Urban road construction planning method and system based on vehicle feature recognition
By extracting and analyzing the vehicle traffic status of urban roads, matching and comparing the road section characteristics to determine the planning width of non-motor vehicle lanes, the problem that urban road construction planning methods in the existing technology is difficult to dynamically adapt to traffic needs, and the improvement is achieved Efficient traffic efficiency and planning accuracy.
Patent Information
- Application Number
- CN202411681184.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-22
- Publication Date
- 2025-02-07
AI Technical Summary
The existing urban road construction planning methods are difficult to dynamically adapt to the rapidly growing traffic demand, especially when the traffic flow in urban areas changes significantly, the accuracy and rationality of the planning are limited and it is difficult to meet actual needs.
By obtaining the vehicle traffic status of the target road section and the road section to be selected, extracting the vehicle morphological characteristics, analyzing various types of vehicles and numbers during peak hours, matching the total width and non-motor lane width, selecting suitable preliminary road sections, and passing efficiency ratio Determine the planned width of non-motorized vehicle lanes.
The quantitative feasibility analysis of the transformation and construction of the target road section has been achieved, the traffic efficiency of the target road section has been improved, the ability to dynamically adapt to changes in traffic demand, and the accuracy and rationality of the planning have been improved.
Smart Images
Figure CN119399956A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of construction planning, and in particular relates to a method and system for urban road construction planning based on vehicle feature recognition. Background Art
[0002] With the acceleration of urbanization, urban traffic pressure is increasing. Existing urban road construction planning is usually based on historical traffic flow data and conventional statistical analysis methods to predict future road demand. However, this traditional planning method often cannot dynamically adapt to the rapidly growing traffic demand, especially when the traffic flow in the urban area changes significantly. The accuracy and rationality of the planning have great limitations and it is difficult to meet the actual needs. Summary of the invention
[0003] The purpose of the present invention is to provide a method and system for urban road construction planning based on vehicle feature recognition, which can provide a quantitative and feasible basis for the reconstruction and construction of the target road section by extracting and analyzing the vehicle traffic conditions of the target road section and the selected road section, and can effectively improve the traffic efficiency of the target road section.
[0004] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:
[0005] The present invention provides a method for urban road construction planning based on vehicle feature recognition, comprising:
[0006] Obtain the vehicle traffic status of the target road section and multiple road sections to be selected, extract the vehicle morphological characteristics to obtain the various types and quantities of vehicles in the target road section and each road section to be selected during peak hours;
[0007] Obtain the total width of the target road section and the road section to be selected and the width of the non-motorized vehicle lane;
[0008] According to the total width of the candidate road section and the target road section and the matching of various types and numbers of vehicles during the peak period, a number of preliminary selected road sections suitable for the target road section for transformation comparison are selected from the multiple candidate road sections;
[0009] The traffic efficiency of the target road section and each preliminary road section is obtained according to the various types and quantities of vehicles in the target road section and each preliminary road section during the peak hours, as well as the total width of the target road section and the preliminary road section;
[0010] According to the target road section and the traffic efficiency of each preliminary selected road section, several reference road sections are selected from the preliminary selected road sections;
[0011] The planned width of the non-motorized vehicle lane of the target road section is obtained according to the total width and the width of the non-motorized vehicle lane of each reference road section and the corresponding traffic efficiency.
[0012] The present invention also discloses an urban road construction planning system based on vehicle feature recognition, comprising:
[0013] The statistical end is used to obtain the vehicle traffic status of the target section and multiple sections to be selected, extract the vehicle morphological characteristics to obtain the various types and quantities of vehicles in the target section and each section to be selected during peak hours;
[0014] Obtain the total width of the target road section and the road section to be selected and the width of the non-motorized vehicle lane;
[0015] The planning end is used to select a number of preliminary selected sections suitable for transformation and comparison with the target section from multiple sections to be selected based on the total width of the sections to be selected and the target section and the matching of various types and numbers of vehicles during peak hours;
[0016] The traffic efficiency of the target road section and each preliminary road section is obtained according to the various types and quantities of vehicles in the target road section and each preliminary road section during the peak hours, as well as the total width of the target road section and the preliminary road section;
[0017] According to the target road section and the traffic efficiency of each preliminary selected road section, several reference road sections are selected from the preliminary selected road sections;
[0018] The planned width of the non-motorized vehicle lane of the target road section is obtained according to the total width and the width of the non-motorized vehicle lane of each reference road section and the corresponding traffic efficiency.
