Road condition data intelligent dynamic acquisition method and system based on automobile data recorder

Abstract

The invention discloses a road condition data intelligent dynamic acquisition method based on an automobile data recorder, and relates to the technical field of traffic information acquisition, and the road condition data intelligent dynamic acquisition method based on the automobile data recorder combines a plurality of steps of real-time data acquisition, data processing, integrated calculation, comparative analysis, reanalysis and signal summarization. The road condition can be comprehensively and accurately monitored and evaluated, scientific basis and data support are provided for traffic management and emergency processing, the safety and efficiency of road traffic are improved, multi-source data including image quality, road environment and vehicle driving data can be comprehensively utilized, and a real-time road condition analysis coefficient SLK can be accurately calculated. According to the method, the accuracy and the real-time performance of the road condition are improved, the weight can be adjusted according to the user requirement so as to adapt to different traffic management and driving scenes, the intelligent level of traffic management can be effectively improved, and the precision of road condition analysis can be optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic information collection, and in particular to a method and system for intelligently and dynamically collecting road condition data based on a driving recorder. Background Art

[0002] As urban traffic congestion becomes increasingly prominent, traditional traffic monitoring systems often rely on fixed-point data collection, lacking real-time and comprehensiveness, and are unable to effectively respond to the dynamic changes and traffic congestion of urban roads. Therefore, using a driving recorder as a mobile data collection device, combined with advanced data processing and analysis technology, can obtain key data such as the position, speed, acceleration, etc. of the vehicle in real time, so as to accurately identify and analyze the real-time traffic status of the road and its changing trends.

[0003] However, the challenges faced by current technologies include how to effectively process large-scale real-time data streams, ensure the accuracy and practicality of data, and how to effectively collect and process data while protecting user privacy. In addition, the transmission and storage of these large amounts of data are also important issues that the current system needs to solve. When processing traffic data in complex urban road environments, existing technologies may have problems such as data delays, lack of accuracy, and slow system response speeds, which limit the comprehensive application and effectiveness of the system in real-time traffic management and driving safety. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides a method for intelligently and dynamically collecting road condition data based on a driving recorder, which solves the problems mentioned in the above background technology.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for intelligent dynamic collection of road condition data based on a driving recorder, characterized in that: the specific steps are as follows;

[0008] S1, data collection, real-time analysis of images captured by the driving recorder to obtain multi-source data;

[0009] S2, data processing, pre-processing the collected multi-source data and reorganizing them into a first data set, a second data set and a third data set;

[0010] S3, data calculation, integrating and calculating the first data set, the second data set and the third data set, so as to generate a real-time traffic analysis coefficient SLK;

[0011] S4, preliminary comparative analysis, comparing the calculated real-time road condition analysis coefficient SLK with a preset first threshold value, thereby generating a first comparative result, and judging whether the current road condition is abnormal according to the first comparative result;

[0012] S5, re-analyze, when the first comparison result determines that the current road condition is abnormal, integrate and calculate the real-time road condition analysis coefficient YFX and the preset first threshold value Y, so as to generate the abnormal analysis coefficient YFX, and compare the abnormal analysis coefficient FX with the preset second threshold value R, so as to generate the second comparison result, and determine the actual abnormal situation of the current road condition according to the second comparison result;

[0013] S6. Signal aggregation: uploading the second comparison result to the cloud platform for aggregation to generate the road condition of the road section.

[0014] Preferably, in step S1, the multi-source data includes image quality data, road environment data and vehicle operation data;

[0015] Among them, the image quality data includes resolution, frame rate, brightness and motion blur value;

[0016] Road environment data includes visibility and light intensity;

[0017] The vehicle driving data includes vehicle speed, vehicle acceleration and vehicle interval.

[0018] Preferably, in step S2, data processing includes data preprocessing and data integration;

[0019] The data preprocessing is to remove noise, fill and repair, and make the collected multi-source data dimensionless;

[0020] The data integration is used to reorganize the preprocessed data according to timestamps, thereby generating a first data set, a second data set, and a third data set.

