A control method and device of a vehicle headlamp and a storage medium

Abstract

The application provides a control method and device of a vehicle headlamp and a storage medium. According to inertial navigation data and a driving map of a vehicle, a predicted driving track of the vehicle is obtained. Based on the predicted driving track of the vehicle, behavior intention prediction information of the vehicle and behavior intention prediction information of other road users, a corresponding quality influence weight ratio parameter is assigned to different visual feature parameters contained in visual data collected by the vehicle. Based on the quality influence weight ratio parameter, quality evaluation information of the visual data collected by the vehicle is determined. When the quality evaluation information is determined to be lower than a preset quality, the vehicle headlamp is controlled and adjusted according to the quality evaluation information, and the control and adjustment at least includes one of light and dark degree adjustment, low beam or high beam adjustment and illumination field angle adjustment of the vehicle headlamp. The visual data of the area irradiated by the headlamp can meet the working requirements of the vehicle on the perception data, and the driving safety and the driving experience of the user are improved.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a method, device and storage medium for controlling vehicle headlights. Background Technology

[0002] With the development of automotive intelligence, vehicle users have increasingly higher demands for the automation and intelligence of vehicle-side control. However, current industry practices for controlling headlights in traditional intelligent driving vehicles still rely on conventional driving habits to adjust the headlight illumination area. This inevitably means that the brightness of the headlights based on this traditional method cannot adequately meet the high standards of road condition and environmental perception data required by intelligent driving vehicles, resulting in insufficient assistance and a poor user experience. Therefore, providing a headlight control method that meets the high requirements of intelligent driving vehicles for road condition and environmental perception data, enabling the controlled headlights to provide appropriate illumination area control based on the driving environment, thereby providing better driving assistance, improving driving safety, and enhancing the user's driving experience, has become a crucial issue that urgently needs to be addressed in the industry. Summary of the Invention

[0003] In view of the above, embodiments of this application provide a method, apparatus, storage medium, and electronic device for controlling vehicle headlights, in order to at least partially solve the above problems.

[0004] In a first aspect, embodiments of this application provide a method for controlling vehicle headlights, including:

[0005] Based on the vehicle's inertial navigation data and driving map information, the predicted driving trajectory of the vehicle is obtained;

[0006] Based on the predicted driving trajectory of the vehicle, the predicted behavioral intentions of the vehicle, and the predicted behavioral intentions of other road users, corresponding quality influence weight ratio parameters are assigned to different visual feature parameters contained in the visual data collected by the vehicle.

[0007] Based on the aforementioned quality impact weight ratio parameter, the quality assessment information of the visual data collected by this vehicle is determined;

[0008] When the quality assessment information is determined to be lower than the preset quality, the vehicle headlights are controlled and adjusted according to the quality assessment information. The control and adjustment include at least one of the following: adjusting the brightness of the vehicle headlights, adjusting the low beam or high beam, and adjusting the illumination field angle.

[0009] Optionally, in one embodiment of this application, the step of assigning corresponding quality influence weight ratio parameters to different visual feature parameters contained in the vehicle's visual data based on the vehicle's predicted driving trajectory, the vehicle's predicted behavioral intention information, and the behavioral intention prediction information of other road users includes:

[0010] The visual data is divided into grid regions;

[0011] Determine the visual feature parameters of the visual data corresponding to each grid region, wherein the visual feature parameters include at least one of the following: brightness, contrast, and sharpness of the visual image.

[0012] Based on the predicted driving trajectory of the vehicle, the predicted behavioral intention of the vehicle, and the predicted behavioral intention of other road users, a corresponding quality influence weight ratio parameter is assigned to different visual feature parameters of each grid area.

[0013] Based on the quality influence weight ratio parameter, the feature weighted average value of each grid region is calculated, and the feature weighted average value is used as the quality assessment information of the visual data.

[0014] Optionally, in one embodiment of this application, the step of controlling and adjusting the vehicle headlights based on the quality assessment information when it is determined that the quality assessment information is lower than a preset quality includes:

[0015] The weighting ratio parameter of the quality impact during the current driving phase is fixed;

[0016] Based on a fixed quality influence weight ratio parameter, the quality assessment information of the visual data collected by the vehicle after control and adjustment is recalculated.

