A highway intelligent traffic guidance system based on big data analysis

Abstract

The application discloses a highway intelligent traffic guidance system based on big data analysis and relates to the technical field of intelligent traffic, which comprises an information collection unit, an information storage unit, an information processing unit and a traffic guidance unit. The information collection unit is used for collecting road section traffic information of the highway; the information storage unit is used for storing the road section traffic information; the information processing unit is used for performing big data analysis on the road section traffic information, obtaining traffic congestion conditions of the highway, and generating traffic guidance information according to the traffic congestion conditions; the traffic guidance unit is connected with the information processing unit and is used for projecting the traffic congestion conditions and the traffic guidance information onto the road surface of the highway so as to induce drivers to drive vehicles according to the traffic guidance information. The application can effectively convey key traffic information to the drivers, induce the drivers to improve the traffic efficiency, and improve the management efficiency and safety of the highway.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, specifically a highway intelligent traffic guidance system based on big data analysis. Background Technology

[0002] To improve traffic efficiency and road safety on highways, drivers often need to stay informed about real-time traffic information, including congestion, accident information, and suggested routes, so they can make informed driving decisions, optimize their routes, reduce unnecessary delays, and improve overall traffic flow.

[0003] In related technologies, traffic information in highway traffic management systems is typically presented through large display screens located on the roadside. However, because drivers on highways need to focus primarily on the road conditions ahead, they often lack the energy to pay attention to and read the content on the roadside screens.

[0004] This limitation in attention allocation means that many drivers may overlook or miss traffic information displayed on large screens, such as road construction detours, accident warnings, or congestion alerts, thus failing to make timely driving adjustments. This not only affects drivers' understanding of real-time traffic conditions but also reduces road efficiency and may sometimes even increase the risk of traffic accidents. Summary of the Invention

[0005] The purpose of this invention is to provide a highway intelligent traffic guidance system based on big data analysis to solve the problems raised in the prior art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a highway intelligent traffic guidance system based on big data analysis, comprising an information collection unit, an information storage unit, an information processing unit, and a traffic guidance unit. The information collection unit collects highway segment traffic information, including vehicle density, vehicle speed, and traffic accident information. The information storage unit, connected to the information collection unit, stores the highway segment traffic information. The information processing unit, connected to the storage server, performs big data analysis on the highway segment traffic information to obtain highway traffic congestion conditions and generates traffic guidance information based on these conditions. The traffic congestion conditions include the current congestion status and a predicted congestion level for a future period. The traffic guidance unit, connected to the information processing unit, projects the traffic congestion status and traffic guidance information onto the highway surface to guide drivers to navigate according to the traffic guidance information.

[0007] This invention utilizes an integrated information acquisition unit to monitor key traffic parameters on highways in real time. It leverages big data analytics to process the massive amounts of collected data, accurately predicting traffic congestion and future trends. The information processing unit generates traffic guidance information, which is then projected directly onto the highway surface by a traffic guidance unit. This effectively conveys crucial traffic information to drivers, guiding them to improve traffic efficiency. This guidance method provides drivers with an intuitive and real-time navigation experience, significantly improving the visibility and readability of traffic information and reducing safety hazards caused by distracted viewing of roadside displays. The application of this embodiment allows drivers to promptly understand the traffic conditions ahead and adjust their routes in advance based on guidance information, effectively avoiding congestion and reducing driving decision errors caused by untimely information acquisition. This helps reduce the traffic accident rate and provides an intelligent and efficient solution for highway traffic management.

[0008] In some embodiments, the highway intelligent traffic guidance system based on big data analysis further includes an edge server connected to the traffic guidance unit. The traffic guidance unit generates traffic guidance images based on traffic congestion and traffic guidance information. The edge server is used to perform image enhancement processing on the traffic guidance images to obtain enhanced traffic guidance images. The traffic guidance unit is also used to project the enhanced traffic guidance images onto the road surface.

[0009] By integrating an edge server, the system can perform real-time image enhancement processing on traffic guidance images, improving their visibility and clarity under various environmental conditions. The introduction of the edge server significantly improves image processing efficiency because it processes data locally at the data source, reducing latency in data transmission to the central server. Thus, even with unstable network connections or limited bandwidth, the system can quickly respond to environmental changes and update traffic guidance images promptly, providing drivers with more accurate and reliable navigation information, thereby improving driving safety and road traffic efficiency.

[0010] In some embodiments, the highway intelligent traffic guidance system based on big data analysis further includes a photosensitive sensor for detecting the ambient brightness of the highway, and the traffic guidance unit is also used to adjust the projection brightness of the enhanced traffic guidance image according to the ambient brightness.

[0011] By employing the technical solution described in the above embodiments and introducing a photosensor to detect the ambient brightness of the highway, the system can more intelligently adjust the projection brightness of the traffic guidance image. This adaptive adjustment mechanism based on ambient brightness ensures that the traffic guidance image is displayed with appropriate brightness under different lighting conditions, avoiding excessive brightness or darkness that could affect the driver's vision and judgment. Especially in scenarios with significant light variations, such as at night or in tunnels, this intelligent adjustment can significantly improve the practicality and safety of the traffic guidance system, reducing traffic accidents caused by inappropriate brightness.

[0012] In some embodiments, the highway intelligent traffic guidance system based on big data analysis further includes a camera for capturing projected road surface images of a projection area on the highway. An edge server determines the road surface color of the projection area based on the projected road surface images and determines the projection adjustment brightness based on the ambient brightness and road surface color. The traffic guidance unit adjusts the projection brightness of the enhanced traffic guidance image based on the projection adjustment brightness.