[0021] Preferably, the first data set includes resolution, frame rate, brightness and motion blur value;

[0022] Among them, the resolutions are recorded as FB1, FB2, FB3, ... FBn according to the timestamp;

[0023] The frames are recorded as ZS1, ZS2, ZS3, ... ZSn according to the timestamp;

[0024] The brightness is recorded as LD1, LD2, LD3, ... LDn according to the timestamp;

[0025] The dynamic fuzzy values ​​are recorded as DT1, DT2, DT3, ... DTn according to the timestamps;

[0026] The second data set includes visibility and light intensity;

[0027] The visibility is recorded as KJD1, KJD2, KJD3, ... KJDn according to the timestamp;

[0028] The light intensity is recorded as GZD1, GZDE2, GZD3, ... GZDn according to the timestamp;

[0029] The third data set includes vehicle speed, vehicle acceleration, and vehicle spacing;

[0030] The vehicle speeds are recorded as CLS1, CLS2, CLS3, ... CLSn according to the timestamps;

[0031] The vehicle accelerations are recorded as JSD1, JSD2, JSD3, ... JSDn according to the timestamps;

[0032] The vehicle intervals are recorded as JG1, JG2, JG3, ... JGn according to the time stamps.

[0033] Preferably, in step S3, the real-time traffic analysis coefficient SLK is calculated and obtained by the following formula:

[0034] ;

[0035] Wherein: a1 and a2 are weight coefficients, the values ​​of a1 and a2 are adjusted and set by the user, S1 and S2 are the first stage value and the second stage value, wherein the first stage value S1 and the second stage value S2 are respectively obtained by integrating the first data set, the second data set and the third data set.

[0036] Preferably, the first stage value S1 and the second stage value S2 are calculated and obtained by the following formulas respectively:

[0037] ;

[0038] ;

[0039] Where: FBn-2, LDn-2, DTn-2, CLSn-2, JSDn-2 and JGn-2 are the resolution, brightness, dynamic blur value, vehicle speed, vehicle acceleration and vehicle interval at the n-2 timestamp respectively;

[0040] FBn-1, LDn-1, DTn-1, CLSn-1, JSDn-1 and JGn-1 are the resolution, brightness, motion blur value, vehicle speed, vehicle acceleration and vehicle interval at the n-1 timestamp respectively;

[0041] FBn, LDn, DTn, CLSn, JSDn and JGn are the resolution, brightness, motion blur value, vehicle speed, vehicle acceleration and vehicle interval at timestamp n, respectively;

[0042] k is a modified intervention value, which is obtained by integrating the first data set and the second data set.

[0043] Preferably, the modified intervention value k is calculated and obtained by the following formula:

[0044] ;

[0045] Where: KJDn, GZDn and ZSn are visibility, light intensity and frame number at timestamp n, respectively, i is the window value, b1, b2 and b3 are weight values, and the values ​​of b1, b2, b3 and i are adjusted and set by the user.

[0046] Preferably, in step S4, the first comparison result is:

[0047] when When , it means that the current road condition is normal;

[0048] when When Y is displayed, it means that the current road condition is abnormal.

[0049] Preferably, in step S5, the second comparison result is as follows:

[0050] when When , it means the current traffic condition is in the first level of congestion;

[0051] when When , it means that the current traffic condition is in the second level of congestion;

[0052] when When , it means that the current traffic condition is in the first level sparse state;

[0053] when , it means that the current traffic condition is in the second-level sparse state.

[0054] The present application also includes an intelligent dynamic collection system for road condition data based on a driving recorder, the system including a data collection unit, a data processing unit, a data calculation unit, a first analysis unit, a second analysis unit and a signal aggregation unit;

[0055] The data acquisition unit analyzes the images captured by the driving recorder in real time and extracts multi-source data;

[0056] A data processing unit performs preprocessing on the collected multi-source data, including denoising, repairing and standardization, to generate the first, second and third data sets;

[0057] A data calculation unit, integrating the first, second and third data sets, and calculating a real-time traffic analysis coefficient SLK;

[0058] A first analysis unit compares the calculated SLK with a preset first threshold value, generates a first comparison result, and determines whether the current road condition is abnormal;

[0059] The second analysis unit, when detecting an abnormal road condition, further integrates and calculates SLK with a preset threshold value to generate an abnormal analysis coefficient YFX, and compares it with a preset second threshold value R to generate a second comparison result;

[0060] The signal aggregation unit uploads the second comparison result to the cloud platform for aggregation and analysis to generate a comprehensive road condition of the road section.