[0017] When the recalculated quality assessment information is greater than or equal to the preset quality, the control and adjustment of the vehicle headlights based on the quality assessment information shall be stopped.

[0018] Optionally, in one embodiment of this application, the step of dividing the visual data into grid regions includes:

[0019] Determine the illumination field of each headlight of the vehicle;

[0020] Based on the illumination field and the shooting area of ​​the vehicle-mounted camera, the visual data is divided into grid regions from near to far.

[0021] Optionally, in one embodiment of this application, when assigning corresponding quality influence weight ratio parameters to different visual feature parameters of each grid region, the quality influence weight ratio assigned to grid regions closer to the vehicle headlights is set to be greater than the quality influence weight ratio assigned to grid regions farther from the vehicle headlights, and the quality influence weight ratio assigned to grid regions where the illumination fields of multiple headlights are superimposed is greater than the quality influence weight ratio assigned to non-superimposed grid regions.

[0022] Optionally, in one embodiment of this application, before assigning corresponding quality influence weight ratio parameters to different visual feature parameters contained in the vehicle's visual data based on the vehicle's driving trajectory, the vehicle's behavioral intention prediction information, and the behavioral intention prediction information of other road users, the method further includes:

[0023] Based on the visual data and / or radar data collected by this vehicle, the behavior of other road users is predicted, and information on the behavioral intentions of other road users is obtained.

[0024] Based on the vehicle's control logic information and vehicle status information, the vehicle's behavioral intention prediction information is determined.

[0025] Optionally, in one embodiment of this application, determining the vehicle's behavioral intention prediction information based on the vehicle's control logic information and vehicle body state information includes:

[0026] Identify the multi-dimensional driving influencing factors that determine the vehicle's control logic information and body status information;

[0027] Assign corresponding weight parameters to driving influencing factors of different dimensions;

[0028] Based on the parameter values ​​of the current multi-dimensional driving influencing factors of the vehicle, and combined with the weight parameters, the behavioral intention prediction information of the vehicle is obtained.

[0029] Optionally, in one embodiment of this application, the method further includes: when the quality assessment information is higher than or equal to the preset quality, controlling and adjusting the vehicle headlights according to the predicted driving trajectory.

[0030] Secondly, based on the vehicle headlight control method described in the first aspect of this application, embodiments of this application also provide a vehicle headlight control device, comprising:

[0031] The planning module is used to obtain the predicted driving trajectory of the vehicle based on the vehicle's inertial navigation data and driving map information;

[0032] The allocation module is used to assign corresponding quality influence weight ratio parameters to different visual feature parameters contained in the visual data collected by the vehicle, based on the predicted driving trajectory of the vehicle, the predicted behavioral intention information of the vehicle, and the predicted behavioral intention information of other road users.

[0033] The calculation module is used to determine the quality assessment information of the visual data collected by the vehicle based on the quality influence weight ratio parameter.

[0034] The control module is used to control and adjust the vehicle headlights according to the quality assessment information when it is determined that the quality assessment information is lower than the preset quality. The control and adjustment includes at least one of adjusting the brightness of the vehicle headlights, adjusting the low beam or high beam, and adjusting the illumination field angle.

[0035] Thirdly, embodiments of this application also provide a computer storage medium storing computer-executable instructions, which, when executed, perform any of the vehicle headlight control methods described in the first aspect of embodiments of this application.

[0036] Fourthly, embodiments of this application also provide an electronic device, including: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus;

[0037] The memory is used to store at least one executable instruction that causes the processor to execute any of the vehicle headlight control methods described in the first aspect of the embodiments of this application.

