High-definition double-recording driving navigation operation optimization method and system

Abstract

The invention relates to the technical field of navigation optimization, in particular to a high-definition double-recording driving navigation operation optimization method and system, which can enhance the practicability and reliability of a navigation system and provide more comprehensive, accurate and timely navigation service for a driver. The method comprises the following steps: acquiring historical driving experience information of a vehicle driver, and setting a navigation optimization frequency based on the historical driving experience information; based on the navigation optimization frequency, collecting real-time lane video stream information of a lane where a vehicle is located and a lane in the same direction through a vehicle-mounted high-definition double-recording camera; for each lane, performing decision feature extraction on the real-time lane video stream information to obtain a lane real-time condition portrait; inputting the lane real-time condition portrait into a pre-trained lane condition evaluation model to obtain a lane real-time condition feasible index; and calculating the distance between the lane and the lane where the vehicle is located to obtain the lane span.

Description

Technical Field

[0001] The present invention relates to the technical field of navigation optimization, and in particular to a high-definition dual-recording driving navigation operation optimization method and system. Background Art

[0002] In the modern transportation system, with the rapid increase in the number of vehicles and the increasingly complex road environment, drivers face many challenges during driving, such as unfamiliar routes, road congestion, sudden accidents, etc.; therefore, driving navigation systems have become an indispensable part of modern driving.

[0003] Existing driving navigation methods mainly rely on map data and GPS positioning technology to provide route planning and navigation services for drivers. However, although this navigation method based on static data and simple location information can provide basic route planning and navigation functions, it cannot reflect the current traffic conditions in real time, especially on multi-lane roads, where drivers often need to judge the optimal lane by themselves, which can easily lead to misjudgment. Summary of the invention

[0004] To solve the above technical problems, the present invention provides a high-definition dual-recording driving navigation operation optimization method and system that can enhance the practicality and reliability of the navigation system and provide drivers with more comprehensive, accurate and timely navigation services.

[0005] In a first aspect, the present invention provides a method for optimizing high-definition dual-recording driving navigation operation, the method comprising:

[0006] Acquire historical driving experience information of the vehicle driver, and set the navigation optimization frequency based on the historical driving experience information;

[0007] Based on the navigation optimization frequency, the vehicle's high-definition dual-recording camera collects real-time lane video stream information of the vehicle's lane and the same-direction lane;

[0008] For each lane, extract decision features from the real-time lane video stream information to obtain a real-time lane status portrait;

[0009] Inputting the lane real-time condition portrait into a pre-trained lane condition evaluation model to obtain a lane real-time condition ease of travel index;

[0010] Calculate the distance between the lane and the lane where the vehicle is located to obtain the lane span, where the lane span represents the number of lane changes required for the vehicle to change from the lane where the vehicle is located to the lane;

[0011] Combined with the lane span, a comprehensive analysis is conducted on the lane real-time condition ease index to obtain the driving navigation characteristic index of the corresponding lane;

[0012] From multiple lanes, the lane with the largest driving navigation feature index is extracted as the vehicle's real-time optimal driving lane and displayed to the driver.

[0013] Furthermore, the real-time lane condition portrait includes quantitative characteristic values ​​of road conditions, quantitative characteristic values ​​of accident conditions, vehicle density, non-motor vehicle density and pedestrian density.

[0014] Furthermore, the mathematical calculation formula of the lane condition evaluation model is:

[0015]

[0016] Among them, E represents the lane real-time condition easy-to-drive index, w i represents the weight coefficient of the i-th feature, C i represents the quantitative feature value of the i-th feature, and n represents the total number of features.

[0017] Furthermore, the method for constructing the lane condition evaluation model includes:

[0018] Collect lane video stream data;

[0019] Clean, denoise and label the collected data;

[0020] Selecting a deep learning model as the infrastructure of the lane condition evaluation model, wherein the deep learning model includes a decision tree, a random forest, a neural network, a convolutional neural network, and a recurrent neural network;

[0021] Divide the preprocessed data set into a training set and a test set, and use the training set data to train the selected model;

[0022] Use the test set data to evaluate the trained model and verify its generalization ability and prediction accuracy; adjust and optimize the model based on the evaluation results;

[0023] Deploy the trained lane condition evaluation model into the vehicle navigation system.

[0024] Furthermore, the calculation formula of the driving navigation characteristic index is:

[0025] I i =α·E i -β·D i

[0026] Among them, E i Indicates the lane real-time condition ease index, D i represents the lane span, I i represents the driving navigation characteristic index, α represents the weight of the lane easy-to-drive index, and β represents the weight of the lane span; α·E irepresents the positive contribution of the lane ease index to the characteristic index, β·D i Indicates the negative impact of lane span on the characteristic index.

