Assisted driving control method and device based on visual distance detection

Abstract

The application provides an auxiliary driving control method and device based on visual distance detection. The method is applied to a vehicle equipped with an image acquisition device and supporting an auxiliary driving function, and comprises the following steps: acquiring a road image collected by the image acquisition device for a current road, and determining a maximum visual distance of the vehicle at a current time based on the road image, when the vehicle starts the auxiliary driving function; determining a minimum safe recognition distance of the vehicle at the current time according to road information of the current road and current driving information of the vehicle; and degrading or closing the auxiliary driving function at least when the maximum visual distance is not greater than the minimum safe recognition distance.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of auxiliary driving of vehicles, and in particular to an auxiliary driving control method and device based on visual distance detection. BACKGROUND

[0002] With the rapid development of auxiliary driving technology, more and more vehicles supporting auxiliary driving function go on the road. Meteorological factors (such as rain, snow, fog, haze, etc.), light factors (such as low illumination at night, backlight, glare, etc.) and other factors may affect the visibility (i.e. maximum visual distance) outside the vehicle, which has a significant impact on driving safety. The visibility determines whether the environment outside the vehicle meets the operational design domain (ODD) of the auxiliary driving function. How to accurately determine whether the current environment meets the ODD of the auxiliary driving function, so as to precisely control the start and stop and upgrade of the function, is a key problem to improve the user experience of the function.

[0003] In related technologies, a rain sensor is usually used to directly detect the amount of rain, and the visibility is inferred accordingly. The accuracy of this method depends on the mapping relationship between rainfall and visibility. However, since the visibility is affected by not only rainfall but also fog, light and other factors, it is difficult to accurately establish the above mapping relationship, resulting in inaccurate visibility prediction. Alternatively, the distance of the vehicle in front can be directly identified through image processing to infer the current visibility. However, this method can only be implemented when there is another vehicle in front of the host vehicle, and the front vehicle must be in the extremely small interval of the like-to-see-not-to-see to achieve accurate prediction. The application range of the scheme is narrow, and the overall prediction accuracy is still low. The above related technical solutions cannot accurately evaluate the visibility outside the vehicle, and thus cannot effectively realize precise control of the auxiliary driving function, which needs to be improved. SUMMARY

[0004] Therefore, the present application provides an auxiliary driving control method and device based on visual distance detection, which determines the maximum visual distance at the current time based on the road image collected for the current road, thereby accurately determining the visibility and precisely controlling the degradation or shutdown of the auxiliary driving function.

[0005] Specifically, the present application is implemented by the following technical solutions:

[0006] According to a first aspect of the present application, an auxiliary driving control method based on visual distance detection is provided, which is applied to a vehicle equipped with an image acquisition device and supporting an auxiliary driving function. The method comprises:

[0007] In a case where the vehicle starts the auxiliary driving function, a road image collected by the image collection device for a current road is acquired, and a maximum visible distance of the vehicle at a current time is determined based on the road image;

[0008] A minimum safe recognition distance of the vehicle at the current time is determined according to road information of the current road and current driving information of the vehicle;

[0009] In a case where the maximum visible distance is not greater than the minimum safe recognition distance, the auxiliary driving function is degraded or closed.

[0010] According to a second aspect of the present application, an auxiliary driving control device based on visible distance detection is provided, which is applied to a vehicle equipped with an image collection device and supporting an auxiliary driving function, and the device comprises:

[0011] A visible distance determination unit is configured to acquire a road image collected by the image collection device for a current road in a case where the vehicle starts the auxiliary driving function, and determine a maximum visible distance of the vehicle at a current time based on the road image;

[0012] A safe distance determination unit is configured to determine a minimum safe recognition distance of the vehicle at the current time according to road information of the current road and current driving information of the vehicle;

[0013] An auxiliary driving control unit is configured to degrade or close the auxiliary driving function in a case where the maximum visible distance is not greater than the minimum safe recognition distance.

[0014] According to a third aspect of the present application, a vehicle is provided, which is equipped with an image collection device and supports an auxiliary driving function, and the vehicle comprises:

[0015] A processor, a memory for storing processor-executable instructions, and a plurality of sensors;

[0016] The processor is configured to implement the method according to the first aspect by running the executable instructions.

[0017] According to a fourth aspect of the present application, a computer program and / or instructions are provided, which are executed by a processor to implement the steps of the method according to the first aspect.

[0018] The technical solutions provided by the present application can at least have the following beneficial effects:

[0019] Through the above embodiment, in the case of starting the auxiliary driving function, the vehicle can acquire the road image collected by the image collection device for the current road, and determine the maximum visible distance of the vehicle at the current time based on the road image; then determine the minimum safe recognition distance thereof at the current time according to the road information of the current road and the current driving information thereof; and finally at least in the case that the maximum visible distance is not greater than the minimum safe recognition distance, degrade or close the auxiliary driving function.

[0020] It can be understood that the present scheme does not distinguish various factors affecting visibility, but directly collects images of the current road as the object (various factors may affect the image content and quality) and determines the maximum visible distance at this time through image recognition and other related algorithms, so as to accurately determine whether the current environment exceeds the ODD of the auxiliary driving function. The present scheme not only does not need a rain sensor to directly detect the rainfall, but also does not need the preceding vehicle to always maintain the distance similar to the unseen distance (even completely does not need the preceding vehicle to exist, which is applicable to the non-following vehicle scene), which not only simplifies the determination logic and accuracy of the maximum visible distance, but also helps to improve the control accuracy of the closing and degradation of the auxiliary driving function. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 is a hardware structure schematic diagram of an auxiliary driving system according to an example embodiment.

