A highway monitoring method based on simulation and high-low bit fusion layout

Abstract

The application provides a kind of expressway monitoring method based on simulation and high-low bit fusion layout, it is related to information retrieval technical field, the application is by collecting the multi-source data of target expressway monitoring section, the vehicle target in high bit and low bit monitoring video is continuously detected and trajectory reconstruction, constructs monitoring view simulation model, the theoretical observability of road space unit and actual recognition effect are comprehensively evaluated;Through calculating monitoring simulation consistent coverage coefficient and monitoring blind area prediction confidence coefficient, realize the dynamic evaluation and optimization of monitoring layout state and blind area prediction result;Combined with historical traffic event data, evaluate the reuse effectiveness of emergency decision data, trigger the re-inference and dynamic generation of emergency disposal strategy for mismatch situation, form the closed-loop mechanism of monitoring layout evaluation, blind area prediction verification, emergency decision output and result feedback reuse, improve the reliability of expressway monitoring coverage and the intelligent level of emergency disposal.

Description

Technical Field

[0001] This invention relates to the field of information retrieval technology, specifically to a highway monitoring method based on simulation and high-low level fusion deployment. Background Technology

[0002] With the continuous growth of highway traffic volume and the increasing complexity of traffic scenarios, higher demands are being placed on traffic safety and emergency response capabilities along highways. To improve road operation monitoring, existing highways typically deploy high-position and low-position video surveillance equipment along the route to monitor road conditions in real time, enabling the detection, analysis, and handling of traffic incidents.

[0003] However, due to factors such as the complexity of road structures, obstruction by bridges and tunnels, differences in monitoring perspectives between high and low positions, and changes in environmental conditions, existing monitoring deployment methods are prone to problems in actual operation, such as blind spots, overlapping and unbalanced fields of view, or inconsistencies between simulation evaluation results and actual monitoring effects. Especially in sections with curves, significant changes in longitudinal slope, or high traffic flow, it is difficult to accurately assess the effectiveness and stability of monitoring coverage by simply relying on static deployment schemes or experience-based configuration methods.

[0004] Existing technical solutions attempt to optimize monitoring deployment schemes through monitoring simulation analysis or coverage evaluation models, but these solutions mostly focus on coverage judgment at a single point in time, lacking a continuous verification mechanism based on real operational data. This makes it difficult to reflect the dynamic deviation between monitoring simulation results and actual observation effects. When simulation predictions deviate, adjustments are often made based on human experience, lacking quantifiable and reliable evaluation indicators and closed-loop correction methods.

[0005] Furthermore, during highway emergency response, traffic management systems typically accumulate a large amount of historical traffic incident data and response results. However, current technologies mostly utilize this data through manual queries or simple statistics, lacking mechanisms for event similarity retrieval and effective reuse based on multi-dimensional features. This hinders the rapid matching of emergency response strategies and the transfer of experience. From an information processing perspective, existing solutions have not fully incorporated data retrieval and information management technologies in the organization, retrieval, and decision reuse of historical event data, making it difficult to support the need for efficient decision-making in complex monitoring scenarios. Summary of the Invention

[0006] The purpose of this invention is to provide a highway monitoring method based on simulation and high-low position fusion deployment, so as to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: A highway monitoring method based on simulation and high-low position fusion deployment includes the following steps: Step 1: Collect road structure status data, high-level monitoring view status data, low-level monitoring view status data, traffic operation status data, environmental status data, and historical traffic event data for the target highway monitoring section; Step 2: By performing unified temporal and spatial preprocessing on multi-source monitoring data, continuous detection and trajectory reconstruction of vehicle targets in high- and low-position monitoring videos are carried out; and spatial units are discretely divided into monitoring road segments to construct a monitoring field simulation model, and the theoretical observability, actual vehicle observation status and stable recognition of each spatial unit are comprehensively analyzed. Step 3: Calculate the monitoring simulation consistency coverage coefficient to assess whether the current monitoring deployment status is qualified. If qualified, generate a simulation consistency coverage compliance status indicator; if not qualified, adjust the high and low viewpoint parameters and implement complementary compensation strategies. Step 4: Calculate the confidence coefficient of the monitoring blind zone prediction and evaluate whether the simulation blind zone prediction result is reliable. If it is reliable, generate a blind zone prediction confidence status flag; if it is not reliable, trigger the monitoring field mapping correction and high and low position deployment optimization strategy. Step 5: Calculate the effective coefficient of emergency decision-making data reuse and evaluate whether the current emergency decision-making data reuse effect is qualified. If it is not qualified, trigger the re-deduction and dynamic generation of emergency response strategies, and supplement the new strategies and their execution results into the historical traffic incident data. At the same time, uniformly store and feedback the monitoring consistency status, blind spot prediction reliability status and response information, and continuously optimize emergency decision-making and update the monitoring system iteratively.

[0008] Further, step one includes: S11. Conduct basic monitoring of the road structure status of the target highway monitoring section. By accessing highway design drawing data, BIM data, or high-precision map data, collect spatial coordinates of the road centerline, road curvature radius, longitudinal slope change parameters, and spatial location data of bridges and tunnels; obtain road structure status data. S12. Real-time monitoring of high-level surveillance angles along the highway is carried out by installing high-level video surveillance equipment on poles, overpass gantry frames, or bridge ancillary structures on both sides of the road, collecting the installation coordinates, height parameters, pitch angle parameters, field of view parameters, and corresponding continuous video stream data of the high-level surveillance equipment; and obtaining high-level surveillance angle status data. S13. Real-time monitoring of the low-position monitoring angle in the near-road area of ​​the highway is carried out by installing low-position video monitoring equipment at the locations of road guardrails, roadside facilities or central dividers, and collecting the installation coordinates, height parameters, lateral distance parameters, field of view parameters and corresponding continuous video stream data of the low-position monitoring equipment; and obtaining the status data of the low-position monitoring angle. S14. Real-time monitoring of traffic operation status of the target highway section; vehicle target detection and tracking processing through high-level and low-level monitoring videos; collection of vehicle detection results, spatial trajectory coordinates of vehicles in time series, and corresponding vehicle speed sequence data; acquisition of traffic operation status data. S15. Real-time monitoring of the environmental conditions of the target highway section is carried out by deploying environmental sensing devices on the roadside or near monitoring equipment to collect visibility data, light intensity data and weather information of the road area; and to obtain environmental condition data. S16. Collect historical traffic event data for the target highway section by accessing the traffic management system or historical monitoring records to collect data on the location of historical events, the duration of events, and the corresponding handling results; obtain historical traffic event data.

