A driving recorder data security storage and tracing system fusing blockchain technology

Abstract

The application relates to a driving recorder data security storage and tracing system fusing a blockchain technology, belongs to the field of internet platforms, and more particularly to the field of accounting systems for registering or indicating the operation of machines, and the system comprises: an encryption storage device for carrying out blockchain encryption storage on each frame of driving picture recorded by the driving recorder; and an intelligent analysis device for intelligently analyzing whether a vehicle turning accident will occur in a current time interval according to a plurality of first accounting values and a plurality of second accounting values corresponding to a plurality of frames of past driving pictures corresponding to the current time by adopting an AI accident analysis model. Through the application, the technical problem that accounting data for accident early warning cannot be collected according to road conditions can be solved by adopting a data storage and tracing mechanism based on the blockchain to acquire road condition visual data, then analyzing relevant various accounting data, and intelligently analyzing the occurrence of a vehicle turning accident, so that the above technical problem is solved.

Description

Technical Field

[0001] The internet platform of the present invention relates more specifically to an accounting system for registering or instructing the operation of machines, and particularly to a data security storage and traceability system for dashcams that integrates blockchain technology. Background Technology

[0002] With the continuous upgrading of vehicle intelligence, improving the controllability and safety of vehicle driving based on Internet platforms has become one of the main trends in vehicle design. Internet platforms can facilitate the intelligent transformation of vehicles in many aspects, such as data security storage and traceability, and data interaction. At the same time, vehicle designers hope to determine whether the vehicle, as a machine, is in an accident-prone state in the future based on the calculation data collected during the vehicle's operation, and then instruct the vehicle's operation to avoid future accidents as much as possible, thereby improving the controllability and safety of the vehicle.

[0003] For example, Chinese invention patent publication CN114970902A proposes a blockchain-based carbon emission accounting system for vehicle power batteries. The system includes: a production process carbon emission module connected to a blockchain module, which records carbon emissions during the production process and uploads these emissions to the blockchain module; and an operation process carbon emission module connected to the blockchain module, which records carbon emissions during vehicle operation. This blockchain-based carbon emission accounting system for vehicle power batteries can monitor the carbon emissions generated by the power battery during vehicle operation, as well as the carbon emissions generated during vehicle production and recycling, thereby obtaining the carbon emissions throughout the vehicle's lifecycle. This carbon emission information can then be shared with enterprises and regulatory authorities, facilitating subsequent optimization of the production process and reducing carbon emissions.

[0004] For example, Chinese invention patent publication CN108256766A proposes a vehicle insurance calculation method based on dangerous driving behavior. The method includes: assessing the level of dangerous driving behavior; obtaining dangerous driving behavior information; obtaining vehicle information; and calculating vehicle insurance costs by analyzing and classifying the dangerous driving behavior information and combining it with the vehicle information. This invention, through collecting and analyzing information on drivers' dangerous driving behavior and assigning a risk level weight to each behavior, derives a vehicle insurance calculation method based on dangerous driving behavior. This improves the rationality of the insurance calculation method and can also encourage drivers to reduce dangerous driving behavior, thereby reducing traffic accidents.

[0005] Clearly, none of the aforementioned existing technologies can collect various calculation data related to traffic accidents from constantly changing road conditions during vehicle operation. This makes it impossible to determine whether a vehicle, as a machine, is in an accident-prone state in the future based on various calculation data related to traffic accidents. Consequently, it is impossible to instruct the vehicle's operation to avoid future accidents as much as possible, affecting the improvement of vehicle controllability and safety. At the same time, the driving data related to constantly changing road conditions lacks a secure data storage and traceability mechanism, which cannot provide sufficiently reliable reference data for subsequent vehicle operation instructions. Summary of the Invention

[0006] To address the technical problems in existing technologies, this invention provides a dashcam data security storage and traceability system integrating blockchain technology. This system can perform blockchain-encrypted storage of each frame of driving footage recorded by the dashcam during vehicle operation. Specifically, each frame is assigned a blockchain storage address in a distributed ledger storage mode for blockchain encryption storage, and a consensus mechanism is used to execute the blockchain encryption storage. This provides a secure data storage mechanism for tracing data from multiple frames of driving footage at a set time. Importantly, it also performs intelligent analysis based on two different calculation values ​​obtained from the visualization data analysis of multiple frames of driving footage before the set time to determine whether a vehicle turning accident will occur within a future time interval starting from the set time. If the intelligent analysis determines that a vehicle turning accident will occur within the future time interval starting from the set time, the system instructs the vehicle to enter a cautious operation mode; otherwise, it instructs the vehicle to exit the cautious operation mode. This establishes an accounting system that instructs the machine's operation, improving the predictability and safety of driving.

[0007] According to the present invention, a dashcam data security storage and traceability system integrating blockchain technology is provided, the system comprising:

[0008] An encrypted storage device is used to encrypt and store each frame of driving footage recorded by the dashcam during vehicle operation using blockchain technology. The dashcam uses a set frame rate.

[0009] The data tracing device is connected to the encrypted storage device and is used to trace multiple frames of driving footage before the current moment to serve as multiple frames of past driving footage corresponding to the current moment.

[0010] The first calculation device, connected to the data traceability device, is used to uniformly divide the road surface image sub-image in each frame of past driving images into uniformly divided blocks of the road surface image sub-image of that frame, and calculate the number of uniformly divided blocks in the road surface image sub-image of that frame whose component standard deviation exceeds the limit as the first calculation value corresponding to the past driving image of that frame.

[0011] The second calculation device is connected to the first calculation device and is used to calculate the number of curves with curvature greater than or equal to a preset curvature value in the road surface imaging sub-frame of each driving frame as the second calculation value corresponding to each driving frame.

[0012] The intelligent analysis device is connected to the first and second calculation devices respectively. It is used to use an AI accident analysis model to intelligently analyze the accident occurrence identifier of vehicle turning accidents within the current time interval based on the resolution of the dashcam, the set frame rate, the duration of the time interval, the number of frames of past driving images corresponding to the current moment, the multiple first calculation values ​​corresponding to the multiple frames of past driving images corresponding to the current moment, and the multiple second calculation values.

[0013] According to a second aspect of the present invention, a dashcam data security storage and traceability system integrating blockchain technology is provided. The system includes a memory and multiple processors. The memory stores a computer program configured to be executed by the multiple processors to complete the following steps:

[0014] Every frame of driving footage recorded by the dashcam during vehicle operation is encrypted and stored using blockchain technology, and the dashcam uses a set frame rate.

[0015] The driving footage from multiple frames prior to the current moment is retrieved to serve as the corresponding multiple frames of past driving footage at the current moment.

[0016] The road surface image sub-image in each frame of past driving scene is uniformly divided into equal areas to obtain uniformly divided blocks of the road surface image sub-image in that frame. The number of uniformly divided blocks in the road surface image sub-image that exceeds the standard deviation of the components is calculated as the first calculated value corresponding to the past driving scene in that frame.