[0013] By employing the technical solution described in the above embodiments and combining a camera and an edge server, the system can dynamically adjust the projection brightness based on real-time captured road surface images to adapt to different road surface colors and ambient brightness. This dual adjustment mechanism based on road surface color and ambient brightness ensures that traffic guidance images maintain optimal visibility under various road surface and lighting conditions. The edge server analyzes the road surface images, intelligently calculates the projection brightness adjustment, and adjusts the projection equipment in real time to ensure that traffic guidance information is clear and eye-catching, thereby improving drivers' perception of road conditions, reducing visual interference caused by changes in road surface color or lighting, and improving driving safety.

[0014] In some embodiments, the edge server calculates the adjusted projection brightness according to the projection brightness adjustment formula, which is:

[0015]

[0016] Among them, B proj To adjust the brightness of the projector, B base The reference projected brightness is α, where α is the weighting coefficient and F is the reference projected brightness. road F is the road surface color adjustment factor corresponding to the road surface color. env is the ambient brightness adjustment factor corresponding to the ambient brightness, and k3 is the third adjustment coefficient.

[0017] By adopting the technical solution of the above embodiments and introducing a projection brightness adjustment formula that comprehensively considers road surface color and ambient brightness, the system can more accurately calculate the appropriate projection brightness. The weighting coefficient α balances the influence of road surface color and ambient brightness, making the adjustment of projection brightness more flexible and reasonable. The third adjustment coefficient k3 further enhances the sensitivity of brightness adjustment, enabling the system to finely adjust the brightness according to actual environmental conditions to achieve the best visual effect. This refined brightness control mechanism significantly improves the visibility of traffic guidance images, increases the driver's recognition rate of traffic information, and thus enhances the practicality and safety of the system.

[0018] In some embodiments, the edge server determines the ambient brightness adjustment factor according to an ambient brightness adjustment formula, which is:

[0019] Among them, L env L represents the ambient light level. ref For reference to ambient brightness, k1 is the first adjustment factor, and e is the natural constant.

[0020] By employing the technical solution described in the above embodiments, and through an ambient brightness adjustment formula, the system can more accurately adjust the brightness of traffic guidance images according to changes in ambient brightness. The Sigmoid function maps the ambient brightness to a continuous value range, resulting in smoother and more natural brightness adjustment. The first adjustment coefficient k1 controls the steepness of the curve and can be adjusted according to actual needs to achieve optimal brightness response. This adaptive brightness adjustment mechanism based on ambient brightness significantly improves the visibility of traffic guidance images under different lighting conditions, reduces safety hazards caused by improper brightness, and enhances the practicality and safety of the system.

[0021] In some embodiments, the edge server determines the road surface color adjustment factor according to a road surface color adjustment formula, which is:

[0022] Among them, L road L represents the brightness of the road surface color. max k2 represents the maximum road surface color brightness, and k2 is the second adjustment factor.

[0023] By employing the technical solution described in the above embodiments, and through a road surface color adjustment formula, the system can more accurately adjust the brightness of the traffic guidance image based on changes in road surface color. A simple power function maps the road surface color brightness to a continuous value range, making brightness adjustment more intuitive and flexible. The second adjustment coefficient k2 can be adjusted according to actual needs to achieve optimal brightness response. This road surface color-based adaptive brightness adjustment mechanism significantly improves the visibility of the traffic guidance image under different road surface conditions, reduces visual interference caused by changes in road surface color, and enhances the system's practicality and safety.

[0024] In some embodiments, the highway intelligent traffic guidance system based on big data analysis further includes a distance sensor for measuring the distance between the traffic guidance unit and vehicles on the highway. When the traffic flow on the highway is less than a preset threshold, the traffic guidance unit pauses projection when the distance is less than a set distance threshold; when the traffic flow on the highway is not less than the preset threshold, the traffic guidance unit reduces the reference projection brightness by a value B. base When traffic volume drops below a preset threshold, the reference projection brightness value B is adjusted. base reduction;

[0025] The preset threshold is determined through the following steps:

[0026] The system acquires traffic flow information and vehicle spacing information on the highway. Vehicle spacing refers to the distance between two adjacent vehicles passing through a traffic guidance unit. The system obtains the time it takes for two adjacent vehicles to pass through the traffic guidance unit, calculating the time difference dt. It also obtains the speed v of the vehicle that passes the traffic guidance unit later in the sequence, calculating the distance x between the two adjacent vehicles, x = v × dt. Within a fixed time period T, the system acquires the average traffic flow information al and the average distance information ax between two adjacent vehicles passing through the traffic guidance unit, adding al and ax as a set of data to the dataset. The measurement is repeated over a translation period T to obtain the dataset. A relationship is established between the average traffic flow information and the average distance information. Using the average traffic flow information as input, the system regresses the output average distance information to train a regression model for the average distance information. Based on the regression model for the average distance information, the system obtains the input to the average distance information regression model when the output is a preset distance threshold.

[0027] By employing the technical solution described in the above embodiments and introducing a distance sensor to measure the distance between the traffic guidance unit and the vehicle in real time, the system can more intelligently control the projection behavior. When a vehicle is too close, the system automatically pauses the projection to avoid overly bright images interfering with or causing glare to the driver's vision. This intelligent control strategy based on real-time distance measurement significantly improves the system's safety and reliability, reducing visual discomfort or accident risks caused by projected images. Simultaneously, this dynamic projection control mechanism also enhances the system's flexibility, enabling it to adapt to different traffic conditions and vehicle densities, optimize traffic flow, and improve road utilization efficiency.