[0009] Furthermore, step two includes: S21. Perform timestamp alignment, spatial coordinate unification, and outlier removal on all types of data collected in Step 1; construct a standardized basic dataset; S22. Based on the high-level and low-level monitoring perspective status data in the standardized basic dataset, target detection and multi-target tracking algorithms are used to continuously identify vehicles; the temporal location coordinates of each vehicle during the monitoring period are obtained through trajectory reconstruction methods to construct a set of vehicle trajectories. S23. Based on the road structure data, including the road centerline, radius of curvature, longitudinal slope parameters, and spatial location of bridges and tunnels, the target monitored road segment is discretized into n road spatial units. S24. Based on the installation coordinates, height, pitch angle, and field of view parameters of the monitoring equipment using high-level and low-level monitoring perspective status data, a three-dimensional spatial calculation and coverage analysis of the visible range of the monitoring equipment is performed using spatial vector transformation view domain modeling and ray projection simulation methods to construct a monitoring view domain simulation model. Through simulation analysis, the degree to which each road space unit is covered by the monitoring equipment under ideal unobstructed conditions is calculated to obtain the theoretical observable weight corresponding to each road space unit. S25. Based on the high-level monitoring perspective status data, low-level monitoring perspective status data and traffic operation status data, and combined with the continuous video stream data corresponding to the high-level monitoring perspective status data and low-level monitoring perspective status data, the spatial consistency analysis method of vehicle target detection results and vehicle spatial trajectory coordinates in time series is adopted to determine the vehicle target observation status in each road spatial unit and generate the actual observation status parameters of the corresponding road spatial unit. S26. Based on the vehicle trajectory set and the simulation model of the monitoring field of view, count the number of times a vehicle is stably identified in a continuous time window within each road space unit; normalize the number of stable identifications with the total number of times a vehicle appears in the current road space unit to obtain the stable identification probability.

[0010] Furthermore, step three includes: S31. Using the obtained n road space units, theoretical observable weights and stable identification probabilities, the weighted consistency accumulation algorithm is used to calculate the monitoring effectiveness of each road space unit. After dimensionless processing, the monitoring simulation consistency coverage coefficient is calculated.

[0011] Furthermore, step three also includes: S32. By setting a consistent coverage threshold for monitoring simulation and comparing the consistent coverage coefficient of monitoring simulation with the consistent coverage threshold, the first evaluation result is obtained, including: When the monitoring simulation consistent coverage coefficient is greater than or equal to the monitoring simulation consistent coverage threshold, it means that the actual monitoring effect is consistent with the simulation coverage result, the current monitoring deployment status is deemed qualified, a simulation consistent coverage compliance status identifier is generated, and continuous monitoring is performed. When the monitoring simulation consistent coverage coefficient is less than the monitoring simulation consistent coverage threshold, it indicates that the actual monitoring effect is inconsistent with the simulation coverage result. The current monitoring deployment status is deemed unqualified, the actual monitoring recognition effect fails to reach the simulation predicted coverage level, and there is a risk of effective monitoring blind spots and visual overlap imbalance between high and low-level monitoring. This triggers the first warning instruction and generates the first strategy: adjust the pitch angle, orientation angle, or field of view parameters of the corresponding high or low-level monitoring equipment to improve the stable recognition probability of key areas; for road space units with insufficient high-level monitoring coverage but suitable low-level deployment conditions, activate the low-level monitoring compensation mechanism; for areas where low-level monitoring is easily obstructed, introduce high-level viewing angle compensation to form a high-low complementary coverage structure; after adjustment, recalculate until the monitoring simulation consistent coverage coefficient is greater than or equal to the monitoring simulation consistent coverage threshold.

[0012] Furthermore, step four includes: S41. Based on the simulation consistent coverage compliance status identifier, combined with the actual observed status parameter oi of the road space unit, under the simulation consistent coverage compliance constraint, the status consistency screening and road space unit counting method are used to statistically analyze the actual observability of the road space unit, screen out the set of road space units in a stable observable state, and perform quantity statistics on the set of road space units to obtain the number of stable observable road space units. S42. Based on the total number of road spatial units and the number of stable observable road spatial units, calculate the number of road spatial units that cannot be effectively observed.

[0013] Furthermore, step four also includes: S43. After dimensionless processing of the number of stable observable road spatial units and the number of road spatial units that cannot be effectively observed, calculate and obtain the prediction confidence coefficient of the monitoring blind spot.

[0014] Furthermore, step four also includes: S44. By setting a confidence threshold for monitoring blind spots, and comparing and analyzing the confidence coefficient of monitoring blind spot prediction with the confidence threshold for monitoring blind spots, the second evaluation result is obtained, including: When the confidence coefficient of the monitoring blind zone prediction is greater than or equal to the confidence threshold of the control blind zone prediction, it indicates that the simulation blind zone prediction result is reliable, and a blind zone prediction confidence status identifier is generated for continuous monitoring. When the confidence coefficient of the monitoring blind zone prediction is less than the confidence threshold of the control blind zone prediction, it indicates that the simulation blind zone prediction result is unreliable, and there is a risk of hidden monitoring blind zones and simulation prediction deviation. This triggers a second warning instruction and generates a second strategy: Analyze the distribution of actual events in the non-predicted area within the road space unit, correct the mapping relationship between the monitoring field of view and the road space unit, update the observable state judgment conditions and occlusion impact parameters of the corresponding road space unit, so that the blind zone identification process reflects the occlusion change characteristics in actual operation; adjust the deployment parameters of the corresponding high-level or low-level monitoring equipment, including monitoring orientation, pitch angle or field of view, or activate temporary monitoring compensation points for the corresponding road segment of the road space unit to reduce the probability of hidden monitoring blind zones; recalculate after adjustment until the confidence coefficient of the monitoring blind zone prediction is greater than or equal to the confidence threshold of the control blind zone prediction.

[0015] Furthermore, step five includes: S51. Based on the blind spot prediction credible status identifier, and combined with the road structure status data, traffic operation status data, environmental status data, and historical traffic event data of the target highway monitoring section, a multi-feature similarity retrieval and event matching analysis method is used to perform similarity matching and filtering of historical traffic events to obtain a set of matching events; and the number of matching events is counted to obtain the total number of matching events; in the set of matching events, based on the reusability judgment rules of event handling results, events with clear handling procedures and stable handling effects are screened and counted to obtain the number of reusable events.