[0019] The present invention performs traffic condition statistics and feature extraction on the target road section and the road sections to be selected through the statistical end, and then performs comparative analysis through the planning end to find a reference road section suitable as a reference sample for the reconstruction and construction of the target road section from among the numerous road sections to be selected, and obtains the planned width of the non-motorized vehicle lane that can improve the overall traffic efficiency of the target road section based on the non-motorized vehicle lane width conditions of each reference road section.
[0020] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0022] Figure 1 A schematic diagram of information interaction between function terminals of an urban road construction planning system based on vehicle feature recognition according to an embodiment of the present invention;
[0023] Figure 2 A schematic diagram of a step flow chart of a statistical terminal and a planning terminal according to an embodiment of the present invention;
[0024] Figure 3 This is a schematic diagram of the step flow of step S3 in one embodiment of the present invention;
[0025] Figure 4 The step flow diagram of step S36 in one embodiment of the present invention is as follows: Figure 1 ;
[0026] Figure 5 The step flow diagram of step S36 in one embodiment of the present invention is as follows: Figure 2 ;
[0027] Figure 6 This is a schematic diagram of the step flow of step S4 in one embodiment of the present invention;
[0028] Figure 7 This is a schematic diagram of the step flow of step S5 in one embodiment of the present invention;
[0029] Figure 8 FIG. 4 is a schematic diagram of a step flow chart of step S61 in an embodiment of the present invention.
[0030] In the accompanying drawings, the components represented by the reference numerals are listed as follows:
[0031] 1- Statistical side, 2- Planning side. DETAILED DESCRIPTION
[0032] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.
[0033] It should be noted that the terms "first", "second", etc. in this application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0034] The traffic conditions on urban roads are more complicated, with not only various types of motor vehicles, but also a large number of non-motor vehicles. Since motor vehicles and non-motor vehicles have different driving rules and speeds, if urban roads are not divided into non-motor vehicle lanes separately, it may affect the overall traffic efficiency of the road. However, there is a lack of reliable and feasible reference for the specific impact conditions and how to divide the width of non-motor vehicle lanes. In view of this, the present invention provides a solution.
[0035] See also Figures 1 to 2 As shown, the present invention provides an urban road construction planning system based on vehicle feature recognition, including a statistics terminal 1 and a planning terminal 2 that interact with each other in terms of information. In actual applications, the statistics terminal 1 can be a virtual functional unit, where staff collects information and then inputs it. The statistics terminal 1 can also be a traffic camera with recognition and statistics functions. The planning terminal 2 can also be a functional unit with a calculation function, which receives the information collected by the statistics terminal 1 during operation and calculates and analyzes it to obtain a construction plan for improving the traffic efficiency of the target road section.
[0036] Before planning and analysis, the system needs to execute step S1 by the statistical end 1 to obtain the vehicle traffic status of the target section and multiple sections to be selected, and extract the morphological characteristics of the vehicles to obtain the various types and quantities of vehicles in the target section and each section to be selected during peak hours. In order to comprehensively analyze the impact of various participants in urban traffic, the types of vehicles in this solution include small non-operating motor vehicles, small operating motor vehicles, medium-sized trucks, large traction trucks, electric two-wheeled non-motor vehicles, electric multi-wheeled non-motor vehicles, bicycles and large and medium-sized buses. Of course, other vehicle types can also be added based on specific circumstances. The statistical end 1 also needs to execute step S2 to obtain the total width and non-motor vehicle lane width of the target section and the section to be selected. If the non-motor vehicle lane has not been set, it is marked as 0.
[0037] See also Figures 1 to 3As shown, the planning end 2 in the present system can firstly perform step S3 in the process of planning analysis, and select several preliminary selected sections suitable for the target section for transformation and comparison according to the total width of the section to be selected and the target section, as well as the matching of various types of vehicles and quantity during the peak hours. Specifically, step S31 can be firstly performed to form multiple feature arrays of the target section with the total width of the target section and the number of various types of vehicles during different peak hours. Next, step S32 can be performed to form multiple feature arrays of each section to be selected with the total width of each section to be selected and the number of various types of vehicles during different peak hours. Next, step S33 can be performed to select several marked feature arrays marked as the target section from the multiple feature arrays of the target section. Next, step S34 can be performed to select several marked feature arrays marked as the section to be selected from the multiple feature arrays of all sections to be selected. Next, step S35 can be executed to use other feature arrays other than the marked feature array of the target section and other feature arrays other than the marked feature array of each section to be selected as the unmarked feature array of the target section and each section to be selected respectively. Next, step S36 can be executed to calculate and obtain the difference between each marked feature array and each unmarked feature array and obtain each feature array with the target section with consistency, and the feature array belonging to the section to be selected is used as the preliminary selection feature array. Finally, step S37 can be executed to use the section to be selected corresponding to the preliminary selection feature array as the preliminary selection section. Of course, the above belongs to abstract conceptual analysis, and specific analysis is carried out below in conjunction with the section to be selected and the target section.