[0028] In some embodiments, the traffic guidance unit further includes a gantry, a display screen, and a projection device, with the gantry positioned above the road surface of the highway and the display screen and projection device both mounted on the gantry.

[0029] By integrating the traffic guidance unit onto the gantry, the system can provide real-time traffic guidance information above the highway surface. This integrated design makes the traffic guidance unit more robust and reliable, while reducing its footprint on the road surface. The display screen and projection equipment are both mounted on the gantry, making the display of traffic guidance information more intuitive and eye-catching, improving drivers' perception of road conditions. This innovative traffic guidance method significantly enhances the system's practicality and safety, providing drivers with clearer and more accurate navigation guidance, optimizing traffic flow, and improving road efficiency.

[0030] In some embodiments, the highway intelligent traffic guidance system based on big data analysis further includes contour warning lights, which are installed along both sides of the highway, and the information processing unit controls the contour warning lights to emit warning lights according to the road segment traffic information.

[0031] By employing the technical solution described in the above embodiments, and by installing contour warning lights on both sides of the highway, and using an information processing unit to control the warning lights based on road traffic information, the system can provide drivers with more comprehensive and intuitive road condition information. The contour warning lights can clearly mark the boundaries and contours of the road at night or in low visibility conditions, reminding drivers to pay attention to driving safety. Simultaneously, by dynamically adjusting the warning mode of the contour warning lights according to real-time traffic information, such as flashing or color changing, potential traffic risks and warning information can be promptly conveyed to drivers. This proactive warning mechanism significantly improves the safety and reliability of the system, reduces traffic accidents, and improves road traffic efficiency.

[0032] Compared with the prior art, the beneficial effects of the present invention are:

[0033] Intelligent Traffic Management and Enhanced Driving Safety: This invention integrates information collection, storage, processing, and traffic guidance units to achieve real-time monitoring and analysis of highway traffic flow. The system collects information on vehicle density, speed, and traffic accidents, which is then analyzed using big data to generate accurate traffic congestion information and predictions. This information is then projected visually onto the road surface via the traffic guidance unit. This intelligent traffic guidance method significantly improves driving safety, reduces accidents caused by traffic congestion, optimizes traffic flow, and increases road utilization efficiency.

[0034] Dynamic environmental adaptability and improved visibility: The system dynamically adjusts the brightness of traffic guidance images through edge servers and photosensors. The edge server calculates the optimal projection brightness based on road surface color and ambient brightness using advanced image processing algorithms, ensuring that traffic guidance images are clearly displayed with appropriate brightness under different lighting and road surface conditions. This dynamic environmental adaptability significantly improves image visibility, reduces the visual burden on drivers in complex lighting conditions, and enhances driving comfort and safety.

[0035] Enhanced Real-Time Interaction and Proactive Warning Capabilities: The system not only adjusts its guidance strategy based on real-time traffic information but also achieves real-time interaction and proactive warnings with vehicles through devices such as distance sensors and contour warning lights. When a vehicle gets too close to the traffic guidance unit, the system automatically pauses projection to avoid glare for the driver; the contour warning lights then issue warning signals when necessary to alert the driver to potential risks. This proactive warning mechanism significantly improves the system's interactivity, providing drivers with timely road condition feedback and effectively preventing traffic accidents. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of the unit connection of a highway intelligent traffic guidance system based on big data analysis according to the present invention. Detailed Implementation

[0037] 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 embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] Example: Figure 1 As shown, the present invention provides a technical solution: a highway intelligent traffic guidance system based on big data analysis, comprising an information collection unit, an information storage unit, an information processing unit, and a traffic guidance unit.

[0039] The information acquisition unit is used to collect traffic information for highway segments, including vehicle density, vehicle speed, and traffic accident information. Specifically, the information acquisition unit uses sensors and monitoring equipment deployed at key locations along the highway to capture real-time traffic information such as vehicle density, speed, and traffic accidents. The information acquisition unit can include various sensors or monitoring equipment, such as geomagnetic sensors, video cameras, radar detectors, infrared sensors, microwave sensors, and on-board diagnostic (OBD) data receivers, to comprehensively collect highway segment traffic information. This traffic information is crucial for understanding the dynamic changes in traffic flow, identifying congestion points, and preventing potential accidents. By accurately measuring traffic density, the system can determine whether a segment is overly congested; by monitoring vehicle speed, it can identify areas where speeds are slowing down or stagnating; and by collecting traffic accident information in real time, it helps to respond quickly and take measures to avoid secondary accidents and further traffic delays. This data provides a solid foundation for subsequent traffic analysis and the development of guidance strategies.

[0040] The information storage unit is connected to the information acquisition unit and is used to store road segment traffic information. The information acquisition unit transmits the road segment traffic information to the information storage unit via a high-speed network. The information storage unit stores the information in a structured format in a high-performance database system, enabling the information processing unit 3 to quickly access and analyze it. To ensure data security and reliability, the information storage unit can also employ redundant backup and encryption technologies to prevent data loss or unauthorized access. Furthermore, the information storage unit is designed with data archiving and cleaning mechanisms to optimize storage space utilization and support long-term historical data analysis. In this way, the system can provide detailed data support for traffic guidance decisions, thereby achieving more precise traffic management and services.