[0027] Furthermore, the method for constructing the real-time lane status portrait includes:

[0028] Preprocess the received real-time lane video stream, including removing image noise and enhancing contrast;

[0029] Perform image recognition on the preprocessed lane video stream data, identify lane boundaries, and separate the lane from the background;

[0030] Number and mark the detected lanes;

[0031] Analyze the image of the lane area and extract the feature values ​​reflecting the road quality;

[0032] Detect whether there are signs of an accident in the lane and quantify its impact;

[0033] Count the number and distribution of vehicles in the lane and calculate vehicle density;

[0034] Identify non-motor vehicles and pedestrians near the lane and calculate their density;

[0035] The extracted decision features are combined to construct a real-time lane condition profile.

[0036] Furthermore, the method for obtaining the lane span includes:

[0037] The vehicle's current lane sign and the target lane sign are obtained through the vehicle's onboard GPS positioning system combined with high-definition dual-recording cameras;

[0038] Obtain the standard lane width, calculate the number of lanes between the vehicle's current lane and the target lane, and multiply it by the standard lane width to obtain the accurate lane change distance;

[0039] Based on the lane change distance, the number of lane changes required for the vehicle to change from the current lane to the target lane is evaluated to obtain the lane span.

[0040] On the other hand, the present application also provides a high-definition dual-recording driving navigation operation optimization system, the system comprising:

[0041] A driving experience analysis module, which obtains the historical driving experience information of the vehicle driver and sets the navigation optimization frequency based on the historical driving experience information;

[0042] The real-time data acquisition module collects real-time lane video stream information of the vehicle's lane and the same-direction lane through the on-board high-definition dual-recording camera based on the navigation optimization frequency;

[0043] A decision feature extraction module extracts decision features from real-time lane video stream information for each lane to obtain a real-time lane status portrait; the real-time lane status portrait includes quantitative feature values ​​of road conditions, quantitative feature values ​​of accident conditions, vehicle density, non-motor vehicle density, and pedestrian density;

[0044] A lane condition evaluation module, inputting the lane real-time condition image into a pre-trained lane condition evaluation model to obtain a lane real-time condition ease index;

[0045] A lane span calculation module calculates the distance between the lane and the lane where the vehicle is located to obtain the lane span, where the lane span represents the number of lane changes required for the vehicle to change from the lane where the vehicle is located to the lane;

[0046] The comprehensive analysis module comprehensively analyzes the lane's real-time condition ease of travel index in combination with the lane span to obtain the driving navigation characteristic index of the corresponding lane;

[0047] The optimal lane recommendation module extracts the lane with the largest driving navigation feature index from multiple lanes as the vehicle's real-time optimal driving lane and displays it to the driver.

[0048] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0049] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0050] Compared with the prior art, the present invention has the following beneficial effects: the method collects lane video stream information in real time through the vehicle-mounted high-definition dual-recording camera, which can dynamically reflect the current road conditions and traffic conditions; it can timely adjust the navigation strategy and provide the driver with the latest road condition information, thereby effectively responding to sudden accidents, road congestion and other dynamic changes;

[0051] By extracting decision features and constructing lane condition profiles from real-time lane video stream information, the system can intelligently evaluate the traffic conditions of each lane. Combined with the pre-trained lane condition evaluation model, the system can calculate the lane real-time condition ease of travel index, providing drivers with a scientific basis for decision-making.

[0052] When recommending the optimal lane, this method not only considers the lane's traffic ease index, but also calculates the lane span, that is, the number of lane changes required for the vehicle to change from the current lane to the target lane. This helps reduce unnecessary lane changes, improve driving efficiency, and reduce safety hazards caused by frequent lane changes.

[0053] By obtaining the historical driving experience information of the vehicle driver and setting the navigation optimization frequency accordingly, the method can make personalized adjustments according to the driving habits and preferences of different drivers; making the navigation system closer to the actual needs of the driver and improving the satisfaction of the navigation experience;

[0054] By reflecting traffic conditions in real time and recommending the best lane, it helps drivers predict and avoid potential dangers in advance, which can not only reduce the psychological pressure and fatigue of drivers, but also significantly improve driving safety and reduce the occurrence of traffic accidents;

[0055] Compared with the traditional navigation method based on static data and simple location information, this method significantly enhances the practicality and reliability of the navigation system by introducing high-definition dual-recording cameras and intelligent decision-making algorithms; it can provide drivers with more comprehensive, accurate and timely navigation services, meeting the urgent needs of modern transportation systems for efficient, safe and convenient navigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 is a flow chart of the present invention;

[0057] Figure 2 is a flow chart of a method for constructing a lane condition evaluation model;

[0058] Figure 3 It is a structural diagram of a high-definition dual-recording driving navigation operation optimization system. DETAILED DESCRIPTION

[0059] In the description of the present application, those skilled in the art should know that the present application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, the present application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0060] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0061] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0062] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0063] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0064] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0065] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0066] The present application is described below in conjunction with the drawings in the present application.