[0016] Furthermore, step five also includes: S52. After dimensionless processing of the total number of matching events and the number of reusable events obtained, calculate the effective coefficient for reusing emergency decision-making data. S53. By setting a preset effective threshold for emergency decision-making data reuse, and comparing and analyzing the effective coefficient of emergency decision-making data reuse with the effective threshold, the third evaluation results are obtained, including: When the effective coefficient of emergency decision-making data reuse is greater than or equal to the effective threshold of emergency decision-making data reuse, it indicates that the current emergency decision-making data reuse effect is qualified and should be continuously monitored. When the effective coefficient of emergency decision-making data reuse is less than the effective threshold of emergency decision-making data reuse, it indicates that the current emergency decision-making data reuse effect is unqualified, the matching degree between historical events and the current situation is insufficient, there is a risk that existing historical events cannot cover the current complex traffic or monitoring situation, existing handling strategies are not adaptable to abnormal scenarios, and relying on existing experience may lead to delayed emergency response or decision deviation. This triggers the third early warning instruction and generates the third strategy: based on the current monitoring status, traffic operation data and reliable blind spot prediction results, the emergency handling process is re-analyzed to generate an emergency handling strategy that is adapted to the current situation, and the newly generated emergency handling strategy and its execution results are added to the historical traffic event data as extended handling information of the historical traffic event data. S54. After the emergency response strategy is output or a new strategy is generated, the monitoring simulation consistent coverage status identifier, the blind spot prediction reliable status identifier, and the extended handling information of historical traffic incident data will be summarized and stored as an important reference for subsequent monitoring deployment optimization, blind spot assessment and emergency decision-making, forming a complete technical closed loop of "monitoring deployment assessment - blind spot prediction verification - emergency decision output - result feedback reuse".

[0017] Compared with the prior art, the beneficial effects of the present invention are: This invention introduces a monitoring and evaluation mechanism that combines simulation with operational data. It unifies the analysis of road structure, monitoring equipment deployment parameters, traffic operation status, and environmental conditions, enabling the monitoring deployment effect to be objectively evaluated and continuously verified during operation. This avoids the monitoring blind spots and unreasonable resource allocation problems caused by experience-based judgment bias in traditional methods, and improves the scientificity and controllability of monitoring system planning and adjustment.

[0018] This invention also integrates high- and low-level monitoring perspectives, combined with road spatial structure and actual traffic conditions, to comprehensively analyze the observable state of road space, enabling refined monitoring and evaluation of complex road sections such as bridges, tunnels, curves, and longitudinal slopes. This allows for more accurate identification of potential monitoring blind spots and areas with insufficient visual coverage, reducing the risk of identification failures caused by obstructions, changes in lighting, or fluctuations in traffic density, and improving the overall spatial perception integrity and stability of the monitoring system.

[0019] This invention also enables emergency response strategies to be matched and optimized based on current road structure, traffic conditions, and environmental factors by correlating real-time monitoring status with historical traffic event data. When existing experience is insufficient to cover new or complex scenarios, the system can generate new response strategies and feed them back into historical data, achieving dynamic accumulation and updating of experience. This improves the accuracy, adaptability, and continuous evolution capability of emergency response, and constructs an intelligent highway monitoring and management mechanism for long-term operation. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of the overall method flow of the present invention. Detailed Implementation

[0021] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0022] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0023] Example 1 Please see Figure 1 This invention provides a technical solution: a highway monitoring method based on simulation and high-low position fusion deployment, the specific steps of which include: Step 1: Collect road structure status data, high-level monitoring view status data, low-level monitoring view status data, traffic operation status data, environmental status data, and historical traffic event data for the target highway monitoring section; Step 2: By performing unified temporal and spatial preprocessing on multi-source monitoring data, continuous detection and trajectory reconstruction of vehicle targets in high- and low-position monitoring videos are carried out; and spatial units are discretely divided into monitoring road segments to construct a monitoring field simulation model, and the theoretical observability, actual vehicle observation status and stable recognition of each spatial unit are comprehensively analyzed. Step 3: Calculate the monitoring simulation consistency coverage coefficient to assess whether the current monitoring deployment status is qualified. If qualified, generate a simulation consistency coverage compliance status indicator; if not qualified, adjust the high and low viewpoint parameters and implement complementary compensation strategies. Step 4: Calculate the confidence coefficient of the monitoring blind zone prediction and evaluate whether the simulation blind zone prediction result is reliable. If it is reliable, generate a blind zone prediction confidence status flag; if it is not reliable, trigger the monitoring field mapping correction and high and low position deployment optimization strategy. Step 5: Calculate the effective coefficient of emergency decision-making data reuse and evaluate whether the current emergency decision-making data reuse effect is qualified. If it is not qualified, trigger the re-deduction and dynamic generation of emergency response strategies, and supplement the new strategies and their execution results into the historical traffic incident data. At the same time, uniformly store and feedback the monitoring consistency status, blind spot prediction reliability status and response information, and continuously optimize emergency decision-making and update the monitoring system iteratively.

[0024] In this embodiment, by unifying and collaboratively analyzing multi-source data such as highway road structure status, monitoring perspective status, traffic operation status, environmental status, and historical traffic events, the monitoring deployment evaluation, blind spot prediction and verification, and emergency decision reuse are organically combined. This avoids the problems of monitoring effect evaluation and emergency response being separated and relying on static experience in the prior art. It enables quantitative evaluation of monitoring deployment status, continuous correction of blind spot risks, and dynamic evolution of emergency response strategies, effectively improving the adaptability of the highway monitoring system to complex operating environments and the reliability and continuous optimization capability of emergency decisions.

