Vehicle driving control method and device for backlight scene, equipment and medium

Abstract

The invention provides a vehicle driving control method and device for a backlight scene, equipment and a medium. The method comprises the steps that multi-source information of a target vehicle is acquired in real time; performing fusion calculation on the multi-source information to obtain a current backlight risk index of the target vehicle; determining a driving assistance strategy or an automatic emergency braking strategy based on the backlight risk index; and controlling the target vehicle according to the driving assistance strategy or the automatic emergency braking strategy. According to the vehicle driving control scheme for the backlight scene, the backlight risk index is generated by fusing the multi-source information, the backlight scene is accurately judged, the corresponding driving assistance or automatic emergency braking strategy is formulated, the driving safety and reliability of the vehicle in the complex backlight environment are improved, and the driving safety of the vehicle in the complex backlight environment is improved. The problems that in the prior art, due to dependence on a single sensor in a backlight scene, the target recognition precision is low, a dynamic adaptation mechanism is lacked, and a braking strategy is difficult to pre-judge and adjust in advance are solved.

Description

Technical Field

[0001] The present application relates to the field of automobile safety technology, and in particular to a vehicle driving control method, device, electronic device, and storage medium for backlighting scenarios. Background Art

[0002] As the number of cars continues to rise, road safety is becoming increasingly severe. Automatic Emergency Braking (AEB), a key active safety technology, automatically applies the brakes when a collision is imminent, effectively reducing the probability and severity of collisions and playing a crucial role in ensuring driving safety. However, existing AEB systems have significant limitations in backlit scenarios, making it difficult to fully realize their intended safety capabilities.

[0003] Because backlighting scenarios are complex, when vehicles approach backlight-prone areas like tunnel exits and mountain roads, existing AEB systems often rely on a single sensor for environmental perception, such as a camera or radar. However, this single-sensor perception model presents significant issues in backlighting. For example, when the camera is exposed to direct strong sunlight, image quality degrades significantly, severely impacting target recognition accuracy and making it prone to misjudgments or missed detections. Furthermore, varying weather conditions, such as rain and fog, further exacerbate the backlighting effect. Existing AEB systems lack effective dynamic adaptation mechanisms, making it impossible to predict and adjust braking strategies in advance. This results in the AEB system's automatic braking function being unreliable in backlighting scenarios, making it difficult to meet safe driving requirements. Therefore, existing technologies suffer from low recognition accuracy and difficulty in predicting and adjusting braking strategies in backlighting scenarios.

[0004] The preceding description is intended to provide general background information and does not necessarily constitute prior art. Summary of the Invention

[0005] In response to the above technical problems, the present application provides a vehicle driving control method, device, equipment and medium for backlighting scenarios, which solves the technical problems of the existing technology in backlighting scenarios, such as low target recognition accuracy, lack of dynamic adaptation mechanism, and difficulty in predicting and adjusting braking strategies in advance due to reliance on a single sensor.

[0006] To solve the above technical problems, the present application provides a vehicle driving control method for backlighting scenes, comprising the following steps:

[0007] Obtain multi-source information of target vehicles in real time;

[0008] Performing a fusion calculation on the multi-source information to obtain a current backlight risk index of the target vehicle;

[0009] determining a driving assistance strategy or an automatic emergency braking strategy based on the backlight risk index;

[0010] The target vehicle is controlled according to the driving assistance strategy or the automatic emergency braking strategy.

[0011] Furthermore, in some embodiments of the present application, the real-time acquisition of multi-source information of the target vehicle includes:

[0012] Obtaining the real-time geographic location, vehicle travel direction and time information of the target vehicle through a positioning device;

[0013] Acquiring weather data of the target vehicle's current environment in real time through an on-board communication device, the weather data including light intensity, weather type, and visibility;

[0014] Real-time image data of the scene in front of the target vehicle is collected by a vehicle-mounted camera device.

[0015] Furthermore, in some embodiments of the present application, the fusing and calculating the multi-source information to obtain the current backlight risk index of the target vehicle includes:

[0016] Calculate the backlight probability of the corresponding vehicle position based on the real-time geographic location, vehicle travel direction and time information of the target vehicle;

[0017] Calculating the corresponding weather backlight probability based on the weather data of the target vehicle's current environment;

[0018] Calculating a corresponding image backlight probability based on real-time image data of a scene in front of the target vehicle;

[0019] The current backlight risk index of the target vehicle is determined according to the vehicle position backlight probability, the weather backlight probability and the image backlight probability through a dynamic weighted algorithm.

[0020] Furthermore, in some embodiments of the present application, the calculating of the corresponding vehicle position backlight probability based on the real-time geographic location, vehicle driving direction, and time information of the target vehicle includes:

[0021] Based on the real-time geographic location and the vehicle's travel direction, determining whether the target vehicle is at a tunnel exit;

[0022] If it is determined that the target vehicle is not at a tunnel exit, calculating the solar azimuth angle according to the real-time geographic location and the time information using a solar position calculation algorithm;

[0023] Determining a relative azimuth angle between the target vehicle and the sun based on the solar azimuth angle and the vehicle's travel direction;

[0024] The backlight probability of the vehicle position of the target vehicle is calculated according to the relative azimuth angle.

[0025] Furthermore, in some embodiments of the present application, the calculating of the corresponding image backlight probability based on the real-time image data of the scene in front of the target vehicle includes:

[0026] Extracting histogram information of the real-time image data, and calculating corresponding image skewness based on the histogram information;

[0027] Calculating a global contrast ratio corresponding to the real-time image data, and setting a weight coefficient corresponding to the global contrast ratio;

[0028] Calculating the probability of the image exposure time affecting the backlit scene based on the image exposure time, brightness gain, and calibration coefficient of the vehicle-mounted camera device;

[0029] An image backlight probability corresponding to the real-time image data is calculated based on the image skewness, the influence probability, the global contrast and the weight coefficient thereof.

[0030] Furthermore, in some embodiments of the present application, determining a driving assistance strategy or an automatic emergency braking strategy based on the backlight risk index includes:

[0031] If it is determined that the backlight risk index is greater than or equal to a preset first threshold, a first level warning strategy is generated;

[0032] If it is determined that the backlight risk index is greater than or equal to a preset second threshold, a second level warning strategy is generated;

[0033] If it is determined that the backlight risk index is greater than or equal to a preset third threshold, an automatic emergency braking strategy is generated.

[0034] Furthermore, in some embodiments of the present application, controlling the target vehicle according to the driving assistance strategy or the automatic emergency braking strategy includes:

[0035] Sending corresponding control signals to the braking system and / or warning system of the target vehicle according to the driving assistance strategy or the emergency braking strategy;

[0036] The braking system is controlled to perform a corresponding emergency braking operation according to the control signal, and / or the warning system is controlled to issue a warning message.

[0037] Accordingly, the present application provides a vehicle driving control device for backlighting scenarios, comprising:

[0038] Information acquisition module, used to obtain multi-source information of the target vehicle in real time;

[0039] An index calculation module, configured to perform fusion calculation on the multi-source information to obtain the current backlight risk index of the target vehicle;

[0040] a strategy determination module, configured to determine a driving assistance strategy or an automatic emergency braking strategy based on the backlight risk index;

[0041] A control module is used to control the target vehicle according to the driving assistance strategy or the automatic emergency braking strategy.