[0067] Embodiment 1: Figure 1 to Figure 2 As shown, a high-definition dual-recording driving navigation operation optimization method of the present invention specifically includes the following steps:

[0068] S1. Obtaining historical driving experience information of the vehicle driver, and setting a navigation optimization frequency based on the historical driving experience information;

[0069] The method for obtaining the historical driving experience information of the vehicle driver includes:

[0070] Utilize the background functions of the vehicle system or navigation software to automatically collect and record the driver's driving data without the driver's active operation;

[0071] Guiding drivers through the user interface to fill out questionnaires or set preferences and manually input information about their driving experience;

[0072] Clean the collected raw data to remove noise data, outliers, etc. to ensure the accuracy and reliability of the data;

[0073] Extract features that can reflect the driver's driving experience from the cleaned data;

[0074] Based on the extracted features, a machine learning method is used to evaluate the driver's driving experience to form quantitative historical driving experience information;

[0075] The historical driving experience information includes:

[0076] Driving experience: records the length of time a driver has held a driver's license, as one of the basic indicators for evaluating driving experience;

[0077] Mileage: The accumulated driving mileage reflects the driver's total driving experience. Drivers who drive long distances are more familiar with various road conditions and driving skills.

[0078] Frequently driven routes: Recording the roads that drivers often travel on helps to understand the driver's familiarity with a specific area and his understanding of the traffic conditions in that area;

[0079] Driving behavior data: speed control reflects the driver's speed control ability; lane changing habits reflect the driver's preference and judgment in lane selection; braking and acceleration evaluate the driver's reaction speed and driving stability; following distance reflects the driver's safety awareness and driving skills;

[0080] Accident records: including the number of traffic accidents, types and liability determinations. This information reflects the driver's safe driving ability and accident prevention awareness;

[0081] Traffic violation records: Records of traffic violations such as speeding, running red lights, and illegal lane changes are important bases for evaluating the driver's driving compliance and safety awareness;

[0082] Driving preferences: Driving preferences derived from user settings or behavioral analysis, including whether you prefer expressways, whether you are willing to take a detour to avoid congestion, and your preference for lane selection.

[0083] In this step, by obtaining and analyzing the historical driving experience information of the vehicle driver, the navigation optimization frequency can be customized to provide more personalized navigation services for drivers with different driving experience; based on the comprehensive evaluation of driving behavior data, accident records and traffic violation records, the driver's potential risk behavior can be identified, and safe driving suggestions or warnings can be provided in a timely manner, thereby effectively improving driving safety; by analyzing frequently traveled routes and driving preferences, the navigation system can more accurately predict the driver's travel needs, provide more accurate route planning and real-time traffic information, help drivers avoid congested sections, and improve travel efficiency; using machine learning methods to quantify driving experience not only improves The accuracy and objectivity of the evaluation also provide a solid foundation for subsequent data analysis and decision support; this step significantly improves the convenience and satisfaction of the user experience by reducing unnecessary user input and active operations, and providing an intuitive and easy-to-use user interface to guide users to fill out questionnaires or set preferences; long-term tracking and analysis of driving behavior data helps drivers to self-evaluate and improve their driving habits, thereby gradually forming good driving habits and safety awareness; this step comprehensively evaluates the vehicle driver's historical driving experience information and sets personalized navigation optimization strategies based on this, which not only improves driving safety and efficiency, but also enhances the user experience and promotes the improvement of driving habits, with significant beneficial effects.

[0084] S2. Based on the navigation optimization frequency, the vehicle's high-definition dual-recording camera is used to collect real-time lane video stream information of the vehicle's lane and the same-direction lane;

[0085] The method for collecting real-time lane video stream information of the lane where the vehicle is located and the lane in the same direction includes:

[0086] Navigation optimization frequency, which determines the rate at which the camera captures video frames;

[0087] The video stream captured by the camera is transmitted to the on-board computing unit in real time through the in-vehicle network for processing; in order to reduce bandwidth usage, a compression algorithm can be used to compress the video data;

[0088] Preprocess the collected raw video stream to improve the accuracy of subsequent analysis;

[0089] Use image segmentation technology to identify different lane boundaries and preliminarily label different objects in each lane;

[0090] Considering the processing power limitation, not all collected data needs to be saved permanently; a buffer can be set to keep only the important data in the recent period;

[0091] For some key events, relevant video clips are selectively saved for subsequent analysis or use as evidence;

[0092] During the processing, personally identifiable information should be blurred to protect the privacy of other road users.