[0061] (III) Beneficial effects

[0062] The present invention provides a method for intelligent dynamic collection of road condition data based on a driving recorder, which has the following beneficial effects:

[0063] 1. This intelligent dynamic collection method of road condition data based on the driving recorder can comprehensively and accurately monitor and evaluate road conditions through the combination of multiple steps of real-time data collection, data processing, integrated calculation, comparative analysis, reanalysis and signal aggregation, provide scientific basis and data support for traffic management and emergency response, and improve the safety and efficiency of road traffic.

[0064] 2. The intelligent dynamic acquisition method of road condition data based on the driving recorder can comprehensively utilize multi-source data, including image quality, road environment and vehicle driving data, to accurately calculate the real-time road condition analysis coefficient SLK. This method not only improves the accuracy and real-time performance of road conditions, but also adjusts the weights according to user needs to adapt to different traffic management and driving scenarios. Therefore, this method can effectively improve the intelligent level of traffic management, optimize the accuracy of road condition analysis, and provide more reliable decision support for drivers and traffic management departments, thereby improving road safety and traffic flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a step diagram of the method of the present invention.

[0066] Figure 2 The figure is a flow chart of the system of the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] Example 1, please refer to Figure 1 , an intelligent dynamic collection method of road condition data based on a driving recorder, characterized in that: the specific steps are as follows;

[0069] S1, data collection, real-time analysis of images captured by the driving recorder to obtain multi-source data;

[0070] S2, data processing, pre-processing the collected multi-source data and reorganizing them into a first data set, a second data set and a third data set;

[0071] S3, data calculation, integrating and calculating the first data set, the second data set and the third data set, so as to generate a real-time traffic analysis coefficient SLK;

[0072] S4, preliminary comparative analysis, comparing the calculated real-time road condition analysis coefficient SLK with a preset first threshold value, thereby generating a first comparative result, and judging whether the current road condition is abnormal according to the first comparative result;

[0073] S5, re-analyze, when the first comparison result determines that the current road condition is abnormal, integrate and calculate the real-time road condition analysis coefficient YFX and the preset first threshold value Y, so as to generate the abnormal analysis coefficient YFX, and compare the abnormal analysis coefficient FX with the preset second threshold value R, so as to generate the second comparison result, and determine the actual abnormal situation of the current road condition according to the second comparison result;

[0074] S6. Signal aggregation: uploading the second comparison result to the cloud platform for aggregation to generate the road condition of the road section.

[0075] In this embodiment: In step S1, the image captured by the driving recorder will be analyzed in real time to obtain multi-source data including vehicle speed, driving direction, road status, etc. By analyzing the real-time image of the driving recorder, accurate and timely road information can be obtained, which helps to timely discover and deal with road conditions. The advantage of this process is that it can quickly and accurately collect real-time data on the road, provide dynamic traffic information, and provide basic data support for subsequent processing and analysis.

[0076] In step S2, the collected multi-source data is preprocessed and reorganized into a first data set, a second data set, and a third data set according to different data types. The preprocessing step includes data cleaning, format conversion, and preliminary screening to ensure the quality and consistency of the data. Classifying and organizing the data into different data sets helps to improve the efficiency and accuracy of data processing and analysis. The advantage of this step is that the data quality is improved through preprocessing, making the subsequent analysis more reliable and accurate.

[0077] In step S3, the first data set, the second data set and the third data set are integrated and calculated to generate the real-time traffic analysis coefficient SLK. The integrated calculation includes the application of multiple algorithms, such as weighted average, regression analysis, etc., to comprehensively evaluate the current road conditions. The real-time traffic analysis coefficient SLK can reflect the traffic conditions of the current road section and provide a basis for further comparative analysis. The advantage of this step is that the SLK generated by the comprehensive calculation can accurately reflect the real-time road conditions and provide a reliable basis for judgment and decision-making.