[0042] The present application also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the vehicle driving control method for backlighting scenes as described above are implemented.

[0043] The present application also provides a storage medium storing a computer program that can be loaded by a processor and execute the vehicle driving control method for backlighting scenes as described above.

[0044] The implementation of the embodiments of the present application has the following beneficial effects:

[0045] As described above, the present application provides a vehicle driving control method, device, equipment and medium for backlighting scenes. First, by collecting multi-source information in real time through multiple sensors, it can perceive the vehicle's driving environment more comprehensively and accurately, provide a richer data basis for subsequent backlighting scene judgment, effectively make up for the insufficient perception of a single sensor in backlighting scenes, and improve the accuracy and reliability of backlighting scene recognition; then, by fusing multi-source information to calculate the backlighting risk index, comprehensively considering the impact of multiple factors on the backlighting scene, making the judgment of the backlighting scene more accurate, and avoiding the errors that may be caused by the judgment of a single factor; then, according to the backlighting risk index, the corresponding driving assistance or automatic emergency braking strategy is determined to improve the reliability of the vehicle's active safety system in backlighting scenes; finally, by accurately controlling the vehicle according to the driving assistance strategy or automatic emergency braking strategy, it can ensure that the vehicle takes appropriate measures to deal with possible dangerous situations in backlighting scenes. It can be seen that the present application can improve the driving safety and reliability of vehicles in complex backlighting environments, reduce the risk of collision accidents, ensure the driving safety of users, and solve the problems of existing technologies in backlighting scenarios, such as low target recognition accuracy, lack of dynamic adaptation mechanism, and difficulty in predicting and adjusting braking strategies in advance due to reliance on a single sensor. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for describing the embodiments. Obviously, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without inventive work.

[0047] Figure 1 Schematic diagram of an application scenario of a vehicle driving control method for a backlighting scene provided by an embodiment of the present application;

[0048] Figure 2 1 is a flow chart of a vehicle driving control method for a backlit scene provided by an embodiment of the present application;

[0049] Figure 3 is a schematic diagram of a flow chart for calculating a backlight risk index according to an embodiment of the present application;

[0050] Figure 4 1 is a schematic structural diagram of a vehicle driving control device for backlighting scenarios provided by an embodiment of the present application;

[0051] Figure 5 It is a structural diagram of an electronic device provided in an embodiment of the present application.

[0052] The purpose of this application, its features, and advantages will be further described in conjunction with the embodiments and with reference to the accompanying drawings. The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and the accompanying text are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of this application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0053] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0054] It should be noted that, in this document, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0055] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0056] In the subsequent description, the use of suffixes such as "module", "component" or "unit" to represent elements is only for the purpose of facilitating the description of the present application and has no specific meaning. Therefore, "module", "component" or "unit" can be used interchangeably.

[0057] Existing AEB systems primarily rely on a single sensor (such as a camera or radar) for environmental perception, which presents significant limitations in backlit scenarios. Especially in backlit environments, cameras are susceptible to decreased target recognition accuracy due to strong direct sunlight, increasing the risk of misjudgment or missed detection. At the same time, different weather conditions (such as rainy or foggy days) can exacerbate the backlight effect, and traditional AEB systems lack dynamic adaptation mechanisms. Furthermore, when vehicles approach areas prone to backlight, such as tunnel exits or mountain roads, existing AEB systems struggle to predict and adjust braking strategies in advance, leading to vehicle collisions.

[0058] To solve the above technical problems, the present application provides a vehicle driving control method, device, equipment and medium for backlighting scenes.

[0059] The vehicle driving control device for backlight scenes can be specifically integrated into an electronic device, which can be a smart phone, tablet computer, laptop computer or desktop computer, but is not limited thereto. The electronic device can be directly or indirectly connected to the server through wired or wireless communication. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. This application does not impose any restrictions on this.

[0060] See also Figure 1 , Figure 1 FIG. 1 is an application environment diagram of a vehicle driving control method for a backlight scene in one embodiment. Figure 1 , the vehicle driving control method for backlighting scenes can be applied to the vehicle driving control system for backlighting scenes. Among them, the vehicle driving control system for backlighting scenes may include a terminal 110 and a server 120. The terminal 110 and the server 120 are connected via a network. The terminal 110 may be a desktop terminal or a mobile terminal. The mobile terminal may be at least one of a mobile phone, a tablet computer, a laptop computer, a car computer, etc. The server 120 may be implemented as an independent server or a server cluster composed of multiple servers. The terminal 110 is used to obtain multi-source information of the target vehicle in real time; perform fusion calculation on the multi-source information to obtain the current backlight risk index of the target vehicle; determine the driving assistance strategy or the automatic emergency braking strategy based on the backlight risk index; and control the target vehicle according to the driving assistance strategy or the automatic emergency braking strategy.

[0061] It should be noted that the order of description of the following embodiments does not limit the priority order of the embodiments.

[0062] The present application provides a vehicle driving control method for backlighting scenarios, comprising: acquiring multi-source information of a target vehicle in real time; fusing and calculating the multi-source information to obtain a current backlighting risk index of the target vehicle; determining a driving assistance strategy or an automatic emergency braking strategy based on the backlighting risk index; and controlling the target vehicle according to the driving assistance strategy or the automatic emergency braking strategy.

[0063] See also Figure 2 , Figure 2 The flowchart of the vehicle driving control method for backlighting scene provided by the embodiment of the present application is as follows. The vehicle driving control method for backlighting scene provided by the embodiment may specifically include the following steps:

[0064] S1. Acquire multi-source information of the target vehicle in real time;

[0065] Specifically, in step S1, multiple sensors are first used to collect multi-source information about the target vehicle in real time. This multi-source information may include the target vehicle's real-time geographic location, driving direction, time information, weather data, and real-time image data of the scene ahead. This step, through the real-time collection of multi-source information by multiple sensors, enables a more comprehensive and accurate perception of the vehicle's driving environment, providing a richer data foundation for subsequent backlit scene identification. This effectively compensates for the limited perception of a single sensor in backlit scenes and improves the accuracy and reliability of backlit scene recognition.

[0066] S2. Fusion calculation of multi-source information to obtain the current backlight risk index of the target vehicle;

[0067] Specifically, in step S2, the multi-source information acquired in step S1 is fused and the backlight risk index of the target vehicle at the current moment is calculated using a preset backlight risk index calculation method. The backlight risk index (IRI) serves as a quantitative indicator reflecting the severity of the vehicle's current backlighting scenario. For example, key features from each data source are extracted, and then a weighted fusion algorithm is used to assign corresponding weights to each feature based on its contribution to the backlight risk to calculate the backlight risk index.

[0068] In addition, before fusion calculation, preliminary data preprocessing is required for the acquired multi-source information, such as coordinate conversion and error correction for GPS data, format unification and unit conversion for weather data, noise filtering and feature enhancement for image data, etc., to improve data quality and availability.