[0025] Example 2 Please see Figure 1 In this embodiment, as explained in Embodiment 1, specifically, step one includes: S11. Conduct basic monitoring of the road structure status of the target highway monitoring section. By accessing highway design drawing data, BIM data, or high-precision map data, collect spatial coordinates of the road centerline, road curvature radius, longitudinal slope change parameters, and spatial location data of bridges and tunnels; obtain road structure status data. S12. Real-time monitoring of high-level surveillance angles along the highway is carried out by installing high-level video surveillance equipment on poles, overpass gantry frames, or bridge ancillary structures on both sides of the road, collecting the installation coordinates, height parameters, pitch angle parameters, field of view parameters, and corresponding continuous video stream data of the high-level surveillance equipment; and obtaining high-level surveillance angle status data. S13. Real-time monitoring of the low-position monitoring angle in the near-road area of ​​the highway is carried out by installing low-position video monitoring equipment at the locations of road guardrails, roadside facilities or central dividers, and collecting the installation coordinates, height parameters, lateral distance parameters, field of view parameters and corresponding continuous video stream data of the low-position monitoring equipment; and obtaining the status data of the low-position monitoring angle. S14. Real-time monitoring of traffic operation status of the target highway section; vehicle target detection and tracking processing through high-level and low-level monitoring videos; collection of vehicle detection results, spatial trajectory coordinates of vehicles in time series, and corresponding vehicle speed sequence data; acquisition of traffic operation status data. S15. Real-time monitoring of the environmental conditions of the target highway section is carried out by deploying environmental sensing devices on the roadside or near monitoring equipment to collect visibility data, light intensity data and weather information of the road area; and to obtain environmental condition data. S16. Collect historical traffic event data for the target highway section by accessing the traffic management system or historical monitoring records to collect data on the location of historical events, the duration of events, and the corresponding handling results; obtain historical traffic event data.

[0026] In this embodiment, by synchronously and systematically collecting data on road structure status, high and low monitoring perspective status, traffic operation status, environmental status, and historical traffic events in step one, unified, complete, and spatially and temporally consistent basic data support is provided for subsequent monitoring field simulation, monitoring effect evaluation, blind spot prediction, and emergency decision analysis. This avoids monitoring and evaluation biases caused by scattered data sources or missing information, thereby improving the reliability and scalability of highway monitoring analysis and decision-making processes from the source.

[0027] Example 3 Please see Figure 1 In the explanation of Example 2, this embodiment specifically includes the following steps: S21. Perform timestamp alignment, spatial coordinate unification, and outlier removal on all types of data collected in Step 1; construct a standardized basic dataset; S22. Based on the high-level and low-level monitoring perspective status data in the standardized basic dataset, target detection and multi-target tracking algorithms are used to continuously identify vehicles; the temporal location coordinates of each vehicle during the monitoring period are obtained through trajectory reconstruction methods, and a set of vehicle trajectories is constructed, denoted as T. S23. Based on the road structure data, including the road centerline, radius of curvature, longitudinal slope parameters, and spatial location of bridges and tunnels, the target monitored road segment is discretized into n road spatial units. S24. Based on the installation coordinates, height, pitch angle, and field of view parameters of the monitoring equipment using high-level and low-level monitoring perspective data, a three-dimensional spatial calculation and coverage analysis of the monitoring equipment's visible range is performed using spatial vector transformation view domain modeling and ray casting simulation methods to construct a monitoring view domain simulation model. Through simulation analysis, the degree to which each road space unit is covered by the monitoring equipment under ideal, unobstructed conditions is calculated, yielding the theoretical observable weight corresponding to each road space unit, denoted as... ; S25. Based on the high-level monitoring perspective status data, low-level monitoring perspective status data, and traffic operation status data, and combined with the continuous video stream data corresponding to the high-level monitoring perspective status data and low-level monitoring perspective status data, the spatial consistency analysis method of vehicle target detection results and vehicle spatial trajectory coordinates in the time series is adopted to determine the vehicle target observation status in each road spatial unit and generate the actual observation status parameters of the corresponding road spatial unit, denoted as oi. S26. Based on the vehicle trajectory set T and the simulation model of the monitoring field of view, count the number of times a vehicle is stably identified within a continuous time window in each road spatial unit; normalize the number of stable identifications with the total number of vehicle occurrences in the current road spatial unit to obtain the stable identification probability, denoted as . .

[0028] In this embodiment, by performing unified spatiotemporal preprocessing on multi-source monitoring data and integrating the continuous vehicle identification results from high and low-level monitoring perspectives, the discrete model of road space units, and the simulation model of monitoring field of view, a comprehensive characterization of the theoretical observability, actual observation status, and stable identification level of road space units is achieved. This makes monitoring evaluation no longer dependent on single video effects or static deployment experience, thereby significantly improving the refinement and reliability of highway monitoring coverage analysis.

[0029] Example 4 Please see Figure 1 In the explanation of Example 3, this embodiment specifically includes the following steps: S31, through the obtained n road spatial units, theoretically observable weights With stable recognition probability The weighted consistency cumulative algorithm is used to fuse and calculate the monitoring effectiveness of each road spatial unit. After dimensionless processing, the monitoring simulation consistency coverage coefficient, denoted as JYF, is calculated and obtained, as shown in the following formula:

[0030] The physical principle of the formula: The monitoring simulation consistent coverage coefficient JYF takes each road spatial unit as the basic evaluation object, and calculates the theoretically observable weights of the spatial units under simulation conditions. Its corresponding stable recognition probability in actual operation Weighted fusion is performed to reflect the consistency between the simulated predicted coverage capability and the actual monitoring and identification effect. The theoretically observable weight is used to characterize the relative importance and coverage contribution of different spatial units in the monitoring field of view, and the stable identification probability is used to characterize the continuous and effective identification capability of vehicle targets in the spatial unit during actual monitoring. By weighted accumulation of all road spatial units and dimensionless normalization processing, the results can reflect the global consistency level between the actual monitoring effect and the simulated coverage result under the current monitoring deployment state.

[0031] In this embodiment, by weighting and fusing the theoretical observable weights of each road space unit with the actual stable recognition level, a unified monitoring simulation consistency coverage coefficient is formed. This enables a quantitative assessment of the consistency between the "simulation visibility" and the "actual recognition effect" of the monitoring deployment. It transforms the judgment of monitoring effect from subjective experience into a comparable and measurable comprehensive indicator, thereby improving the objectivity and repeatability of the assessment of the rationality of monitoring deployment.