[0078] In step S4, the calculated real-time road condition analysis coefficient SLK is compared with a preset first threshold value to generate a first comparison result. Whether the current road condition is abnormal is determined based on the first comparison result. By setting a reasonable threshold value, abnormal road conditions can be quickly identified, so that measures can be taken in a timely manner. The advantage of this step is that potential abnormal road conditions can be quickly screened out through comparative analysis, thereby improving the efficiency of road condition monitoring.

[0079] In step S5, when the first comparison result determines that the current road condition is abnormal, the real-time road condition analysis coefficient YFX is integrated and calculated with the preset first threshold value Y to generate the abnormal analysis coefficient YFX, and the abnormal analysis coefficient FX is compared with the preset second threshold value R to generate the second comparison result. The actual abnormal situation of the current road condition is determined according to the second comparison result. Through further analysis, the severity and type of abnormal road conditions can be more accurately located and evaluated. The advantage of this step is that through multi-level analysis, abnormal road conditions can be more accurately identified and classified, which facilitates the adoption of targeted measures.

[0080] In step S6, the second comparison result is uploaded to the cloud platform for summary, thereby generating the road condition of the road section. Through the summary analysis of the cloud platform, the road condition information of different sections can be integrated to provide data support for global traffic management. The advantage of this step is that through the summary analysis of the cloud platform, data sharing and real-time monitoring can be achieved, thereby improving the intelligent level of traffic management.

[0081] This method combines multiple steps of real-time data collection, data processing, integrated calculation, comparative analysis, reanalysis and signal aggregation to comprehensively and accurately monitor and evaluate road conditions, provide scientific basis and data support for traffic management and emergency response, and improve the safety and efficiency of road traffic.

[0082] Example 2, please refer to Figure 1 ,In step S1, the multi-source data includes image quality data, road environment data, and vehicle operation data;

[0083] Among them, the image quality data includes resolution, frame rate, brightness and motion blur value;

[0084] Road environment data includes visibility and light intensity;

[0085] The vehicle driving data includes vehicle speed, vehicle acceleration and vehicle interval.

[0086] In this embodiment: through high-resolution and high-frame-rate image data, road details and dynamic changes can be accurately captured to ensure the accuracy of real-time monitoring. The analysis of brightness and dynamic blur values ​​ensures that clear images can be obtained under different lighting and speed conditions, which helps to accurately assess road conditions.

[0087] Visibility and light intensity data can provide detailed information on current environmental conditions, help assess and predict possible driving risks, conduct a comprehensive analysis of road conditions under different weather and lighting conditions, and improve the reliability of overall road condition monitoring.

[0088] Data on vehicle speed, acceleration and interval can reflect traffic flow and driving behavior in real time, help identify potential dangerous driving and traffic bottlenecks. By analyzing these data, traffic management measures can be adjusted in a timely manner to optimize traffic flow and improve driving safety.

[0089] Comprehensive real-time analysis of multi-source data can quickly detect and respond to abnormal road conditions, improve the system's response speed, and accurate data processing and calculation help provide reliable decision support and improve the accuracy and efficiency of traffic management.

[0090] Through intelligent analysis and processing of collected data, it can provide scientific basis and support for traffic management departments, optimize traffic management strategies, realize real-time monitoring and management of large-scale and diversified road conditions, and improve the intelligence level of the transportation system.

[0091] Through the data collection in step S1 above, comprehensive monitoring and analysis of image quality, road environment and vehicle driving conditions can be achieved, providing high-quality basic data for subsequent data processing, calculation and analysis. Accurate real-time road condition monitoring, comprehensive environmental analysis, driving behavior and traffic flow analysis, and intelligent traffic management support will greatly improve the safety, efficiency and intelligence level of the transportation system.

[0092] Example 3, please refer to Figure 1 ,In step S2, data processing includes data preprocessing and data integration;

[0093] The data preprocessing is to remove noise, fill and repair, and make the collected multi-source data dimensionless;

[0094] The data integration is used to reorganize the preprocessed data according to timestamps, thereby generating a first data set, a second data set, and a third data set.

[0095] In this embodiment: the pre-processed multi-source data are reorganized according to timestamps to form a first data set, a second data set and a third data set. The first data set contains processed image quality data and road environment data for detailed visual and environmental analysis. The second data set covers vehicle driving data, including speed, acceleration and interval, for driving behavior analysis and traffic flow calculation. The third data set combines the above data, performs comprehensive calculation and analysis, and generates a real-time road condition analysis coefficient.