[0069] This step achieves a comprehensive, multi-dimensional analysis of backlit scenes by comprehensively considering multi-source information, overcoming the problem of inaccurate judgment from a single information source and significantly improving the accuracy and reliability of backlit scene recognition. It converts complex backlit scene information into a concise and clear quantitative indicator, providing a scientific and intuitive basis for the subsequent formulation of driving assistance strategies and automatic emergency braking strategies.

[0070] S3. Determining a driving assistance strategy or an automatic emergency braking strategy based on the backlight risk index;

[0071] Specifically, in step S3, the calculated backlight risk index is compared with a preset threshold. The comparison results determine the subsequent decision logic and, consequently, the corresponding driver assistance strategy or automatic emergency braking strategy to guide the vehicle's subsequent driving behavior. This enables intelligent and dynamic adjustment of driver assistance and automatic emergency braking strategies, enabling appropriate measures to be taken based on varying backlight risk levels. This ensures timely and effective action in high-risk situations, reducing the probability and severity of collisions.

[0072] S4. controlling the target vehicle according to the driving assistance strategy or the automatic emergency braking strategy;

[0073] Specifically, in step S4, based on the driving assistance strategy or automatic emergency braking strategy determined in step S3, corresponding control signals are sent to the vehicle's braking system and / or warning system to implement specific control operations on the vehicle. For example, for the braking system, the braking pressure and braking force are precisely controlled based on the control signals to achieve smooth and effective emergency braking operations. For the warning system, corresponding warning devices are activated, such as instrument panel warning lights, sound prompts, and heads-up displays (HUDs), to remind the driver of backlit scenes and potential dangerous situations ahead in an intuitive and eye-catching manner. This achieves precise and efficient control of the vehicle, ensuring that the driving assistance strategy and automatic emergency braking strategy can be executed promptly and accurately.

[0074] Furthermore, in some embodiments, step S1 of “obtaining multi-source information of the target vehicle in real time” may specifically include:

[0075] S11 obtains the real-time geographic location, vehicle travel direction and time information of the target vehicle through the positioning device;

[0076] Specifically, the positioning device equipped on the vehicle, such as GPS, Beidou and other satellite positioning systems, is used to accurately obtain the latitude and longitude coordinates of the vehicle on the earth's surface and determine the vehicle's specific geographical location. At the same time, the vehicle's driving direction is obtained, which is usually expressed in an angle range of 0-360°, as well as the current time information, including time and date. In addition to basic positioning functions, the positioning device can also be combined with differential GPS technology to further improve positioning accuracy and reduce errors. For example, in urban canyon environments, differential GPS can effectively correct errors caused by satellite signal obstruction and reflection, bringing positioning accuracy to the centimeter level. In addition, the trajectory recording function of the positioning device can be used to analyze the vehicle's driving path and predict whether the road section to be entered contains tunnels, mountainous areas and other areas prone to backlighting.

[0077] S12. Real-time weather data of the target vehicle's current environment is obtained through the vehicle-mounted communication device. Weather data includes light intensity, weather type, and visibility.

[0078] Specifically, the on-board communication device communicates in real time with the data interface of the meteorological department or a third-party weather service provider to obtain weather data at the vehicle's location, including information such as light intensity, weather type (such as sunny, cloudy, rainy, foggy, etc.) and visibility. The on-board communication device can use 4G / 5G networks, satellite communications, etc. to ensure that weather data can be obtained stably in different regions and environments. In addition, the weather data can be locally verified and supplemented in combination with on-board sensors (such as rain sensors, light sensors, etc.). For example, when the weather data shows that it is sunny, but the on-board light sensor detects that the light intensity is weak, it may mean that the vehicle is in a local shadow area or is about to enter a special environment such as a tunnel.

[0079] S13. Real-time image data of the scene in front of the target vehicle is collected by the on-board camera;

[0080] Specifically, on-board cameras are typically installed behind the vehicle's windshield or at the front of the vehicle, facing the direction of travel, and capture real-time images of the road and scene ahead at a high frame rate and high resolution. These real-time images contain rich visual information that can be used for subsequent analysis of road conditions, traffic signs, other vehicles, pedestrians, etc. On-board cameras can use high dynamic range (HDR) cameras to better adapt to image acquisition under different lighting conditions. HDR technology can simultaneously capture details in both bright and dark areas of the same scene, reducing overexposure and underexposure and improving image quality. In addition, cameras can also have functions such as autofocus and anti-shake to ensure clear and stable images while the vehicle is driving. At the same time, image processing algorithms are used to analyze the captured images in real time to extract target features, such as the edges, shapes, and colors of vehicles and pedestrians, further improving the perception of the scene ahead.

[0081] This embodiment uses high-precision positioning and driving direction information acquisition by the positioning device, combined with real-time weather data from the on-board communication device and forward image acquisition by the on-board camera device, to enable the system to perceive the vehicle's driving environment from multiple dimensions. This not only improves the accuracy and reliability of backlit scene recognition, but also provides a reliable data basis for the formulation of subsequent driving assistance strategies and automatic emergency braking strategies.

[0082] Further, if Figure 3 As shown, in some embodiments, step S2 of "performing fusion calculation on multi-source information to obtain the current backlight risk index of the target vehicle" may specifically include:

[0083] S21. Based on the real-time geographic location of the target vehicle, the vehicle's direction of travel and time information, calculate the corresponding vehicle position backlight probability;

[0084] Specifically, the vehicle's real-time geographic location (latitude and longitude), driving direction (0-360°) and current time (date and moment) are used to calculate the sun's azimuth and altitude using a solar position calculation algorithm (such as the SPA algorithm). Then, based on the relative relationship between the vehicle's driving direction and the solar azimuth, it is determined whether the vehicle is in a backlight state. High-precision map data can also be combined to pre-mark areas prone to backlighting (such as tunnel exits, mountain road bends, etc.). When the vehicle approaches these areas, an early warning is issued and the calculation logic is adjusted. In addition, a machine learning algorithm can be introduced to continuously optimize the calculation model of the backlight probability based on historical data and real-time data.

[0085] S22. Calculate the corresponding weather backlight probability based on the weather data of the target vehicle's current environment;

[0086] Specifically, based on real-time weather data (such as light intensity, weather type, visibility, etc.), the propagation and scattering characteristics of light under different weather conditions are analyzed to establish a mapping relationship between weather and backlight risk. For example, on sunny days, direct sunlight may cause strong backlight; on rainy or foggy days, light scattering may form diffuse backlight. It is also possible to combine weather radar and satellite cloud image data to predict weather trends and adjust the calculation of weather backlight probability in advance. In addition, deep learning algorithms are introduced to train image data under different weather conditions to improve the prediction accuracy of weather backlight probability.

[0087] S23. Based on the real-time image data of the scene in front of the target vehicle, the corresponding image backlight probability is calculated;

[0088] Specifically, by analyzing real-time image data captured by the camera, characteristic parameters such as the image's histogram, skewness, contrast, exposure time, and brightness gain are extracted. Based on these parameters, the unevenness of light distribution in the image and the contrast between the target and the background are calculated, thereby determining whether the image is dimmed or details are lost due to backlighting. Convolutional neural networks (CNNs) can also be used to analyze images in real time to identify target objects (such as pedestrians and vehicles) and assess the impact of backlighting on their visibility. Furthermore, ambient light sensor data can be combined to further calibrate the calculation of the image's backlight probability.

