Method and device for optimizing landscape design scheme of high-altitude long-straight-line expressway and medium

Abstract

The invention relates to a landscape design scheme optimization method and device for a high-altitude long-straight-line expressway and a medium, and the method comprises the steps: collecting multi-source driving data which comprises vehicle operation data and driver physiological data; inputting the multi-source driving data into the key fatigue feature-design parameter incidence matrix to obtain an influence weight between the key fatigue feature index and the landscape design parameter; constructing and solving a multi-objective optimization model based on the influence weight, wherein objective functions of the multi-objective optimization model comprise an anti-fatigue efficiency maximization function, an ecological and cost constraint satisfaction degree function and a visual rhythm rationality function; and outputting a solution of the multi-objective optimization model as an optimization design parameter set of the landscape design scheme, wherein the optimization design parameter set comprises an optimization color parameter, an optimization modeling parameter, an optimization rhythm interval parameter, an optimization spatial hierarchy parameter and an optimization vegetation configuration parameter. Compared with the prior art, the method has the advantages of high reliability, high pertinence, improved safety and the like.

Description

Technical Field

[0001] This invention relates to the field of landscape design, and in particular to a method, equipment, and medium for optimizing landscape design schemes for long, straight highways at high altitudes. Background Technology

[0002] As a crucial component of modern transportation networks, highways directly impact driver behavior and road safety through their road environment's safety and comfort. Long, straight sections of highways, a common feature, are prone to driver fatigue due to their monotonous scenery and lack of visual stimulation, making them a significant cause of traffic accidents. This is especially true in high-altitude and desert environments, where the lack of varied natural scenery further exacerbates driver fatigue and distraction during long journeys. Truck drivers, as the primary carriers of long-distance transport, face a particularly high risk of driver fatigue on these road sections due to the nature of their work.

[0003] Currently, the main problems with landscape design and evaluation methods for long, straight sections of highways are as follows: First, existing landscape design methods lack objective data support. Traditional designs mainly rely on engineering experience, aesthetic principles, or ecological restoration goals. While considering vegetation selection, spatial layout, and visual effects, they fail to incorporate the core safety goal of alleviating driver fatigue into a systematic design process. Especially for special environments such as high altitudes and deserts, and for the specific group of truck drivers, existing methods struggle to provide targeted design parameters and quantitative basis, making it impossible to predict and guarantee the actual anti-fatigue effect of the design schemes. Second, existing schemes lack a mapping mechanism from driving behavior and physiological responses to landscape design parameters. Although existing research has collected vehicle operation data during driving, such as speed and offset, and driver physiological data such as blinking and heart rate, using sensors, this data is mostly used for passive detection and early warning of fatigue, and has not been effectively transformed into decision parameters to guide early-stage landscape design. There is a significant disconnect between the design process and the objective manifestations of driver fatigue, failing to form a closed loop of mechanism analysis, design intervention, and effect feedback. Finally, existing technical solutions use limited evaluation methods, making it difficult to quantitatively compare the anti-fatigue effectiveness of different design schemes. For existing landscape design schemes, the lack of a standardized evaluation framework based on objective driving data and road segment environmental characteristics makes it impossible to scientifically predict the actual effect of the design schemes on reducing fatigue in real or simulated driving scenarios, thus lacking a reliable basis for scheme optimization and selection. Therefore, how to construct an optimization method for landscape design schemes that can integrate objective driving data and environmental characteristics to generate quantifiable anti-fatigue effects for long, straight highway sections at high altitudes has become a technical problem that needs to be solved. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the existing technology by providing a method, equipment and medium for optimizing landscape design schemes for long straight highways at high altitudes. By constructing a key fatigue feature-design parameter correlation matrix and a multi-objective optimization model, objective driving data and landscape design parameters are quantitatively correlated and collaboratively optimized, thereby achieving direct mapping from driving fatigue mechanism to quantifiable design parameters and efficient optimization.