[0038] This application provides a method, device, and related equipment for controlling vehicle headlights. Based on the vehicle's inertial navigation data and driving map information, a predicted driving trajectory of the vehicle is obtained. Based on the predicted driving trajectory, the vehicle's predicted behavioral intentions, and the predicted behavioral intentions of other road users, corresponding quality influence weight ratio parameters are assigned to different visual feature parameters included in the visual data collected by the vehicle. Based on the quality influence weight ratio parameters, quality assessment information of the visual data collected by the vehicle is determined. When the quality assessment information is determined to be lower than a preset quality, the vehicle headlights are controlled and adjusted according to the quality assessment information. The control and adjustment include at least one of adjusting the brightness of the vehicle headlights, adjusting the low beam or high beam, and adjusting the illumination field angle. Through the above-described vehicle headlight control method, this application can provide appropriate illumination area control according to the driving environment, meeting the high standard requirements of road condition and environmental perception data for intelligent driving vehicles, providing better driving assistance for intelligent driving vehicles, and improving the driving safety and user driving experience of intelligent driving vehicles. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0040] Figure 1 A schematic diagram illustrating the workflow of a vehicle headlight control method provided in this application embodiment;

[0041] Figure 2 This is a schematic diagram of the structure of a vehicle headlight control device provided in an embodiment of this application.

[0042] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0043] To enable those skilled in the art to better understand the technical solutions in the embodiments of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art should fall within the protection scope of the embodiments of this application.

[0044] It should be understood that the steps described in the method embodiments of this application may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this application is not limited in this respect.

[0045] Example 1

[0046] This application provides a method for controlling vehicle headlights, such as... Figure 1 As shown, Figure 1 A schematic diagram of the workflow of a vehicle headlight control method provided in this application embodiment includes:

[0047] Step S101: Obtain the predicted driving trajectory of the vehicle based on its inertial navigation data and driving map information. In this embodiment, the vehicle's inertial navigation data is collected in real time by its onboard inertial navigation system (INS), specifically, by an onboard IMU (Inertial Measurement Unit), which generally consists of one or more electronic units such as a speedometer, gyroscope, or magnetometer. The collected data includes vehicle position information, speed information, and vehicle attitude information. The driving map information is obtained in real time through the onboard positioning system, such as high-precision map information. This embodiment predicts the vehicle's driving trajectory at the next moment using both its own inertial navigation data and driving map information to reduce the amount of data that needs to be processed when predicting the driving trajectory and to ensure that the obtained prediction results have good accuracy. This is to meet the high timeliness requirements of vehicle headlight control.

[0048] Specifically, in one optional implementation of this application embodiment, the predicted driving trajectory of the vehicle is obtained based on the vehicle's inertial navigation data and driving map information, including: extracting the vehicle's acceleration, angular velocity, and speed information from the acquired inertial navigation data; extracting the road topology, lane line information, and traffic sign information of the road the vehicle is traveling on from the high-precision map information; performing Kalman filter processing on the extracted vehicle acceleration, angular velocity, and speed information; converting the extracted road topology, lane line information, and traffic sign information into a local map representation centered on the vehicle; using a preset Interacting Multiple Model (IMM), combining multiple motion models, dynamically adjusting the weights of each motion model through model switching probabilities, and combining the filtered acceleration, angular velocity, and speed information to predict the vehicle's driving position and speed in the next stage; optimizing the predicted driving position and speed of the vehicle in the next stage using the local map representation, so that the predicted driving trajectory conforms to the current road topology, thereby obtaining the predicted driving trajectory of the vehicle, wherein the multiple motion models include at least one or more of motion neural network models such as constant speed models and uniform acceleration models. In this embodiment, noise and outliers in the collected inertial navigation data are removed in this way, enabling high-precision and fast vehicle trajectory prediction with only a small amount of data to be processed, thus better meeting the needs of the working scenario of timely control of vehicle lights in this embodiment.