[0089] S24. Determine the target vehicle's current backlight risk index based on the vehicle's position backlight probability, weather backlight probability, and image backlight probability using a dynamic weighted algorithm;

[0090] Specifically, a dynamic weighting algorithm is used to assign different weights based on the vehicle's location, weather, and image backlight probability, and a comprehensive calculation is performed to determine the backlight risk index. The weights can be dynamically adjusted based on actual scenarios and statistical data to ensure that the backlight risk index more accurately reflects the vehicle's current backlight risk level. Furthermore, the dynamic adjustment mechanism for the weights can be optimized by combining historical accident data and driving behavior data.

[0091] The calculation of the backlight risk index can be further combined with the real-time speed of the target vehicle and the distance to the obstacle ahead to dynamically correct the triggering timing of the braking intervention. Specifically, when the vehicle speed is higher than 60km / h, the judgment threshold of the backlight risk index is reduced by 10%; when the obstacle distance is less than 10 meters, the braking force of the automatic emergency braking strategy is increased to the maximum value.

[0092] This embodiment calculates the backlight probability of the vehicle position, the weather backlight probability and the image backlight probability, and adopts a dynamic weighting algorithm to comprehensively derive a backlight risk index. It can more accurately determine whether the vehicle is in a backlight scene and the severity of the backlight, thereby achieving accurate identification and quantitative evaluation of backlight scenes.

[0093] Furthermore, in some embodiments, step S21 of “calculating the corresponding vehicle position backlight probability based on the real-time geographic location, vehicle driving direction, and time information of the target vehicle” may specifically include:

[0094] S211 based on the real-time geographic location and vehicle direction, determine whether the target vehicle is at the tunnel exit;

[0095] Specifically, the vehicle's real-time geographic location (latitude and longitude) and driving direction information are combined with high-precision map data to determine whether the vehicle is near the tunnel exit. The location and exit coordinates of the tunnel are usually marked in the high-precision map. By comparing the positional relationship between the vehicle's current position and the tunnel exit, it is determined whether the vehicle is about to exit the tunnel. When the target vehicle enters the preset geo-fenced area, the GPS positioning can be used to match the tunnel exit or mountain road section information, triggering the pre-calculation of the backlight risk index in advance and adjusting the braking strategy to a high-sensitivity mode. For example, the vehicle's speed and driving direction can be combined to predict the time it will take for the vehicle to exit the tunnel, and adjust the backlight risk assessment logic in advance. For example, if the vehicle is traveling towards the tunnel exit at a speed of 60 kilometers per hour and is 100 meters away from the exit, the system can predict a few seconds in advance that it is about to enter a backlight scene and prepare corresponding measures.

[0096] S212. If the target vehicle is determined to be at a non-tunnel exit, the solar azimuth is calculated based on the real-time geographic location and time information using a solar position calculation algorithm;

[0097] Specifically, a solar position algorithm (such as the SPA algorithm) is used to calculate the sun's azimuth in the sky (i.e., the angle of the sun relative to the vehicle's horizontal position) based on the vehicle's real-time geographic location (latitude and longitude) and the current time (date and moment). A more accurate solar position model can be introduced, such as one that takes into account factors such as solar altitude and atmospheric refraction, to improve the accuracy of solar azimuth calculations. Furthermore, historical solar position data can be combined for calibration to reduce calculation errors.

[0098] S213. Determine the relative azimuth angle between the target vehicle and the sun based on the solar azimuth and the vehicle's travel direction;

[0099] Specifically, the solar azimuth angle is compared with the vehicle's direction of travel to calculate the angle between them. For example, if the vehicle is heading due east (90°) and the solar azimuth angle is 120°, the relative azimuth angle is 30°. A three-dimensional coordinate system can be used to more accurately model the vehicle's direction of travel and the solar azimuth angle, taking into account factors such as the vehicle's pitch and roll angles, thereby improving the accuracy of the relative azimuth angle calculation.

[0100] S214. Calculate the backlight probability of the target vehicle's position based on the relative azimuth angle;

[0101] Specifically, based on the relative azimuth angle and combined with a pre-set backlight probability model, the backlight probability of the vehicle position is calculated. For example, when the relative azimuth angle is between 0° and 30°, the backlight probability is high; when the angle is between 30° and 60°, the backlight probability is medium; when the angle is greater than 60°, the backlight probability is low. Not only can machine learning algorithms be introduced to optimize the backlight probability model based on historical driving data and accident statistics to make it more in line with actual conditions, but the backlight probability calculation can also be dynamically adjusted based on factors such as time (such as the probability of backlight is higher when the sun is lower in the morning and evening) and season (such as the sun angle is lower in winter).

[0102] This embodiment determines whether the vehicle is in the special scenario of a tunnel exit, combines the sun position calculation algorithm and the vehicle's driving direction, accurately calculates the relative azimuth angle between the vehicle and the sun, and determines the backlight probability of the vehicle position based on this, thereby achieving a precise assessment of the backlight probability of the vehicle position. This not only improves the accuracy and reliability of backlight scene recognition, but also can predict the backlight risk of the vehicle in special scenarios (such as tunnel exits) in advance, providing key data support for the formulation of subsequent driving assistance strategies and automatic emergency braking strategies.

[0103] Furthermore, in some embodiments, step S23 of “calculating the corresponding image backlight probability based on the real-time image data of the scene in front of the target vehicle” may specifically include:

[0104] S231 extracts the histogram information of the real-time image data and calculates the corresponding image skewness based on the histogram information;

[0105] Specifically, the histogram information reflects the distribution of pixel intensities in the image. By calculating the skewness of the histogram, we can understand the symmetry of the image pixel intensity distribution. The larger the skewness value, the more asymmetric the pixel intensity distribution of the image is. This may be due to backlighting, where one area is overexposed and another area is underexposed. In addition to calculating the skewness, other statistical features such as the kurtosis of the histogram can also be calculated to further analyze the contrast and brightness distribution of the image. For example, multi-scale histogram analysis is used, that is, the image is divided into blocks of different scales, the histogram features of each block are calculated separately, and then a fusion analysis is performed to more comprehensively reflect the local and global illumination characteristics of the image. Alternatively, image enhancement techniques such as histogram equalization can be introduced to pre-process the image to improve the image quality and contrast, thereby more accurately extracting feature information.

[0106] S232. Calculate the global contrast corresponding to the real-time image data and set the weight coefficient corresponding to the global contrast;

[0107] Specifically, global contrast is a measure of the overall brightness and darkness differences in an image. Backlit scenes typically result in reduced global contrast. Calculating the global contrast of an image can be achieved through a variety of methods, such as calculating the difference between the maximum and minimum pixel intensities in the image, or using more complex algorithms to calculate the average contrast difference between adjacent pixels in the image. Local contrast analysis methods can be used to calculate the local contrast of different regions in the image and combine this with the global contrast for a comprehensive analysis. For example, the image can be divided into multiple regions, and the local contrast of each region is calculated separately. Then, based on factors such as the region's importance and location, different weights are assigned to the local contrast of each region. Finally, the weighted local contrast and global contrast are combined to obtain a more comprehensive image contrast feature. Furthermore, adaptive contrast enhancement techniques can be combined to dynamically adjust the image contrast to improve its visual quality and analyzability.