[0005] The objective of this invention can be achieved through the following technical solutions: According to one aspect of the present invention, a method for optimizing the landscape design scheme of a long, straight highway at high altitude is provided, the specific steps of which include: S1. Collect multi-source driving data, which includes vehicle operation data and driver physiological data collected in a preset high-altitude long straight-line simulation driving scenario, and the multi-source driving data is distinguished and preprocessed according to two environmental scenarios: daytime and nighttime. S2. Input the multi-source driving data into the key fatigue feature-design parameter correlation matrix to obtain the influence weight between key fatigue feature indicators and landscape design parameters; the design parameters include candidate sets of color parameters, candidate sets of shape parameters, candidate sets of rhythm spacing parameters, candidate sets of spatial hierarchy parameters, and candidate sets of vegetation selection parameters; S3. Construct and solve a multi-objective optimization model based on the influence weights. The objective functions of the multi-objective optimization model include the fatigue resistance efficiency maximization function, the ecological and cost constraint satisfaction function, and the visual rhythm rationality function. S4. Output the solution of the multi-objective optimization model as the set of optimized design parameters for the landscape design scheme. The set of optimized design parameters includes optimized color parameters, optimized shape parameters, optimized rhythm spacing parameters, optimized spatial hierarchy parameters, and optimized vegetation configuration parameters.

[0006] Furthermore, the vehicle operation data includes a vehicle speed sequence and a vehicle lateral offset distance sequence; the driver physiological data includes a blink frequency sequence, a gaze duration sequence, a pupil area change sequence, and a steering wheel angle sequence.

[0007] Furthermore, the candidate set of color parameters in the design experience parameters includes the hue, saturation, and brightness range of the primary color, secondary color, and warning color; the candidate set of shape parameters includes linear, dotted, and clustered landscape shape types, and corresponding size and outline feature parameters; the candidate set of rhythm spacing parameters includes the minimum and maximum interval distances of landscape node changes; the candidate set of spatial hierarchy parameters includes the height gradient combination of vegetation or structures and the range of lateral distances from the roadside; and the candidate set of vegetation selection parameters includes local plant species and attributes that conform to the ecological adaptability of high-altitude Gobi road sections.

[0008] Furthermore, the key fatigue characteristic indicators include: vehicle speed, vehicle lateral offset distance, blink frequency, fixation duration, pupil area, and steering wheel angle, and each indicator has been extracted separately for daytime and nighttime scenarios.

[0009] Furthermore, the influence weights in the key fatigue feature-design parameter correlation matrix are determined based on an ordered multi-class Logistic regression model, with the key fatigue feature index as the independent variable and driving fatigue state as the dependent variable, and are constructed for daytime and nighttime scenarios respectively.

[0010] Furthermore, the expression for the Logistic regression model is: , in, Driver fatigue level; This is a preset level reference value; The intercept of the Logistic Regression model is when all independent variables... When both are 0, the probability that the fatigue state does not exceed the baseline logarithm of level j; The regression coefficients correspond to vehicle speed, lateral offset distance, blink frequency, fixation duration, pupil area, and steering wheel angle, respectively.

[0011] Furthermore, the standardized regression coefficients of the key fatigue characteristic indicators... The influence weights are obtained by allocating the influence ratios of each fatigue characteristic, and the expression is as follows: , , in, Key fatigue characteristic indicators Standard deviation; Key fatigue characteristic indicators The regression coefficients, The standard deviation of the predicted Logistic values; Mapping parameters to preset design parameters, i.e., the first... i Class design parameters for mitigating the first j The contribution distribution ratio of each fatigue feature; For the first i Class design parameters for mitigating the first j The influence weight of each fatigue feature.

[0012] Furthermore, the expression for the fatigue resistance maximization function is: , Where n is the number of key fatigue characteristic indicators; m is the number of design parameters to be optimized; For the first i Class design parameters for mitigating the first j The influence weight of each fatigue feature; For the first Optimization candidate values ​​for each design parameter, This is a mapping function used to evaluate design parameters. The specific value of is the theoretical contribution of the parameter to alleviating the j-th fatigue feature relative to the baseline value; the optimization objective is to maximize the anti-fatigue effectiveness maximization function. The expression for the ecological and cost constraint satisfaction function is as follows: , Where E is the ecological adaptability score. Based on the candidate set of vegetation selection parameters, the plant species, combinations and densities selected in the optimized vegetation configuration parameters are scored. Combinations that fully meet the local ecological requirements such as adaptability and windbreak and sand fixation are scored as 1, and combinations that do not match at all are scored as 0. The normalized relative cost coefficient is used to estimate the landscape construction and initial maintenance costs required using the optimized parameter set. The lowest cost feasible solution corresponds to a value of 0, and the highest cost solution corresponds to a value of 1. and These are the weighting coefficients for ecological and cost constraints, used to balance the importance of ecology and cost; the optimization objective is to ensure that the ecological and cost constraint satisfaction function is greater than a preset threshold. The expression for the visual rhythm rationality function is: , Where K represents the total number of landscape change nodes planned to be set on the optimized road section; This represents the location of the k-th landscape change node on the highway, i.e., its kilometer marker. This represents the actual distance between adjacent nodes; The recommended value for the optimal variation rhythm is determined based on the candidate set of rhythm and spacing parameters and the statistical conclusions of driver preferences collected. The tolerance parameter for allowed rhythm deviation is defined; the optimization objective is to maximize the visual rhythm rationality function. The solution is obtained by using a multi-objective evolutionary algorithm, which searches within the value space defined by the preset design empirical parameters to obtain the Pareto optimal solution set.