[0017] The number of curves with curvature greater than or equal to a preset curvature value within the road surface image sub-frame in each frame of driving image is calculated as the second calculated value corresponding to each frame of driving image.

[0018] The AI ​​accident analysis model uses the dashcam's resolution, set frame rate, duration of time interval, number of frames of past driving footage corresponding to the current moment, multiple first calculation values ​​and multiple second calculation values ​​corresponding to the multiple frames of past driving footage corresponding to the current moment to intelligently analyze the accident occurrence identifier of vehicle turning accidents within the current time interval.

[0019] Therefore, it can be seen that the present invention has at least the following prominent substantive features:

[0020] Substantial Feature 1: Every frame of driving footage recorded by the dashcam during vehicle operation is encrypted and stored using blockchain. The dashcam uses a set frame rate, and each frame is allocated a blockchain storage address in a distributed ledger storage mode for blockchain encryption and storage. A consensus mechanism is also used to perform blockchain encryption and storage, thereby providing a secure data storage mechanism for subsequent data tracing of multiple frames of driving footage at a set time.

[0021] Substantial Feature Two: Based on the analysis of various visual data from multiple frames of driving footage prior to a set time, two different calculation values ​​are obtained to perform intelligent analysis on whether a vehicle turning accident will occur within a future time interval starting from the set time. When the intelligent analysis determines that a vehicle turning accident will occur within a future time interval starting from the set time, the vehicle is instructed to enter a cautious operation mode; otherwise, the vehicle is instructed to exit the cautious operation mode. This establishes a calculation system that instructs the machine's operation, improving the predictability and safety of driving.

[0022] Substantial Feature Three: To achieve intelligent analysis of whether a vehicle turning accident will occur within a future time interval starting from a set time, a customized AI accident analysis model is introduced. This AI accident analysis model is a feedforward neural network that has performed multiple learning actions. The number of learning actions performed by the feedforward neural network is positively correlated with the resolution of the dashcam. The feedforward neural network includes hidden layers, an input layer, and an output layer. There are multiple hidden layers, which are located between the input layer and the output layer. The number of hidden layers in the feedforward neural network is inversely correlated with the set frame rate. This allows for the design of AI accident analysis models with different customized structures for different dashcams, ensuring the reliability and stability of the intelligent analysis results regarding whether a vehicle turning accident will occur within a future time interval.

[0023] Substantial Feature Four: To achieve intelligent analysis of whether a vehicle turning accident will occur within a future time interval starting from a set time, multiple basic data are introduced. These basic data include the dashcam's resolution, set frame rate, duration of the time interval, number of frames of past driving footage corresponding to the current time, multiple first-value calculations and multiple second-value calculations corresponding to the multiple frames of past driving footage corresponding to the current time. The thorough and comprehensive screening of the above-mentioned basic data further ensures the reliability and stability of the intelligent analysis results of whether a vehicle turning accident will occur within a future time interval.

[0024] Substantive Feature 5: Specifically, the road surface image sub-image in each frame of past driving scene is uniformly divided into equal areas to obtain uniformly divided blocks of the road surface image sub-image in that frame. The number of uniformly divided blocks in the road surface image sub-image in that frame with the component standard deviation exceeding the limit is calculated as the first calculated value corresponding to the past driving scene in that frame. The number of curves in the road surface image sub-image in each frame of driving scene with curvature greater than or equal to a preset curvature value is calculated as the second calculated value corresponding to each frame of driving scene. Thus, the data structure design of two different calculated values ​​for intelligent analysis is completed.

[0025] Substantive Feature Six: In each learning action performed on the feedforward neural network, the accident occurrence identifier of a known vehicle turning accident within a certain past time interval is used as a single output of the feedforward neural network. The resolution of the dashcam, the set frame rate, the duration of the time interval, the number of frames of past driving footage corresponding to the start time of the certain past time interval, and multiple first-valued and second-valued data corresponding to the multiple frames of past driving footage corresponding to the start time of the certain past time interval are used as multiple inputs of the feedforward neural network to complete the learning action, thereby ensuring the learning effect of each learning action of the feedforward neural network. Attached Figure Description

[0026] The embodiments of the present invention will now be described with reference to the accompanying drawings, wherein:

[0027] Figure 1 This is a schematic diagram illustrating the working scenario of the dashcam data security storage and traceability system integrating blockchain technology according to the present invention.

[0028] Figure 2 This is an internal structure diagram of a dashcam data security storage and traceability system integrating blockchain technology, as shown in the first embodiment of the present invention.

[0029] Figure 3 This is an internal structure diagram of a dashcam data security storage and traceability system integrating blockchain technology, as shown in the second embodiment of the present invention.

[0030] Figure 4 This is an internal structure diagram of a dashcam data security storage and traceability system integrating blockchain technology, as shown in the third embodiment of the present invention.

[0031] Figure 5 This is an internal structure diagram of a dashcam data security storage and traceability system integrating blockchain technology, as shown in the fourth embodiment of the present invention.

[0032] Figure 6This is an internal structure diagram of a dashcam data security storage and traceability system integrating blockchain technology, as shown in the fifth embodiment of the present invention.

[0033] Figure 7 This is an internal structure diagram of a dashcam data security storage and traceability system integrating blockchain technology, as shown in the sixth embodiment of the present invention. Detailed Implementation

[0034] like Figure 1 The diagram illustrates a working scenario of a dashcam data security storage and traceability system integrating blockchain technology according to the present invention. More specifically, the internet platform of the present invention relates to an accounting system for registering or instructing the operation of machines.

[0035] The specific technical process of this invention is as follows:

[0036] Technical Process A: For each vehicle, each frame of driving footage recorded by its dashcam during the vehicle's driving process is encrypted and stored using blockchain. The dashcam uses a set frame rate and has a corresponding resolution.

[0037] Specifically, each frame of driving footage is assigned a blockchain storage address in the blockchain distributed ledger storage mode for performing blockchain encrypted storage of that frame of driving footage, and a consensus mechanism is used to perform blockchain encrypted storage.

[0038] This provides a secure data storage mechanism for tracing the data of multiple frames of driving footage corresponding to the set time, ensuring the security and reliability of the retrieved data.

[0039] Technical Process B: To achieve intelligent analysis of whether vehicle turning accidents will occur within a future time interval starting from a set time, a customized AI accident analysis model is introduced, such as... Figure 1 As shown;

[0040] Specifically, the customized structural design of the AI ​​accident analysis model is mainly reflected in the following aspects:

[0041] First: The AI ​​accident analysis model is a feedforward neural network that has performed multiple learning actions, and the number of learning actions performed by the feedforward neural network is positively correlated with the resolution of the dashcam.

