data, the contour positions of the clustering clusters, and the undisguised vehicle exterior environment image data, and decrypt the encrypted ciphertext to obtain the undisguised vehicle exterior environment image data;

[0101] And, remove the layer of the disguised vehicle exterior environment image data according to the contour positions of the clustering clusters for the disguised vehicle exterior environment image data, and, adjust the sizes of the remaining clustering clusters in the disguised vehicle exterior environment image data to obtain all the vehicle exterior environment image data.

[0102] Specifically, it further includes a display module for displaying the image data of the external environment of the vehicle.

[0103] The modules described in the embodiments of the present application can be implemented in software or in hardware. The described modules can also be provided in a processor, where the names of these modules do not constitute a limitation to the module itself in certain cases.

[0104] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the devices, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based device for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0105] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0106] The above are only the preferred embodiments of the present invention and are not used to limit the present invention; for those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent networked vehicle safety enhancement method based on artificial intelligence, characterized in that, Including: Step S1: Obtain the vehicle exterior environment image data and vehicle operation data, where the vehicle operation data includes vehicle driving speed, engine speed, vehicle acceleration, and vehicle steering angle; Step S2: Automatically extract the image features of the vehicle exterior environment image data through a convolutional neural network, perform clustering analysis on the image features based on shape and size, and obtain the number of clustering clusters; Step S3: Divide the safety enhancement tendency category by combining the number of clustering clusters with the change value of vehicle operation data; In step S3, it also includes calculating a safety enhancement tendency characterization value according to the number of clustering clusters and the change value of vehicle operation data. Denote the ratio of the number of clustering clusters to the preset number threshold of clustering clusters as the first weight influence amount; Obtain the ratio of the vehicle driving speed change value to the preset vehicle driving speed change value threshold, the ratio of the engine speed change value to the preset engine speed change value threshold, the ratio of the vehicle acceleration change value to the preset vehicle acceleration change value threshold, and the sum of the ratio of the vehicle steering angle change value to the preset vehicle steering angle change value threshold as the second weight influence amount; Weightedly sum the first weight influence amount and the second weight influence amount to obtain the safety enhancement tendency characterization value; In step S3, it also includes dividing the safety enhancement tendency category according to the safety enhancement tendency characterization value. The process of dividing the safety enhancement tendency category includes: Compare the safety enhancement tendency characterization value with the preset safety enhancement tendency characterization value comparison threshold; If the safety enhancement tendency characterization value is greater than the preset safety enhancement tendency characterization value comparison threshold, divide the safety enhancement tendency category into a strong safety enhancement tendency category; If the safety enhancement tendency characterization value is less than or equal to the preset safety enhancement tendency characterization value comparison threshold, divide the safety enhancement tendency category into a weak safety enhancement tendency category; Step S4: In response to a preset category, select several clustering clusters, add a layer on the clustering clusters, and obtain the contour positions of the clustering clusters. Also, adjust the sizes of the remaining clustering clusters in the vehicle exterior environment image data to obtain a camouflaged vehicle exterior environment image data; Step S5: Encrypt the camouflaged vehicle exterior environment image data, the contour positions of the clustering clusters, and the uncamouflaged vehicle exterior environment image data, and send all the encrypted ciphertexts to the data receiving end; Step S6: The data receiving end obtains the encrypted ciphertext, the encrypted camouflaged vehicle exterior environment image data, the contour positions of the clustering clusters, and the uncamouflaged vehicle exterior environment image data, decrypts the encrypted ciphertext, and obtains the uncamouflaged vehicle exterior environment image data; And, remove the layer of the camouflaged vehicle exterior environment image data according to the contour positions of the clustering clusters for the camouflaged vehicle exterior environment image data, and adjust the sizes of the remaining clustering clusters in the camouflaged vehicle exterior environment image data to obtain all the vehicle exterior environment image data.

2. The method for enhancing the safety of intelligent connected vehicles based on artificial intelligence according to claim 1, wherein In step S4, in response to a preset category, where the preset category is a strong safety enhancement tendency category.

3. The method for enhancing the safety of intelligent networked vehicles based on artificial intelligence according to claim 1, wherein In step S4, select several clustering clusters, where the number of selected clustering clusters has a positive correlation with the number of clustering clusters in the vehicle exterior environment image data.

4. The method for enhancing the safety of intelligent connected vehicles based on artificial intelligence according to claim 1, wherein In step S4, the sizes of the remaining clustering clusters in the vehicle exterior environment image data are adjusted, where there is an adjustment ratio corresponding to the number of the remaining clustering clusters.

5. The method for enhancing the safety of intelligent networked vehicles based on artificial intelligence according to claim 1, wherein In step S5, the vehicle exterior environment image data without camouflage is the vehicle exterior environment image data of the weakly security-enhanced tendency category.

6. The method for enhancing the safety of intelligent connected vehicles based on artificial intelligence according to claim 1, wherein, In step S6, the process of adjusting the sizes of the remaining clustering clusters in the camouflaged vehicle exterior environment image data includes: Determining the number of the remaining clustering clusters; Determining the adjustment ratio according to the number of the remaining clustering clusters; Adjusting the sizes of the remaining clustering clusters in the camouflaged vehicle exterior environment image data according to the adjustment ratio.

7. An intelligent networked vehicle safety enhancement system based on artificial intelligence, characterized in that, Applying the method for enhancing the security of an intelligent connected vehicle based on artificial intelligence according to any one of claims 1-6, the system for enhancing the security of an intelligent connected vehicle based on artificial intelligence includes: A data acquisition module for acquiring vehicle exterior environment image data and vehicle operation data, where the vehicle operation data includes vehicle driving speed, engine speed, vehicle acceleration, and vehicle steering angle; An image analysis module connected to the data acquisition module for automatically extracting the image features of the vehicle exterior environment image data through a convolutional neural network, performing clustering analysis on the image features based on shape and size, and obtaining the number of clustering clusters; A data processing module connected to each of the data acquisition module and the image analysis module, including an image classification unit, an image encryption unit, and a data sending unit. The image classification unit is used to divide the security-enhanced tendency category by combining the number of clustering clusters with the change value of vehicle operation data; The image encryption unit is used to, in response to a preset category, select several clustering clusters at random, add a layer to the clustering clusters, obtain the contour positions of the clustering clusters, and adjust the sizes of the remaining clustering clusters in the vehicle exterior environment image data to obtain camouflaged vehicle exterior environment image data; The data sending unit is used to encrypt the camouflaged vehicle exterior environment image data, the contour positions of the clustering clusters, and the vehicle exterior environment image data without camouflage, and send all of them to the data receiving end after obtaining the encrypted ciphertext; An image decryption module connected to the data processing module for the data receiving end to obtain the encrypted ciphertext, the encrypted camouflaged vehicle exterior environment image data, the contour positions of the clustering clusters, and the vehicle exterior environment image data without camouflage, and decrypt the encrypted ciphertext to obtain the vehicle exterior environment image data without camouflage; And removing the layer of the camouflaged vehicle exterior environment image data according to the contour positions of the clustering clusters from the camouflaged vehicle exterior environment image data, and adjusting the sizes of the remaining clustering clusters in the camouflaged vehicle exterior environment image data to obtain all the vehicle exterior environment image data.

8. The intelligent networked vehicle safety enhancement system based on artificial intelligence according to claim 7, characterized in that, It further includes a display module for displaying the vehicle exterior environment image data.

Images