[0093] In this step, by adjusting the rate at which the camera captures video frames based on the navigation optimization frequency, it is possible to ensure that high-quality real-time lane video stream information is obtained when needed, providing the driver with timely and accurate navigation suggestions; the in-vehicle network is used to transmit the video stream in real time to the on-board computing unit for processing, and the compression algorithm is used to reduce bandwidth occupancy, thereby improving the efficiency of data transmission and processing; it not only reduces the demand for on-board system hardware resources, but also reduces the delay in the data transmission process, ensuring the response speed of the system; pre-processing the collected raw video stream can significantly improve the accuracy of subsequent image analysis and lane recognition; it helps to more accurately extract the real-time status portrait of the lane and provide more reliable data support for navigation optimization; using image segmentation technology to identify lane boundaries and preliminarily mark different objects in the lane are key steps in achieving real-time lane status portraits; it can automatically distinguish lanes, vehicles, pedestrians, and non-motor vehicles. Traffic elements such as cars are collected, providing a rich information basis for subsequent decision-making analysis; by setting a buffer to manage data, only important data in the most recent period is retained, and data storage is optimized under processing power constraints, which can effectively reduce the waste of system resources; at the same time, video clips of key events are selectively saved, which not only retains important evidence but also avoids redundant storage of irrelevant data; personal identity information is blurred during the processing process, reflecting the importance of privacy protection; it helps to enhance users' trust in the system and ensure that the privacy of other road users is not violated while providing navigation services; step S2 provides a solid data foundation for subsequent navigation optimization by efficiently and accurately collecting real-time lane video stream information of the vehicle's lane and its same-direction lane; at the same time, this step also focuses on data processing efficiency, privacy protection and data management optimization, further improving the overall performance of the system and user experience.

[0094] S3. For each lane, extract decision features from the real-time lane video stream information to obtain a real-time lane status portrait; the real-time lane status portrait includes quantitative characteristic values ​​of road conditions, quantitative characteristic values ​​of accident conditions, vehicle density, non-motor vehicle density, and pedestrian density;

[0095] The method for constructing the lane real-time condition portrait comprises:

[0096] Preprocess the received real-time lane video stream, including removing image noise and enhancing contrast, to improve image quality and provide clear visual input for subsequent processing;

[0097] Use image processing technology to identify lane boundaries and separate lanes from the background;

[0098] The detected lanes are numbered and labeled so that each lane can be analyzed independently later;

[0099] By analyzing the image of the lane area, feature values ​​reflecting the road surface quality are extracted;

[0100] Use image recognition technology to detect whether there are signs of accidents in the lane and quantify their impact;

[0101] Calculate vehicle density by counting the number and distribution of vehicles in the lane;

[0102] Use the object detection algorithm to identify non-motor vehicles and pedestrians near the lane and calculate their density;

[0103] The extracted decision features are combined to construct a real-time lane condition profile; this profile is a multi-dimensional data set that contains comprehensive lane condition information at a specific moment.

[0104] In this step, the real-time lane video stream is preprocessed and decision features are extracted to instantly reflect the current real-time status of the lane; including accurate assessments of road quality, accident conditions, vehicle density, non-motor vehicle density and pedestrian density, providing drivers with instant and accurate navigation information; the lane real-time status portrait is a multi-dimensional data set, which not only covers traditional traffic flow information, but also incorporates key information such as road quality, accident conditions, and density of non-motor vehicles and pedestrians; this comprehensive information integration enables the navigation system to more comprehensively evaluate the lane traffic conditions, thereby making more scientific and reasonable navigation suggestions; the intelligent feature extraction and portrait construction of step S3 provides strong data support for subsequent navigation optimization; through the analysis of the lane real-time status portrait, the system can intelligently identify the optimal driving lane and provide real-time navigation guidance to the driver, not only It improves the convenience of driving and significantly improves the safety and efficiency of road traffic. Since this step can reflect the overall condition of the lane in real time and provide drivers with accurate navigation suggestions based on these conditions, it can significantly improve the driver's user experience. During driving, drivers no longer need to worry about the troubles caused by unfamiliar routes or traffic congestion, and only need to follow the instructions of the navigation system. In addition to providing convenience to individual drivers, the real-time lane condition portrait can also provide important reference data for traffic management departments. By analyzing and mining these data, traffic management departments can more accurately grasp the changing trends of traffic conditions, thereby formulating more scientific and reasonable traffic management strategies. The beneficial effects of step S3 are not only reflected in improving the real-time and accuracy of the navigation system, but also in providing users with intelligent decision-making support, improving user experience, and promoting traffic management.

[0105] S4, inputting the lane real-time condition portrait into a pre-trained lane condition evaluation model to obtain a lane real-time condition drivability index;

[0106] The method for constructing the lane condition evaluation model includes:

[0107] Use on-board high-definition dual-recording cameras or other traffic monitoring equipment to collect a large amount of lane video stream data; at the same time, combine multi-source information such as traffic management department records, GPS positioning data, vehicle sensor data, etc. to form a comprehensive data set;

[0108] Clean, denoise and label the collected data;

[0109] According to the characteristics of the problem and the characteristics of the data, a deep learning model is selected as the basic architecture of the lane condition evaluation model, and the deep learning model includes a decision tree, a random forest, a neural network, a convolutional neural network, and a recurrent neural network;