[0049] Step S102: Based on the predicted driving trajectory of the vehicle, the predicted behavioral intention information of the vehicle, and the predicted behavioral intention information of other road users, assign corresponding quality influence weight ratio parameters to different visual feature parameters contained in the visual data collected by the vehicle. In this embodiment, the predicted driving trajectory is used to characterize the possible movement route of the vehicle in the next stage based on the current control logic. The predicted behavioral intention information of the vehicle is used to represent the possible driving state of the vehicle in the next stage, such as acceleration, braking, or turn signal information. The predicted behavioral intention information of other road users is used to represent the change information of the position of other people, vehicles, road signs, or other driving obstacles relative to the vehicle in the next stage. This application assigns quality influence weight ratio parameters to different visual feature parameters in the visual data of the vehicle based on these three dimensions. For example, when the visual data is single image data, the visual feature parameters can be the pixel value, brightness, and contrast information of the image data, and corresponding quality influence weight ratio parameters are assigned to these visual feature parameters. When the visual data is video data, key image frames need to be extracted from the video data as target visual data to participate in the assignment of corresponding quality influence weight ratio parameters. This embodiment of the application illustrates the following example: When a vehicle is in motion, the predicted driving trajectory indicates that the vehicle needs to proceed straight through an intersection with traffic lights. The vehicle's behavioral intention prediction information indicates that the vehicle will continue to proceed straight. The prediction information of other road users indicates that the red light at the intersection will turn green at the next moment. In order to identify whether there are pedestrians crossing the road at a distant intersection, it is necessary to turn on the high beams or increase the brightness of the vehicle's headlights as soon as possible. At this time, it is necessary to assign a high image quality influence weight ratio parameter to the brightness and contrast in the visual data through this step. The control and adjustment of the vehicle's headlights are influenced by these two high weight ratio parameters so that the vehicle can obtain a high-quality image of the intersection as soon as possible, providing better driving assistance for the vehicle.

[0050] Step S103: Based on the quality influence weight ratio parameter, determine the quality assessment information of the visual data collected by the vehicle. For example, the quality assessment information can be determined by weighted summation. This method of the present application performs quality assessment on the current visual data, and the assessment results are reasonable and reliable, providing an appropriate adjustment basis for the vehicle headlight control adjustment, ensuring that the visual data acquired by the vehicle in the next stage has high visual quality, so as to better meet the needs of vehicle driving.

[0051] Step S104: When it is determined that the quality assessment information is lower than the preset quality, the vehicle headlights are controlled and adjusted according to the quality assessment information. The control and adjustment includes at least one of adjusting the brightness of the vehicle headlights, adjusting the low beam or high beam, and adjusting the illumination field angle. This embodiment of the application, through multi-dimensional control and adjustment, can better meet the vehicle's specific needs for the collected visual data in the next moment, improve vehicle driving safety, and enhance the user's driving experience.

[0052] Optionally, in one embodiment of this application, the step of assigning corresponding quality influence weight ratio parameters to different visual feature parameters contained in the vehicle's visual data based on the vehicle's predicted driving trajectory, the vehicle's predicted behavioral intention information, and the behavioral intention prediction information of other road users includes: dividing the visual data into grid regions, determining the visual feature parameters of the visual data corresponding to each grid region, wherein the visual feature parameters include at least one of the feature parameter values ​​of brightness, contrast, and sharpness of the visual image; assigning corresponding quality influence weight ratio parameters to different visual feature parameters of each grid region based on the vehicle's predicted driving trajectory, the vehicle's predicted behavioral intention information, and the behavioral intention prediction information of other road users; calculating the feature weighted average value of each grid region according to the quality influence weight ratio parameters; and using the feature weighted average value as the quality assessment information of the visual data. In this embodiment of the application, by dividing the visual data into multiple grid regions and then calculating the feature-weighted average of multiple feature parameters for each grid region, the quality assessment of different regions of the visual data can be performed in a more detailed manner. This allows for a better determination of which regions of the visual data are not clear enough, or the reasons for low quality acquisition due to reflectors or other factors. This enables more targeted adjustments to the vehicle headlights, ensuring fast and accurate adjustment of the vehicle headlights, and allowing the vehicle to obtain high-quality visual data that meets the vehicle's needs in the next stage.

[0053] Optionally, in one embodiment of this application, the step of controlling and adjusting the vehicle headlights according to the quality assessment information when the quality assessment information is determined to be lower than the preset quality includes: fixing the quality influence weight ratio parameter for the current driving stage; recalculating the quality assessment information of the visual data collected by the vehicle after control and adjustment based on the fixed quality influence weight ratio parameter; and stopping the control and adjustment of the vehicle headlights according to the quality assessment information when the recalculated quality assessment information is greater than or equal to the preset quality. In this embodiment of the application, by fixing the quality influence weight ratio parameter of each grid area, it is not necessary to reallocate a new quality influence weight ratio parameter for each grid area, which improves the efficiency of recalculating the quality of the newly collected visual data to a certain extent. Under the premise of meeting the current driving needs of the vehicle, a continuous steady-state dynamic adjustment of the vehicle headlights is achieved, instead of directly adjusting the vehicle headlights to be too bright. While meeting the requirements of the vehicle to collect high-quality visual data and achieve high-precision control of the vehicle headlights, it avoids that excessive control and adjustment will affect the quality of the collected visual data, such as causing overexposure or reflection in the image.

