Method for identifying long and large downhill high-risk area based on traffic four elements
Through the identification method based on the four elements of traffic, the risk areas of the growing downhill section are refined, which solves the problem of difficult to identify high-risk areas in the existing technology, and has achieved the subdivision and safety of the risk areas of the growing downhill section.
Patent Information
- Application Number
- CN202510305528.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-14
- Publication Date
- 2025-06-06
AI Technical Summary
The prior art is difficult to effectively identify and subdivide high-risk areas in growing downhill sections, resulting in high economic costs and difficult actual implementation when installing traffic perception facilities on the overall section.
The identification method based on the four elements of traffic is adopted, and the risk areas of the growing downhill section are refined by taking into account the driver's visual characteristics, truck driving simulation data, road safety risk index and Gaode data.
The refinement of risk areas for growing downhill sections has been achieved, helping relevant departments to concentrate resources to control high-risk areas, provide theoretical support for the key deployment and control locations of traffic perception facilities, and improve the safety of roads and traffic operations.
Smart Images
Figure CN120108186A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of traffic safety risk identification, and in particular to a method for identifying long downhill high-risk areas based on four traffic elements. Background Art
[0002] In order to improve the safety of long downhill sections, traffic status sensing facilities are installed on long downhill sections to feed back the collected information to drivers in a timely manner to help them avoid traffic accidents. Therefore, the selection of the layout location of long downhill traffic sensing facilities is worth studying. The existing standard for risk level classification of long downhill sections - the overall slope length and slope of long downhill sections are graded, which is an overall evaluation of all long downhill sections. However, the economic cost of installing a complete set of traffic sensing facilities on the entire long downhill section is relatively high, and it is difficult to achieve in actual engineering practice. Therefore, it is necessary to further subdivide the risk sections of long downhill sections.
[0003] Therefore, how to identify risky sections of long downhill sections is an urgent problem that technicians in this field need to solve. Summary of the invention
[0004] In view of this, the purpose of the present invention is to provide a method for identifying high-risk areas of long downhill sections based on the four traffic elements, and to carry out a refined division of risk safety for long downhill sections based on the four traffic elements of people, vehicles, roads and rings, which is conducive to relevant departments to select long downhill safety control positions, grasp the key points of attention in long downhill sections, and improve the safety of roads and traffic operations in long downhill sections.
[0005] The present invention solves the technical problem by adopting the following technical solution:
[0006] A method for identifying high-risk areas of long downhill slopes based on four traffic elements includes the following steps:
[0007] Step S1, considering the visual characteristics of the driver, obtaining risk area 1;
[0008] Step S2, based on the truck driving simulation data, comparing the spatial difference between the excellent driver data and the natural driver data to obtain the risk area 2;
[0009] Step S3, calculating the road safety risk index according to the basic road data of the road section to obtain the risk area three;
[0010] Step S4, using Amap data, considering driving behavior, traffic conditions and external environmental factors in multiple aspects, evaluating the road operation risk, and obtaining risk area 4;
[0011] Step S5: Integrate the above four risk areas and select the overlapping area as the risk area of the long downhill section.
[0012] Furthermore, step S1 is for driver factors. Based on the driver's visual characteristics, the characteristics of the change in pupil area of the driver on the entire long downhill section are sorted out. The greater the pupil dilation, the greater the psychological, physiological load or mental stress of the driver. The abnormal area of the driver's pupil area on the long downhill section is marked as risk area one.
[0013] Furthermore, step S2 is about vehicle factors. Brake failure of trucks on long downhill sections is the most common traffic accident. Therefore, based on the driving data of truck drivers on long downhill sections, the speed and acceleration behavior parameters of truck drivers are recorded. Using wheel hub temperature, acceleration and speed as reward functions, an excellent driver model is constructed, and the speed and acceleration operating curves of excellent drivers are output. These curves are compared with the actual speed and acceleration operating curves of truck drivers, and areas with large differences are selected as risk areas II.
[0014] Furthermore, step S3 is about road attributes. Based on the basic road attribute data of the slope, slope length and turning radius of the long downhill section, the road safety risk index model HRI is established according to the iRAP analysis, the risk index of different areas is calculated, and the long downhill area is divided into grades according to the risk index rating table. According to the results, risk area three is selected.