[0096] Data preprocessing removes noise and repairs abnormal data, significantly improving the quality and credibility of the data. Dimensionless processing eliminates differences in data units and magnitudes, making the data more consistent and comparable. The preprocessed and integrated data sets are clearer and more complete, providing a good foundation for subsequent data calculation and analysis. Unified timestamp organization ensures the continuity and sequentiality of the data in time, making real-time traffic condition analysis more accurate and reliable.

[0097] The data processing in step S2, including data preprocessing and data integration, effectively improves the quality and availability of multi-source data obtained from the driving recorder. The denoising, filling and dimensionless processing in the preprocessing stage significantly improves the accuracy and consistency of the data, providing a reliable basis for subsequent data calculation, analysis and decision-making. The timestamp reorganization in the data integration stage ensures the time sequence and continuity of the data, further optimizes the accuracy and intelligence level of real-time road condition analysis, and helps to improve the safety, efficiency and management level of the transportation system.

[0098] Example 4, please refer to Figure 1 ,The first data set includes resolution, frame number, brightness and motion blur value;

[0099] Among them, the resolutions are recorded as FB1, FB2, FB3, ... FBn according to the timestamp;

[0100] The frames are recorded as ZS1, ZS2, ZS3, ... ZSn according to the timestamp;

[0101] The brightness is recorded as LD1, LD2, LD3, ... LDn according to the timestamp;

[0102] The dynamic fuzzy values ​​are recorded as DT1, DT2, DT3, ... DTn according to the timestamps;

[0103] The second data set includes visibility and light intensity;

[0104] The visibility is recorded as KJD1, KJD2, KJD3, ... KJDn according to the timestamp;

[0105] The light intensity is recorded as GZD1, GZDE2, GZD3, ... GZDn according to the timestamp;

[0106] The third data set includes vehicle speed, vehicle acceleration, and vehicle spacing;

[0107] The vehicle speeds are recorded as CLS1, CLS2, CLS3, ... CLSn according to the timestamps;

[0108] The vehicle accelerations are recorded as JSD1, JSD2, JSD3, ... JSDn according to the timestamps;

[0109] The vehicle intervals are recorded as JG1, JG2, JG3, ... JGn according to the time stamps.

[0110] In this embodiment: the first data set includes resolution, frame number, brightness and dynamic blur value, which are recorded in FB1, FB2, FB3...FBn, ZS1, ZS2, ZS3...ZSn, LD1, LD2, LD3...LDn and DT1, DT2, DT3...DTn according to the timestamp. These data reflect the image quality captured by the driving recorder. Through this information, the system can analyze the visual clarity, lighting conditions and image stability of the road environment in real time, effectively improve the quality and accuracy of the data, and thus improve the accuracy and reliability of subsequent road condition analysis.

[0111] The second data set includes visibility and light intensity, which are recorded in KJD1, KJD2, KJD3...KJDn and GZD1, GZD2, GZD3...GZDn according to the timestamp. This information can help the system evaluate the visibility and light intensity changes of the road in real time, which is of great significance for vehicle driving and traffic management under different lighting conditions, and improves driving safety and driving experience.

[0112] The third data set includes vehicle speed, vehicle acceleration and vehicle interval, which are recorded in CLS1, CLS2, CLS3...CLSn, JSD1, JSD2, JSD3...JSDn and JG1, JG2, JG3...JGn according to the timestamp. These data reflect the real-time operation status and interaction of vehicles. Through the integration and analysis of these data, the system can accurately evaluate traffic flow, driving speed and road congestion, provide important support for traffic management and road condition warning, and further improve the intelligence level and operation efficiency of the transportation system.

[0113] Example 5, please refer to Figure 1 In step S3, the real-time traffic analysis coefficient SLK is calculated and obtained by the following formula;

[0114] ;

[0115] Wherein: a1 and a2 are weight coefficients, the values ​​of a1 and a2 are adjusted and set by the user, S1 and S2 are the first stage value and the second stage value, wherein the first stage value S1 and the second stage value S2 are respectively obtained by integrating the first data set, the second data set and the third data set.