[0041] The information processing unit connects to the storage server to perform big data analysis on road segment traffic information, obtaining highway traffic congestion data and generating traffic guidance information based on this data. The traffic congestion data includes the current congestion situation and congestion predictions for a future period. Specifically, the information processing unit first receives a large amount of real-time road segment traffic information and historical traffic data collected by the information acquisition unit from the information storage unit, including vehicle density, driving speed, and traffic accident records. Then, it uses data preprocessing techniques to clean and organize this data to improve the accuracy of the analysis. Next, it applies machine learning algorithms, such as cluster analysis to identify traffic patterns, association rule mining to discover relationships between different traffic variables, and time series analysis to predict changes in traffic flow. Furthermore, it combines geographic information system (GIS) analysis to assess the traffic conditions of different road segments. By combining these analytical results, the information processing unit can accurately determine the current traffic congestion situation on various road segments of the highway, including the location, severity, and possible causes of congestion, thus providing a scientific basis for traffic guidance. This process leverages big data analytics to transform massive amounts of data into valuable traffic information, providing data support for traffic management decisions. Next, the information processing unit employs data preprocessing techniques, such as data cleaning and normalization, to ensure data quality and consistency. Then, machine learning algorithms, such as Support Vector Machines (SVM) and Random Forests, are used to classify and regress traffic data, thereby identifying congestion patterns and trends. Furthermore, time series analysis, such as Autoregressive Moving Average (ARMA) models, and deep learning methods, such as Recurrent Neural Networks (RNNs) and Long Short-Term Memory Networks (LSTMs), can be used to predict traffic flow and congestion over a future period. By fusing these analytical results and applying shortest path algorithms and network flow optimization techniques from graph theory, the information processing unit can generate dynamic traffic guidance information, such as suggested routes, speed adjustments, and accident avoidance measures, to guide drivers to take optimal actions, reduce congestion, and improve driving safety and efficiency. The integrated application of these algorithms and technologies enables the system to extract valuable information from complex traffic data and generate effective traffic guidance strategies.

[0042] The traffic guidance unit, connected to the information processing unit, projects traffic congestion information and traffic guidance information onto the highway surface to guide drivers. The traffic guidance unit includes laser or LED projection equipment that projects high-brightness, high-contrast images of traffic congestion and traffic guidance information directly onto the highway surface. In some embodiments, these projection devices can be mounted on a highway gantry or other fixed structure, dynamically adjusting the projection angle and focal length based on vehicle speed and position to ensure the information is clearly visible at an appropriate distance in front of the vehicle. The projected content includes simplified graphics, arrows, text, or symbols, intuitively instructing drivers on actions such as slowing down, changing lanes, or taking an alternate route. In this way, drivers can obtain crucial traffic information while keeping their eyes forward and make driving decisions based on this guidance, effectively guiding traffic flow, alleviating traffic congestion, and improving road safety.

[0043] This embodiment employs the aforementioned system, which uses an integrated information acquisition unit to monitor key traffic parameters of the highway in real time. Big data analytics is used to process the massive amounts of collected data in depth, accurately predicting traffic congestion and future trends. The traffic guidance information generated by the information processing unit is projected directly onto the highway surface by the traffic guidance unit, effectively conveying key traffic information to drivers and guiding them to improve traffic efficiency. This guidance method provides drivers with an intuitive and real-time navigation experience, greatly improving the visibility and readability of traffic information and reducing safety hazards caused by distraction from roadside displays. The application of this embodiment allows drivers to understand the traffic conditions ahead in a timely manner and make route adjustments in advance based on guidance information, effectively avoiding congestion, reducing driving decision errors caused by untimely information acquisition, and helping to reduce the traffic accident rate. It provides an intelligent and efficient solution for highway traffic management.

[0044] The following example illustrates the application process of this embodiment:

[0045] Suppose that on a busy section of a highway connecting point A and point B, traffic volume surges during the morning rush hour. The information acquisition unit of this embodiment's system, including geomagnetic sensors, video cameras, and radar detectors distributed along the road section, begins to monitor and collect traffic data in real time. This data includes vehicle density, speed, and information on any traffic accidents that could cause delays, and is then transmitted to the information storage unit via a high-speed network.

[0046] The information storage unit stores this data in a high-capacity database while ensuring data security and accessibility. Subsequently, the information processing unit employs big data analytics, including machine learning and pattern recognition algorithms, to conduct in-depth analysis of the collected data. It not only assesses current traffic conditions but also predicts traffic trends over a future period, identifying impending congestion.

[0047] Based on these analyses, the information processing unit generates dynamic traffic guidance information, including suggested alternative routes, estimated travel time, and speed adjustment suggestions, such as "congestion ahead 2 km" or "advance via the next intersection." This information aims to guide drivers to take optimal action to reduce congestion and improve driving safety and efficiency.

[0048] The traffic guidance unit then projects this traffic guidance information onto the road surface in real time as a high-brightness, high-contrast image, ensuring clear visibility under various lighting and weather conditions. This allows drivers to observe the traffic guidance information even while traveling at high speeds, enabling them to adjust their routes in advance, effectively avoid congestion, and reduce travel delays.

[0049] At the same time, traffic management departments can also deploy emergency response resources, such as traffic control personnel and rescue vehicles, more effectively based on the data and suggestions provided by the system, in order to quickly handle traffic accidents and alleviate congestion.

[0050] Through this integrated information collection, processing, and guidance process, the system in this embodiment can provide an intelligent and efficient solution for highway traffic management, significantly improving traffic efficiency, reducing congestion, enhancing road safety, and providing drivers with a safer and smoother driving environment.

[0051] In some embodiments, the system further includes an edge server connected to the traffic guidance unit. The traffic guidance unit generates a traffic guidance image based on traffic congestion and traffic guidance information. The edge server performs image enhancement processing on the traffic guidance image to obtain an enhanced traffic guidance image. The traffic guidance unit projects the enhanced traffic guidance image onto the road surface.