[0038] See also Figures 4 to 5 As shown, the feature arrays corresponding to the selected sections with the same or similar traffic conditions as the target section also have similarity, and the feature arrays corresponding to the same section also have similarity. Therefore, it is possible to determine whether the grouping is completed by the distribution of feature arrays in different array sets. Specifically, step S361 can be first executed to calculate the cumulative sum of the corresponding element differences between each marked feature array and each unmarked feature array as the difference between the feature arrays. Next, step S362 can be executed to classify each unmarked feature array and the marked feature array with the smallest difference into the same array set. Next, step S363 can be executed to determine whether there are feature arrays belonging to the same selected section or target section classified in different array sets.
[0039] If yes, it means that the feature arrays in the array set have not been fully classified and grouped, so step S364 can be executed next to reselect the marked feature array and generate an array set based on this classification. Step S3641 can be executed next to calculate the feature mean array of all feature arrays in each array set. Step S3642 can be executed next to use the feature array with the smallest difference from the corresponding feature mean data in each array set as the updated marked feature array. Steps S363 to S3642 can be executed next to recalculate and generate multiple array sets based on the updated marked feature array, and repeatedly determine whether there are feature arrays belonging to the same to-be-selected road section or target road section classified in different array sets.
[0040] If it is not, it means that the feature arrays of the selected road section that are consistent with the target road section have been classified in the same array set, so step S365 can be executed next to use the array set where the feature array of the target road section is located as the preliminary selection array set. Finally, step S366 can be executed to use all the feature arrays contained in the preliminary selection array set as the preliminary selection feature arrays.
[0041] In order to supplement the implementation process of the above steps S361 to S366, the source code of some functional modules is provided, and the explanation is compared in the comment section. In order to avoid the leakage of data involving commercial secrets, some data that does not affect the implementation of the solution are desensitized, the same below.
[0042]
[0043]
[0044]
[0045]
[0046]
[0047]
[0048]
[0049] This code implements the steps of calculating the difference and grouping analysis based on the feature arrays of the target road section and the road section to be selected, and screening the preliminary feature array. During the operation, the difference calculation is first performed, and the difference between the feature arrays is calculated based on the total width and the number of vehicles. After that, classification is performed, and the unmarked features are assigned to the array set corresponding to the marked features with the smallest difference. Next, re-marking is performed to determine whether the marked feature array needs to be reselected and the classification is updated. Finally, mean calculation and screening are performed, the feature mean of each set is calculated, the marked feature array is updated, and the set containing the target road section features is found as the preliminary array set. This method ensures the consistency of the classification results, and provides a scientific basis for screening the preliminary road section feature array, providing support for urban road reconstruction planning.
[0050] Please continue reading Figure 1 , 2 As shown in Figure 6, after completing the classification in the above step S3, step S4 can be executed next to obtain the traffic efficiency of the target section and each preliminary section according to the various types of vehicles and the number of vehicles during the peak hours of the target section and each preliminary section, as well as the total width of the target section and the preliminary section. Since different types of vehicles have different impacts on traffic, the traffic contribution of a large passenger vehicle passing through is much greater than that of a small car passing through. Therefore, it is necessary to assign traffic weights to different types of vehicles in order to more accurately measure the traffic efficiency of the road. Specifically, step S41 can be executed to set traffic weight coefficients for various types of vehicles. Next, step S42 can be executed to calculate the weighted sum of the number of various types of vehicles in the target section and each preliminary section during the peak hours according to the corresponding traffic weight coefficients to obtain the traffic burden of the target section and each preliminary section during the peak hours. Finally, step S43 may be executed to divide the traffic load of the target section and each preliminary section during the peak period by the total duration of the corresponding peak period and the total width of the road to obtain the traffic efficiency of the target section and each preliminary section.
[0051] Please continue reading Figures 1 to 2 As shown, step S5 can be performed next to select several reference sections from the preliminary selected sections according to the traffic efficiency of the target section and each preliminary selected section. Since the planning of the target section in this scheme is to improve the traffic efficiency, the selected reference section should have a higher traffic efficiency. In practical applications, the preliminary selected section with a traffic efficiency greater than the target section is usually used as the reference section.