[0042] Second: The feedforward neural network used in the AI ​​accident analysis model includes hidden layers, input layers and output layers. The number of hidden layers is multiple and lies between the input layers and the output layers. The number of hidden layers in the feedforward neural network is inversely related to the value of the set frame rate.

[0043] Third: In each learning action performed on the feedforward neural network, the accident occurrence identifier of a known past vehicle turning accident within a certain past time interval is used as a single output of the feedforward neural network. The resolution of the dashcam, the set frame rate, the duration of the time interval, the number of frames of past driving footage corresponding to the start time of the past time interval, and the multiple first calculation values ​​and multiple second calculation values ​​corresponding to the multiple frames of past driving footage corresponding to the start time of the past time interval are used as multiple inputs of the feedforward neural network to complete the learning action, thereby ensuring the learning effect of each learning action of the feedforward neural network.

[0044] In this way, AI accident analysis models with different customized structures can be designed for different dashcams, ensuring the reliability and stability of intelligent analysis results on whether a vehicle turning accident will occur within a future time interval.

[0045] Technical Process C: To achieve intelligent analysis of whether a vehicle turning accident will occur within a future time interval starting from a set time, several basic data points are introduced;

[0046] Specifically, the multiple basic data include the dashcam's resolution, set frame rate, duration of time interval, number of frames of past driving footage corresponding to the current moment, multiple first calculation values ​​and multiple second calculation values ​​corresponding to the multiple frames of past driving footage corresponding to the current moment.

[0047] like Figure 1 As shown, in addition to multiple sets of first-value calculations and multiple sets of second-value calculations, the basic data also includes other auxiliary data for intelligent analysis. The other auxiliary data includes the dashcam's resolution, set frame rate, duration of time interval, and the number of frames of past driving footage corresponding to the current moment.

[0048] More specifically, the road surface image sub-image in each frame of past driving scene is uniformly divided into equal areas to obtain uniformly divided blocks of the road surface image sub-image in that frame. The number of uniformly divided blocks in the road surface image sub-image in that frame with the component standard deviation exceeding the limit is calculated as the first calculated value corresponding to the past driving scene in that frame. The number of curves in the road surface image sub-image in each frame of driving scene with curvature greater than or equal to a preset curvature value is calculated as the second calculated value corresponding to each frame of driving scene. Thus, the data structure design of two different calculated values ​​for intelligent analysis is completed.

[0049] In this way, through the thorough and comprehensive screening of the above-mentioned basic data, the reliability and stability of the intelligent analysis results on whether vehicle turning accidents will occur in the future time interval are further guaranteed.

[0050] Technical Process D: Using Technical Process B, the AI ​​accident analysis model for the current vehicle's dashcam is customized and designed. Based on multiple basic data that have been fully and comprehensively screened by Technical Process C, it intelligently analyzes whether the current vehicle will be involved in a turning accident in the future time interval.

[0051] For example, if the above intelligent analysis is performed at the current moment, then the current time interval, which is the starting point of the current moment, is a future time interval;

[0052] Specifically, the intelligent analysis obtains an accident occurrence indicator that indicates whether the current vehicle will be involved in a turning accident within a future time interval;

[0053] Technical Process E: Based on the intelligent analysis results of various calculation data collected according to changing road conditions from Technical Process D, it indicates whether the current vehicle needs to enter a cautious operation mode, such as... Figure 1 As shown;

[0054] For example, if intelligent analysis determines that a vehicle turning accident will occur within a future time interval starting from a set time, the vehicle is instructed to enter a cautious operation mode; otherwise, the vehicle is instructed to exit the cautious operation mode.

[0055] In this way, an accounting system that indicates the operation of the machine is built, which improves the predictability and safety of driving for every vehicle equipped with a dashcam.

[0056] Therefore, this invention can perform blockchain-encrypted storage of each frame of driving footage recorded by the dashcam during vehicle operation. Specifically, it assigns blockchain storage addresses in a distributed ledger storage mode to each frame for blockchain-encrypted storage, and employs a consensus mechanism to perform this encryption. This provides a secure data storage mechanism for tracing data from multiple frames of driving footage at a set time. More importantly, it intelligently analyzes whether a vehicle turning accident will occur within a future time interval starting from the set time, based on two different calculation values ​​obtained from the visualization data analysis of multiple frames of driving footage before the set time. If the intelligent analysis determines that a vehicle turning accident will occur within the future time interval starting from the set time, it instructs the vehicle to enter a cautious operation mode; otherwise, it instructs the vehicle to exit the cautious operation mode. This establishes a calculation system to instruct the machine's operation, improving the predictability and safety of driving.

[0057] The key points of this invention are: targeted collection of various accounting data based on changing road conditions; design of AI accident analysis models with different customized structures for different dashcams; thorough and comprehensive screening of multiple basic data for intelligent analysis; and blockchain encrypted storage of road condition data combined with blockchain distributed ledger storage mode and consensus mechanism.

[0058] The following will describe in detail, by way of an embodiment, a dashcam data security storage and traceability system that integrates blockchain technology and is implemented by a smart chip according to the present invention.

[0059] First Embodiment

[0060] Figure 2 This is an internal structure diagram of a dashcam data security storage and traceability system integrating blockchain technology, as shown in the first embodiment of the present invention.

[0061] like Figure 2 As shown, the dashcam data security storage and traceability system integrating blockchain technology includes the following components:

[0062] An encrypted storage device is used to encrypt and store each frame of driving footage recorded by the dashcam during vehicle operation using blockchain technology. The dashcam uses a set frame rate.

[0063] For example, each vehicle's dashcam has a set frame rate and a set resolution. For instance, the dashcam has a set frame rate of 120 frames per second and a set resolution of 4096×2160, which is 4K ultra-high definition resolution. It has a horizontal resolution of 4096, a vertical resolution of 2160, and a total number of pixels of 4096×2160.

[0064] The data tracing device is connected to the encrypted storage device and is used to trace multiple frames of driving footage before the current moment to serve as multiple frames of past driving footage corresponding to the current moment.

[0065] In this way, by using blockchain-based encrypted storage, it is ensured that the multiple frames of driving footage retrieved up to the current moment are safe, reliable, and authentic data.

[0066] The first calculation device, connected to the data traceability device, is used to uniformly divide the road surface image sub-image in each frame of past driving images into uniformly divided blocks of the road surface image sub-image of that frame, and calculate the number of uniformly divided blocks in the road surface image sub-image of that frame whose component standard deviation exceeds the limit as the first calculation value corresponding to the past driving image of that frame.

[0067] For example, when uniformly dividing the road surface image sub-image in each frame of past driving scene into equal area, the uniform division of equal area is completed based on pixel precision.

[0068] Here, the first calculated value corresponding to each frame of past driving footage represents the complexity of the road conditions in that frame. The multiple first calculated values ​​corresponding to multiple frames of driving footage before the current moment represent the changes in the complexity of the road conditions before the current moment, thus serving as an important basic data for analyzing whether a turning accident will occur in the subsequent time interval.