[0032] Example 5 Please see Figure 1 In the explanation of Example 4, specifically, step three further includes: S32. By setting a consistent coverage threshold for monitoring simulation, denoted as Jth, and comparing and analyzing the consistent coverage coefficient JYF of monitoring simulation with the consistent coverage threshold Jth, the first evaluation results are obtained, including: When the monitoring simulation consistent coverage coefficient JYF ≥ the monitoring simulation consistent coverage threshold Jth, it means that the actual monitoring effect is consistent with the simulation coverage result, the current monitoring deployment status is deemed qualified, a simulation consistent coverage compliance status identifier is generated, and continuous monitoring is performed. When the monitoring simulation consistent coverage coefficient JYF < the monitoring simulation consistent coverage threshold Jth, it indicates that the actual monitoring effect is inconsistent with the simulation coverage result. The current monitoring deployment status is deemed unqualified, the actual monitoring recognition effect fails to reach the simulation predicted coverage level, and there is a risk of effective monitoring blind spots and visual overlap imbalance between high and low-level monitoring. This triggers the first warning instruction and generates the first strategy: adjust the pitch angle, orientation angle, or field of view parameters of the corresponding high or low-level monitoring equipment to improve the stable recognition probability of key areas; for road space units with insufficient high-level monitoring coverage but suitable low-level deployment conditions, activate the low-level monitoring compensation mechanism; for areas where low-level monitoring is easily obstructed, introduce high-level viewing angle compensation to form a high-low complementary coverage structure; after adjustment, recalculate until the monitoring simulation consistent coverage coefficient JYF ≥ the monitoring simulation consistent coverage threshold Jth.

[0033] The method for obtaining the consistent coverage threshold Jth in the monitoring simulation is as follows: By comparing and statistically analyzing the simulated coverage results and actual monitoring identification effects of a large number of highway monitoring sections under different deployment conditions, the distribution characteristic intervals of the consistent coverage coefficient in the monitoring simulation are extracted when the monitoring deployment status is judged as effective or ineffective. Combining monitoring equipment deployment experience, actual operation evaluation conclusions from traffic management departments, and professional judgment from engineering technicians, a reasonable threshold for distinguishing whether the simulated coverage results are consistent with the actual monitoring effect is determined. Simultaneously, relevant technical specifications for road video surveillance systems, industry recommended indicators, and existing engineering application standards are referenced to ensure that this threshold effectively reflects the overall effectiveness and engineering acceptability of the monitoring deployment.

[0034] In this embodiment, by comparing the consistent coverage coefficient of the monitoring simulation with a preset threshold, it is possible to automatically determine whether the current monitoring deployment status meets the actual operation requirements. When there is a discrepancy, targeted high and low position monitoring coordination adjustment and complementary compensation are triggered in a timely manner, so that the identification of monitoring blind spots and deployment optimization form a closed-loop feedback mechanism, thereby improving the coverage balance and operational adaptability of the highway monitoring system for key areas and avoiding the risk of monitoring failure caused by long-term reliance on static deployment.

[0035] Example 6 Please see Figure 1 In the explanation of Example 5, specifically, step four includes: S41. Based on the simulation consistent coverage compliance status identifier, combined with the actual observed status parameter oi of the road space unit, under the constraint of simulation consistent coverage compliance, the status consistency screening and road space unit counting method are used to statistically analyze the actual observability of the road space unit, screen out the set of road space units in a stable observable state, and count the number of road space units in the set to obtain the number of stable observable road space units, denoted as np. S42. Based on the total number of road spatial units n and the number of stable observable road spatial units np, calculate the number of road spatial units that cannot be effectively observed, denoted as nu.

[0036] In this embodiment, by performing consistency screening and quantitative statistics on the actual observation status of road space units under the premise of consistent coverage in simulation, the overall monitoring coverage effect can be refined to the specific space unit level, objectively distinguishing between stable observable areas and ineffective observable areas. This provides clear and quantifiable spatial basis for subsequent reliability assessment and deployment optimization of monitoring blind spots, avoiding the problem of ignoring the lack of local hidden monitoring based solely on the overall coverage conclusion.

[0037] Example 7 Please see Figure 1 In the explanation of Example Six, specifically, step four further includes: S43. After obtaining the number of stable observable road spatial units np and the number of road spatial units that cannot be effectively observed nu, and after dimensionless processing, calculate the prediction confidence coefficient of the monitoring blind zone, denoted as MYK, as follows:

[0038] The physical principle of the formula: The credibility coefficient MYK for monitoring blind spot prediction is based on the observability statistics of road space units. By comparing the ratio between the number of stable observable road space units and the number of road space units that cannot be effectively observed, the overall credibility of the current blind spot prediction results is quantified. Among them, the number of road space units that cannot be effectively observed reflects the scale of potential monitoring blind spots in the actual operation of the monitoring system, while the number of stable observable road space units reflects the effective coverage capability of the monitoring system over road space. By expressing the relationship between the two in a dimensionless way, the coefficient can intuitively reflect the degree of matching between the simulated blind spot prediction results and the actual observable state, thereby being used to evaluate the reliability of the blind spot prediction results.

[0039] In this embodiment, by introducing the proportional relationship between the number of stable observable road space units and the number of road space units that cannot be effectively observed, a monitoring blind spot prediction credibility coefficient is formed. This transforms the blind spot judgment from qualitative experience analysis into a quantitative assessment based on spatial statistical results, thereby objectively reflecting the consistency between simulation prediction results and actual monitoring effects, and improving the credibility of monitoring blind spot identification conclusions and the reliability of engineering applications.

[0040] Example 8 Please see Figure 1 In the explanation of Example 7, specifically, step four further includes: S44. A confidence threshold for predicting the monitoring blind zone is set by pre-defined criteria, denoted as Mth. The confidence coefficient MYK for the monitoring blind zone prediction is compared and analyzed with the confidence threshold Mth to obtain the second evaluation result, including: When the confidence coefficient MYK of the blind zone prediction is greater than or equal to the confidence threshold Mth of the blind zone prediction, it indicates that the simulation blind zone prediction result is reliable, and a blind zone prediction confidence status identifier is generated for continuous monitoring. When the confidence coefficient MYK for monitoring blind zone prediction is less than the confidence threshold Mth for control blind zone prediction, it indicates that the simulation blind zone prediction result is unreliable, and there is a risk of hidden monitoring blind zone and simulation prediction deviation. This triggers a second warning instruction and generates a second strategy: Analyze the distribution of actual events in the non-predicted area within the road space unit, correct the mapping relationship between the monitoring field of view and the road space unit, update the observable state judgment conditions and occlusion impact parameters of the corresponding road space unit, so that the blind zone identification process reflects the occlusion change characteristics in actual operation; adjust the deployment parameters of the corresponding high-level or low-level monitoring equipment, including monitoring orientation, pitch angle or field of view, or activate temporary monitoring compensation points for the corresponding road segment of the road space unit to reduce the probability of hidden monitoring blind zone occurrence; recalculate after adjustment until the confidence coefficient MYK for monitoring blind zone prediction is greater than or equal to the confidence threshold Mth for control blind zone prediction.