[0052] See also Figure 1 , 2, 7 and 8, after selecting the reference section, it is also necessary to select the model section that is truly used for the target section planning based on the standard, and use this to plan the non-motor vehicle lane width of the target section, that is, to execute step S6 according to the total width of each reference section and the non-motor vehicle lane width, and the corresponding traffic efficiency to obtain the planned width of the non-motor vehicle lane of the target section. In practical applications, firstly, step S61 can be executed to select multiple model sections according to the difference between the traffic efficiency of each reference section. The model section is the final basis standard for the planning and transformation of the target section, and its traffic efficiency needs to maintain a leading level. Therefore, firstly, step S611 can be executed to use the reference section with the largest traffic efficiency as the benchmark section. Next, step S612 can be executed to calculate the difference between the maximum and minimum values of the traffic efficiency of all reference sections, and the ratio to the number of all reference sections is used as the benchmark range. Finally, step S613 can be executed to use the reference sections whose difference between the traffic efficiency of the benchmark section is less than the benchmark range as model sections, and a larger number of model sections are more valuable.
[0053] Since the width of the motor vehicle lane is not divided arbitrarily, it is necessary to construct and divide it according to "Urban Road Design Specification" (CJJ 37-2012). The width of the motor vehicle lane on the expressway is generally 3.5 meters, and the width of the motor vehicle lane on the main road is 3.5 meters. The width of the motor vehicle lane on the secondary trunk road is 3.0-3.5 meters. The width of the motor vehicle lane on the branch road is 2.75-3.0 meters. Therefore, step S62 can be executed next to use the mean of the ratio between the non-motor vehicle lane width and the total width of the model section as the ideal ratio between the non-motor vehicle lane width and the total width of the target section. Finally, step S63 can be executed to control the width of each motor vehicle lane of the target section to meet the national standard, and the number of motor vehicle lanes of the target section is adjusted so that the planning ratio between the non-motor vehicle lane width and the total width of the target section is closest to the ideal ratio. Usually, the parking strip width also needs to be considered, which is usually 2.5 meters according to the design requirements.
[0054] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device, system, method and computer program product according to multiple embodiments of the present application. In this regard, each square frame in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the square frame can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square frames can actually be executed substantially in parallel, and they can also be executed in reverse order sometimes, depending on the functions involved.
[0055] It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented by hardware that performs the corresponding function or action, such as a circuit or ASIC (Application Specific Integrated Circuit), or can be implemented by a combination of hardware and software, such as firmware.
[0056] Although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.
[0057] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those of ordinary skill in the art without departing from the scope of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.
Claims
1. A method for urban road construction planning based on vehicle feature recognition, characterized in that: include, Obtain the vehicle traffic status of the target road section and multiple road sections to be selected, extract the vehicle morphological characteristics to obtain the various types and quantities of vehicles in the target road section and each road section to be selected during peak hours; Obtain the total width of the target road section and the road section to be selected and the width of the non-motorized vehicle lane; According to the total width of the candidate road section and the target road section and the matching of various types and numbers of vehicles during the peak period, a number of preliminary selected road sections suitable for the target road section for transformation comparison are selected from the multiple candidate road sections; The traffic efficiency of the target road section and each preliminary road section is obtained according to the various types and quantities of vehicles in the target road section and each preliminary road section during the peak hours, as well as the total width of the target road section and the preliminary road section; According to the target road section and the traffic efficiency of each preliminary selected road section, several reference road sections are selected from the preliminary selected road sections; The planned width of the non-motorized vehicle lane of the target road section is obtained according to the total width and the width of the non-motorized vehicle lane of each reference road section and the corresponding traffic efficiency.
2. The method according to claim 1, characterized in that: The types of vehicles include small non-commercial motor vehicles, small commercial motor vehicles, medium-sized trucks, large traction trucks, electric two-wheeled non-motor vehicles, electric multi-wheeled non-motor vehicles, bicycles and / or large and medium-sized buses.
3. The method according to claim 1, characterized in that The step of selecting a plurality of preliminary selected road sections suitable for transformation and comparison of the target road section from a plurality of road sections to be selected according to the total width of the road section to be selected and the target road section and the matching of various types and numbers of vehicles during peak hours includes: The total width of the target road section and the number of various types of vehicles in different peak hours are respectively used to form multiple feature arrays of the target road section; The total width of each road section to be selected and the number of various types of vehicles in different peak hours are respectively used to form multiple feature arrays for each road section to be selected; Selecting a number of marked feature arrays marked as target road sections from a plurality of feature arrays of the target road section; Selecting a number of marked feature arrays marked as the road sections to be selected from the multiple feature arrays of all the road sections to be selected; Using other feature arrays other than the marked feature array of the target road section and other feature arrays other than the marked feature array of each road section to be selected as the unmarked feature arrays of the target road section and each road section to be selected respectively; Calculate and obtain the difference between each marked feature array and each unmarked feature array, and thereby obtain a feature array that is consistent with each feature array of the target road section and belongs to the road section to be selected as a preliminary feature array; The unselected road section corresponding to the preliminary feature array is used as the preliminary selected road section.