[0108] S233. Calculate the probability of the image exposure time affecting the backlit scene based on the image exposure time, brightness gain, and calibration coefficient of the vehicle-mounted camera device;

[0109] Specifically, image exposure time and brightness gain are important parameters used by cameras to adjust image brightness under different lighting conditions. In backlit scenes, to obtain a clear image, the camera may shorten the exposure time and increase the brightness gain. By analyzing changes in exposure time and brightness gain, combined with the camera's calibration coefficients (which reflect characteristics such as the camera's light sensitivity), it is possible to infer the presence and severity of backlighting in the current scene. A backlighting scenario model based on exposure time and brightness gain can be established and trained and optimized using extensive experimental data to more accurately describe the relationship between exposure time and brightness gain and backlighting scenarios. For example, a machine learning algorithm can be used to train a classifier or regression model using exposure time, brightness gain, and labeled backlighting scenario data as input to predict the probability of backlighting under the current exposure parameters. Furthermore, other camera parameters, such as aperture and ISO value, can be considered to further enrich the model's input features and enhance its predictive capabilities.

[0110] S234. Calculate the image backlight probability corresponding to the real-time image data based on the image skewness, impact probability, global contrast and its weight coefficient;

[0111] Specifically, the obtained feature parameters such as image skewness, exposure time influence probability, global contrast, and its corresponding contrast weight parameter are summed to obtain the image backlight probability. The weight coefficient can be determined by statistical analysis and machine learning model training of a large number of image data in backlight and non-backlight scenes to ensure that each feature parameter has a reasonable weight distribution in the backlight probability calculation. The neural network algorithm in deep learning is introduced, and feature parameters such as image skewness, influence probability, and global contrast are used as input to train a neural network model to automatically learn how to calculate the image backlight probability. The neural network can automatically explore the complex relationships and nonlinear combinations between features, thereby more accurately calculating the image backlight probability. In addition, it can also be combined with image processing technologies such as convolutional neural networks (CNN) to directly extract deeper features from the raw image data, further improving the accuracy of the image backlight probability calculation.

[0112] This embodiment calculates the image skewness by extracting histogram information, calculates the global contrast and sets the weight coefficient, analyzes parameters such as exposure time and brightness gain to calculate the impact probability, and combines these characteristic parameters to calculate the image backlight probability. The system can evaluate the degree of backlighting of the image from multiple angles, achieve accurate calculation of the image backlight probability, and provide accurate image-level data support for the calculation of the backlight risk index.

[0113] In a specific embodiment, the specific process for calculating the backlight risk index is as follows:

[0114] First, the real-time location and driving direction of the vehicle are obtained through GPS positioning and matched with the geo-fence database. The geo-fence database contains information on special road sections such as tunnels and mountain roads. If the vehicle is at the exit of a tunnel, the probability of the vehicle position being backlit is Pbacklit. -gps It is directly assigned a value of 1, which means that in this case the vehicle is very likely to be in a backlight state. In the case of non-tunnel exits, the SPA algorithm is used to calculate the solar azimuth angle θs based on the longitude, latitude, and current date and time of the vehicle's location. The solar azimuth angle represents the direction of the sun in the sky and is crucial for determining the position of the sun relative to the vehicle. The vehicle's driving direction (obtained by GPS, ranging from 0-360°) and the solar azimuth angle (also expressed as 0-360°) are unified into the same coordinate system to obtain the vehicle azimuth angle θcar. This step ensures that the vehicle's driving direction and the solar azimuth angle are comparable, providing a basis for the subsequent calculation of the backlight probability.

[0115] Calculate the angle difference Δθ between the vehicle's direction of travel and the sun's azimuth, Δθ==|θcar-θs|. Based on the size of Δθ, use the following formula to calculate the vehicle's backlight probability Pbacklight-gps,

[0116]

[0117] When Δθ≤90° or Δθ≥270°, it means that the vehicle is facing the sun or on the back of the sun. At this time, the probability of backlight is high. The calculation formula is Pbacklight-gps=0.8*(1-180°Δθ-180°). As the deviation of Δθ from 180° increases, the probability of backlight gradually decreases.

[0118] In other cases, that is, when the relative azimuth angle between the vehicle and the sun is between 90° and 270°, the vehicle position backlight probability Pbacklight-gps is considered to be 0, that is, the sun is located at the side or rear of the vehicle at this time, and the backlight risk is relatively small.

[0119] Then, the vehicle is connected to the 4G network through the onboard communication device to obtain real-time weather data for the vehicle's current location. This weather data includes information such as light intensity, weather type (such as sunny, cloudy, overcast, rain / snow / fog, etc.) and visibility. This information is crucial for determining the impact of weather on backlighting. Among them, based on the obtained weather type, the backlight weather probability P backlight-weather is calculated according to the preset probability value. The specific probability values ​​are as follows:

[0120]

[0121] On clear days, the sun shines directly, and the backlight risk is high, so a higher backlight probability value is assigned. On cloudy days, the sun's rays are partially blocked by clouds, and the backlight risk is moderate, so a medium backlight probability value is assigned. On overcast days, the clouds are thicker, and the sun's rays are scattered, so the backlight risk is low, so a backlight probability value of zero is assigned. In inclement weather conditions such as rain, snow, or fog, although the backlight risk may be low, other factors such as reduced visibility may increase driving risks, so a negative value is assigned, indicating that the impact of these factors needs to be considered when comprehensively calculating the backlight risk index.

[0122] Next, a camera mounted on the front of the vehicle collects real-time image information of the road ahead. It also obtains parameters such as the image's histogram, exposure time, and brightness gain. This data is used to analyze the current image's lighting conditions and visual characteristics.

[0123] The image skewness is calculated according to the following formula:

[0124]

[0125] Where μ is the image mean, σ is the image standard deviation, p(i) is the probability of pixel intensity i, and N is the total number of pixels.

[0126] The global contrast of the image is calculated according to the following formula:

[0127]

[0128] Among them, Imax and Imin are the maximum brightness value and the minimum brightness value in the image respectively.

[0129] The probability of image exposure time for backlight scenes is calculated according to the following formula:

[0130] P exp =exptime*gain*k / 100

[0131] Where exptime is the exposure time of the current image, gain is the brightness gain of the current image, and k is the calibration coefficient, which needs to be calculated and adjusted based on the actual measurement of the photosensitivity performance of the current camera sensor.

[0132] The probability of backlit images is calculated according to the following formula:

[0133] P 逆光-图像 =|skewneww|*contrast*t*P exp

[0134] Where t is the contrast weight coefficient, which needs to be adjusted and calculated according to the actual scene, skewness is the image skewness, Contrast is the global image contrast, and Pexp is the probability of the image exposure time for the backlit scene.