[0116] In this embodiment: Through this step, the method can comprehensively utilize multi-source data, including image quality, road environment and vehicle driving data, to accurately calculate the real-time road condition analysis coefficient SLK. This method not only improves the accuracy and real-time performance of road conditions, but also can adjust the weights according to user needs to adapt to different traffic management and driving scenarios. Therefore, this method can effectively improve the intelligent level of traffic management, optimize the accuracy of road condition analysis, and provide more reliable decision support for drivers and traffic management departments, thereby improving road safety and traffic flow.

[0117] Example 6, please refer to Figure 1 , the first stage value S1 and the second stage value S2 are calculated and obtained by the following formulas respectively;

[0118] ;

[0119] ;

[0120] Where: FBn-2, LDn-2, DTn-2, CLSn-2, JSDn-2 and JGn-2 are the resolution, brightness, dynamic blur value, vehicle speed, vehicle acceleration and vehicle interval at the n-2 timestamp respectively;

[0121] FBn-1, LDn-1, DTn-1, CLSn-1, JSDn-1 and JGn-1 are the resolution, brightness, motion blur value, vehicle speed, vehicle acceleration and vehicle interval at the n-1 timestamp respectively;

[0122] FBn, LDn, DTn, CLSn, JSDn and JGn are the resolution, brightness, motion blur value, vehicle speed, vehicle acceleration and vehicle interval at timestamp n, respectively;

[0123] k is a modified intervention value, which is obtained by integrating the first data set and the second data set.

[0124] In this embodiment: Through these calculations, this method can use the data change trend under continuous timestamps to accurately capture and evaluate the real-time changes in road conditions. This method not only improves the comprehensive analysis capability of road conditions, but also can adjust the calculation results according to the modified access value k, making the road condition analysis more accurate and flexible, and providing reliable data support for traffic management and driving decisions. Therefore, this method can effectively optimize the operating efficiency of the traffic management system, improve the accuracy and practicality of road condition analysis, and thus improve driving safety and road traffic efficiency.

[0125] Example 7, please refer to Figure 1 , the modified intervention value k is calculated by the following formula;

[0126] ;

[0127] Where: KJDn, GZDn and ZSn are visibility, light intensity and frame number at timestamp n, respectively, i is the window value, b1, b2 and b3 are weight values, and the values ​​of b1, b2, b3 and i are adjusted and set by the user.

[0128] In this embodiment: through this calculation formula, the system can dynamically adjust the corrected intervention value k according to the environmental conditions at the current timestamp, thereby introducing the influence of environmental factors in real-time traffic analysis. This method not only makes the traffic analysis more comprehensive and accurate, but also provides users with the flexibility to adjust weights and window values ​​to cope with changes in different traffic scenarios and environmental conditions. Therefore, by optimizing the calculation of k, the adaptability and accuracy of the traffic analysis system can be effectively improved, providing more reliable data support for traffic management and driving safety.

[0129] Example 8, please refer to Figure 1, in step S4, the first comparison result is;

[0130] when When , it means that the current road condition is normal;

[0131] when When Y is displayed, it means that the current road condition is abnormal.

[0132] In this embodiment: through this comparative analysis, the method can quickly and effectively identify abnormal road conditions, helping traffic management departments to take timely measures to ensure road safety and smooth vehicle traffic. This not only improves transportation efficiency, but also enhances the sense of driving safety for drivers and passengers, bringing significant advantages and improvements to urban traffic management and road operations.

[0133] Example 9, please refer to Figure 1 , in step S5, the second comparison result is as follows;

[0134] when When , it means the current traffic condition is in the first level of congestion;

[0135] when When , it means that the current traffic condition is in the second level of congestion;

[0136] when When , it means that the current traffic condition is in the first level sparse state;

[0137] when , it means that the current traffic condition is in the second-level sparse state.

[0138] In this embodiment: When the system determines that the current road condition is in the first level of congestion, this accurate identification of congestion status helps traffic management departments to adjust the signal light cycle and guide traffic in a timely manner, thereby reducing traffic congestion and improving road network operation efficiency.