[0110] The preprocessed data set is divided into a training set and a test set, and the selected model is trained using the training set data; during the training process, the model's performance is optimized by adjusting the model's parameters and structure, so that it can accurately predict the lane's real-time condition ease of travel index;

[0111] Use the test set data to evaluate the trained model and verify its generalization ability and prediction accuracy; adjust and optimize the model based on the evaluation results;

[0112] Deploy the trained lane condition evaluation model to the vehicle navigation system to realize the real-time lane condition evaluation function;

[0113] The mathematical calculation formula of the lane condition evaluation model is:

[0114]

[0115] Among them, E represents the lane real-time condition easy-to-drive index, w i represents the weight coefficient of the i-th feature, C i represents the quantitative feature value of the i-th feature, and n represents the total number of features.

[0116] In this step, by inputting the real-time lane condition portrait into the pre-trained lane condition evaluation model, the lane's drivability index can be calculated in real time, providing the driver with instant road condition information, significantly improving the accuracy and efficiency of driving decisions; a comprehensive data set is constructed using multi-source information such as on-board high-definition dual-recording cameras, records from traffic management departments, GPS positioning data, and vehicle sensor data; the evaluation model is able to more comprehensively consider various factors affecting lane conditions, thereby improving the accuracy and reliability of the evaluation; a deep learning model is used as the infrastructure of the lane condition evaluation model to achieve intelligent and automated lane condition evaluation; the deep learning model can automatically learn and extract features from data, reducing manual intervention and subjective judgment The model is constantly influenced by traffic congestion, which improves the objectivity and consistency of the evaluation. By training the model, adjusting parameters, optimizing performance, and evaluating the test set, the model is ensured to have good generalization ability and prediction accuracy. It can cope with changes in lane conditions at different times and locations, which improves its practicality and stability. Real-time and accurate lane condition evaluation information helps drivers plan routes in advance, avoid congestion and dangerous sections, thereby improving driving safety and comfort. At the same time, for traffic management departments, this information is also helpful to optimize traffic flow management and alleviate traffic congestion. By continuously optimizing and improving the model, the entire intelligent transportation system can be promoted to develop in a more intelligent and efficient direction, providing strong technical support for urban traffic management.

[0117] S5. Calculate the distance between the lane and the lane where the vehicle is located to obtain a lane span, where the lane span represents the number of lane changes required for the vehicle to change from the lane where the vehicle is located to the lane;

[0118] The method for obtaining the lane span includes:

[0119] The vehicle's current lane sign and the target lane sign are obtained through the vehicle's onboard GPS positioning system combined with high-definition dual-recording cameras;

[0120] Obtain the standard lane width, which is usually 3.5 meters or 3.75 meters. Calculate the number of lanes between the vehicle's current lane and the target lane and multiply it by the standard lane width to get the accurate lane change distance.

[0121] Based on the lane change distance, the number of lane changes required for the vehicle to change from the current lane to the target lane is evaluated to obtain the lane span;

[0122] The lane span is a quantitative indicator that will be output, and this indicator will serve as an important basis for comprehensive analysis of the lane's real-time condition ease of travel index and determination of the optimal driving lane in subsequent steps.

[0123] In this step, by combining the on-board GPS positioning system with the high-definition dual-recording camera, the vehicle's current lane and the target lane's identification can be obtained in real time and accurately, ensuring that the vehicle can quickly locate and calculate the lane span even in complex and changeable road environments; lane span, as a quantitative indicator, not only takes into account the straight-line distance from the current lane to the target lane of the vehicle, but more importantly, by calculating the number of required lane changes, it directly reflects the actual difficulty of lane change; this quantitative method enables the driver to more intuitively understand the complexity and risk of lane changes when accepting navigation suggestions, thereby making more reasonable driving decisions; by comprehensively considering multiple factors such as lane span and lane real-time condition ease index, the navigation system can more accurately recommend the optimal driving lane; this helps to reduce the driver's blind lane changes and misjudgments during driving, and improve driving safety and road safety. The calculation and application of lane span make the navigation system more intelligent and user-friendly. By providing drivers with clear and intuitive lane change suggestions, the anxiety and uneasiness of drivers in complex traffic environments are reduced, and the user experience and satisfaction are enhanced. The lane span calculation method in this step has high adaptability and can be applied to different types of roads and traffic environments. Whether it is a congested urban road section or a highway, the lane span can be accurately calculated by adjusting the standard lane width and considering factors such as traffic rules, providing effective navigation support for drivers. The S5 step provides an important basis for subsequent navigation decisions by accurately calculating the lane span in real time, which significantly improves the intelligence level and practicality of the driving navigation system.

[0124] S6. Combined with the lane span, a comprehensive analysis is performed on the lane real-time condition ease index to obtain the driving navigation characteristic index of the corresponding lane;

[0125] The lane real-time condition ease of travel index is calculated through a pre-trained model. The index reflects the overall driving conditions of the lane. This includes the lane's accident rate, vehicle density, road conditions, etc. Each index is a quantitative value used to represent the current traffic efficiency and safety of the lane.