[0135] Finally, based on the previously calculated vehicle position backlight probability, weather backlight probability, and image backlight probability, the current backlight risk index of the target vehicle is determined. The specific formula is as follows:

[0136] IRI=P 逆光-gps *c1+O 逆光-天气 *c2+O 逆光-图像 *c3

[0137] (c1+c2+c3=1)

[0138] Among them, c1, c2, and c3 are the weight coefficients of the vehicle position backlight probability, weather backlight probability, and image backlight probability, respectively, and the sum is 1. The weight coefficients can be adjusted and determined according to the actual scenario and importance.

[0139] After calculating the backlight risk index, if the backlight risk index (IRI) is greater than or equal to 0.6, the instrument panel warning light and sound prompt will be activated, indicating that the scene ahead may be backlighting and the driver should pay attention. If the backlight risk index (IRI) is greater than or equal to 0.8, the instrument panel warning light and sound prompt will be activated, indicating that the scene ahead is backlighting and the driver should pay attention to the road conditions and not rely solely on the AEB system. If the backlight risk index (IRI) is greater than or equal to 0.9, the instrument panel warning light and sound prompt will be activated, indicating that the scene ahead is extremely backlighting and the driver should take full control of the vehicle.

[0140] Furthermore, in some embodiments, step S3 of “determining a driving assistance strategy or an automatic emergency braking strategy based on a backlight risk index” may specifically include:

[0141] S31. If it is determined that the backlight risk index is greater than or equal to the preset first threshold, a first level warning strategy is generated;

[0142] Specifically, when the backlight risk index (IRI) reaches or exceeds the first preset threshold (e.g., IRI ≥ 0.6), the system triggers the first-level warning strategy. This strategy uses the vehicle's warning system to alert the driver to the current backlight condition, including illuminating a warning light on the dashboard and sounding an audible alarm. This can be combined with the vehicle's head-up display (HUD) system to project warning information into the driver's field of view, reducing the driver's attention diversion. Furthermore, intelligent voice assistants can provide personalized voice prompts, such as "Currently experiencing backlight, please pay attention to the road conditions ahead."

[0143] S32. If it is determined that the backlight risk index is greater than or equal to the preset second threshold, a second level warning strategy is generated;

[0144] Specifically, when the backlight risk index (IRI) reaches or exceeds a higher second preset threshold (for example, IRI ≥ 0.8), the system activates the second-level warning strategy, including stronger warning measures, such as increasing the flashing frequency of the warning light, increasing the volume of the sound alarm, or displaying detailed backlight risk information and recommended actions on the vehicle's display screen. It can be combined with the vehicle's automatic driving assistance systems, such as lane keeping assist (LKA) and adaptive cruise control (ACC), to automatically adjust the vehicle's driving status. For example, the system can automatically reduce the speed, increase the distance to the vehicle in front, and keep the vehicle in the center of the lane.

[0145] S33. If it is determined that the backlight risk index is greater than or equal to the preset third threshold, an automatic emergency braking strategy is generated;

[0146] Specifically, when the backlight risk index (IRI) reaches or exceeds the highest preset threshold (for example, IRI ≥ 0.9), the system determines that the current backlight condition is extremely dangerous and may seriously interfere with the driver's vision and judgment. At this time, an automatic emergency braking strategy is generated. The system will automatically control the vehicle's braking system and perform emergency braking operations to avoid or mitigate possible collisions. It can be combined with the vehicle's forward collision warning (FCW) system and automatic emergency braking system (AEB) to use sensors such as millimeter-wave radar and cameras to monitor the road conditions ahead in real time. During emergency braking, the system can optimize the distribution of braking force to ensure the stability and controllability of the vehicle during braking.

[0147] This embodiment effectively addresses different degrees of backlight risks through hierarchical warning and braking strategies. The graded response mechanism ensures that the system can provide appropriate intervention at the right time, avoiding unnecessary excessive warnings and braking interference, optimizing the driving experience, and enabling rapid emergency measures in high-risk situations.

[0148] Furthermore, in some embodiments, step S4 of “controlling the target vehicle according to the driving assistance strategy or the automatic emergency braking strategy” may specifically include:

[0149] S41. According to the driving assistance strategy or emergency braking strategy, the corresponding control signal is sent to the braking system and / or warning system of the target vehicle;

[0150] Specifically, the system generates corresponding driving assistance strategies or automatic emergency braking strategies based on the backlight risk index (IRI) and converts these strategies into specific control signals. The control signals are sent to the braking system and / or warning system through the vehicle's electronic control unit (ECU) to perform the corresponding operations. Redundant communication protocols and control signal transmission mechanisms can be adopted to ensure the reliable transmission of control signals in emergency situations. For example, using a dual-channel communication protocol, even if one channel fails, the other channel can still ensure normal signal transmission. In addition, the vehicle's network diagnostic system can be combined to monitor the transmission status of the control signal in real time, and transmission anomalies can be detected and handled promptly.

[0151] S42. Controlling the braking system to perform the corresponding emergency braking operation according to the control signal, and / or controlling the warning system to issue a warning message;

[0152] Specifically, after receiving the control signal, the braking system performs the corresponding emergency braking operation based on the specific content of the signal, including rapidly increasing braking force and optimizing braking force distribution (such as the proper distribution of braking force between the front and rear axles) to achieve smooth and efficient braking. The vehicle's anti-lock braking system (ABS) and electronic stability control system (ESC) can be combined to maintain vehicle stability and controllability during emergency braking. For example, the ESC system monitors the vehicle's yaw rate and lateral acceleration in real time and dynamically adjusts the braking force of each wheel to prevent the vehicle from skidding or losing control during braking. Furthermore, intelligent braking technologies, such as electro-hydraulic braking systems (EMB), can be introduced to achieve more precise and rapid braking force control.

[0153] Based on the control signals it receives, the warning system alerts the driver of the current backlight risk and the system's actions through various means, including illuminating a warning light on the instrument panel, sounding an audible alarm, and displaying a warning message on the head-up display (HUD). This can be combined with intelligent voice assistants to provide personalized voice warnings, such as "The current backlight risk is high. Please pay attention to the road conditions ahead and be prepared to take over the vehicle." Furthermore, the vehicle's external warning devices, such as hazard lights and buzzers, can be used to alert surrounding vehicles and pedestrians, improving overall traffic safety. Furthermore, the vehicle's intelligent interconnected system can be used to transmit warning information to a remote monitoring center or the vehicle manufacturer, enabling emergency assistance or technical support when needed.

[0154] This embodiment ensures the effective implementation of driving assistance strategies and automatic emergency braking strategies through precise control signal transmission and execution mechanisms, ensures that the vehicle takes appropriate measures to deal with possible dangerous situations in backlighting scenarios, and improves the vehicle's driving safety and reliability in complex backlighting environments.

[0155] Furthermore, in some embodiments, the vehicle driving control method for backlighting scenes may further include:

[0156] S51. After performing an emergency braking operation, real-time monitoring of the target vehicle's surrounding environment information and vehicle status information;

[0157] Specifically, after the emergency braking operation is performed, the system continues to monitor the environmental information around the vehicle in real time through various sensors of the vehicle (such as millimeter-wave radar, camera, ultrasonic sensor, etc.), including the distance to the vehicle in front, relative speed, lane line position, etc. At the same time, through the vehicle's CAN bus and other communication protocols, the vehicle's own status information, such as speed, acceleration, steering wheel angle, brake pressure, etc., is obtained in real time. Laser radar (LiDAR) technology can be introduced to further improve the perception accuracy and range of the surrounding environment, especially the detection ability of stationary objects and low-reflectivity objects. In addition, high-precision maps and positioning systems can be combined to update the vehicle's position and posture in the map in real time to provide support for more accurate environmental modeling.