[0139] when When the system determines that the current road condition is in the second-level congestion state, timely identification of serious traffic congestion will help to quickly take measures to divert traffic, avoid accidents, and improve road safety and traffic efficiency.

[0140] when When the system determines that the current road condition is in the first level of sparse traffic, the traffic flow can be optimized by adjusting the duration of traffic lights, etc., to improve the road capacity and reduce the risk of traffic accidents.

[0141] when When the system determines that the current road condition is in the second-level sparse state, it can timely identify the sparse situation of vehicles on the road and provide reasonable road resource allocation suggestions to the traffic management department to improve the efficiency of road resource utilization.

[0142] See also Figure 2 , the present application also includes an intelligent dynamic collection system for road condition data based on a driving recorder, the system including a data collection unit, a data processing unit, a data calculation unit, a first analysis unit, a second analysis unit and a signal aggregation unit;

[0143] The data acquisition unit analyzes the images captured by the driving recorder in real time and extracts multi-source data;

[0144] A data processing unit performs preprocessing on the collected multi-source data, including denoising, repairing and standardization, to generate the first, second and third data sets;

[0145] A data calculation unit, integrating the first, second and third data sets, and calculating a real-time traffic analysis coefficient SLK;

[0146] A first analysis unit compares the calculated SLK with a preset first threshold value, generates a first comparison result, and determines whether the current road condition is abnormal;

[0147] The second analysis unit, when detecting an abnormal road condition, further integrates and calculates SLK with a preset threshold value to generate an abnormal analysis coefficient YFX, and compares it with a preset second threshold value R to generate a second comparison result;

[0148] The signal aggregation unit uploads the second comparison result to the cloud platform for aggregation and analysis to generate a comprehensive road condition of the road section.

[0149] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent dynamic collection method of road condition data based on a driving recorder, characterized in that: The specific steps are as follows; S1, data collection, real-time analysis of images captured by the driving recorder to obtain multi-source data; S2, data processing, pre-processing the collected multi-source data and reorganizing them into a first data set, a second data set and a third data set; S3, data calculation, integrating and calculating the first data set, the second data set and the third data set, so as to generate a real-time traffic analysis coefficient SLK; S4, preliminary comparative analysis, comparing the calculated real-time road condition analysis coefficient SLK with a preset first threshold value, thereby generating a first comparative result, and judging whether the current road condition is abnormal according to the first comparative result; S5, re-analyze, when the first comparison result determines that the current road condition is abnormal, integrate and calculate the real-time road condition analysis coefficient YFX and the preset first threshold value Y, so as to generate the abnormal analysis coefficient YFX, and compare the abnormal analysis coefficient FX with the preset second threshold value R, so as to generate the second comparison result, and determine the actual abnormal situation of the current road condition according to the second comparison result; S6. Signal aggregation: uploading the second comparison result to the cloud platform for aggregation to generate the road condition of the road section.

2. The intelligent dynamic collection method of road condition data based on a driving recorder according to claim 1 is characterized in that: In step S1, the multi-source data includes image quality data, road environment data, and vehicle operation data; Among them, the image quality data includes resolution, frame rate, brightness and motion blur value; Road environment data includes visibility and light intensity; The vehicle driving data includes vehicle speed, vehicle acceleration and vehicle interval.

3. The intelligent dynamic collection method of road condition data based on a driving recorder according to claim 2 is characterized in that: In step S2, data processing includes data preprocessing and data integration; The data preprocessing is to remove noise, fill and repair, and make the collected multi-source data dimensionless; The data integration is used to reorganize the preprocessed data according to timestamps, thereby generating a first data set, a second data set, and a third data set.