[0126] Lane span refers to the minimum number of lane changes required for a vehicle to move from its current lane to its target lane; this is an important metric because frequent or multiple lane changes can increase the risk of accidents and can affect driving comfort.

[0127] According to the actual application scenarios and demand analysis, different weights are assigned to the lane span and the real-time traffic ease index; the real-time traffic ease index directly reflects the current traffic conditions of the lane; while the lane span is an auxiliary factor that considers the difficulty and potential risks of lane changes;

[0128] The calculation formula of driving navigation characteristic index is:

[0129] I i =α·E i -β·D i Among them, E i Indicates the lane real-time condition ease index, D i represents the lane span, I i represents the driving navigation characteristic index, α represents the weight of the lane easy-to-drive index, and β represents the weight of the lane span; α·E i represents the positive contribution of the lane ease index to the characteristic index, β·D i Indicates the negative impact of lane span on the characteristic index.

[0130] In this step, by introducing two key parameters, the lane real-time condition ease index and lane span, and combining their respective weights for comprehensive analysis, navigation decisions are no longer solely dependent on static map data and simple location information, but can dynamically evaluate the traffic efficiency and safety of each lane in real time; this intelligent decision-making method is closer to actual driving scenarios and helps provide drivers with more accurate navigation suggestions; the lane real-time condition ease index directly reflects the traffic conditions of the lane, including factors such as accident rate, vehicle density, and road conditions, while the lane span takes into account the difficulty and potential risks of lane changes; by comprehensively considering these two factors, drivers can avoid choosing lanes that seem to be unobstructed but are actually accident-prone or require frequent lane changes, thereby reducing the probability of accidents and improving safety during driving; frequent or multiple lane changes not only increase the risk of accidents, but also affect the driver's comfort; by Introducing lane span as a negative influencing factor makes navigation decisions more inclined to choose lanes that require fewer lane changes; it helps to reduce unnecessary operations of the driver during driving and improve driving fluency and comfort; traditional navigation methods can often only provide basic route planning and navigation functions, and cannot reflect the current traffic conditions in real time; this step comprehensively analyzes the lane real-time condition ease index and lane span, so that the navigation system can more accurately evaluate the actual traffic capacity of each lane and provide drivers with more practical and reliable navigation suggestions; this helps to improve the overall practicality and market competitiveness of the navigation system; step S6 comprehensively analyzes the lane real-time condition ease index and lane span, calculates the driving navigation characteristic index, and provides drivers with more intelligent, safe, comfortable and practical navigation services, which not only improves the performance of the navigation system, but also makes positive contributions to the intelligent development of modern transportation systems.

[0131] S7, extracting a lane with the largest driving navigation characteristic index from the multiple lanes as the real-time optimal driving lane for the vehicle, and displaying it to the driver;

[0132] Summarize the driving navigation characteristic indexes to form a data set including the driving navigation characteristic indexes of all lanes in the same direction;

[0133] Compare the driving navigation feature indexes in the data set; find the lane with the largest feature index through comparison; this lane is considered to be the best driving option under the current situation after comprehensively considering the real-time traffic conditions of the lane and the difficulty of lane change;

[0134] After determining the lane with the maximum characteristic index, a feasibility verification is performed to ensure the rationality of the selected lane;

[0135] If the verification process finds that the selected lane has non-negligible negative factors, the system re-evaluates other lanes and selects the suboptimal lane as a recommendation;

[0136] Once the real-time optimal driving lane is determined, the recommended information is displayed to the driver through the on-board display and voice prompts;

[0137] The information displayed includes the number of the optimal lane, direction guidance, lane change suggestions and precautions.

[0138] In this step, by calculating the driving navigation characteristic index of each lane in real time and selecting the lane with the largest characteristic index as the recommendation, it can ensure that the information provided by the navigation system is highly matched with the current traffic conditions; the improvement of this real-time and accuracy helps drivers make more informed decisions in complex traffic environments and reduce driving risks caused by misjudgment or information lag; selecting the real-time optimal driving lane not only considers the lane's traffic efficiency, but also takes into account the difficulty of changing lanes, thereby reducing unnecessary lane changes and potential driving conflicts; it helps to improve driving smoothness and comfort and optimize the driving experience; feasibility verification is performed before determining the optimal lane to ensure that there are no significant negative factors in the selected lane, thereby further enhancing driving safety; at the same time, by providing clear direction guidance, lane change suggestions and precautions, it helps drivers to be more The system can complete the lane changing and driving process more safely; by introducing advanced technologies such as real-time lane video stream information, decision feature extraction, and lane condition evaluation model, it realizes intelligent analysis and judgment of traffic conditions; this intelligent navigation method not only improves the performance of the navigation system, but also lays the foundation for the development of future intelligent transportation systems; when a large number of drivers adopt this navigation suggestion based on real-time information, it will help promote the uniform distribution of traffic flow, reduce excessive congestion in certain lanes, and thus improve the operating efficiency of the entire transportation system; the S7 step extracts the lane with the largest driving navigation feature index as the real-time optimal driving lane and displays relevant information to the driver, which not only improves the real-time and accuracy of navigation, optimizes the driving experience, enhances driving safety, but also improves the intelligence level of the navigation system, and is expected to have a positive impact on traffic flow optimization.