[0069] The second calculation device is connected to the first calculation device and is used to calculate the number of curves with curvature greater than or equal to a preset curvature value in the road surface imaging sub-frame of each driving frame as the second calculation value corresponding to each driving frame.

[0070] Here, the multiple sets of second-calculated values ​​corresponding to the multiple frames of driving footage before the current moment represent the changes in road conditions before the current moment, thus serving as another important basic data for analyzing whether a turning accident will occur in subsequent time intervals;

[0071] The intelligent analysis device is connected to the first and second accounting devices respectively. It is used to use an AI accident analysis model to intelligently analyze the accident occurrence identifier of vehicle turning accidents in the current time interval based on the resolution of the dashcam, the set frame rate, the duration of the time interval, the number of frames of the past driving images corresponding to the current moment, the multiple first accounting values ​​corresponding to the multiple frames of past driving images corresponding to the current moment, and the multiple second accounting values.

[0072] Obviously, in addition to the first and second calculation values ​​that reflect changes in road conditions, multiple data points are also introduced as auxiliary data, including the dashcam's resolution, set frame rate, duration of the time interval, and the number of frames of the past driving footage corresponding to the current moment, to help complete the intelligent analysis of whether a turning accident will occur in the subsequent time interval.

[0073] The AI ​​accident analysis model is a feedforward neural network that has performed multiple learning actions. The number of learning actions performed by the feedforward neural network is positively correlated with the resolution of the dashcam. The feedforward neural network includes a hidden layer, an input layer, and an output layer. The number of hidden layers is multiple and lies between the input layer and the output layer.

[0074] For example, the positive correlation between the number of learning actions performed by the feedforward neural network and the resolution of the dashcam includes: when the dashcam resolution is 8K ultra-high definition, the number of learning actions performed by the feedforward neural network is 1000; when the dashcam resolution is 4K ultra-high definition, the number of learning actions performed by the feedforward neural network is 900; when the dashcam resolution is 2K ultra-high definition, the number of learning actions performed by the feedforward neural network is 800; when the dashcam resolution is high definition, the number of learning actions performed by the feedforward neural network is 700, and so on.

[0075] In each learning action performed on the feedforward neural network, the accident occurrence identifier of a known vehicle turning accident within a certain past time interval is used as a single output of the feedforward neural network. The resolution of the dashcam, the set frame rate, the duration of the time interval, the number of frames of the past driving footage corresponding to the start time of the certain past time interval, and the multiple first calculation values ​​and multiple second calculation values ​​corresponding to the multiple frames of the past driving footage corresponding to the start time of the certain past time interval are used as multiple inputs of the feedforward neural network to complete this learning action.

[0076] Specifically, numerical simulation can be used to test and simulate each learning action performed by the feedforward neural network.

[0077] Specifically, the road surface imaging sub-frame in each past driving scene is uniformly divided into equal-area segments to obtain uniformly segmented blocks of the road surface imaging sub-frame. The number of uniformly segmented blocks in the road surface imaging sub-frame with excessive component standard deviation is calculated as the first calculated value corresponding to the past driving scene. This includes: when the standard deviation of the Y component, the standard deviation of the U component, and / or the standard deviation of the V component in the YUV space of a certain uniformly segmented block in the road surface imaging sub-frame exceeds the limit, the certain uniformly segmented block is regarded as the uniformly segmented block with excessive component standard deviation in the road surface imaging sub-frame.

[0078] For example, if the component values ​​of each pixel in the provided past driving scene are R component values, G component values ​​and B component values ​​in RGB space, the Y component values, U component values ​​and V component values ​​of each pixel in the past driving scene in YUV space can be obtained by using the RGB to YUV conversion formula.

[0079] Specifically, the core formula for RGB to YUV conversion differs across standards, but the commonly used formula under the ITU-R BT.601 standard is:

[0080] Y = 0.299R + 0.587G + 0.114B;

[0081] U = -0.1687R - 0.3313G + 0.5B + ​​128;

[0082] V = 0.5R - 0.4187G - 0.0813B + 128;

[0083] And wherein, when a uniform segment in a road surface imaging sub-frame exceeds the standard deviation of the Y component, the standard deviation of the U component, and / or the standard deviation of the V component in the YUV space, the uniform segment is designated as a uniform segment in the road surface imaging sub-frame with the component standard deviation exceeding the limit. This includes: obtaining the Y component value, U component value, and V component value corresponding to each constituent pixel of the uniform segment; and determining that the Y component standard deviation, U component value, and V component value of the uniform segment exceeds the limit when the standard deviation of the Y component value, U component value, and V component value in the YUV space is greater than a preset standard deviation threshold.

[0084] Second Embodiment

[0085] Figure 3 This is an internal structure diagram of a dashcam data security storage and traceability system integrating blockchain technology, as shown in the second embodiment of the present invention.

[0086] like Figure 3 As shown, compared to Figure 2 The dashcam data security storage and traceability system integrating blockchain technology also includes:

[0087] The mode switching device, connected to the intelligent analysis device, is used to instruct the vehicle to enter a cautious operation mode when the accident occurrence indicator of a vehicle turning accident within the current time interval obtained by the intelligent analysis indicates that a vehicle turning accident will occur within the current time interval.

[0088] For example, the mode switching device can be implemented using a programmable logic device, which instructs the vehicle to enter a cautious operation mode when the accident occurrence identifier of a vehicle turning accident in the current time interval obtained by intelligent analysis indicates that a vehicle turning accident will occur in the current time interval.

[0089] As a further example, the mode switching device can be implemented using a programmable logic device. When the accident occurrence identifier of a vehicle turning accident obtained by intelligent analysis indicates that a vehicle turning accident will occur in the current time interval, the device instructs the vehicle to enter a cautious operation mode. The programmable logic device is an FPGA chip designed in VHDL language.

[0090] The mode switching device is also used to instruct the vehicle to exit the cautious operation mode when the accident occurrence indicator of a vehicle turning accident within the current time interval obtained by intelligent analysis indicates that no vehicle turning accident will occur within the current time interval.

[0091] Third Embodiment

[0092] Figure 4 This is an internal structure diagram of a dashcam data security storage and traceability system integrating blockchain technology, as shown in the third embodiment of the present invention.

[0093] like Figure 4 As shown, compared to Figure 3 The dashcam data security storage and traceability system integrating blockchain technology also includes:

[0094] A multi-layer learning device, connected to an intelligent analysis device, is used to perform multiple learning actions on a feedforward neural network to obtain a feedforward neural network after performing multiple learning actions, and outputs the feedforward neural network after performing multiple learning actions as an AI accident analysis model.