4. The intelligent dynamic collection method of road condition data based on a driving recorder according to claim 3 is characterized in that: The first data set includes resolution, frame rate, brightness, and motion blur value; Among them, the resolutions are recorded as FB1, FB2, FB3, ... FBn according to the timestamp; The frames are recorded as ZS1, ZS2, ZS3, ... ZSn according to the timestamp; The brightness is recorded as LD1, LD2, LD3, ... LDn according to the timestamp; The dynamic fuzzy values ​​are recorded as DT1, DT2, DT3, ... DTn according to the timestamps; The second data set includes visibility and light intensity; The visibility is recorded as KJD1, KJD2, KJD3, ... KJDn according to the timestamp; The light intensity is recorded as GZD1, GZDE2, GZD3, ... GZDn according to the timestamp; The third data set includes vehicle speed, vehicle acceleration, and vehicle spacing; The vehicle speeds are recorded as CLS1, CLS2, CLS3, ... CLSn according to the timestamps; The vehicle accelerations are recorded as JSD1, JSD2, JSD3, ... JSDn according to the timestamps; The vehicle intervals are recorded as JG1, JG2, JG3, ... JGn according to the time stamps.

5. The intelligent dynamic collection method of road condition data based on a driving recorder according to claim 4 is characterized in that: In step S3, the real-time traffic analysis coefficient SLK is calculated and obtained by the following formula: ； Wherein: a1 and a2 are weight coefficients, the values ​​of a1 and a2 are adjusted and set by the user, S1 and S2 are the first stage value and the second stage value, wherein the first stage value S1 and the second stage value S2 are respectively obtained by integrating the first data set, the second data set and the third data set.

6. The intelligent dynamic collection method of road condition data based on a driving recorder according to claim 5 is characterized in that: The first stage value S1 and the second stage value S2 are calculated and obtained by the following formulas respectively; ； ； Where: FBn-2, LDn-2, DTn-2, CLSn-2, JSDn-2 and JGn-2 are the resolution, brightness, dynamic blur value, vehicle speed, vehicle acceleration and vehicle interval at the n-2 timestamp respectively; FBn-1, LDn-1, DTn-1, CLSn-1, JSDn-1 and JGn-1 are the resolution, brightness, motion blur value, vehicle speed, vehicle acceleration and vehicle interval at timestamp n-1 respectively; FBn, LDn, DTn, CLSn, JSDn and JGn are the resolution, brightness, motion blur value, vehicle speed, vehicle acceleration and vehicle interval at timestamp n, respectively; k is a modified intervention value, which is obtained by integrating the first data set and the second data set.

7. The intelligent dynamic collection method of road condition data based on a driving recorder according to claim 6 is characterized in that: The modified intervention value k is calculated by the following formula: ； Where: KJDn, GZDn and ZSn are visibility, light intensity and frame number at timestamp n, respectively, i is the window value, b1, b2 and b3 are weight values, and the values ​​of b1, b2, b3 and i are adjusted and set by the user.

8. The intelligent dynamic collection method of road condition data based on a driving recorder according to claim 7 is characterized in that: In step S4, the first comparison result is: when When , it means that the current road condition is normal; when When Y is displayed, it means that the current road condition is abnormal.

9. The intelligent dynamic collection method of road condition data based on a driving recorder according to claim 8 is characterized in that: In step S5, the second comparison result is as follows; when When , it means the current traffic condition is in the first level of congestion; when When , it means that the current traffic condition is in the second level of congestion; when When , it means that the current traffic condition is in the first level sparse state; when , it means that the current traffic condition is in the second level sparse state.

10. An intelligent dynamic collection system for road condition data based on a driving recorder, characterized in that: The system is used to execute the intelligent dynamic collection method of road condition data based on a driving recorder as described in any one of claims 1 to 9 above, and the system includes a data collection unit, a data processing unit, a data calculation unit, a first analysis unit, a second analysis unit and a signal aggregation unit; The data acquisition unit analyzes the images captured by the driving recorder in real time and extracts multi-source data; A data processing unit performs preprocessing on the collected multi-source data, including denoising, repairing and standardization, to generate the first, second and third data sets; A data calculation unit, integrating the first, second and third data sets, and calculating a real-time traffic analysis coefficient SLK; A first analysis unit compares the calculated SLK with a preset first threshold value, generates a first comparison result, and determines whether the current road condition is abnormal; The second analysis unit, when detecting an abnormal road condition, further integrates and calculates SLK with a preset threshold value to generate an abnormal analysis coefficient YFX, and compares it with a preset second threshold value R to generate a second comparison result; The signal aggregation unit uploads the second comparison result to the cloud platform for aggregation and analysis to generate a comprehensive road condition of the road section.

Images