[0139] Embodiment 2: Figure 3 As shown, a high-definition dual-recording driving navigation operation optimization system of the present invention specifically includes the following modules;

[0140] A driving experience analysis module, which obtains the historical driving experience information of the vehicle driver and sets the navigation optimization frequency based on the historical driving experience information;

[0141] The real-time data acquisition module collects real-time lane video stream information of the vehicle's lane and the same-direction lane through the on-board high-definition dual-recording camera based on the navigation optimization frequency;

[0142] A decision feature extraction module extracts decision features from real-time lane video stream information for each lane to obtain a real-time lane status portrait; the real-time lane status portrait includes quantitative feature values ​​of road conditions, quantitative feature values ​​of accident conditions, vehicle density, non-motor vehicle density, and pedestrian density;

[0143] A lane condition evaluation module, inputting the lane real-time condition image into a pre-trained lane condition evaluation model to obtain a lane real-time condition ease index;

[0144] A lane span calculation module calculates the distance between the lane and the lane where the vehicle is located to obtain the lane span, where the lane span represents the number of lane changes required for the vehicle to change from the lane where the vehicle is located to the lane;

[0145] The comprehensive analysis module comprehensively analyzes the lane's real-time condition ease of travel index in combination with the lane span to obtain the driving navigation characteristic index of the corresponding lane;

[0146] The optimal lane recommendation module extracts the lane with the largest driving navigation feature index from multiple lanes as the vehicle's real-time optimal driving lane and displays it to the driver.

[0147] The system uses a real-time data acquisition module and a high-definition dual-recording camera to obtain real-time video stream information of the vehicle's lane and the same-direction lane. This enables the navigation system to dynamically reflect the current traffic conditions, thereby providing more accurate and timely navigation information.

[0148] The driving experience analysis module sets the navigation optimization frequency based on the driver's historical driving experience, allowing the system to make intelligent adjustments based on the habits and preferences of different drivers, improving the system's adaptability and user satisfaction;

[0149] The system converts complex real-time video information into a quantitative real-time lane condition portrait through the decision feature extraction module and the lane condition evaluation module, and calculates the easy-to-drive index using the lane condition evaluation model. This comprehensive decision-making capability enables the system to more accurately evaluate the traffic conditions of each lane and provide drivers with more reasonable lane selection suggestions.

[0150] The lane span calculation module takes into account the distance between lanes and the number of lane changes. When recommending the optimal lane, it not only considers the traffic conditions of the lanes, but also takes into account the convenience and safety of lane changes, which helps to reduce unnecessary lane changes and improve driving efficiency.

[0151] By reflecting traffic conditions in real time and recommending the best lane, the system can help drivers predict and avoid potential dangers in advance, thereby reducing driving risks and improving driving safety. The system shows the driver the best driving lane in real time, allowing the driver to make decisions more easily and confidently during driving, enhancing driving comfort and convenience.

[0152] In summary, the high-definition dual-recording driving navigation operation optimization system has significantly enhanced the practicality and reliability of the navigation system by introducing high-definition dual-recording cameras and intelligent decision-making algorithms; it can provide drivers with more comprehensive, accurate and timely navigation services, meeting the urgent needs of modern transportation systems for efficient, safe and convenient navigation.

[0153] The various variations and specific embodiments of the high-definition dual-recording driving navigation operation optimization method in the aforementioned embodiment 1 are also applicable to the high-definition dual-recording driving navigation operation optimization system of this embodiment. Through the aforementioned detailed description of the high-definition dual-recording driving navigation operation optimization method, those skilled in the art can clearly know the implementation method of the high-definition dual-recording driving navigation operation optimization system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0154] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0155] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A high-definition dual-recording driving navigation operation optimization method, characterized in that: The method comprises: Acquire historical driving experience information of the vehicle driver, and set the navigation optimization frequency based on the historical driving experience information; Based on the navigation optimization frequency, the vehicle's high-definition dual-recording camera collects real-time lane video stream information of the vehicle's lane and the same-direction lane; For each lane, extract decision features from the real-time lane video stream information to obtain a real-time lane status portrait; Inputting the lane real-time condition portrait into a pre-trained lane condition evaluation model to obtain a lane real-time condition ease of travel index; Calculate the distance between the lane and the lane where the vehicle is located to obtain the lane span, where the lane span represents the number of lane changes required for the vehicle to change from the lane where the vehicle is located to the lane; Combined with the lane span, a comprehensive analysis is conducted on the lane real-time condition ease index to obtain the driving navigation characteristic index of the corresponding lane; From multiple lanes, the lane with the largest driving navigation feature index is extracted as the vehicle's real-time optimal driving lane and displayed to the driver.