[0013] According to a second aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the method described thereon.

[0014] According to a third aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described thereon.

[0015] Compared with the prior art, the present invention has the following beneficial effects: (1) By collecting vehicle operation data and driver physiological data obtained in a preset high-altitude long straight-line simulated driving scenario, and processing the data according to daytime and nighttime environmental scenarios, a key fatigue feature-design parameter correlation matrix based on an ordered multi-class Logistic regression model was constructed. The influence relationship between key characteristics of driving fatigue and landscape design parameter categories was objectively and quantitatively established, overcoming the defects of existing technologies that rely on subjective experience and lack data support. This provides a quantitative basis for landscape design of high-altitude long straight-line highways based on driving fatigue mechanisms, significantly improving the scientific nature and pertinence of the design process, thereby fundamentally enhancing the potential effectiveness of landscape schemes in alleviating driving fatigue. (2) Based on the influence weights output by the correlation matrix, this invention constructs a multi-objective optimization model that includes maximizing anti-fatigue effectiveness, satisfying ecological and cost constraints, and rationality of visual rhythm. It uses a multi-objective evolutionary algorithm to solve the problem, and realizes the automatic search and output of a set of Pareto optimal landscape design parameters under multiple constraints of ecological adaptability, economic cost and visual comfort. This solves the problem of arbitrary determination of design parameters and difficulty in coordinating the optimization of various objectives in existing methods. It can generate a balanced optimization scheme that comprehensively considers safety, ecology, economy and psychological feelings, avoids the bias of the design scheme on a single objective, improves the feasibility and comprehensive benefits of the scheme, and provides decision-makers with parameterized suggestions that can be directly used to guide specific designs.

[0016] (3) The final output of this invention is a structured set of optimized design parameters. The optimization process is solidified into a repeatable and verifiable standardized process that receives objective data, performs model calculations, and outputs quantitative parameters. This forms a set of quantifiable landscape design optimization tools and methods applicable to high-altitude long straight highway scenarios. The process is clear and the parameters are well-defined, making it easy to transfer and apply the technology and compare the effects in different projects or road sections. This provides highway operation and management departments with an efficient and scientific means of supporting fatigue-resistant landscape design decisions, which helps to systematically reduce the fatigue risk of long-distance driving from the source of the road environment and improve driving safety. Attached Figure Description

[0017] Figure 1 Flowchart of the optimization method for landscape design schemes of long straight highways at high altitudes. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0019] like Figure 1 The image shows an optimization method for the landscape design of a long, straight highway at high altitude. The specific steps include: S1. Collect multi-source driving data, which includes vehicle operation data and driver physiological data collected in a preset high-altitude long straight-line simulation driving scenario. The multi-source driving data is distinguished and preprocessed according to two environmental scenarios: daytime and nighttime. S2. Input the multi-source driving data into the key fatigue feature-design parameter correlation matrix to obtain the influence weight between key fatigue feature indicators and landscape design parameters; the design parameters include candidate sets of color parameters, candidate sets of shape parameters, candidate sets of rhythm spacing parameters, candidate sets of spatial hierarchy parameters, and candidate sets of vegetation selection parameters; S3. Construct and solve a multi-objective optimization model based on the influence weights. The objective functions of the multi-objective optimization model include the fatigue resistance efficiency maximization function, the ecological and cost constraint satisfaction function, and the visual rhythm rationality function. S4. Output the solution of the multi-objective optimization model as the set of optimization design parameters for the landscape design scheme. The set of optimization design parameters includes optimization color parameters, optimization shape parameters, optimization rhythm spacing parameters, optimization spatial hierarchy parameters, and optimization vegetation configuration parameters.