[0054] Optionally, in one embodiment of this application, the step of dividing the visual data into grid regions includes: determining the illumination field of each headlight of the vehicle, and dividing the visual data into grid regions from near to far based on the illumination field and the shooting area of ​​the vehicle camera. This limitation in the embodiment of this application avoids the possibility of dividing areas of the visual data that do not contribute to driving assistance and thus affecting the adjustment of the vehicle's headlights. It also reduces the number of grid regions that need to be considered during data processing, making the effective areas have a more significant impact on the quality of the visual data. Furthermore, it reduces the amount of data to be processed when evaluating the quality of the visual data, thereby improving the accuracy and efficiency of controlling and adjusting the vehicle's headlights according to different dimensions to a certain extent.

[0055] Optionally, in one embodiment of this application, when assigning corresponding quality influence weight ratio parameters to different visual feature parameters of each grid region, the quality influence weight ratio assigned to grid regions closer to the vehicle headlights is set to be greater than that assigned to grid regions farther from the vehicle headlights. Furthermore, the quality influence weight ratio assigned to grid regions where the illumination fields of multiple headlights are superimposed is greater than that assigned to non-superimposed grid regions. This step in the embodiment of this application, by imposing the above-mentioned limitations on the assigned quality influence weight ratio parameters, improves the scientific rationality of the assigned quality influence weight ratios.

[0056] Optionally, in one embodiment of this application, before assigning corresponding quality influence weight ratio parameters to different visual feature parameters contained in the vehicle's visual data based on the vehicle's driving trajectory, the vehicle's behavioral intention prediction information, and the behavioral intention prediction information of other road users, the method further includes: predicting the behavior of other road users based on the visual data and / or radar data collected by the vehicle to obtain behavioral intention prediction information of other road users; and determining the behavioral intention prediction information of the vehicle based on the vehicle's control logic information and vehicle body state information. This allows for obtaining high-precision behavioral intention prediction information while ensuring a smaller amount of data needs to be processed.

[0057] Optionally, in one embodiment of this application, determining the vehicle's behavioral intention prediction information based on the vehicle's control logic information and vehicle body state information includes: determining multi-dimensional driving influence factors that determine the vehicle's control logic information and vehicle body state information; assigning corresponding weight parameters to different dimensions of driving influence factors; and obtaining the vehicle's behavioral intention prediction information based on the parameter values ​​of the current multi-dimensional driving influence factors and the weight parameters. This embodiment provides an example: information such as vehicle acceleration, speed, steering angle, vehicle tilt angle, and vehicle navigation information are determined as multi-dimensional driving influence factors. Different weight parameters are set for these driving influence factors under different dimensions of driving control logic, so as to predict the vehicle's behavioral intention prediction information for the next stage based on the determined influence factor parameter values. If the weight parameters of driving shadow factors such as speed / acceleration are set higher under the straight driving control logic, and the weight parameters of driving factors such as steering angle and vehicle tilt angle are set higher under the steering or parking control logic, the driving intention prediction information of the vehicle obtained when driving prediction is performed based on the parameter values ​​of the determined driving influencing factors and the corresponding weight parameters will be more accurate and reliable.

[0058] Optionally, in one embodiment of this application, the method further includes: when the quality assessment information is higher than or equal to the preset quality, controlling and adjusting the vehicle headlights according to the predicted driving trajectory. In this embodiment, when it is determined that the quality assessment information is higher than the preset quality, it indicates that the current visual data can meet the driving needs of the vehicle at the current stage. No additional factors need to be introduced to control and adjust the vehicle headlights; it is only necessary to control the headlights that meet the requirements of the corresponding driving position based on the predicted driving trajectory information. This reduces the complexity of the headlight control and adjustment described in this embodiment and the resource consumption of the vehicle data processing during the control and adjustment process.