[0015] Furthermore, the above risk index rating table is as follows:
[0016]
[0017] Furthermore, step S4 is about the road environment. Based on the road operation data of Gaode, the driving behavior, traffic conditions, environmental conditions and traffic accident factors are considered, the road risk is calculated using the NMF model, and the risk index is clustered using the K-Means clustering method to obtain risk area four.
[0018] The present invention provides a method for identifying high-risk areas of long downhill slopes based on four traffic elements, which has the following beneficial effects:
[0019] (1) Based on multi-source data, the present invention comprehensively considers the four elements of pedestrian, vehicle, road and ring traffic to evaluate the risk area of long downhill sections.
[0020] (2) Compared with the existing classification standards for the entire section of a long downhill slope, the present invention divides the risk levels of the long downhill section into finer levels and focuses on the risk area, which is conducive to the relevant departments to concentrate resources to control the risk area and provide theoretical support for the key control locations of traffic sensing facilities. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Figure 1 is a flow chart of the method of the present invention;
[0022] Figure 2This is a result diagram of an embodiment of the present invention. DETAILED DESCRIPTION
[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.
[0024] refer to Figure 1 The present invention provides a method for identifying high-risk areas of long downhill slopes based on four traffic elements, comprising the following steps:
[0025] Step S1, considering the visual characteristics of the driver, obtaining risk area 1;
[0026] Step S2, based on the truck driving simulation data, comparing the spatial difference between the excellent driver data and the natural driver data to obtain the risk area 2;
[0027] Step S3, calculating the road safety risk index according to the basic road data of the road section to obtain the risk area three;
[0028] Step S4, using Amap data, considering driving behavior, traffic conditions and external environmental factors in multiple aspects, evaluating the road operation risk, and obtaining risk area 4;
[0029] Step S5: Integrate the above four risk areas and select the overlapping area as the risk area of the long downhill section.
[0030] The present invention is based on navigation data and driving simulation data, comprehensively considers driver factors, vehicle factors, road attributes and road environment, that is, based on the four elements of human-vehicle-road-loop traffic, to carry out a refined division of risk safety for long downhill sections. This is conducive to relevant departments to select long downhill safety control positions, grasp the key points of long downhill sections, and improve the safety of roads and traffic operations in long downhill sections.
[0031] To further optimize the technical solution, step S1 is for driver factors. Based on the driver's visual characteristics, the characteristics of the change in pupil area of the driver on the entire long downhill section are sorted out. The greater the pupil dilation, the greater the psychological, physiological load or mental stress of the driver. The abnormal area of the driver's pupil area on the long downhill section is marked as risk area one.
[0032] To further optimize the technical solution, step S2 is about vehicle factors. Brake failure of trucks on long downhill sections is the most common traffic accident. Therefore, based on the driving data of truck drivers on long downhill sections, the speed and acceleration behavior parameters of truck drivers are recorded. Using wheel hub temperature, acceleration and speed as reward functions, an excellent driver model is constructed, and the speed and acceleration operating curves of excellent drivers are output. These curves are compared with the actual speed and acceleration operating curves of truck drivers, and areas with large differences are selected as risk areas 2.
[0033] To further optimize the technical solution, step S3 is about road attributes. Based on the basic road attribute data of the slope, slope length and turning radius of the long downhill section, the road safety risk index model HRI (Highway Risk Index) is established according to the iRAP analysis, and the risk index of different areas is calculated. The long downhill area is divided into grades according to the risk index rating table. The risk index rating table is shown in Table 1. Risk area three is selected according to the results.
[0034] Risk Level Risk Profile Risk Index (HRI) Range Level V high HRI ≥ 28 Level IV Higher 28>HRI≥13 Grade III middle 13>HRI≥6 Level II Lower 6>HRI≥4 Level I Low HRI<4
[0035] Table 1
[0036] To further optimize the technical solution, step S4 is about the road environment. Based on the Gaode data of road operation, driving behavior, traffic conditions, environmental conditions and traffic accident factors are considered, the road risk is calculated using the NMF model, and the risk index is clustered using the K-Means clustering method to obtain risk area four.