[0041] The method for obtaining the reliability threshold Mth for blind zone prediction is as follows: Long-term statistical analysis is conducted on the distribution of blind zone prediction results and actual events at different operational stages of multiple highway monitoring sections. The range of variation in the reliability coefficient of the monitoring blind zone prediction under reliable and unreliable states is extracted. Combined with road monitoring operation and maintenance experience, historical event review results, and the comprehensive judgment of professional technicians on blind zone risk tolerance, a critical threshold for determining the reliability of the simulated blind zone prediction results is determined. Simultaneously, traffic safety management regulations and monitoring system operation evaluation standards are referenced to ensure that this threshold balances the stability and practicality of the prediction results while guaranteeing safety.

[0042] In this embodiment, by comparing and evaluating the confidence coefficient of the monitoring blind zone prediction with a preset threshold, a dynamic verification and correction mechanism for the blind zone prediction results is constructed. This prevents the simulation blind zone judgment from being fixed at once, and enables the automatic triggering of monitoring field mapping correction and high / low position deployment optimization strategies when the prediction results are unreliable. This effectively reduces the risks caused by hidden monitoring blind zones and simulation deviations, and improves the adaptive adjustment capability and long-term operational reliability of the highway monitoring system under complex operating conditions.

[0043] Example 9 Please see Figure 1 In the explanation of Embodiment Eight, specifically, step five includes: S51. Based on the blind zone prediction of reliable status identifiers, and combining road structure status data, traffic operation status data, environmental status data, and historical traffic event data of the target highway monitoring section, a multi-feature similarity retrieval and event matching analysis method is used to perform similarity matching and filtering on historical traffic events, obtaining a set of matching events, denoted as Em; and the number of matching events is counted to obtain the total number of matching events, denoted as . In the matching event set Em, based on the reusability judgment rules of event handling results, events with clear handling procedures and stable handling effects are screened and counted to obtain the number of reusable events, denoted as me.

[0044] In this embodiment, by combining road structure status, traffic operation status, environmental status and historical traffic event data under the constraint of blind zone prediction credible state identifier, the similarity of historical traffic events is accurately screened and hierarchically statistically analyzed. This enables emergency decision-making to no longer rely on single experience or generalized rules, but to be based on historical events that are highly similar to the current monitoring situation and have stable handling effects, thereby significantly improving the pertinence, reusability and practical adaptability of emergency response strategies.

[0045] Example 10 Please see Figure 1 In the explanation of Embodiment Nine, specifically, step five further includes: S52, based on the total number of matching events obtained. Given the number of reusable events (me), after dimensionless processing, calculate the effective coefficient for reusing emergency decision-making data, denoted as YFY, as follows:

[0046] The physical principle of the formula: The effective coefficient for emergency decision-making data reuse, YFY, uses historical traffic events in the matching event set as the statistical object. By measuring the proportion of reusable events in the total number of matching events, it reflects the actual usability of historical emergency response experience under the current monitoring situation. Among them, the total number of matching events describes the similarity coverage of historical events and the current road, traffic, and environmental conditions at the feature level, while the number of reusable events reflects the scale of events with clear handling procedures, stable handling effects, and direct reference. Through a dimensionless ratio, this coefficient can characterize the effective support capability of historical event data in current emergency decision-making, providing a quantitative basis for evaluating the reuse value of emergency decision-making experience.

[0047] S53. By setting a preset effective threshold for emergency decision-making data reuse, denoted as Yth, and comparing and analyzing the effective coefficient YFY of emergency decision-making data reuse with the effective threshold Yth, the third evaluation results are obtained, including: When the effective coefficient of emergency decision data reuse YFY is greater than or equal to the effective threshold Yth of emergency decision data reuse, it indicates that the current emergency decision data reuse effect is qualified and should be continuously monitored. When the effective coefficient of emergency decision-making data reuse YFY is less than the effective threshold Yth of emergency decision-making data reuse, it indicates that the current emergency decision-making data reuse effect is unqualified, the matching degree between historical events and the current situation is insufficient, there is a risk that existing historical events cannot cover the current complex traffic or monitoring situation, existing handling strategies are not adaptable to abnormal scenarios, and relying on existing experience may lead to delayed emergency response or decision deviation. This triggers the third early warning instruction and generates the third strategy: based on the current monitoring status, traffic operation data and reliable blind spot prediction results, the emergency handling process is re-analyzed to generate an emergency handling strategy that is adapted to the current situation, and the newly generated emergency handling strategy and its execution results are added to the historical traffic event data as extended handling information of the historical traffic event data. S54. After the emergency response strategy is output or a new strategy is generated, the monitoring simulation consistent coverage status identifier, the blind spot prediction reliable status identifier, and the extended handling information of historical traffic incident data will be summarized and stored as an important reference for subsequent monitoring deployment optimization, blind spot assessment and emergency decision-making, forming a complete technical closed loop of "monitoring deployment assessment - blind spot prediction verification - emergency decision output - result feedback reuse".

[0048] The method for obtaining the effective threshold Yth for emergency decision-making data reuse is as follows: By statistically analyzing the reuse effect of historical traffic incident data under different monitoring situations and traffic operation conditions, the distribution range of the effective coefficient for emergency decision-making data reuse when emergency response strategies can be stably reused and when the reuse effect is insufficient is extracted. Combining emergency management practical experience, the comprehensive assessment of traffic management departments' requirements for handling efficiency and risk control, and the experience-based judgment of professionals on decision suitability, a threshold for measuring whether historical incident handling experience has effective reuse value is determined. At the same time, relevant traffic emergency management standards and typical application scenarios are referenced to ensure that this threshold can support reliable output and continuous optimization of emergency decisions.

[0049] In this embodiment, by introducing an effective coefficient for the reuse of emergency decision-making data and evaluating and controlling it, historical traffic events and their handling experience can be dynamically filtered and updated according to their matching degree with the current monitoring situation. When the reuse effect is insufficient, emergency strategy re-deduction and result supplementation are automatically triggered, thereby constructing a continuously evolving event data and decision-making knowledge system, avoiding long-term reliance on outdated experience for emergency decisions, and improving the timeliness, adaptability and overall decision reliability of emergency response in complex traffic scenarios.