[0059] This application provides a method for controlling vehicle headlights. Based on the vehicle's inertial navigation data and driving map information, a predicted driving trajectory of the vehicle is obtained. Based on the predicted driving trajectory, the vehicle's predicted behavioral intentions, and the predicted behavioral intentions of other road users, corresponding quality influence weight ratio parameters are assigned to different visual feature parameters included in the visual data collected by the vehicle. Based on the quality influence weight ratio parameters, quality assessment information of the visual data collected by the vehicle is determined. When the quality assessment information is determined to be lower than a preset quality, the vehicle headlights are controlled and adjusted according to the quality assessment information. The control and adjustment include at least one of adjusting the brightness of the headlights, adjusting the low beam or high beam, and adjusting the illumination field angle. This application, through the above-described vehicle headlight control method, can provide appropriate illumination area control according to the driving environment, meeting the high standard requirements of road condition and environmental perception data for intelligent driving vehicles, providing better driving assistance for intelligent driving vehicles, and improving the driving safety and user driving experience of intelligent driving vehicles.

[0060] Example 2

[0061] Based on the vehicle headlight control method provided in Embodiment 1 of this application, this embodiment also provides a vehicle headlight control device, such as... Figure 2 As shown, Figure 2 This is a schematic diagram of the structure of a vehicle headlight control device 20 provided in an embodiment of this application. The vehicle headlight control device 20 includes:

[0062] The planning module 201 is used to obtain the predicted driving trajectory of the vehicle based on the vehicle's inertial navigation data and driving map information.

[0063] The allocation module 202 is used to allocate corresponding quality influence weight ratio parameters to different visual feature parameters contained in the visual data collected by the vehicle based on the predicted driving trajectory of the vehicle, the predicted behavioral intention information of the vehicle, and the predicted behavioral intention information of other road users.

[0064] The calculation module 203 is used to determine the quality assessment information of the visual data collected by the vehicle based on the quality influence weight ratio parameter.

[0065] The control module 204 is used to control and adjust the vehicle headlights according to the quality assessment information when it is determined that the quality assessment information is lower than the preset quality. The control and adjustment includes at least one of adjusting the brightness of the vehicle headlights, adjusting the low beam or high beam, and adjusting the illumination field angle.

[0066] Optionally, in one embodiment of this application, the allocation module 202 is further configured to:

[0067] The visual data is divided into grid regions;

[0068] Determine the visual feature parameters of the visual data corresponding to each grid region, wherein the visual feature parameters include at least one of the following: brightness, contrast, and sharpness of the visual image.

[0069] Based on the predicted driving trajectory of the vehicle, the predicted behavioral intention of the vehicle, and the predicted behavioral intention of other road users, a corresponding quality influence weight ratio parameter is assigned to different visual feature parameters of each grid area.

[0070] Based on the quality influence weight ratio parameter, the feature weighted average value of each grid region is calculated, and the feature weighted average value is used as the quality assessment information of the visual data.

[0071] Optionally, in one embodiment of this application, the control module 204 is further configured to:

[0072] The weighting ratio parameter of the quality impact during the current driving phase is fixed;

[0073] Based on a fixed quality influence weight ratio parameter, the quality assessment information of the visual data collected by the vehicle after control and adjustment is recalculated.

[0074] When the recalculated quality assessment information is greater than or equal to the preset quality, the control and adjustment of the vehicle headlights based on the quality assessment information shall be stopped.

[0075] Optionally, in one embodiment of this application, the allocation module 202 is further configured to:

[0076] Determine the illumination field of each headlight of the vehicle;

[0077] Based on the illumination field and the shooting area of ​​the vehicle-mounted camera, the visual data is divided into grid regions from near to far.

[0078] Optionally, in one embodiment of this application, the allocation module 202 is further configured to, when allocating corresponding quality influence weight ratio parameters for different visual feature parameters of each grid region, set the quality influence weight ratio allocated to grid regions closer to the vehicle headlights to be greater than the quality influence weight ratio allocated to grid regions farther from the vehicle headlights, and the quality influence weight ratio allocated to grid regions where the illumination fields of multiple headlights are superimposed is greater than the quality influence weight ratio allocated to non-superimposed grid regions.