[0095] For example, a SOC chip can be used to implement a multi-layer learning device, which performs multiple learning actions on the feedforward neural network to obtain the feedforward neural network after performing multiple learning actions, and outputs the feedforward neural network after performing multiple learning actions as an AI accident analysis model.

[0096] The process of performing multiple learning actions on the feedforward neural network to obtain the feedforward neural network after performing multiple learning actions, and using the feedforward neural network after performing multiple learning actions as the output of the AI ​​accident analysis model, includes: using the various model parameters of the AI ​​accident analysis model to complete the model representation of the AI ​​accident analysis model.

[0097] Fourth embodiment

[0098] Figure 5 This is an internal structure diagram of a dashcam data security storage and traceability system integrating blockchain technology, as shown in the fourth embodiment of the present invention.

[0099] like Figure 5 As shown, compared to Figure 2 The dashcam data security storage and traceability system integrating blockchain technology also includes:

[0100] A real-time display device, connected to the intelligent analysis device, is used to receive accident occurrence identifiers of vehicle turning accidents within the current time interval and to perform real-time display operations on the accident occurrence identifiers of vehicle turning accidents within the current time interval.

[0101] For example, a real-time display device, connected to the intelligent analysis device, is used to receive accident occurrence identifiers of vehicle turning accidents within the current time interval, and to perform a real-time display operation on the accident occurrence identifiers of vehicle turning accidents within the current time interval, including: the real-time display device is a liquid crystal display screen or an LCD display matrix.

[0102] Fifth Embodiment

[0103] Figure 6 This is an internal structure diagram of a dashcam data security storage and traceability system integrating blockchain technology, as shown in the fifth embodiment of the present invention.

[0104] like Figure 6 As shown, compared to Figure 2 The dashcam data security storage and traceability system integrating blockchain technology also includes:

[0105] A Bluetooth transmission device, connected to the intelligent analysis device, is used to receive the accident occurrence identifier of vehicle turning accidents within the current time interval, and wirelessly transmit the accident occurrence identifier of vehicle turning accidents within the current time interval to the vehicle driver's Bluetooth headset via a Bluetooth transmission link.

[0106] For example, a Bluetooth transmission device, connected to the intelligent analysis device, is used to receive an accident occurrence identifier of a vehicle turning accident within the current time interval, and wirelessly transmit the accident occurrence identifier of the vehicle turning accident within the current time interval to the Bluetooth headset of the vehicle driver via a Bluetooth transmission link. This includes: an accident occurrence identifier of a vehicle turning accident within the current time interval that can use the value 0B10, indicating that no vehicle turning accident will occur within the current time interval; and an accident occurrence identifier of a vehicle turning accident within the current time interval that can use the value 0B11, indicating that a vehicle turning accident will occur within the current time interval.

[0107] Next, various embodiments of the present invention will be further described.

[0108] Optionally, within the above embodiments, in the dashcam data security storage and traceability system integrating blockchain technology:

[0109] The AI ​​accident analysis model uses the dashcam's resolution, set frame rate, duration of time interval, number of frames of past driving footage corresponding to the current moment, multiple first calculation values ​​and multiple second calculation values ​​corresponding to the multiple frames of past driving footage corresponding to the current moment to intelligently analyze the accident occurrence indicators of vehicle turning accidents within the current time interval. The accident occurrence indicators are: the current time interval starts from the current moment, and different values ​​indicate whether a vehicle turning accident will occur within the current time interval.

[0110] For example, the current time interval starts from the current time, and different values ​​of the accident occurrence indicator indicate whether a vehicle turning accident will occur within the current time interval, including: the current time is 10:00 AM, the current time interval is from 10:00 AM to 10:05 AM, and the duration of each time interval is 5 minutes.

[0111] The process of obtaining the Y component values, U component values, and V component values ​​corresponding to each constituent pixel of a uniform segmentation block, and determining that the Y component standard deviation, U component value, and V component value of a uniform segmentation block exceeds the limit when the standard deviation of each Y component value, U component value, and V component value is greater than a preset standard deviation threshold, includes: the Y component value, U component value, and V component value of each constituent pixel of each uniform segmentation block are within the range of 0-255 in the YUV space.

[0112] The process of uniformly dividing the road surface image sub-image in each frame of past driving scene into uniformly divided blocks of the road surface image sub-image in that frame, and calculating the number of uniformly divided blocks in the road surface image sub-image in that frame whose component standard deviation exceeds the limit as the first calculated value corresponding to the past driving scene in that frame, also includes: performing a road surface recognition operation on each frame of past driving scene to obtain the road surface image sub-image in each frame of past driving scene.

[0113] The process of performing road recognition operation on each frame of past driving footage to obtain a road image sub-frame in each frame of past driving footage includes: identifying road component pixels in each frame of past driving footage based on the color imaging features corresponding to the road surface, and fitting each road component pixel in the frame of past driving footage to obtain a road image sub-frame in the frame of past driving footage.

[0114] And, optionally, within the aforementioned embodiments, in the dashcam data security storage and traceability system integrating blockchain technology:

[0115] Each frame of driving footage recorded by the dashcam during vehicle driving is encrypted and stored using blockchain. The dashcam uses a set frame rate and allocates blockchain storage addresses in a distributed ledger storage mode for each frame of driving footage to perform blockchain encryption and storage. A consensus mechanism is used to perform blockchain encryption and storage.

[0116] The so-called blockchain distributed ledger storage model distributes data that originally needed to be stored centrally to different blockchain storage nodes, thereby eliminating the possibility of a single power center interfering with the entire storage system.

[0117] The consensus mechanism is an important component of blockchain technology. As a data structure that stores data in chronological order, blockchain can support different consensus mechanisms. The goal of a blockchain consensus mechanism is to ensure that all honest nodes maintain a consistent view of the blockchain, while satisfying two properties: 1) Consistency, that is, the prefix part of the blockchain maintained by all honest nodes is exactly the same; 2) Validity, that is, the information published by an honest node will eventually be recorded in the blockchains of all other honest nodes.

[0118] Among them, each frame of driving footage recorded by the dashcam during vehicle driving is encrypted and stored using blockchain. The dashcam also uses a set frame rate and the timestamps of each frame of driving footage recorded by the dashcam during vehicle driving are evenly distributed on the timeline.

[0119] The process involves simultaneously inputting the dashcam's resolution, set frame rate, duration of the time interval, number of frames of past driving footage corresponding to the current moment, multiple first calculation values ​​and multiple second calculation values ​​corresponding to the multiple frames of past driving footage corresponding to the current moment into the AI ​​accident analysis model, and running the AI ​​accident analysis model to obtain the accident occurrence identifier of the vehicle turning accident within the current time interval output by the AI ​​accident analysis model.