[0052] An edge server is a server deployed at the network edge, close to the data source or user location. Its main function is to reduce data latency during transmission and improve data processing speed and efficiency. Unlike traditional centralized data centers, edge servers can process real-time data from IoT devices, vehicles, or users, perform necessary computational and analytical tasks, and then quickly feed the results back to the requester. This not only reduces the burden on data centers (information processing units) but also provides a low-latency service experience for applications requiring rapid response, such as intelligent transportation systems, video streaming, and online games. Edge servers are typically equipped with high-performance processors and sufficient storage capacity, enabling them to perform complex data analysis and machine learning tasks. They also feature modularity and scalability to adapt to ever-changing computing needs.

[0053] In this embodiment, the application of an edge server can improve the processing efficiency and quality of traffic guidance images. The edge server is directly connected to the traffic guidance unit and undertakes the crucial task of enhancing the generated traffic guidance images. After the traffic guidance unit generates preliminary traffic guidance images based on traffic congestion information and traffic guidance information provided by the information processing unit, these images are transmitted to the edge server in real time. The edge server uses advanced image processing algorithms, such as contrast enhancement, edge sharpening, and noise suppression, to optimize the traffic guidance images, thereby improving their visibility and clarity under various lighting and weather conditions.

[0054] The enhanced traffic guidance images, or augmented traffic guidance images, are sent back to the traffic guidance unit. The traffic guidance unit then precisely projects these enhanced images onto the highway surface in a high-brightness, high-contrast format. This allows drivers to clearly see traffic guidance information under various environmental conditions, enabling them to make timely and correct driving decisions and effectively improve driving safety and traffic efficiency.

[0055] The introduction of edge servers enables the system in this embodiment to process data near the source of the data, greatly reducing the latency of data transmission and processing, and improving the system's response speed and reliability.

[0056] In some embodiments, the system further includes a photosensor for detecting the ambient brightness of the highway, and the traffic guidance unit adjusts the projection brightness of the enhanced traffic guidance image according to the ambient brightness.

[0057] The system in this embodiment integrates photosensors that can be placed near highways to monitor the ambient brightness on the highway in real time, including the light intensity generated by natural light sources (such as sunlight) and artificial light sources (such as streetlights). The photosensors transmit the detected brightness data to the traffic guidance unit, which intelligently adjusts and enhances the projection brightness of the traffic guidance image based on the received ambient brightness information.

[0058] Specifically, when ambient light is high, such as during the day or under strong sunlight, the traffic guidance unit automatically increases the projection brightness to ensure the image's visibility on the road surface. Conversely, when ambient light is low, such as at dusk or at night, the traffic guidance unit appropriately reduces the projection brightness to avoid glare or discomfort to drivers caused by overly bright images. Through this intelligent adjustment, the system can maintain the clarity and readability of traffic guidance images under different lighting conditions, thereby improving drivers' recognition rate of traffic guidance information and enhancing driving safety.

[0059] In some embodiments, the system further includes a camera for capturing projected road surface images of the projection area on the highway. An edge server determines the road surface color of the projection area based on the projected road surface images and determines the projection adjustment brightness based on the ambient brightness and the road surface color. A traffic guidance unit adjusts the projection brightness of the enhanced traffic guidance image based on the projection adjustment brightness.

[0060] Specifically, the camera captures real-time images of the road surface in the projection area. These images are then transmitted to an edge server, where image processing software analyzes the texture and color of the road surface to determine its current color characteristics. The edge server receives ambient brightness data from the traffic guidance unit and further uses a pre-defined algorithm, considering the impact of road surface color on light reflection, to precisely calculate the optimal projection brightness. This brightness adjustment strategy aims to ensure that traffic guidance images are projected onto the road surface with appropriate brightness under different road surface colors and lighting conditions, thereby improving visibility and recognizability.

[0061] Subsequently, the traffic guidance unit adjusts the brightness of the projection based on the projection calculated by the edge server, dynamically adjusting the projection intensity of the enhanced traffic guidance image to ensure that drivers can clearly see the traffic guidance information under various environmental conditions, thereby optimizing driving decisions and improving road safety and traffic efficiency.

[0062] In some embodiments, the edge server calculates the adjusted projection brightness according to a projection brightness adjustment formula, which includes:

[0063]

[0064] Among them, B projAdjusting the brightness of the projector indicates the projector brightness after adjustment based on environmental conditions;

[0065] B base This serves as the baseline projection brightness, used to ensure image visibility under standard conditions;

[0066] α is a weighting coefficient used to balance the influence of road surface color and ambient brightness on the final projected brightness;

[0067] F road This is the road surface color adjustment factor corresponding to the road surface color, reflecting the influence of the road surface color depth on the visibility of the projected image; F env It is the ambient brightness adjustment factor corresponding to the ambient brightness, reflecting the influence of ambient brightness on the visibility of the projected image;

[0068] k3 is the third adjustment factor used to control the sensitivity of brightness adjustment. It can be obtained through experimentation and optimization. It is determined based on field tests, simulation experiments, or expert experience to ensure that the projection brightness adjustment can adapt to different environmental conditions and achieve the best visibility effect.

[0069] The edge server uses a projection brightness adjustment formula to intelligently and dynamically adjust the projection brightness of traffic guidance images based on real-time ambient brightness and road surface color data. This ensures that drivers can clearly see the projected traffic information under different lighting and road surface conditions, thereby improving driving safety and road traffic efficiency.