[0020] In this embodiment, the design of the preset high-altitude long straight-line simulation driving scenario includes importing road CAD design drawings into SILAB software, drawing the road centerline in segments according to the CAD drawings, designing road speed, number of lanes, and width of the central median, connecting each lane segment, setting the road vehicle traffic direction, and drawing road markings. According to the road design drawings, lane edge lines, carriageway boundaries, and central median indicators are added to the road network. Finally, according to the road design drawings, using station numbers as references, traffic signs and directional signs are added to the road network. The road network model mainly includes long straight road sections, windy and sandy (low visibility) road sections, and wetland speed-limited road sections.

[0021] Based on the road design drawings, the landscape on both sides of the road is set up, adding relevant trees, buildings, and grass. According to actual road environment data, the simulated road section is primarily composed of Gobi desert with minimal man-made landscape. The simulated road section is a highway, a two-way four-lane road with each lane 3.75 meters wide and a 3-meter-wide central median. The simulated road section is approximately 15km long. In the road model setup: tree models are placed on both sides of the road at approximately 5km and 10km to indicate the driver's position within the simulated road; near the end of the simulated road, a checkpoint with speed reduction signs is set up to remind the driver that the simulated road is about to end.

[0022] In addition, according to the requirements of the simulation experiment, vehicles such as trucks and cars that are driving normally are set on the road network, and the behavior of the vehicles is set to simulate real driving conditions. The simulated vehicles are large trucks, and the speed limit for large trucks on highways is 80~100km / h, and they drive in the rightmost lane.

[0023] In the daytime simulated road section, oncoming traffic, primarily large trucks, is included, with a speed of 100 km / h. In the nighttime simulated road section, no other vehicles are included. The nighttime environment is set so that the time gradually changes from daytime to nighttime after the driver has driven approximately 200 meters in the simulated road section. The remaining road sections are all nighttime driving sections, with the ambient time set at 8:00 PM. Finally, a section of approximately 2000 meters is set up with heavy fog to reduce visibility in the simulated scenario, simulating a sandstorm area.

[0024] Data collected through instruments and equipment, along with observations of the subjects' driving behavior by researchers, includes eye-tracking data, ECG heart rate monitoring data, and hand data. Vehicle data acquisition primarily utilizes A-Lab software to monitor real-time data from the simulated driving vehicle. After the experiment, the data is calculated and compiled into a TXT format document. Eye data acquisition primarily uses the Dikablis Pro head-mounted eye tracker to record the subjects' eyes in both video and first-person perspective, recording data such as blink frequency, blink duration, pupil size, and gaze direction, and exporting the data as a TXT file. Hand data acquisition mainly involves observation of the subjects during simulated driving. Key data collected include the tightness of the grip on the steering wheel, the level of tension and sweating, and the speed of steering wheel rotation. Heart rate data acquisition primarily uses an ECG heart rate monitor to monitor the subjects' heart rate in real-time, and the heart rate data is analyzed and output as a TXT file.

[0025] The collected vehicle operation data includes vehicle speed sequences and vehicle lateral offset distance sequences; driver physiological data includes blink frequency sequences, fixation duration sequences, pupil area change sequences, and steering wheel angle sequences.

[0026] The candidate set of color parameters in the design experience parameters includes the hue, saturation, and brightness range of the primary color, secondary color, and warning color; the candidate set of shape parameters includes linear, point-like, and cluster landscape shape types, and corresponding size and outline characteristic parameters; the candidate set of rhythm spacing parameters includes the minimum and maximum interval distances of landscape node changes; the candidate set of spatial hierarchy parameters includes the height gradient combination of vegetation or structures and the range of lateral distances from the roadside; and the candidate set of vegetation selection parameters includes local plant species and attributes that are ecologically adaptable to high-altitude Gobi desert road sections.

[0027] Key fatigue characteristic indicators include: vehicle speed, vehicle lateral deviation distance, blink frequency, fixation duration, pupil area, and steering wheel angle, and each indicator has been extracted separately for daytime and nighttime scenarios.

[0028] The influence weights in the key fatigue feature-design parameter correlation matrix were determined based on an ordered multi-class Logistic regression model. The model was constructed for daytime and nighttime scenarios, with key fatigue feature indicators as independent variables and driving fatigue state as the dependent variable.