[0050] It should be noted that all calculation formulas in this application employ regression analysis, including but not limited to machine learning algorithms, to deeply analyze the collected parameters and identify their natural trends and interrelationships. Specialized software, such as Python's Scikit-learn library or the R language, is used to automatically generate mathematical models that match the data. Then, cross-validation and other methods are used to objectively evaluate the model performance, and continuous feedback and optimization are combined to ensure that the created formulas truly reflect the inherent laws of the data, thereby guaranteeing their effectiveness and accuracy. In all calculation formulas in this application, the parameters in each formula undergo dimensionless processing within a consistent range to ensure that different physical quantities are compared on the same scale; dimensionless processing techniques include, but are not limited to, min-max-normalization and Z-score standardization. The algorithm of this invention is implemented as a Python script. Before executing the core logic, the program first executes a data loading module (e.g., using the widely used pandas library in Python) configured to read the aforementioned spreadsheet file and load its contents into the program's working memory (e.g., a DataFrame data structure). Subsequent algorithm steps will directly query and retrieve the required configuration parameters from this in-memory data structure.

[0051] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A highway monitoring method based on simulation and high-low position fusion deployment, characterized in that, The specific steps include: Step 1: Collect road structure status data, high-level monitoring view status data, low-level monitoring view status data, traffic operation status data, environmental status data, and historical traffic event data for the target highway monitoring section; Step 2: By performing unified temporal and spatial preprocessing on multi-source monitoring data, continuous detection and trajectory reconstruction of vehicle targets in high- and low-position monitoring videos are carried out; and spatial units are discretely divided into monitoring road segments to construct a monitoring field simulation model, and the theoretical observability, actual vehicle observation status and stable recognition of each spatial unit are comprehensively analyzed. Step 3: Calculate the monitoring simulation consistency coverage coefficient to assess whether the current monitoring deployment status is qualified. If qualified, generate a simulation consistency coverage compliance status indicator; if not qualified, adjust the high and low viewpoint parameters and implement complementary compensation strategies. Step 4: Calculate the confidence coefficient of the monitoring blind zone prediction and evaluate whether the simulation blind zone prediction result is reliable. If it is reliable, generate a blind zone prediction confidence status flag; if it is not reliable, trigger the monitoring field mapping correction and high and low position deployment optimization strategy. Step 5: Calculate the effective coefficient of emergency decision-making data reuse and evaluate whether the current emergency decision-making data reuse effect is qualified. If it is not qualified, trigger the re-deduction and dynamic generation of emergency response strategies, and supplement the new strategies and their execution results into the historical traffic incident data. At the same time, uniformly store and feedback the monitoring consistency status, blind spot prediction reliability status and response information, and continuously optimize emergency decision-making and update the monitoring system iteratively.

2. The highway monitoring method based on simulation and high-low position fusion deployment according to claim 1, characterized in that: Step one includes: S11. Conduct basic monitoring of the road structure status of the target highway monitoring section. By accessing highway design drawing data, BIM data, or high-precision map data, collect spatial coordinates of the road centerline, road curvature radius, longitudinal slope change parameters, and spatial location data of bridges and tunnels; obtain road structure status data. S12. Real-time monitoring of high-level surveillance angles along the highway is carried out by installing high-level video surveillance equipment on poles, overpass gantry frames, or bridge ancillary structures on both sides of the road, collecting the installation coordinates, height parameters, pitch angle parameters, field of view parameters, and corresponding continuous video stream data of the high-level surveillance equipment; and obtaining high-level surveillance angle status data. S13. Real-time monitoring of the low-position monitoring angle in the near-road area of ​​the highway is carried out by installing low-position video monitoring equipment at the locations of road guardrails, roadside facilities or central dividers, and collecting the installation coordinates, height parameters, lateral distance parameters, field of view parameters and corresponding continuous video stream data of the low-position monitoring equipment; and obtaining the status data of the low-position monitoring angle. S14. Real-time monitoring of traffic operation status of the target highway section; vehicle target detection and tracking processing through high-level and low-level monitoring videos; collection of vehicle detection results, spatial trajectory coordinates of vehicles in time series, and corresponding vehicle speed sequence data; acquisition of traffic operation status data. S15. Real-time monitoring of the environmental conditions of the target highway section is carried out by deploying environmental sensing devices on the roadside or near monitoring equipment to collect visibility data, light intensity data and weather information of the road area; and to obtain environmental condition data. S16. Collect historical traffic event data for the target highway section by accessing the traffic management system or historical monitoring records to collect data on the location of historical events, the duration of events, and the corresponding handling results; obtain historical traffic event data.

3. The highway monitoring method based on simulation and high-low position fusion deployment according to claim 2, characterized in that: Step two includes: S21. Perform timestamp alignment, spatial coordinate unification, and outlier removal on all types of data collected in Step 1; construct a standardized basic dataset; S22. Based on the high-level and low-level monitoring perspective status data in the standardized basic dataset, target detection and multi-target tracking algorithms are used to continuously identify vehicles; the temporal location coordinates of each vehicle during the monitoring period are obtained through trajectory reconstruction methods to construct a set of vehicle trajectories. S23. Based on the road structure data, including the road centerline, radius of curvature, longitudinal slope parameters, and spatial location of bridges and tunnels, the target monitored road segment is discretized into n road spatial units. S24. Based on the installation coordinates, height, pitch angle, and field of view parameters of the monitoring equipment using high-level and low-level monitoring perspective status data, a three-dimensional spatial calculation and coverage analysis of the visible range of the monitoring equipment is performed using spatial vector transformation view domain modeling and ray projection simulation methods to construct a monitoring view domain simulation model. Through simulation analysis, the degree to which each road space unit is covered by the monitoring equipment under ideal unobstructed conditions is calculated to obtain the theoretical observable weight corresponding to each road space unit. S25. Based on the high-level monitoring perspective status data, low-level monitoring perspective status data and traffic operation status data, and combined with the continuous video stream data corresponding to the high-level monitoring perspective status data and low-level monitoring perspective status data, the spatial consistency analysis method of vehicle target detection results and vehicle spatial trajectory coordinates in time series is adopted to determine the vehicle target observation status in each road spatial unit and generate the actual observation status parameters of the corresponding road spatial unit. S26. Based on the vehicle trajectory set and the simulation model of the monitoring field of view, count the number of times a vehicle is stably identified in each road space unit within a continuous time window; normalize the number of stable identifications with the total number of times a vehicle appears in the current road space unit to obtain the stable identification probability.

4. The highway monitoring method based on simulation and high-low position fusion deployment according to claim 3, characterized in that: Step three includes: S31. Using the obtained n road space units, theoretical observable weights and stable identification probabilities, the weighted consistency accumulation algorithm is used to calculate the monitoring effectiveness of each road space unit. After dimensionless processing, the monitoring simulation consistency coverage coefficient is calculated and obtained.