[0070] In this embodiment, the edge server is used to determine the ambient brightness adjustment factor according to the ambient brightness adjustment formula. The ambient brightness adjustment factor formula is as follows:

[0071] Among them, L env Ambient brightness is the ambient brightness measured in real time by a photosensor; L ref The reference ambient brightness is the preset reference ambient brightness, which represents the ambient brightness under standard conditions; k1 is the first adjustment coefficient, used to control the curve shape and sensitivity of the formula, which can be obtained through experiments and optimization, and is determined based on field tests, simulation experiments or expert experience; e is the natural constant, which serves as the base in the formula, ensuring that the value of Fenv varies between 0 and 1, thereby enabling intelligent adjustment of the projection brightness according to the actual ambient brightness.

[0072] By using the ambient brightness adjustment formula, the edge server can dynamically calculate the corresponding ambient brightness adjustment factor based on the real-time changes in ambient brightness, and then adjust the projection brightness of the traffic guidance image to ensure that drivers can clearly see the traffic guidance information on the road surface under different lighting conditions.

[0073] In this embodiment, the edge server determines the road surface color adjustment factor according to the road surface color adjustment formula. The road surface color adjustment factor formula is as follows:

[0074] Among them, L road The brightness representing the road surface color is the brightness value of the road surface color collected in real time by a camera or optical sensor, reflecting the current optical reflectivity of the road surface; L max k1 represents the maximum road surface color brightness, which is the maximum possible road surface color brightness preset by the system based on historical data and environmental conditions. It represents the brightest level that the road surface may reach under specific lighting conditions. k2 is the second adjustment coefficient, which is used to adjust the sensitivity of brightness adjustment according to actual needs.

[0075] Through this road surface color adjustment formula, the edge server can dynamically calculate the corresponding road surface color adjustment factor based on the real-time changes in road surface color, and then intelligently adjust the projection brightness of the traffic guidance image to ensure that drivers can clearly see the traffic guidance information on the road surface under different road surface color conditions, thereby improving driving safety.

[0076] In some embodiments, the system further includes a distance sensor for measuring the distance between the traffic guidance unit and vehicles on the highway. When the traffic flow on the highway is less than a preset threshold, the traffic guidance unit is used to pause projection when the distance is less than a set distance threshold. When the traffic flow on the highway is not less than the preset threshold, the traffic guidance unit reduces the value of the reference projection brightness Bbase. When the traffic flow drops below the preset threshold, the value of the reference projection brightness Bbase is restored.

[0077] The preset threshold is determined through the following steps:

[0078] The system acquires traffic flow information and vehicle spacing information on the highway. Vehicle spacing refers to the distance between two adjacent vehicles passing through a traffic guidance unit. The system obtains the time it takes for two adjacent vehicles to pass through the traffic guidance unit, calculating the time difference dt. It also obtains the speed v of the vehicle that passes the traffic guidance unit later in the sequence, calculating the distance x between the two adjacent vehicles, x = v × dt. Within a fixed time period T, the system acquires the average traffic flow information al and the average distance information ax between two adjacent vehicles passing through the traffic guidance unit, adding al and ax as a set of data to the dataset. The measurement is repeated over a translation period T to obtain the dataset. A relationship is established between the average traffic flow information and the average distance information. Using the average traffic flow information as input, the system regresses the output average distance information to train a regression model for the average distance information. Based on the regression model for the average distance information, the system obtains the input to the average distance information regression model when the output is a preset distance threshold.

[0079] Specifically, a distance sensor can be installed near and connected to the traffic guidance unit. The traffic guidance unit has built-in intelligent control logic. When the distance sensor detects that the distance between the vehicle and the traffic guidance unit is less than a preset safe distance, i.e., a distance threshold, the traffic guidance unit will pause projection to prevent the overly bright projected image from interfering with or glaring the driver's vision when the vehicle approaches the traffic guidance unit, thereby ensuring that it does not affect the driver's driving safety.

[0080] Once a vehicle has passed, the distance sensor detects that the distance has returned to a safe range, and the traffic guidance unit will automatically resume projection and continue to provide necessary traffic guidance information to subsequent vehicles.

[0081] This intelligent control strategy based on real-time distance measurement enables the traffic guidance unit to adapt to different traffic conditions and project flexibly, effectively improving the safety and reliability of the system.

[0082] On the other hand, when there are many vehicles on the road and the traffic flow is heavy, frequent pauses in the projection by the traffic guidance unit may affect the traffic guidance effect. Therefore, when the traffic flow exceeds a set threshold, the traffic guidance unit can reduce the projection brightness to a safe level to reduce interference with drivers while still providing visible traffic information.

[0083] Specifically, the edge server can obtain traffic flow information on the road segment through the information storage unit. When the traffic flow exceeds a preset threshold, the edge server analyzes the current ambient brightness data and road surface color information, and then uses the projection brightness adjustment formula mentioned earlier to calculate an optimal projection brightness that is both safe and does not interfere with the driver. The edge server sends this calculation result to the traffic guidance unit to adjust the brightness of the traffic guidance image, ensuring that even in heavy traffic, the projection information still has a certain degree of visibility, while not excessively affecting the driver's vision.

[0084] The adjusted image is then projected onto the road surface through the traffic guidance unit's projection equipment, providing drivers with necessary traffic guidance information. Simultaneously, the system continuously monitors changes in traffic conditions and dynamically adjusts the projection brightness based on real-time data to adapt to the ever-changing traffic environment and ensure maximum traffic guidance effectiveness.

[0085] When traffic is heavy, the projection brightness can be reduced to a safe level (sacrificing some projection visibility) to minimize driver interference while still providing visible traffic information. When traffic is heavy, the edge server can reduce the baseline projection brightness B in the formula. base The value of B is used to reduce the final calculated brightness value. base The value to be lowered can be determined through prior experiments.