[0120] The process involves simultaneously inputting the dashcam's resolution, set frame rate, duration of the time interval, number of frames in the current time frame corresponding to the multiple past driving images, multiple first-calculated values ​​corresponding to the multiple past driving images corresponding to the current time frame, and multiple second-calculated values ​​into the AI ​​accident analysis model. The AI ​​accident analysis model is then run to obtain the accident occurrence identifier of the vehicle turning accident within the current time interval, which includes: the accident occurrence identifier of the vehicle turning accident within the current time interval, the dashcam's resolution, set frame rate, duration of the time interval, number of frames in the current time frame corresponding to the multiple past driving images, and multiple first-calculated values ​​corresponding to the multiple past driving images corresponding to the current time frame, all of which are numerical representations after numerical normalization.

[0121] For example, the accident occurrence identifier of the vehicle turning accident in the current time interval, the resolution of the dashcam, the set frame rate, the duration of the time interval, the number of frames of the multiple past driving images corresponding to the current moment, the multiple first calculation values ​​and multiple second calculation values ​​corresponding to the multiple past driving images corresponding to the current moment are all numerical representations after numerical normalization processing, including: the numerical normalization processing is binary numerical conversion processing;

[0122] The process involves simultaneously inputting the dashcam's resolution, frame rate setting, duration of the time interval, number of frames from past driving footage at the current moment, multiple first-valued data points corresponding to the past driving footage at the current moment, and multiple second-valued data points into the AI ​​accident analysis model. The AI ​​accident analysis model is then run to obtain the accident identification of a vehicle turning accident within the current time interval output by the AI ​​accident analysis model. The dashcam's resolution is defined as its vertical resolution and horizontal resolution.

[0123] Sixth Embodiment

[0124] Figure 7 This is an internal structure diagram of a dashcam data security storage and traceability system integrating blockchain technology, as shown in the sixth embodiment of the present invention.

[0125] like Figure 7 As shown, the multimedia content automatic generation and publishing system includes a memory and multiple processors. The memory stores a computer program, which is configured to be executed by the multiple processors to complete the following steps:

[0126] Step 71: Encrypt and store each frame of driving footage recorded by the dashcam during vehicle operation using blockchain technology, with the dashcam using a set frame rate;

[0127] For example, each vehicle's dashcam has a set frame rate and a set resolution. For instance, the dashcam has a set frame rate of 120 frames per second and a set resolution of 4096×2160, which is 4K ultra-high definition resolution. It has a horizontal resolution of 4096, a vertical resolution of 2160, and a total number of pixels of 4096×2160.

[0128] Step 72: Retrace multiple frames of driving footage before the current moment to obtain the multiple frames of past driving footage corresponding to the current moment;

[0129] In this way, by using blockchain-based encrypted storage, it is ensured that the multiple frames of driving footage retrieved up to the current moment are safe, reliable, and authentic data.

[0130] Step 73: Divide the road surface image sub-image in each past driving image frame into uniform segments of equal area to obtain uniform segments of the road surface image sub-image frame. Calculate the number of uniform segments in the road surface image sub-image frame whose component standard deviation exceeds the limit and use it as the first calculation value corresponding to the past driving image frame.

[0131] For example, when uniformly dividing the road surface image sub-image in each frame of past driving scene into equal area, the uniform division of equal area is completed based on pixel precision.

[0132] Here, the first calculated value corresponding to each frame of past driving footage represents the complexity of the road conditions in that frame. The multiple first calculated values ​​corresponding to multiple frames of driving footage before the current moment represent the changes in the complexity of the road conditions before the current moment, thus serving as an important basic data for analyzing whether a turning accident will occur in the subsequent time interval.

[0133] Step 74: Calculate the number of curves with curvature greater than or equal to a preset curvature value within the road surface image sub-frame in each driving frame to serve as the second calculation value for each driving frame.

[0134] Here, the multiple sets of second-calculated values ​​corresponding to the multiple frames of driving footage before the current moment represent the changes in road conditions before the current moment, thus serving as another important basic data for analyzing whether a turning accident will occur in subsequent time intervals;

[0135] Step 75: Using an AI accident analysis model, based on the dashcam's resolution, set frame rate, duration of the time interval, number of frames of past driving footage corresponding to the current moment, multiple first calculation values ​​and multiple second calculation values ​​corresponding to the multiple frames of past driving footage corresponding to the current moment, the accident occurrence identifier of the vehicle turning accident within the current time interval is intelligently analyzed.

[0136] Obviously, in addition to the first and second calculation values ​​that reflect changes in road conditions, multiple data points are also introduced as auxiliary data, including the dashcam's resolution, set frame rate, duration of the time interval, and the number of frames of the past driving footage corresponding to the current moment, to help complete the intelligent analysis of whether a turning accident will occur in the subsequent time interval.

[0137] The AI ​​accident analysis model is a feedforward neural network that has performed multiple learning actions. The number of learning actions performed by the feedforward neural network is positively correlated with the resolution of the dashcam. The feedforward neural network includes a hidden layer, an input layer, and an output layer. The number of hidden layers is multiple and lies between the input layer and the output layer.

[0138] For example, the positive correlation between the number of learning actions performed by the feedforward neural network and the resolution of the dashcam includes: when the dashcam resolution is 8K ultra-high definition, the number of learning actions performed by the feedforward neural network is 1000; when the dashcam resolution is 4K ultra-high definition, the number of learning actions performed by the feedforward neural network is 900; when the dashcam resolution is 2K ultra-high definition, the number of learning actions performed by the feedforward neural network is 800; when the dashcam resolution is high definition, the number of learning actions performed by the feedforward neural network is 700, and so on.

[0139] In each learning action performed on the feedforward neural network, the accident occurrence identifier of a known vehicle turning accident within a certain past time interval is used as a single output of the feedforward neural network. The resolution of the dashcam, the set frame rate, the duration of the time interval, the number of frames of the past driving footage corresponding to the start time of the certain past time interval, and the multiple first calculation values ​​and multiple second calculation values ​​corresponding to the multiple frames of the past driving footage corresponding to the start time of the certain past time interval are used as multiple inputs of the feedforward neural network to complete this learning action.

[0140] Specifically, numerical simulation can be used to test and simulate each learning action performed by the feedforward neural network.

[0141] Specifically, the road surface imaging sub-frame in each past driving scene is uniformly divided into equal-area segments to obtain uniformly segmented blocks of the road surface imaging sub-frame. The number of uniformly segmented blocks in the road surface imaging sub-frame with excessive component standard deviation is calculated as the first calculated value corresponding to the past driving scene. This includes: when the standard deviation of the Y component, the standard deviation of the U component, and / or the standard deviation of the V component in the YUV space of a certain uniformly segmented block in the road surface imaging sub-frame exceeds the limit, the certain uniformly segmented block is regarded as the uniformly segmented block with excessive component standard deviation in the road surface imaging sub-frame.

[0142] For example, if the component values ​​of each pixel in the provided past driving scene are R component values, G component values ​​and B component values ​​in RGB space, the Y component values, U component values ​​and V component values ​​of each pixel in the past driving scene in YUV space can be obtained by using the RGB to YUV conversion formula.