[0158] S52. Adjust the emergency braking strategy based on the surrounding environment information and vehicle status information;

[0159] Specifically, the system dynamically adjusts the current emergency braking strategy based on real-time monitoring of the surrounding environment and vehicle status. For example, if the distance to the vehicle ahead is detected to be sufficiently safe, braking force can be appropriately reduced to improve driving comfort; if the distance to the vehicle ahead is still decreasing, braking force can be further increased to avoid a collision. A model predictive control (MPC) algorithm can be used to predict vehicle state changes over the next few seconds based on real-time data and optimize the braking strategy accordingly. Furthermore, the vehicle's electronic stability control system (ESC) and anti-lock braking system (ABS) can be integrated to ensure vehicle stability and controllability when adjusting the braking strategy.

[0160] This embodiment effectively improves the intelligence level and safety of the emergency braking system by monitoring the vehicle's surrounding environment and its own status in real time after emergency braking and dynamically adjusting the braking strategy based on this information.

[0161] To sum up, the present embodiment provides a vehicle driving control method for backlighting scenarios. First, by collecting multi-source information in real time through multiple sensors, it can perceive the vehicle's driving environment more comprehensively and accurately, provide a richer data basis for subsequent backlighting scene judgment, effectively make up for the perception deficiencies of a single sensor in backlighting scenarios, and improve the accuracy and reliability of backlighting scene recognition; then, by fusing multi-source information to calculate the backlighting risk index, the impact of multiple factors on the backlighting scene is comprehensively considered, making the judgment of the backlighting scene more accurate and avoiding the errors that may be caused by the judgment of a single factor; then, according to the backlighting risk index, the corresponding driving assistance or automatic emergency braking strategy is determined to improve the reliability of the vehicle's active safety system in backlighting scenarios; finally, by accurately controlling the vehicle according to the driving assistance strategy or the automatic emergency braking strategy, it can ensure that the vehicle takes appropriate measures to deal with possible dangerous situations in backlighting scenarios.

[0162] To facilitate better implementation of the vehicle driving control method for backlit scenes in the embodiments of the present application, the embodiments of the present application also provide a vehicle driving control device for backlit scenes. The meanings of the terms herein are the same as those in the aforementioned vehicle driving control method for backlit scenes. For specific implementation details, please refer to the description in the method embodiment.

[0163] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of a vehicle driving control device for backlighting scenes provided in an embodiment of the present application, wherein the vehicle driving control device for backlighting scenes may specifically include an information acquisition module 201, an index calculation module 202, a strategy determination module 203, and a control module 204, which may be specifically as follows:

[0164] Information acquisition module 201, used to acquire multi-source information of the target vehicle in real time;

[0165] The index calculation module 202 is used to perform fusion calculation on multi-source information to obtain the current backlight risk index of the target vehicle;

[0166] A strategy determination module 203 is configured to determine a driving assistance strategy or an automatic emergency braking strategy based on the backlight risk index;

[0167] The control module 204 is configured to control the target vehicle according to a driving assistance strategy or an automatic emergency braking strategy.

[0168] Furthermore, in some embodiments, the information acquisition module 201 may specifically include:

[0169] A first acquisition unit is used to acquire the real-time geographic location, vehicle travel direction and time information of the target vehicle through a positioning device;

[0170] a second acquisition unit, configured to acquire, in real time, weather data of the target vehicle's current environment through an onboard communication device, the weather data including light intensity, weather type, and visibility;

[0171] The third acquisition unit is used to collect real-time image data of the scene in front of the target vehicle through the vehicle-mounted camera device.

[0172] Furthermore, in some embodiments, the index calculation module 202 may specifically include:

[0173] A first probability calculation unit is used to calculate the backlight probability of the corresponding vehicle position based on the real-time geographical location, vehicle driving direction and time information of the target vehicle;

[0174] A second probability calculation unit is used to calculate the corresponding weather backlight probability based on the weather data of the target vehicle's current environment;

[0175] a third probability calculation unit, configured to calculate a corresponding image backlight probability based on real-time image data of a scene in front of the target vehicle;

[0176] The index calculation unit is used to determine the current backlight risk index of the target vehicle based on the backlight probability of the vehicle position, the weather backlight probability and the image backlight probability through a dynamic weighted algorithm.

[0177] Furthermore, in some embodiments, the first probability calculation unit is specifically configured to:

[0178] Determine whether the target vehicle is at the tunnel exit based on real-time geographic location and vehicle travel direction;

[0179] If the target vehicle is judged to be at a non-tunnel exit, the solar azimuth is calculated based on the real-time geographic location and time information using the solar position calculation algorithm;

[0180] Determine the relative azimuth angle between the target vehicle and the sun based on the solar azimuth angle and the vehicle's travel direction;

[0181] The backlight probability of the target vehicle's position is calculated based on the relative azimuth angle.

[0182] Furthermore, in some embodiments, the third probability calculation unit is specifically configured to:

[0183] Extracting histogram information of real-time image data and calculating the corresponding image skewness based on the histogram information;

[0184] Calculate the global contrast corresponding to the real-time image data and set the weight coefficient corresponding to the global contrast;

[0185] Calculate the probability of image exposure time affecting backlit scenes based on the image exposure time, brightness gain, and calibration coefficient of the vehicle-mounted camera device;

[0186] Based on image skewness, influence probability, global contrast and its weight coefficient, the image backlight probability corresponding to the real-time image data is calculated.

[0187] Furthermore, in some embodiments, the policy determination module 203 may specifically include:

[0188] A first strategy generating unit is configured to generate a first level warning strategy if it is determined that the backlight risk index is greater than or equal to a preset first threshold;

[0189] A second strategy generating unit is configured to generate a second-level warning strategy if it is determined that the backlight risk index is greater than or equal to a preset second threshold;

[0190] The third strategy generating unit is configured to generate an automatic emergency braking strategy if it is determined that the backlight risk index is greater than or equal to a preset third threshold.

[0191] Furthermore, in some embodiments, the control module 204 may specifically include:

[0192] A signal unit, configured to send corresponding control signals to the braking system and / or warning system of the target vehicle according to the driving assistance strategy or the emergency braking strategy;

[0193] The control unit is used to control the braking system to perform corresponding emergency braking operations according to the control signal, and / or control the warning system to issue a warning message.

[0194] Furthermore, in some embodiments, the apparatus may further include an adjustment module, specifically configured to:

[0195] After executing the emergency braking operation, real-time monitoring of the target vehicle's surrounding environment information and vehicle status information;

[0196] Adjust emergency braking strategies based on surrounding environment information and vehicle status information.