[0086] For example, suppose during the evening rush hour, traffic flow on a highway increases sharply. The system detects through sensors that the traffic flow has exceeded a preset threshold. At this time, the ambient brightness is 200 lux, the road surface color brightness is 70 lux, and the maximum road surface color brightness is 100 lux. Based on the projection brightness adjustment formula... Among them, the reference projection brightness B base Set to 200 lumens, weighting coefficient α to 0.6, and adjustment coefficient k3 to 2.

[0087] The edge server first calculates the ambient brightness adjustment factor F. env and road surface color adjustment factor F road Then, based on these factors and a preset formula, the optimal projection brightness B is calculated. proj For example, if F env The calculated result is 0.8, Froad is 0.7, and after substituting into the formula, we get B. proj =200×(0.6×0.7+0.4×0.8) 2 =200×(0.42+0.32) 2 =200 × 0.74 2 ≈110 lumens.

[0088] Under normal circumstances, traffic information is projected with a brightness of 110 lumens. Drivers can observe the projected traffic information outside the spacing threshold. When the distance between the vehicle and the traffic guidance unit is less than the preset spacing threshold, the traffic guidance unit will pause the projection. However, due to the high traffic volume on highways during the evening rush hour, there are vehicles that are continuously present at the distance between the traffic guidance unit and the preset spacing threshold. At this time, the traffic guidance unit will remain in a paused projection state for a long time and will not be able to achieve the purpose of projecting traffic information.

[0089] Therefore, when the system detects through sensors that the traffic flow exceeds a preset threshold, it reduces the reference projection brightness B. base The projection brightness is set to 100, resulting in a calculated brightness of 55 lumens. The traffic guidance unit can then automatically adjust the projection brightness to a safe level of 55 lumens, ensuring the visibility of traffic guidance information while avoiding excessive interference with drivers, thus achieving effective traffic guidance even under high traffic conditions. When the evening rush hour ends and traffic volume decreases below the preset threshold, the baseline projection brightness B is adjusted again. base Up to 200.

[0090] In some embodiments, the traffic guidance unit includes a gantry, a display screen, and a projection device, with the gantry positioned above the road surface of the highway and the display screen and projection device both mounted on the gantry.

[0091] The traffic guidance unit is the core component of this system, consisting of a robust gantry, a high-resolution display screen, and advanced projection equipment. The gantry is securely mounted above the highway surface, providing a reliable support platform for the display screen and projection equipment.

[0092] The displays and projection equipment are cleverly mounted on the gantry to ensure that traffic guidance information is clearly displayed on the road surface or projected directly into the driver's field of vision as vehicles approach.

[0093] This design makes traffic information transmission more direct and efficient, while reducing the occupation of road space and improving the safety and reliability of information dissemination. Through this integrated traffic guidance unit, the system can provide drivers with real-time and accurate navigation guidance under various traffic and environmental conditions, thereby optimizing traffic flow and improving road utilization efficiency.

[0094] In some embodiments, the system further includes contour warning lights, which are arranged along both sides of the highway, and the information processing unit is also used to control the contour warning lights to emit warning lights according to the road traffic information.

[0095] This embodiment assists drivers in better identifying road boundaries by installing contour warning lights on both sides of the highway. These contour warning lights are installed at the edge of the highway and are designed to provide continuous light, helping drivers to see the road outline more clearly at night or in low visibility conditions.

[0096] The information processing unit not only analyzes road traffic information to generate traffic guidance information, but also monitors traffic conditions in real time. When congestion, accidents, or other situations requiring warning are detected, it automatically controls the outline warning lights to flash or change color to remind drivers to pay attention to the road conditions ahead, thereby allowing them to take safety measures such as slowing down, changing lanes, or taking detours in advance. This intelligent warning system significantly improves the level of proactive road safety and reduces the occurrence of traffic accidents.

[0097] This embodiment proposes a highway intelligent traffic guidance system based on big data analytics. It aims to achieve real-time monitoring, analysis, and optimized management of highway traffic flow through highly integrated intelligent hardware and advanced data processing algorithms. The system mainly consists of an information acquisition unit, an information storage unit, an information processing unit, a traffic guidance unit, and an edge server. These components work together to provide accurate traffic information and guide drivers to drive safely and efficiently.

[0098] The information acquisition unit is responsible for collecting key traffic parameters, such as vehicle density, speed, and traffic accident information, providing the system with raw data. This data is transmitted to the information storage unit, a high-capacity, high-reliability database to ensure data security and accessibility. The information processing unit then uses big data analytics to deeply process the stored traffic information, not only assessing current traffic conditions but also predicting future congestion trends, thereby generating targeted traffic guidance information.

[0099] The traffic guidance unit serves as the interface between the system and the driver. Based on information generated by the processing unit, it projects traffic congestion information and guidance details onto the road surface as images. To improve the visibility and readability of the information, the system also integrates an edge server to enhance the traffic guidance images and intelligently adjust the projection brightness according to ambient light and road surface color, ensuring that drivers can clearly see the traffic guidance information under various lighting and road surface conditions.

[0100] In addition, the system includes a photosensor and a camera to detect ambient brightness and road surface color, respectively, to further optimize the brightness and contrast of the projected image. The introduction of a distance sensor allows the system to dynamically adjust the projection based on vehicle distance, avoiding glare for the driver. The traffic guidance unit also includes a gantry, display screen, projection equipment, and contour warning lights to provide additional warnings and guidance when necessary.