2. A high-definition dual-recording driving navigation operation optimization method as claimed in claim 1, characterized in that: The lane real-time condition portrait includes quantitative characteristic values ​​of road conditions, quantitative characteristic values ​​of accident conditions, vehicle density, non-motor vehicle density and pedestrian density.

3. A high-definition dual-recording driving navigation operation optimization method as claimed in claim 1, characterized in that: The mathematical calculation formula of the lane condition evaluation model is: Among them, E represents the lane real-time condition easy-to-drive index, w i represents the weight coefficient of the i-th feature, C i represents the quantitative feature value of the i-th feature, and n represents the total number of features.

4. A high-definition dual-recording driving navigation operation optimization method as claimed in claim 3, characterized in that: The method for constructing the lane condition evaluation model includes: Collect lane video stream data; Clean, denoise and label the collected data; Selecting a deep learning model as the infrastructure of the lane condition evaluation model, wherein the deep learning model includes a decision tree, a random forest, a neural network, a convolutional neural network, and a recurrent neural network; Divide the preprocessed data set into a training set and a test set, and use the training set data to train the selected model; Use the test set data to evaluate the trained model and verify its generalization ability and prediction accuracy; adjust and optimize the model based on the evaluation results; Deploy the trained lane condition evaluation model into the vehicle navigation system.

5. The high-definition dual-recording driving navigation operation optimization method as claimed in claim 1, characterized in that: The calculation formula of driving navigation characteristic index is: αEi-β·D Among them, Ei represents the lane real-time condition easy-to-drive index, Di represents the lane span, Ii represents the driving navigation characteristic index, α represents the weight of the lane easy-to-drive index, and β represents the weight of the lane span; α·Ei represents the positive contribution of the lane easy-to-drive index to the characteristic index, and β·Di represents the negative impact of the lane span on the characteristic index.

6. A high-definition dual-recording driving navigation operation optimization method as claimed in claim 1, characterized in that: The method for constructing the lane real-time condition portrait comprises: Preprocess the received real-time lane video stream, including removing image noise and enhancing contrast; Perform image recognition on the preprocessed lane video stream data, identify lane boundaries, and separate the lane from the background; Number and mark the detected lanes; Analyze the image of the lane area and extract the feature values ​​reflecting the road quality; Detect whether there are signs of an accident in the lane and quantify its impact; Count the number and distribution of vehicles in the lane and calculate vehicle density; Identify non-motor vehicles and pedestrians near the lane and calculate their density; The extracted decision features are combined to construct a real-time lane condition profile.

7. A high-definition dual-recording driving navigation operation optimization method as claimed in claim 1, characterized in that: The method for obtaining the lane span includes: The vehicle's current lane sign and the target lane sign are obtained through the vehicle's onboard GPS positioning system combined with high-definition dual-recording cameras; Obtain the standard lane width, calculate the number of lanes between the vehicle's current lane and the target lane, and multiply it by the standard lane width to obtain the accurate lane change distance; Based on the lane change distance, the number of lane changes required for the vehicle to change from the current lane to the target lane is evaluated to obtain the lane span.

8. A high-definition dual-recording driving navigation operation optimization system, characterized in that: The system comprises: A driving experience analysis module, which obtains the historical driving experience information of the vehicle driver and sets the navigation optimization frequency based on the historical driving experience information; The real-time data acquisition module collects real-time lane video stream information of the vehicle's lane and the same-direction lane through the on-board high-definition dual-recording camera based on the navigation optimization frequency; A decision feature extraction module extracts decision features from real-time lane video stream information for each lane to obtain a real-time lane status portrait; the real-time lane status portrait includes quantitative feature values ​​of road conditions, quantitative feature values ​​of accident conditions, vehicle density, non-motor vehicle density, and pedestrian density; A lane condition evaluation module, inputting the lane real-time condition image into a pre-trained lane condition evaluation model to obtain a lane real-time condition ease index; A lane span calculation module calculates the distance between the lane and the lane where the vehicle is located to obtain the lane span, where the lane span represents the number of lane changes required for the vehicle to change from the lane where the vehicle is located to the lane; The comprehensive analysis module comprehensively analyzes the lane's real-time condition ease of travel index in combination with the lane span to obtain the driving navigation characteristic index of the corresponding lane; The optimal lane recommendation module extracts the lane with the largest driving navigation feature index from multiple lanes as the vehicle's real-time optimal driving lane and displays it to the driver.

9. An electronic device for optimizing high-definition dual-recording driving navigation operation, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and characterized in that: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 7 are implemented.

Images