[0029] In this embodiment, since the degree of driver fatigue (dependent variable) is an ordered multi-level variable, for example, it can be divided into four levels: "sober, mild fatigue, moderate fatigue, and severe fatigue," it cannot be simply combined into a binary classification problem for processing. Therefore, it is necessary to construct multiple cumulative probability models corresponding to the number of levels of the dependent variable.

[0030] Specifically, taking fatigue levels as divided into four levels (values ​​1, 2, 3, and 4, corresponding to probabilities P1, P2, P3, and P4 respectively) as an example, based on multiple key fatigue characteristic indicators collected from simulated driving scenarios (such as vehicle speed, lateral offset distance, blink frequency, etc., denoted as independent variables x1, x2, ..., x...),... n Three cumulative logistic regression models need to be fitted. These models represent the relationship between the probability that the fatigue level does not exceed a certain level and various influencing factors: The first model describes the relationship between the probability of being at level one fatigue (awake) and the independent variable: ; The second model describes the relationship between the cumulative probability of fatigue levels not exceeding level two (awake or mild fatigue) and the independent variables: ; The third model describes the relationship between the cumulative probability of fatigue levels not exceeding level three (awake, mild, or moderate fatigue) and the independent variables: ; Where α1, α2, and α3 are the intercept terms of each model, and β1, β2, ..., β n The regression coefficients of each independent variable (i.e., key fatigue characteristic indicators) reflect the magnitude and direction of the influence of each driving characteristic on the degree of fatigue.

[0031] By solving the above model, we can obtain the probability formula for calculating the driver's level of fatigue. For example, the probability of being at level one (awake) is: ; The probability of being in Level 2 (awake or mildly fatigued) is: ; The probability of being in level three (awake, mild or moderate fatigue) is: .

[0032] In this invention, the ordered multi-class Logistic regression model is the core theoretical foundation for constructing the "key fatigue feature-design parameter correlation matrix". The standardized regression coefficients (β) obtained after model fitting are... kstd This is used to quantify the importance of each fatigue characteristic index, and then through a preset mapping rule (assignment coefficient S) ij The influence weights w in the correlation matrix are calculated. ij This series of processes transforms objective physiological and behavioral data during driving into quantifiable, interpretable weight values ​​that are correlated with landscape design parameters, providing a data-driven basis for subsequent multi-objective optimization based on the mechanism of driving fatigue.

[0033] In this embodiment, the expression for the Logistic regression model is: , in, Driver fatigue level; This is a preset level reference value; The intercept of the Logistic Regression model is when all independent variables... When both are 0, the probability that the fatigue state does not exceed the baseline logarithm of level j; , where are regression coefficients, corresponding to vehicle speed, lateral deviation distance, blink frequency, fixation duration, pupil area, and steering wheel angle, respectively. The results are... and After estimating the parameters, we can obtain the specific case using the formula ( y=j The probability of this occurring is: .

[0034] Standardized regression coefficients of key fatigue characteristic indicators The influence weights are obtained by allocating the influence ratios of each fatigue characteristic, and the expression is as follows: , , in, Key fatigue characteristic indicators Standard deviation; Key fatigue characteristic indicators The regression coefficients, The standard deviation of the predicted Logistic values; Mapping parameters to preset design parameters, i.e., the first... i Class design parameters for mitigating the first j The contribution distribution ratio of each fatigue feature; For the first i Class design parameters for mitigating the first j The influence weight of each fatigue feature.