[0101] Overall, this system significantly improves highway traffic management efficiency and road safety through intelligent data analysis and real-time traffic guidance. It not only alleviates traffic congestion and reduces travel delays, but also provides drivers with clear and accurate navigation information under adverse weather or complex lighting conditions, thereby reducing the accident rate. Furthermore, the system's real-time interaction and proactive warning capabilities further enhance driving safety, providing an innovative, efficient, and reliable solution for highway traffic management.

[0102] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A highway intelligent traffic guidance system based on big data analysis, characterized in that, The application relates to a traffic information collection and induction system. The system comprises an information collection unit, an information storage unit, an information processing unit and a traffic induction unit; the information collection unit is used for collecting road section traffic information of an expressway, wherein the road section traffic information of the expressway comprises road section vehicle density, vehicle driving speed and traffic accident information; the information storage unit is connected with the information collection unit and is used for storing the road section traffic information of the expressway; the information processing unit is connected with the information storage unit and is used for performing big data analysis on the road section traffic information of the expressway, obtaining traffic congestion conditions of the expressway, and generating traffic guidance information according to the traffic congestion conditions, wherein the traffic congestion conditions comprise current congestion conditions of a road section and congestion prediction conditions of a future time period; the traffic induction unit is connected with the information processing unit and is used for projecting the traffic congestion conditions of the expressway and the traffic guidance information onto a road surface of the expressway so as to induce drivers to drive vehicles according to the traffic guidance information. The system further comprises an edge server, the traffic induction unit generates traffic induction images according to the traffic congestion conditions of the expressway and the traffic guidance information, and the edge server is used for performing image enhancement processing on the traffic induction images to obtain enhanced traffic induction images, and the traffic induction unit is used for projecting the enhanced traffic induction images onto the road surface. The system further comprises a photosensitive sensor, the photosensitive sensor is used for detecting environmental brightness of the expressway, and the traffic induction unit adjusts projection brightness of the enhanced traffic induction images according to the environmental brightness. The system further comprises a camera, the camera is used for shooting a projection road surface image of a projection area on the expressway, the edge server determines road surface color of the projection area according to the projection road surface image, and determines projection adjustment brightness according to the environmental brightness and the road surface color, and the traffic induction unit is used for adjusting the projection brightness of the enhanced traffic induction images according to the projection adjustment brightness. The system further comprises a distance sensor, the distance sensor is used for measuring a distance between the traffic induction unit and a vehicle on the expressway, and the traffic induction unit is used for pausing projection when the distance is less than a set distance threshold value when vehicle flow on the expressway is less than a preset threshold value. When the traffic volume on the highway is not less than a preset threshold, the traffic guidance unit reduces the value B of the reference projection brightness base When the traffic volume is reduced below the preset threshold, the value B of the reference projection brightness is increased base restore; The preset threshold value is determined by the following steps: Vehicle flow information and vehicle distance information on the expressway are obtained; the vehicle distance is the distance between adjacent two vehicles passing through the traffic induction unit, the time when the adjacent two vehicles pass through the traffic induction unit is obtained, a time difference dt is obtained, the speed v of a rear vehicle in the adjacent two vehicles when the rear vehicle passes through the traffic induction unit is obtained, the distance x between the adjacent two vehicles is calculated as x=v*dt; average vehicle flow information al on the expressway and average distance information ax between the adjacent two vehicles passing through the traffic induction unit are obtained within a fixed time period T, al and ax are taken as a group of data and added into a data set; the measurement is repeatedly performed in a translation period T to obtain the data set. A relationship between average traffic flow information and average spacing information is established, and a regression model of the average spacing information is trained with the average traffic flow information as input and the average spacing information as output; According to the regression model of the average spacing information, when the output is the spacing threshold, the input of the average spacing information regression model is obtained, and the input at this time is the preset threshold.

2. The intelligent highway traffic induction system based on big data analysis according to claim 1, characterized in that, The edge server calculates the projection adjustment brightness according to a projection brightness adjustment formula, and the projection brightness adjustment formula is: ； Wherein, B proj is the projection adjustment brightness, B base is the reference projection brightness, and α is a weight coefficient, F road is the road surface color adjustment factor corresponding to the road surface color, F env is the environmental brightness adjustment factor corresponding to the environmental brightness, and k3 is a third adjustment coefficient.

3. The intelligent highway traffic induction system based on big data analysis according to claim 2, characterized in that, The edge server determines the environmental brightness adjustment factor according to an environmental brightness adjustment formula, and the environmental brightness adjustment factor is calculated by the following formula: ; wherein L env is the ambient luminance, L ref is a reference ambient luminance, k1 is a first adjustment coefficient, and e is a natural constant.

4. The intelligent highway traffic induction system based on big data analysis according to claim 3, characterized in that, The edge server determines the road surface color adjustment factor according to a road surface color adjustment formula, and the road surface color adjustment factor is calculated by the following formula: ; wherein L road represents the luminance of the road surface color, L max represents the maximum road surface color luminance, k2 is a second adjustment coefficient.

5. The intelligent highway traffic induction system based on big data analysis according to claim 1, wherein, The traffic guidance unit further comprises a gantry, a display screen and a projection device, the gantry is arranged above the road surface of the expressway, and the display screen and the projection device are arranged on the gantry.

6. The intelligent highway traffic induction system based on big data analysis according to claim 1, wherein, Further comprising a contour warning light, the contour warning light is arranged along the two sides of the expressway, and the information processing unit is further used for controlling the warning light of the contour warning light to emit warning light according to the road section traffic information.

Images