[0037] The present invention achieves the goal of subdividing long downhill sections, and comprehensively considering the four elements of pedestrian, vehicle, road and ring traffic to evaluate the risk areas of long downhill sections. Compared with the existing overall grading of long downhill sections, the present invention highlights the risk areas, which is conducive to concentrating resources on risk areas and providing theoretical support for the key control locations of traffic sensing facilities.
[0038] Example
[0039] This embodiment provides a method for identifying high-risk areas of long downhill slopes based on four traffic elements, which is as follows:
[0040] (1) Taking a long downhill section of a domestic highway as an example, the driver's eye movement data, basic road attribute data, Amap data, and truck driving simulation data of this section are obtained, and the data preprocessing is completed.
[0041] (2) Based on the driver's eye movement data, pupil area parameters are extracted, and the pupil area dilation area of the driver on the long downhill section is screened as the risk area. Based on the basic road attribute data, the road safety risk index model HRI is used to calculate the risk index of different areas of the long downhill section, and the risk area is evaluated according to Table 1. Based on the driving simulation data of truck drivers, the spatial difference in the running speed of natural drivers and excellent drivers is compared and analyzed to obtain the risk area. Based on the Amap data, the road operation risk of the long downhill section is evaluated to obtain the risk area.
[0042] (4) Finally, the four risk areas are integrated and their overlapping parts are selected as the risk area of the long downhill section. The results are as follows: Figure 2 shown.
[0043] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for identifying high-risk areas of long downhill slopes based on four traffic elements, characterized in that: The steps include: Step S1, considering the visual characteristics of the driver, obtaining risk area 1; Step S2, based on the truck driving simulation data, comparing the spatial difference between the excellent driver data and the natural driver data to obtain the risk area 2; Step S3, calculating the road safety risk index according to the basic road data of the road section to obtain the risk area three; Step S4, using Amap data, considering driving behavior, traffic conditions and external environmental factors in multiple aspects, evaluating the road operation risk, and obtaining risk area 4; Step S5: Integrate the above four risk areas and select the overlapping area as the risk area of the long downhill section.
2. According to claim 1, a method for identifying high-risk areas of long downhill slopes based on four traffic elements is characterized in that: Step S1 is about the driver factors. Based on the driver's visual characteristics, the pupil area change characteristics of the driver on the long downhill section are sorted out. The greater the pupil dilation, the greater the psychological, physiological load or mental stress of the driver. The abnormal pupil area area of the driver on the long downhill section is marked as risk area one.
3. The method for identifying high-risk areas of long downhill slopes based on four traffic elements according to claim 2 is characterized in that: Step S2 is about vehicle factors. Brake failure of trucks on long downhill sections is the most common traffic accident. Therefore, based on the driving data of truck drivers on long downhill sections, the speed and acceleration behavior parameters of truck drivers are recorded. Using wheel hub temperature, acceleration, and speed as reward functions, an excellent driver model is constructed, and the speed and acceleration operating curves of the excellent driver are output. They are compared with the speed and acceleration operating curves of actual truck drivers, and areas with large differences are selected as risk areas II.
4. The method for identifying high-risk areas of long downhill slopes based on four traffic elements according to claim 3 is characterized in that: Step S3 is about road attributes. Based on the basic road attribute data of the slope, slope length and turning radius of the long downhill section, the road safety risk index model HRI is established according to the iRAP analysis, the risk index of different areas is calculated, and the long downhill area is divided into grades according to the risk index rating table. Risk area three is selected based on the results.
5. The method for identifying high-risk areas of long downhill slopes based on four traffic elements according to claim 4 is characterized in that: The above risk index rating table is as follows:
6. The method for identifying high-risk areas of long downhill slopes based on four traffic elements according to claim 5 is characterized in that: Step S4 is about the road environment. Based on the road operation data of Gaode, the driving behavior, traffic conditions, environmental conditions and traffic accident factors are considered, the road risk is calculated using the NMF model, and the risk index is clustered using the K-Means clustering method to obtain risk area four.