[0143] Specifically, the core formula for RGB to YUV conversion differs across standards, but the commonly used formula under the ITU-R BT.601 standard is:

[0144] Y = 0.299R + 0.587G + 0.114B;

[0145] U = -0.1687R - 0.3313G + 0.5B + ​​128;

[0146] V = 0.5R - 0.4187G - 0.0813B + 128;

[0147] And wherein, when a uniform segment in a road surface imaging sub-frame exceeds the standard deviation of the Y component, the standard deviation of the U component, and / or the standard deviation of the V component in the YUV space, the uniform segment is designated as a uniform segment in the road surface imaging sub-frame with the component standard deviation exceeding the limit. This includes: obtaining the Y component value, U component value, and V component value corresponding to each constituent pixel of the uniform segment; and determining that the Y component standard deviation, U component value, and V component value of the uniform segment exceeds the limit when the standard deviation of the Y component value, U component value, and V component value in the YUV space is greater than a preset standard deviation threshold.

[0148] Furthermore, in the dashcam data security storage and traceability system integrating blockchain technology according to the present invention:

[0149] The AI ​​accident analysis model is a feedforward neural network that has performed multiple learning actions. The number of learning actions performed by the feedforward neural network is positively correlated with the resolution of the dashcam. The feedforward neural network includes hidden layers, input layers, and output layers. The number of hidden layers is multiple and lies between the input layer and the output layer. The number of hidden layers in the feedforward neural network is inversely correlated with the set frame rate.

[0150] The inverse relationship between the number of hidden layers in the feedforward neural network and the set frame rate includes: using a numerical mapping formula to express the numerical mapping relationship between the number of hidden layers in the feedforward neural network and the set frame rate.

[0151] For example, you can choose to use the MATLAB toolbox to test and simulate the numerical mapping process that uses a numerical mapping formula to express the inverse relationship between the number of hidden layers in the feedforward neural network and the set frame rate.

[0152] In the numerical mapping formula, the set frame rate is the input parameter of the numerical mapping formula, and the number of hidden layers in the feedforward neural network used, which is inversely related to the set frame rate, is the output parameter of the numerical mapping formula.

[0153] The foregoing description of exemplary embodiments of the invention is provided for purposes of illustration and description. It is not intended to be exhaustive or to limit the invention to the precise forms disclosed. Many modifications and variations will obviously be apparent to those skilled in the art. Exemplary embodiments were chosen and described in order to best illustrate the principles of the invention and its practical application, thereby enabling others skilled in the art to understand the various embodiments and variations of the invention suitable for the particular purpose contemplated. The scope of the invention is intended to be defined by the appended claims and their equivalents.

Claims

1. A dashcam data security storage and traceability system integrating blockchain technology, characterized in that, The system includes: An encrypted storage device is used to encrypt and store each frame of driving footage recorded by the dashcam during vehicle operation using blockchain technology. The dashcam uses a set frame rate. The data tracing device is connected to the encrypted storage device and is used to trace multiple frames of driving footage before the current moment to serve as multiple frames of past driving footage corresponding to the current moment. The first calculation device, connected to the data traceability device, is used to uniformly divide the road surface image sub-image in each frame of past driving images into uniformly divided blocks of the road surface image sub-image of that frame, and calculate the number of uniformly divided blocks in the road surface image sub-image of that frame whose component standard deviation exceeds the limit as the first calculation value corresponding to the past driving image of that frame. The second calculation device is connected to the first calculation device and is used to calculate the number of curves with curvature greater than or equal to a preset curvature value in the road surface imaging sub-frame of each driving frame as the second calculation value corresponding to each driving frame. The intelligent analysis device is connected to the first and second calculation devices respectively. It is used to use an AI accident analysis model to intelligently analyze the accident occurrence identifier of vehicle turning accidents within the current time interval based on the resolution of the dashcam, the set frame rate, the duration of the time interval, the number of frames of past driving images corresponding to the current moment, the multiple first calculation values ​​corresponding to the multiple frames of past driving images corresponding to the current moment, and the multiple second calculation values.

2. The dashcam data security storage and traceability system integrating blockchain technology as described in claim 1, characterized in that: The AI ​​accident analysis model is a feedforward neural network that has performed multiple learning actions. The number of learning actions performed by the feedforward neural network is positively correlated with the resolution of the dashcam. The feedforward neural network includes hidden layers, input layers, and output layers. The number of hidden layers is multiple and lies between the input layers and the output layers. In each learning action performed on the feedforward neural network, the accident identifier of a known past vehicle turning accident within a certain past time interval is used as a single output of the feedforward neural network. The resolution of the dashcam, the set frame rate, the duration of the time interval, the number of frames of past driving footage corresponding to the start time of the past time interval, and multiple first calculation values ​​and multiple second calculation values ​​corresponding to the multiple frames of past driving footage corresponding to the start time of the past time interval are used as multiple inputs of the feedforward neural network to complete this learning action.

3. The dashcam data security storage and traceability system integrating blockchain technology as described in claim 2, characterized in that: The road surface imaging sub-frame in each past driving scene is uniformly divided into equal areas to obtain uniformly divided blocks of the road surface imaging sub-frame. The number of uniformly divided blocks in the road surface imaging sub-frame with excessive component standard deviation is calculated as the first calculated value corresponding to the past driving scene. This includes: when the standard deviation of the Y component, the standard deviation of the U component, and / or the standard deviation of the V component in the YUV space of a certain uniformly divided block in the road surface imaging sub-frame exceeds the limit, the certain uniformly divided block is regarded as the uniformly divided block with excessive component standard deviation in the road surface imaging sub-frame. Specifically, when a uniform segment in a road surface imaging sub-frame exceeds the standard deviation of the Y component, U component, and / or V component in the YUV space, the uniform segment is designated as a uniform segment with excessive component standard deviation in the road surface imaging sub-frame. This includes: obtaining the Y component values, U component values, and V component values ​​corresponding to each constituent pixel of the uniform segment; and determining that the Y component standard deviation, U component value, and V component value of the uniform segment exceeds the standard deviation threshold when the standard deviation of each Y component value, U component value, and V component value in the YUV space exceeds the standard deviation threshold.

4. The dashcam data security storage and traceability system integrating blockchain technology as described in claim 3, characterized in that, The system also includes: The mode switching device, connected to the intelligent analysis device, is used to instruct the vehicle to enter a cautious operation mode when the accident occurrence indicator of a vehicle turning accident within the current time interval obtained by the intelligent analysis indicates that a vehicle turning accident will occur within the current time interval. The mode switching device is also used to instruct the vehicle to exit the cautious operation mode when the accident occurrence indicator of a vehicle turning accident within the current time interval obtained by intelligent analysis indicates that no vehicle turning accident will occur within the current time interval.