[0035] The expression for the fatigue resistance maximization function is: , Where n is the number of key fatigue characteristic indicators; m is the number of design parameters to be optimized; For the first i Class design parameters for mitigating the first j The influence weight of each fatigue feature; For the first Optimization candidate values ​​for each design parameter, This is a mapping function used to evaluate design parameters. The specific value of is the theoretical contribution of the parameter to alleviating the j-th fatigue feature relative to the baseline value; the optimization objective is to maximize the anti-fatigue effectiveness maximization function. The expression for the ecological and cost constraint satisfaction function is: , E represents the ecological adaptability score. Based on the candidate set of vegetation selection parameters, the plant species, combinations, and densities selected in the optimized vegetation configuration parameters are scored. Combinations that fully meet the local ecological requirements such as adaptability and windbreak and sand fixation score 1, while combinations that do not match at all score 0. The normalized relative cost coefficient is used to estimate the landscape construction and initial maintenance costs required using the optimized parameter set. The lowest cost feasible solution corresponds to a value of 0, and the highest cost solution corresponds to a value of 1. and These are the weighting coefficients for ecological and cost constraints, used to balance the importance of ecology and cost; the optimization objective is to ensure that the ecological and cost constraint satisfaction function is greater than a preset threshold. The expression for the visual rhythm rationality function is: , Where K represents the total number of landscape change nodes planned to be set on the optimized road section; This represents the location of the k-th landscape change node on the highway, i.e., its kilometer marker. This represents the actual distance between adjacent nodes; The recommended value for the optimal variation rhythm is determined based on the candidate set of rhythm and spacing parameters and the statistical conclusions of driver preferences collected. The tolerance parameter for allowed rhythm deviation is defined; the optimization objective is to maximize the visual rhythm rationality function. The solution is obtained by using a multi-objective evolutionary algorithm, which searches within the value space defined by the pre-defined design empirical parameters to obtain the Pareto optimal solution set.

[0036] In this embodiment, the key fatigue features extracted for daytime scene data are shown in Table 1.

[0037] Table 1 Key Statistical Indicators of Daytime Scene Model Results The relationship model between various independent variables and fatigue in the daytime scenario is as follows: , in, This represents the probability of fatigue in a daytime scene (Y=1). For vehicle speed, This represents the lateral offset distance of the vehicle. The frequency of blinking. For the duration of fixation, The pupil area, Steering wheel angle.

[0038] The resulting Logit function is: , The daytime scenario model showed that all independent variables were significant (P < 0.05), indicating a statistically significant impact on fatigue probability. The regression coefficients for driving speed, blink frequency, and steering wheel angle were all positive, indicating a positive correlation as the values ​​of these dependent variables gradually increased, leading to a higher probability of fatigue. The regression coefficients for vehicle lateral deviation, sustained fixation time, and pupil area were all negative, indicating a negative correlation as these values ​​gradually increased, leading to a lower probability of fatigue. Blink frequency had the greatest impact (coefficient = 1.10), while steering wheel angle had the least (coefficient = 0.28).

[0039] For nighttime scene data, a logistic regression model was used with Python to output the key statistical indicators, as shown in Table 2.

[0040] Table 2 Key Statistical Indicators of Night Scene Model Results The final relationship model between each independent variable and fatigue in nighttime scenarios is as follows: , in, Let Y be the probability of fatigue in a nighttime scene (Y=1). For vehicle speed, This represents the lateral offset distance of the vehicle. The frequency of blinking. For the duration of fixation, The pupil area, Steering wheel angle The resulting Logit function is: , The nighttime scene model showed that all independent variables were significant (P < 0.05), indicating a statistically significant impact on fatigue probability. The regression coefficients for driving speed, blink frequency, sustained fixation time, and steering wheel angle were all positive, indicating a positive correlation between these variables and the probability of fatigue. The regression coefficients for vehicle lateral deviation and pupil area were both negative, indicating a negative correlation between these variables and the probability of fatigue. Blink frequency had the greatest impact (coefficient = 1.20), while sustained fixation time had the least impact (coefficient = 0.33).

[0041] In summary, based on the analysis results of the model for day and night cycles and the paired t-test (significance level), α =0.05), and selected a set of key indicators that are significantly related to fatigue state: vehicle speed, vehicle lateral offset distance, blink frequency, fixation duration, pupil area, and steering wheel angle.

[0042] In this embodiment, statistical analysis of the feedback from subjects in a simulated driving scenario yielded several empirical parameter preference conclusions for guiding landscape design. These parameter preference conclusions reflect the general tendencies of the driver group regarding landscape design elements that alleviate driving fatigue, mainly including the following aspects: In terms of color design, participants generally felt that blue and green helped relieve visual fatigue and create a sense of relaxation, while gray easily caused fatigue, and red and black easily triggered tension or distraction. Therefore, in parametric design, a principle can be established to use blue and green as the main colors, red as the warning color, and to avoid using large areas of gray and black. At the same time, a strategy of alternating multiple colors can be adopted to combat visual monotony.