[0079] Optionally, in one embodiment of this application, the device 20 further includes a preprocessing module (not shown in the figures). This preprocessing module is used to predict the behavior of other road users based on the visual data and / or radar data collected by the vehicle before assigning corresponding quality influence weight ratio parameters to different visual feature parameters contained in the vehicle's visual data based on the vehicle's driving trajectory, the vehicle's behavior intention prediction information, and the behavior intention prediction information of other road users; and to determine the vehicle's behavior intention prediction information based on the vehicle's control logic information and vehicle body state information.

[0080] Optionally, in one embodiment of this application, the preprocessing module is further configured to: determine multi-dimensional driving influencing factors that determine the control logic information and vehicle body state information of the vehicle; assign corresponding weight parameters to driving influencing factors of different dimensions; and obtain the vehicle's behavioral intention prediction information based on the parameter values ​​of the current multi-dimensional driving influencing factors of the vehicle and in combination with the weight parameters.

[0081] Optionally, in one embodiment of this application, the control module 204 is further configured to: control and adjust the vehicle headlights according to the predicted driving trajectory when the quality assessment information is higher than or equal to the preset quality.

[0082] This application provides a vehicle headlight control device. A planning module acquires the predicted driving trajectory of the vehicle based on its inertial navigation data and driving map information. An allocation module assigns corresponding quality influence weight ratio parameters to different visual feature parameters included in the visual data collected by the vehicle, based on the predicted driving trajectory, the vehicle's predicted behavioral intention information, and the predicted behavioral intention information of other road users. A calculation module determines the quality assessment information of the visual data collected by the vehicle based on the quality influence weight ratio parameters. A control module, when determining that the quality assessment information is lower than a preset quality, controls and adjusts the vehicle headlights according to the quality assessment information. The control adjustment includes at least one of adjusting the brightness of the headlights, adjusting the low beam or high beam, and adjusting the illumination field angle. The device described in this application has a simple structure and is easy to implement. Through step-by-step processing between various modules, the vehicle headlight control method can be more suitable for the current driving needs of the vehicle, meeting the business requirements of obtaining high-standard road conditions and environments for intelligent driving vehicles, thereby providing better driving assistance for intelligent driving vehicles, improving driving safety, and enhancing the user's driving experience.

[0083] Example 3

[0084] This application also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements any of the vehicle headlight control methods described in Embodiment 1 of this application.

[0085] Example 4

[0086] This application also provides an electronic device, such as... Figure 3 As shown, Figure 3 This application provides a schematic diagram of the structure of an electronic device 30, which includes:

[0087] One or more processors 301, communication interface 302, memory 303 and communication bus 304, the processors 301, memory 303 and communication interface 302 communicate with each other through communication bus 304;

[0088] Memory 303 is used to store one or more programs;

[0089] When the one or more programs are executed by the one or more processors 301, the one or more processors 301 implement any of the vehicle headlight control methods described in Embodiment 1 of this application.

[0090] This application has now described specific embodiments of the subject matter. In some cases, the actions described in the claims can be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing can be advantageous.

[0091] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system layer onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0092] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0093] The system layers, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0094] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0095] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0096] Those skilled in the art will understand that embodiments of this application can be provided as methods, system-level, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0097] This application can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific transactions or implement specific abstract data types. This application can also be practiced in distributed computing environments where transactions are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0098] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system-level embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0099] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for controlling vehicle headlights, characterized in that, include: Based on the vehicle's inertial navigation data and driving map information, the predicted driving trajectory of the vehicle is obtained; Based on the predicted driving trajectory of the vehicle, the predicted behavioral intentions of the vehicle, and the predicted behavioral intentions of other road users, corresponding quality influence weight ratio parameters are assigned to different visual feature parameters contained in the visual data collected by the vehicle. Based on the aforementioned quality impact weight ratio parameter, the quality assessment information of the visual data collected by this vehicle is determined; When the quality assessment information is determined to be lower than the preset quality, the vehicle headlights are controlled and adjusted according to the quality assessment information. The control and adjustment include at least one of the following: adjusting the brightness of the vehicle headlights, adjusting the low beam or high beam, and adjusting the illumination field angle.