4. The method according to claim 3, characterized in that: The step of calculating and obtaining the difference between each marked feature array and each unmarked feature array and thereby obtaining a feature array that is consistent with each feature array of the target road section and belongs to the road section to be selected as a preliminary feature array includes: Calculate the cumulative sum of the corresponding element differences between each marked feature array and each unmarked feature array as the difference between the feature arrays; Classify each unlabeled feature array and the labeled feature array with the smallest difference into the same array set; Determine whether there are feature arrays belonging to the same candidate road section or target road section classified in different array sets; If so, reselect the marker feature array and generate the array set by this classification; If not, the array set where the characteristic array of the target road section is located is used as the preliminary array set; All feature arrays contained in the preliminary selection array set are taken as preliminary selection feature arrays.
5. The method according to claim 4, characterized in that The step of reselecting the marker feature array and classifying and generating the array set, include, Calculate and obtain a feature mean array of all feature arrays in each of the array sets; The feature array with the smallest difference from the corresponding feature mean data in each array set is used as the updated marked feature array; Recalculate and generate multiple array sets based on the updated marking feature array, and repeatedly determine whether there are feature arrays belonging to the same candidate road section or target road section classified in different array sets.
6. The method according to claim 1, characterized in that The step of obtaining the traffic efficiency of the target road section and each of the preliminary selected road sections according to the various types and quantities of vehicles in the target road section and each of the preliminary selected road sections during peak hours, and the total width of the target road section and the preliminary selected road sections, comprises: Set traffic weight coefficients for various types of vehicles; The number of various types of vehicles on the target road section and each preliminary road section during the peak hours is calculated according to the corresponding traffic weight coefficients to obtain the traffic load of the target road section and each preliminary road section during the peak hours; The traffic load of the target section and each preliminary section during the peak period is divided by the total duration of the corresponding peak period and the total width of the road to obtain the traffic efficiency of the target section and each preliminary section.
7. The method according to claim 1, characterized in that The step of selecting a plurality of reference sections from the preliminary selected sections according to the target section and the traffic efficiency of each preliminary selected section, include, The initially selected road section whose traffic efficiency is greater than the target road section is used as a reference road section.
8. The method according to claim 1 or 7, characterized in that: The step of obtaining the planned width of the non-motorized vehicle lane of the target road section according to the total width and the non-motorized vehicle lane width of each reference road section and the corresponding traffic efficiency includes: Selecting a plurality of sample road sections according to the difference between the traffic efficiencies of each reference road section; The average of the ratios between the width of the non-motorized vehicle lane and the total width of the sample road section is taken as the ideal ratio between the width of the non-motorized vehicle lane and the total width of the target road section; The width of each motor vehicle lane of the target road section is controlled to comply with national standards, and the number of motor vehicle lanes of the target road section is adjusted so that the planned ratio between the width of the non-motor vehicle lanes and the total width of the target road section is closest to the ideal ratio.
9. The method according to claim 8, characterized in that The step of selecting a plurality of sample sections according to the difference between the traffic efficiencies of each reference section comprises: Take the reference road section with the highest traffic efficiency as the benchmark road section; Calculate the difference between the maximum and minimum traffic efficiency of all reference sections, and use the ratio of the difference to the number of all reference sections as the benchmark range; The reference sections whose difference in traffic efficiency with the benchmark section is less than the benchmark range are all used as model sections.
10. An urban road construction planning system based on vehicle feature recognition, characterized in that: include, The statistical end is used to obtain the vehicle traffic status of the target section and multiple sections to be selected, extract the vehicle morphological characteristics to obtain the various types and quantities of vehicles in the target section and each section to be selected during peak hours; Obtain the total width of the target road section and the road section to be selected and the width of the non-motorized vehicle lane; The planning end is used to select a number of preliminary selected sections suitable for transformation and comparison with the target section from multiple sections to be selected based on the total width of the sections to be selected and the target section and the matching of various types and numbers of vehicles during peak hours; The traffic efficiency of the target road section and each preliminary road section is obtained according to the various types and quantities of vehicles in the target road section and each preliminary road section during the peak hours, as well as the total width of the target road section and the preliminary road section; According to the target road section and the traffic efficiency of each preliminary selected road section, several reference road sections are selected from the preliminary selected road sections; The planned width of the non-motorized vehicle lane of the target road section is obtained according to the total width and the width of the non-motorized vehicle lane of each reference road section and the corresponding traffic efficiency.