[0043] Regarding form and rhythm, participant feedback indicated that clustered and point-like landscapes were more attention-grabbing than linear landscapes. Furthermore, most participants noted that fatigue and a tendency to unconsciously increase speed were common when the landscape remained unchanged for approximately 5 to 15 minutes (equivalent to about 5-10 kilometers on a highway). This provides a basis for selecting the form type (prioritizing point-like and clustered landscapes) and setting the spacing between visually changing nodes (recommended 5-10 kilometers) in the design parameters.

[0044] In terms of space and hierarchy, about half of the respondents believed that a layered landscape helps to perceive whether a vehicle is deviating from its course, indicating that vertical layering design can serve as an effective design parameter to provide spatial reference and enhance trajectory stability.

[0045] The design preferences summarized from the group feedback are transformed into structured preset design experience parameters, including candidate sets of color parameters, candidate sets of shape parameters, candidate sets of spacing parameters, and candidate sets of spatial hierarchy parameters.

[0046] Applying the method of this embodiment to landscape design, for example: In terms of color parameters, blue and green were chosen as the primary colors, with red used as a warning color for special road sections, and gray and black avoided. A pattern of alternating colors was also specified. For design parameters, point-like and clustered landscape elements were selected as the main design nodes, and based on driver fatigue feedback, the spacing between these visual change nodes was set at 5 to 10 kilometers. In terms of spatial hierarchy, a gradient structure with a clear foreground, middle ground, and background was adopted, with a 2-meter lateral distance between the main vegetation belt and the edge of the roadway. In vegetation configuration, tamarisk and Potentilla fruticosa were selected as native plants suitable for high-altitude ecology and planted alternately, with a spacing controlled between 2.5 and 4 meters.

[0047] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the described module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0048] The electronic device of this invention includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in read-only memory (ROM) or loaded from a storage unit into random access memory (RAM). The RAM may also store various programs and data required for device operation. The CPU, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0049] Multiple components in the device are connected to an I / O interface, including: input units such as a keyboard, mouse, etc.; output units such as various types of displays, speakers, etc.; storage units such as disks, optical disks, etc.; and communication units such as network interface cards, modems, wireless transceivers, etc. The communication unit allows the device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks. The processing unit performs the various methods and processes described above, such as the method of the present invention. For example, in some embodiments, the method of the present invention may be implemented as a computer software program tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on the device via ROM and / or the communication unit. When the computer program is loaded into RAM and executed by the CPU, one or more steps of the method of the present invention described above may be performed. Alternatively, in other embodiments, the CPU may be configured to execute the method of the present invention by any other suitable means (e.g., by means of firmware).

[0050] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0051] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0052] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0053] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for optimizing the landscape design scheme of a long, straight highway at high altitude, characterized in that: The specific steps include: S1. Collect multi-source driving data, which includes vehicle operation data and driver physiological data collected in a preset high-altitude long straight-line simulation driving scenario, and the multi-source driving data is distinguished and preprocessed according to two environmental scenarios: daytime and nighttime. S2. Input the multi-source driving data into the key fatigue feature-design parameter correlation matrix to obtain the influence weight between key fatigue feature indicators and landscape design parameters; the design parameters include candidate sets of color parameters, candidate sets of shape parameters, candidate sets of rhythm spacing parameters, candidate sets of spatial hierarchy parameters, and candidate sets of vegetation selection parameters; S3. Construct and solve a multi-objective optimization model based on the influence weights. The objective functions of the multi-objective optimization model include the fatigue resistance efficiency maximization function, the ecological and cost constraint satisfaction function, and the visual rhythm rationality function. S4. Output the solution of the multi-objective optimization model as the set of optimized design parameters for the landscape design scheme. The set of optimized design parameters includes optimized color parameters, optimized shape parameters, optimized rhythm spacing parameters, optimized spatial hierarchy parameters, and optimized vegetation configuration parameters.

2. The method for optimizing the landscape design scheme of a long, straight highway at high altitude according to claim 1, characterized in that, The vehicle operation data includes vehicle speed sequence and vehicle lateral offset distance sequence; the driver physiological data includes blink frequency sequence, fixation duration sequence, pupil area change sequence and steering wheel angle sequence.