2. The vehicle headlight control method according to claim 1, characterized in that, The method of assigning corresponding quality influence weight ratio parameters to different visual feature parameters contained in the visual data collected by the vehicle, based on the predicted driving trajectory of the vehicle, the predicted behavioral intention information of the vehicle, and the predicted behavioral intention information of other road users, includes: The visual data is divided into grid regions; Determine the visual feature parameters of the visual data corresponding to each grid region, wherein the visual feature parameters include at least one of the following: brightness, contrast, and sharpness of the visual image. Based on the predicted driving trajectory of the vehicle, the predicted behavioral intention of the vehicle, and the predicted behavioral intention of other road users, a corresponding quality influence weight ratio parameter is assigned to different visual feature parameters of each grid area. Based on the quality influence weight ratio parameter, the feature weighted average value of each grid region is calculated, and the feature weighted average value is used as the quality assessment information of the visual data.

3. The vehicle headlight control method according to claim 2, characterized in that, When it is determined that the quality assessment information is lower than a preset quality, the headlights of the vehicle are controlled and adjusted according to the quality assessment information, including: The weighting ratio parameter of the quality impact during the current driving phase is fixed; Based on a fixed quality influence weight ratio parameter, the quality assessment information of the visual data collected by the vehicle after control and adjustment is recalculated. When the recalculated quality assessment information is greater than or equal to the preset quality, the control and adjustment of the vehicle headlights based on the quality assessment information shall be stopped.

4. The vehicle headlight control method according to claim 2, characterized in that, The step of dividing the visual data into grid regions includes: Determine the illumination field of each headlight of the vehicle; Based on the illumination field and the shooting area of ​​the vehicle-mounted camera, the visual data is divided into grid regions from near to far.

5. The vehicle headlight control method according to claim 4, characterized in that, When assigning corresponding quality influence weight ratio parameters to different visual feature parameters of each grid region, the quality influence weight ratio assigned to grid regions closer to the headlights is set to be greater than that assigned to grid regions farther from the headlights. Furthermore, the quality influence weight ratio assigned to grid regions where the illumination fields of multiple headlights are superimposed is greater than that assigned to non-superimposed grid regions.

6. The vehicle headlight control method according to claim 1, characterized in that, Before assigning corresponding quality influence weight ratio parameters to different visual feature parameters contained in the vehicle's visual data based on the vehicle's driving trajectory, the vehicle's behavioral intention prediction information, and the behavioral intention prediction information of other road users, the method further includes: Based on the visual data and / or radar data collected by this vehicle, the behavior of other road users is predicted, and information on the behavioral intentions of other road users is obtained. Based on the vehicle's control logic information and vehicle body status information, the vehicle's behavioral intention prediction information is determined.

7. The vehicle headlight control method according to claim 6, characterized in that, The determination of the vehicle's behavioral intention prediction information based on the vehicle's control logic information and vehicle status information includes: Identify the multi-dimensional driving influencing factors that determine the vehicle's control logic information and body status information; Assign corresponding weight parameters to driving influencing factors of different dimensions; Based on the parameter values ​​of the current multi-dimensional driving influencing factors of the vehicle, and combined with the weight parameters, the behavioral intention prediction information of the vehicle is obtained.

8. The vehicle headlight control method according to claim 1, characterized in that, The method further includes: when the quality assessment information is higher than or equal to the preset quality, controlling and adjusting the vehicle headlights according to the predicted driving trajectory.

9. A control device for vehicle headlights, characterized in that, include: The planning module is used to obtain the predicted driving trajectory of the vehicle based on the vehicle's inertial navigation data and driving map information; The allocation module is used to assign corresponding quality influence weight ratio parameters to different visual feature parameters contained in the visual data collected by the vehicle, based on the predicted driving trajectory of the vehicle, the predicted behavioral intention information of the vehicle, and the predicted behavioral intention information of other road users. The calculation module is used to determine the quality assessment information of the visual data collected by the vehicle based on the quality influence weight ratio parameter. The control module is used to control and adjust the vehicle headlights according to the quality assessment information when it is determined that the quality assessment information is lower than the preset quality. The control and adjustment includes at least one of adjusting the brightness of the vehicle headlights, adjusting the low beam or high beam, and adjusting the illumination field angle.

10. A computer storage medium, characterized in that, The computer storage medium stores computer-executable instructions, which, when executed, perform the vehicle headlight control method as described in any one of claims 1-8.

Images