5. A dashcam data security storage and traceability system integrating blockchain technology as described in claim 3, characterized in that, The system also includes: A multi-layer learning device, connected to an intelligent analysis device, is used to perform multiple learning actions on a feedforward neural network to obtain a feedforward neural network after performing multiple learning actions, and outputs the feedforward neural network after performing multiple learning actions as an AI accident analysis model. The process of performing multiple learning actions on the feedforward neural network to obtain a feedforward neural network after performing multiple learning actions, and using the feedforward neural network after performing multiple learning actions as the output of the AI ​​accident analysis model, includes: using the various model parameters of the AI ​​accident analysis model to complete the model representation of the AI ​​accident analysis model.

6. A dashcam data security storage and traceability system integrating blockchain technology as described in claim 3, characterized in that, The system also includes: The real-time display device, connected to the intelligent analysis device, is used to receive accident occurrence indicators of vehicle turning accidents within the current time interval and to perform real-time display operations on the accident occurrence indicators of vehicle turning accidents within the current time interval.

7. A dashcam data security storage and traceability system integrating blockchain technology as described in claim 3, characterized in that, The system also includes: A Bluetooth transmission device, connected to the intelligent analysis device, is used to receive the accident occurrence identifier of vehicle turning accidents within the current time interval, and wirelessly transmit the accident occurrence identifier of vehicle turning accidents within the current time interval to the vehicle driver's Bluetooth headset via a Bluetooth transmission link.

8. A dashcam data security storage and traceability system integrating blockchain technology as described in any one of claims 3-7, characterized in that: The AI ​​accident analysis model uses the dashcam's resolution, set frame rate, duration of time interval, number of frames of past driving footage corresponding to the current moment, multiple first calculation values ​​and multiple second calculation values ​​corresponding to the multiple frames of past driving footage corresponding to the current moment to intelligently analyze the accident occurrence indicators of vehicle turning accidents within the current time interval. The accident occurrence indicators are: the current time interval starts from the current moment, and different values ​​indicate whether a vehicle turning accident will occur within the current time interval. The process of obtaining the Y component values, U component values, and V component values ​​corresponding to each constituent pixel of a uniform segmentation block, and determining that the Y component standard deviation, U component value, and V component value of a uniform segmentation block exceeds the limit when the standard deviation of each Y component value, U component value, and V component value is greater than a preset standard deviation threshold, includes: the Y component value, U component value, and V component value of each constituent pixel of each uniform segmentation block are within the range of 0-255 in the YUV space. The process of uniformly dividing the road surface image sub-image in each frame of past driving scene into uniformly divided blocks of the road surface image sub-image in that frame, and calculating the number of uniformly divided blocks in the road surface image sub-image in that frame whose component standard deviation exceeds the limit as the first calculated value corresponding to the past driving scene in that frame, also includes: performing a road surface recognition operation on each frame of past driving scene to obtain the road surface image sub-image in each frame of past driving scene. Specifically, performing road recognition operations on each frame of past driving footage to obtain a road image sub-frame in each frame of past driving footage includes: identifying road component pixels in each frame of past driving footage based on the color imaging features corresponding to the road surface, and fitting each road component pixel in the frame of past driving footage to obtain a road image sub-frame in the frame of past driving footage.

9. A dashcam data security storage and traceability system integrating blockchain technology as described in any one of claims 3-7, characterized in that: Each frame of driving footage recorded by the dashcam during vehicle driving is encrypted and stored using blockchain. The dashcam uses a set frame rate and allocates blockchain storage addresses in a distributed ledger storage mode for each frame of driving footage to perform blockchain encryption and storage. A consensus mechanism is used to perform blockchain encryption and storage. Among them, each frame of driving footage recorded by the dashcam during vehicle driving is encrypted and stored using blockchain. The dashcam also uses a set frame rate and the timestamps of each frame of driving footage recorded by the dashcam during vehicle driving are evenly distributed on the timeline. The process involves simultaneously inputting the dashcam's resolution, set frame rate, duration of the time interval, number of frames of past driving footage corresponding to the current moment, multiple first calculation values ​​and multiple second calculation values ​​corresponding to the multiple frames of past driving footage corresponding to the current moment into the AI ​​accident analysis model, and running the AI ​​accident analysis model to obtain the accident occurrence identifier of the vehicle turning accident within the current time interval output by the AI ​​accident analysis model. The process involves simultaneously inputting the dashcam's resolution, set frame rate, duration of the time interval, number of frames in the current time frame corresponding to the multiple past driving images, multiple first-calculated values ​​corresponding to the multiple past driving images corresponding to the current time frame, and multiple second-calculated values ​​into the AI ​​accident analysis model. The AI ​​accident analysis model is then run to obtain the accident occurrence identifier of the vehicle turning accident within the current time interval, which includes: the accident occurrence identifier of the vehicle turning accident within the current time interval, the dashcam's resolution, set frame rate, duration of the time interval, number of frames in the current time frame corresponding to the multiple past driving images, and multiple first-calculated values ​​corresponding to the multiple past driving images corresponding to the current time frame, all of which are numerical representations after numerical normalization. The process involves simultaneously inputting the dashcam's resolution, set frame rate, duration of the time interval, number of frames from past driving footage at the current moment, multiple first-valued data points corresponding to the past driving footage at the current moment, and multiple second-valued data points into the AI ​​accident analysis model. The AI ​​accident analysis model is then run to obtain the accident identification of a vehicle turning accident within the current time interval output by the AI ​​accident analysis model. The dashcam's resolution is defined as its vertical resolution and horizontal resolution.

10. A dashcam data security storage and traceability system integrating blockchain technology, the system comprising a memory and multiple processors, the memory storing a computer program, characterized in that, The computer program is configured to be executed by the plurality of processors to complete the following steps: Every frame of driving footage recorded by the dashcam during vehicle operation is encrypted and stored using blockchain technology, and the dashcam uses a set frame rate. The driving footage from multiple frames prior to the current moment is retrieved to serve as the corresponding multiple frames of past driving footage at the current moment. The road surface image sub-image in each frame of past driving scene is uniformly divided into equal areas to obtain uniformly divided blocks of the road surface image sub-image in that frame. The number of uniformly divided blocks in the road surface image sub-image that exceeds the standard deviation of the components is calculated as the first calculated value corresponding to the past driving scene in that frame. The number of curves with curvature greater than or equal to a preset curvature value within the road surface image sub-frame in each frame of driving image is calculated as the second calculated value corresponding to each frame of driving image. The AI ​​accident analysis model uses the dashcam's resolution, set frame rate, duration of time interval, number of frames of past driving footage corresponding to the current moment, multiple first calculation values ​​and multiple second calculation values ​​corresponding to the multiple frames of past driving footage corresponding to the current moment to intelligently analyze the accident occurrence identifier of vehicle turning accidents within the current time interval.

Images