[0197] In summary, the vehicle driving control device for backlighting scenarios provided in this embodiment acquires multi-source information of the target vehicle in real time through the information acquisition module 201; fuses and calculates the multi-source information through the index calculation module 202 to obtain the current backlighting risk index of the target vehicle; determines the driving assistance strategy or automatic emergency braking strategy based on the backlighting risk index through the strategy determination module 203; and controls the target vehicle according to the driving assistance strategy or automatic emergency braking strategy through the control module 204. The vehicle driving control device for backlighting scenarios provided in this embodiment generates a backlighting risk index by fusing multi-source information, accurately determines the backlighting scenario, and formulates corresponding driving assistance or automatic emergency braking strategies, thereby improving the driving safety and reliability of the vehicle in complex backlighting environments, reducing the risk of collision accidents, and ensuring the driving safety of users.

[0198] In addition, the present invention also provides an electronic device, such as Figure 5 , which shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application. Specifically, the electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will understand that Figure 5 The electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.

[0199] The processor 301 is the control center of the electronic device. It connects all parts of the electronic device using various interfaces and lines. By running or executing software programs and / or modules stored in the memory 302 and accessing data stored in the memory 302, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor primarily processes the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into the processor 301.

[0200] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and a vehicle driving control method for a backlighting scene by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0201] The electronic device also includes a power supply 303 for supplying power to various components. Preferably, the power supply 303 can be logically connected to the processor 301 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 303 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0202] The electronic device may further include an input unit 304, which may be configured to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0203] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302 to implement various functions as follows:

[0204] Acquire multi-source information of the target vehicle in real time; perform fusion calculation on the multi-source information to obtain the current backlight risk index of the target vehicle; determine the driving assistance strategy or automatic emergency braking strategy based on the backlight risk index; and control the target vehicle according to the driving assistance strategy or automatic emergency braking strategy.

[0205] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0206] The embodiment of the present application generates a backlight risk index by fusing multi-source information, accurately judges the backlight scene and formulates corresponding driving assistance or automatic emergency braking strategies, thereby improving the vehicle's driving safety and reliability in complex backlight environments, reducing the risk of collision accidents, and ensuring user driving safety.

[0207] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0208] To this end, an embodiment of the present application provides a storage medium storing a plurality of instructions that can be loaded by a processor to execute the steps of any of the vehicle driving control methods for backlighting scenarios provided in the embodiments of the present application. For example, the instructions can execute the following steps:

[0209] Acquire multi-source information of the target vehicle in real time; perform fusion calculation on the multi-source information to obtain the current backlight risk index of the target vehicle; determine the driving assistance strategy or automatic emergency braking strategy based on the backlight risk index; and control the target vehicle according to the driving assistance strategy or automatic emergency braking strategy.

[0210] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0211] The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc. Since the instructions stored in the storage medium can execute the steps of any of the vehicle driving control methods for backlit scenes provided in the embodiments of the present application, the beneficial effects that can be achieved by any of the vehicle driving control methods for backlit scenes provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0212] The above is a detailed introduction to the vehicle driving control method, device, equipment and medium for backlight scenes provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A vehicle driving control method for backlighting scenes, characterized in that: The steps include: Obtain multi-source information of target vehicles in real time; Performing a fusion calculation on the multi-source information to obtain a current backlight risk index of the target vehicle; determining a driving assistance strategy or an automatic emergency braking strategy based on the backlight risk index; The target vehicle is controlled according to the driving assistance strategy or the automatic emergency braking strategy.

2. The vehicle driving control method for backlighting scenes according to claim 1, characterized in that: The real-time acquisition of multi-source information of the target vehicle includes: Obtaining the real-time geographic location, vehicle travel direction and time information of the target vehicle through a positioning device; Acquiring weather data of the target vehicle's current environment in real time through an on-board communication device, the weather data including light intensity, weather type, and visibility; Real-time image data of the scene in front of the target vehicle is collected by a vehicle-mounted camera device.

3. The vehicle driving control method for backlighting scene according to claim 2, characterized in that: The fusing and calculating the multi-source information to obtain the current backlight risk index of the target vehicle includes: Calculate the backlight probability of the corresponding vehicle position based on the real-time geographic location, vehicle travel direction and time information of the target vehicle; Calculating the corresponding weather backlight probability based on the weather data of the target vehicle's current environment; Calculating a corresponding image backlight probability based on real-time image data of a scene in front of the target vehicle; The current backlight risk index of the target vehicle is determined according to the vehicle position backlight probability, the weather backlight probability and the image backlight probability through a dynamic weighted algorithm.

4. The vehicle driving control method for backlighting scene according to claim 3, characterized in that: The calculating of the corresponding vehicle position backlight probability based on the real-time geographic location, vehicle driving direction and time information of the target vehicle includes: Based on the real-time geographic location and the vehicle's travel direction, determining whether the target vehicle is at a tunnel exit; If it is determined that the target vehicle is not at a tunnel exit, calculating the solar azimuth angle according to the real-time geographic location and the time information using a solar position calculation algorithm; Determining a relative azimuth angle between the target vehicle and the sun based on the solar azimuth angle and the vehicle's travel direction; The backlight probability of the vehicle position of the target vehicle is calculated according to the relative azimuth angle.

5. The vehicle driving control method for backlighting scene according to claim 3, characterized in that: The calculating of the corresponding image backlight probability based on the real-time image data of the scene in front of the target vehicle includes: Extracting histogram information of the real-time image data, and calculating corresponding image skewness based on the histogram information; Calculating a global contrast ratio corresponding to the real-time image data, and setting a weight coefficient corresponding to the global contrast ratio; Calculating the probability of the image exposure time affecting the backlit scene based on the image exposure time, brightness gain, and calibration coefficient of the vehicle-mounted camera device; An image backlight probability corresponding to the real-time image data is calculated based on the image skewness, the influence probability, the global contrast and the weight coefficient thereof.

6. The vehicle driving control method for backlighting scene according to claim 1, characterized in that: The determining of a driving assistance strategy or an automatic emergency braking strategy based on the backlight risk index includes: If it is determined that the backlight risk index is greater than or equal to a preset first threshold, a first level warning strategy is generated; If it is determined that the backlight risk index is greater than or equal to a preset second threshold, a second level warning strategy is generated; If it is determined that the backlight risk index is greater than or equal to a preset third threshold, an automatic emergency braking strategy is generated.

7. The vehicle driving control method for backlighting scene according to claim 1, characterized in that: The controlling the target vehicle according to the driving assistance strategy or the automatic emergency braking strategy includes: Sending corresponding control signals to the braking system and / or warning system of the target vehicle according to the driving assistance strategy or the emergency braking strategy; The braking system is controlled to perform a corresponding emergency braking operation according to the control signal, and / or the warning system is controlled to issue a warning message.

8. A vehicle driving control device for backlighting scenes, characterized in that: include: Information acquisition module, used to obtain multi-source information of the target vehicle in real time; An index calculation module, configured to perform fusion calculation on the multi-source information to obtain the current backlight risk index of the target vehicle; a strategy determination module, configured to determine a driving assistance strategy or an automatic emergency braking strategy based on the backlight risk index; A control module is used to control the target vehicle according to the driving assistance strategy or the automatic emergency braking strategy.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the vehicle driving control method for backlighting scenes as described in any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: A computer program is stored which can be loaded by a processor and executes the vehicle driving control method for a backlighting scene according to any one of claims 1 to 7.

Images