5. The highway monitoring method based on simulation and high-low position fusion deployment according to claim 4, characterized in that: Step three also includes: S32. By setting a consistent coverage threshold for monitoring simulation and comparing the consistent coverage coefficient of monitoring simulation with the consistent coverage threshold, the first evaluation result is obtained, including: When the monitoring simulation consistent coverage coefficient is greater than or equal to the monitoring simulation consistent coverage threshold, it means that the actual monitoring effect is consistent with the simulation coverage result, the current monitoring deployment status is deemed qualified, a simulation consistent coverage compliance status identifier is generated, and continuous monitoring is performed. When the monitoring simulation consistent coverage coefficient is less than the monitoring simulation consistent coverage threshold, it indicates that the actual monitoring effect is inconsistent with the simulation coverage result. The current monitoring deployment status is deemed unqualified, the actual monitoring recognition effect fails to reach the simulation predicted coverage level, and there is a risk of effective monitoring blind spots and visual overlap imbalance between high and low-level monitoring. This triggers the first warning instruction and generates the first strategy: adjust the pitch angle, orientation angle, or field of view parameters of the corresponding high or low-level monitoring equipment to improve the stable recognition probability of key areas; for road space units with insufficient high-level monitoring coverage but suitable low-level deployment conditions, activate the low-level monitoring compensation mechanism; for areas where low-level monitoring is easily obstructed, introduce high-level viewing angle compensation to form a high-low complementary coverage structure; after adjustment, recalculate until the monitoring simulation consistent coverage coefficient is greater than or equal to the monitoring simulation consistent coverage threshold.

6. The highway monitoring method based on simulation and high-low position fusion deployment according to claim 5, characterized in that: Step four includes: S41. Based on the simulation consistent coverage compliance status identifier, combined with the actual observed status parameter oi of the road space unit, under the simulation consistent coverage compliance constraint, the status consistency screening and road space unit counting method are used to statistically analyze the actual observability of the road space unit, screen out the set of road space units in a stable observable state, and perform quantity statistics on the set of road space units to obtain the number of stable observable road space units. S42. Based on the total number of road spatial units and the number of stable observable road spatial units, calculate the number of road spatial units that cannot be effectively observed.

7. The highway monitoring method based on simulation and high-low position fusion deployment according to claim 6, characterized in that: Step four also includes: S43. After dimensionless processing of the number of stable observable road spatial units and the number of road spatial units that cannot be effectively observed, calculate and obtain the prediction confidence coefficient of the monitoring blind spot.

8. The highway monitoring method based on simulation and high-low position fusion deployment according to claim 7, characterized in that: Step four also includes: S44. By setting a confidence threshold for monitoring blind spots, and comparing and analyzing the confidence coefficient of monitoring blind spot prediction with the confidence threshold for monitoring blind spots, the second evaluation result is obtained, including: When the confidence coefficient of the monitoring blind zone prediction is greater than or equal to the confidence threshold of the control blind zone prediction, it indicates that the simulation blind zone prediction result is reliable, and a blind zone prediction confidence status identifier is generated for continuous monitoring. When the confidence coefficient of the monitoring blind zone prediction is less than the confidence threshold of the control blind zone prediction, it indicates that the simulation blind zone prediction result is unreliable, and there is a risk of hidden monitoring blind zones and simulation prediction deviation. This triggers a second warning instruction and generates a second strategy: Analyze the distribution of actual events in the non-predicted area within the road space unit, correct the mapping relationship between the monitoring field of view and the road space unit, update the observable state judgment conditions and occlusion impact parameters of the corresponding road space unit, so that the blind zone identification process reflects the occlusion change characteristics in actual operation; adjust the deployment parameters of the corresponding high-level or low-level monitoring equipment, including monitoring orientation, pitch angle or field of view, or activate temporary monitoring compensation points for the corresponding road segment of the road space unit to reduce the probability of hidden monitoring blind zones; recalculate after adjustment until the confidence coefficient of the monitoring blind zone prediction is greater than or equal to the confidence threshold of the control blind zone prediction.

9. A highway monitoring method based on simulation and high-low position fusion deployment according to claim 8, characterized in that: Step five includes: S51. Based on the blind spot prediction credible status identifier, and combined with the road structure status data, traffic operation status data, environmental status data, and historical traffic event data of the target highway monitoring section, a multi-feature similarity retrieval and event matching analysis method is used to perform similarity matching and filtering of historical traffic events to obtain a set of matching events; and the number of matching events is counted to obtain the total number of matching events; in the set of matching events, based on the reusability judgment rules of event handling results, events with clear handling procedures and stable handling effects are screened and counted to obtain the number of reusable events.

10. A highway monitoring method based on simulation and high-low position fusion deployment according to claim 9, characterized in that: Step five also includes: S52. After dimensionless processing of the total number of matching events and the number of reusable events obtained, calculate the effective coefficient for reusing emergency decision-making data. S53. By setting a preset effective threshold for emergency decision-making data reuse, and comparing and analyzing the effective coefficient of emergency decision-making data reuse with the effective threshold, the third evaluation results are obtained, including: When the effective coefficient of emergency decision-making data reuse is greater than or equal to the effective threshold of emergency decision-making data reuse, it indicates that the current emergency decision-making data reuse effect is qualified and should be continuously monitored. When the effective coefficient of emergency decision-making data reuse is less than the effective threshold of emergency decision-making data reuse, it indicates that the current emergency decision-making data reuse effect is unqualified, the matching degree between historical events and the current situation is insufficient, there is a risk that existing historical events cannot cover the current complex traffic or monitoring situation, existing handling strategies are not adaptable to abnormal scenarios, and relying on existing experience may lead to delayed emergency response or decision deviation. This triggers the third early warning instruction and generates the third strategy: based on the current monitoring status, traffic operation data and reliable blind spot prediction results, the emergency handling process is re-analyzed to generate an emergency handling strategy that is adapted to the current situation, and the newly generated emergency handling strategy and its execution results are added to the historical traffic event data as extended handling information of the historical traffic event data. S54. After the emergency response strategy is output or a new strategy is generated, the monitoring simulation consistent coverage status identifier, the blind spot prediction reliable status identifier, and the extended handling information of historical traffic incident data will be summarized and stored as an important reference for subsequent monitoring deployment optimization, blind spot assessment and emergency decision-making, forming a complete technical closed loop of "monitoring deployment assessment - blind spot prediction verification - emergency decision output - result feedback reuse".

Images