3. The method for optimizing the landscape design scheme of a long, straight highway at high altitude according to claim 1, characterized in that, The candidate set of color parameters in the design experience parameters includes the hue, saturation, and brightness range of the primary color, secondary color, and warning color; the candidate set of shape parameters includes linear, dotted, and clustered landscape shape types, and corresponding size and outline feature parameters; the candidate set of rhythm spacing parameters includes the minimum and maximum interval distances of landscape node changes; the candidate set of spatial hierarchy parameters includes the height gradient combination of vegetation or structures and the range of lateral distances from the roadside; and the candidate set of vegetation selection parameters includes local plant species and attributes that conform to the ecological adaptability of high-altitude Gobi road sections.

4. The method for optimizing the landscape design scheme of a long, straight highway at high altitude according to claim 1, characterized in that, The key fatigue characteristic indicators include: vehicle speed, vehicle lateral offset distance, blink frequency, fixation duration, pupil area, and steering wheel angle, and each indicator has been extracted separately for daytime and nighttime scenarios.

5. The method for optimizing the landscape design scheme of a long, straight highway at high altitude according to claim 1, characterized in that, The influence weights in the key fatigue feature-design parameter correlation matrix are determined based on an ordered multi-class Logistic regression model. The key fatigue feature indicators are used as independent variables, and driving fatigue state is used as the dependent variable. The matrix is ​​constructed for daytime and nighttime scenarios respectively.

6. The method for optimizing the landscape design scheme of a long, straight highway at high altitude according to claim 5, characterized in that, The expression for the Logistic regression model is: ， in, Driver fatigue level; This is a preset level reference value; The intercept of the Logistic Regression model is when all independent variables... When both are 0, the probability that the fatigue state does not exceed the baseline logarithm of level j; The regression coefficients correspond to vehicle speed, lateral offset distance, blink frequency, fixation duration, pupil area, and steering wheel angle, respectively.

7. The method for optimizing the landscape design scheme of a long, straight highway at high altitude according to claim 6, characterized in that, The standardized regression coefficients of key fatigue characteristic indicators The influence weights are obtained by allocating the influence ratios of each fatigue characteristic, and the expression is as follows: ， ， in, Key fatigue characteristic indicators Standard deviation; Key fatigue characteristic indicators The regression coefficients, The standard deviation of the predicted Logistic values; Mapping parameters to preset design parameters, i.e., the first... i Class design parameters for mitigating the first j The contribution distribution ratio of each fatigue feature; For the first i Class design parameters for mitigating the first j The influence weight of each fatigue feature.

8. The method for optimizing the landscape design scheme of a long, straight highway at high altitude according to claim 1, characterized in that, The expression for the fatigue resistance maximization function is: ， Where n is the number of key fatigue characteristic indicators; m is the number of design parameters to be optimized; For the first i Class design parameters for mitigating the first j The influence weight of each fatigue feature; For the first Optimization candidate values ​​for each design parameter This is a mapping function used to evaluate design parameters. The specific value of is the theoretical contribution of the parameter to alleviating the j-th fatigue feature relative to the baseline value; the optimization objective is to maximize the anti-fatigue effectiveness maximization function. The expression for the ecological and cost constraint satisfaction function is as follows: ， Where E is the ecological adaptability score. Based on the candidate set of vegetation selection parameters, the plant species, combinations and densities selected in the optimized vegetation configuration parameters are scored. Combinations that fully meet the local ecological requirements such as adaptability and windbreak and sand fixation are scored as 1, and combinations that do not match at all are scored as 0. The normalized relative cost coefficient is used to estimate the landscape construction and initial maintenance costs required using the optimized parameter set. The lowest cost feasible solution corresponds to a value of 0, and the highest cost solution corresponds to a value of 1. and These are the weighting coefficients for ecological and cost constraints, used to balance the importance of ecology and cost; the optimization objective is to ensure that the ecological and cost constraint satisfaction function is greater than a preset threshold. The expression for the visual rhythm rationality function is: ， Where K represents the total number of landscape change nodes planned to be set on the optimized road section; The location of the k-th landscape change node on the highway is represented by its kilometer marker. This represents the actual distance between adjacent nodes; The recommended value for the optimal variation rhythm is determined based on the candidate set of rhythm and spacing parameters and the statistical conclusions of driver preferences collected. The tolerance parameter for allowed rhythm deviation is defined; the optimization objective is to maximize the visual rhythm rationality function. The solution is obtained by using a multi-objective evolutionary algorithm, which searches within the value space defined by the preset design empirical parameters to obtain the Pareto optimal solution set.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 8.

Images