[0022] Figure 2 is a software architecture schematic diagram of an auxiliary driving system according to an example embodiment.

[0023] Figure 3 is a flowchart of an auxiliary driving control method based on visible distance detection according to an example embodiment.

[0024] Figure 4 is a road image schematic diagram in a rainfall environment and a glare environment according to an example embodiment.

[0025] Figure 5 is a schematic structure diagram of a vehicle according to an example embodiment.

[0026] Figure 6 is a block diagram of an auxiliary driving control device based on visible distance detection according to an example embodiment. DETAILED DESCRIPTION

[0027] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0028] It should be noted that the steps of the corresponding methods in other embodiments are not necessarily performed in the order shown and described in this application. In some other embodiments, the methods may include more or fewer steps than those described in this application. Furthermore, a single step described in this application may be broken down into multiple steps in other embodiments; and multiple steps described in this application may be combined into a single step in other embodiments.

[0029] In related technologies, rain sensors are typically used to directly detect rainfall and infer visibility based on this. The accuracy of this method relies on the mapping relationship between rainfall and visibility. However, since visibility is affected not only by rainfall but also by various factors such as fog and light, it is impossible to accurately establish this mapping relationship, leading to inaccurate visibility predictions. Alternatively, image processing can be used to directly identify the distance to vehicles ahead and infer current visibility. However, this method only works when other vehicles are present in front of the vehicle, and requires the vehicles ahead to be within a very small, barely visible area for accurate prediction. This limits the applicability of the solution, and the overall prediction accuracy remains low. None of the above-mentioned technical solutions can accurately assess visibility outside the vehicle, thus hindering precise control of assisted driving functions and urgently requiring improvement.

[0030] In view of the technical problems existing in the related technologies, this application proposes an assisted driving control scheme based on line-of-sight distance detection, which will be described in detail below with reference to the accompanying drawings and related embodiments.

[0031] The assisted driving control scheme described in this application mainly involves the assisted driving system identifying the maximum visible distance of the vehicle in the current environment through visual images, and determining whether the current environment meets the ODD of assisted driving, thereby precisely controlling the function.

[0032] Figure 1 This is a schematic diagram of the hardware architecture of a driver assistance system shown in an embodiment of this application. Figure 1As shown, from the hardware perspective, the system can only include the vehicle 11, or can include both the vehicle 11 and the server 13. From the software perspective, the auxiliary driving system can include the visibility ODD detection module and the auxiliary driving control module. If the auxiliary driving system only includes the vehicle 11, the visibility ODD detection module and the auxiliary driving control module are both deployed locally on the vehicle 11, for example, in the domain controller of the vehicle 11. For example, the visibility ODD detection module and the auxiliary driving control module can be deployed in the domain controller (for example, the intelligent driving domain controller ADCU) of the auxiliary driving domain of the vehicle 11. It can be understood that the auxiliary driving system at this time is a vehicle-mounted system, and the system can even run offline. If the auxiliary driving system includes both the vehicle 11 and the server 13, any one of the visibility ODD detection module or the auxiliary driving control module can be deployed in the server 13, and the other module can be deployed locally on the vehicle. For example, the visibility ODD detection module can be deployed in the server 13 and the auxiliary driving control module can be deployed in the intelligent driving domain controller of the vehicle, and details are not described herein.

[0033] In addition to the domain control, the vehicle 11 can also be equipped with sensors for collecting external environment data, and the number and installation position of the sensors are not limited in the embodiments of the present application. For example, the sensors can include image acquisition devices (such as front-view cameras 111, side-view cameras 112, rear-view cameras 113, etc.), ranging radars 114 (such as laser radars Lider, millimeter wave radars Rader, ultrasonic radars, etc.), laser radars 114, millimeter wave radars, rain and fog sensors 115 (such as rain sensors, particulate matter sensors, haze sensors, etc.), etc., and details are not described herein. Of course, the vehicle can also be equipped with at least one in-vehicle sensor (such as an in-vehicle camera, an in-vehicle microphone, an in-vehicle biological sensor, an in-vehicle odor sensor, etc.) at a suitable position to realize corresponding vehicle-mounted functions, and the embodiments of the present application do not limit this.

[0034] In addition, in the case that the auxiliary driving system includes the server 13 or there is an interaction demand with the server 13, the vehicle can establish a network connection with the remote server 13 through a wireless communication module to interact with the server 13. For example, if the server 13 locally maintains high-precision map information, road section speed limit information, weather information, distance threshold information corresponding to the road section, etc., the vehicle 11 can initiate an acquisition request for specific information to the server 13 when there is a data acquisition demand, to receive the corresponding information returned by the other party.

[0035] The server 13 can be a physical server including a standalone host, or a virtual server carried by a host cluster, a cloud server, etc. In addition, the number, type, and specific interaction mode of the server 13 are not limited in the embodiments of the present application. The network 10 between the vehicle 11 and the server 13 can be a wireless network based on the communication mode supported by the corresponding device, and the present application does not limit the communication mode.

[0036] In addition, the vehicle (e.g., the vehicle 11) described in the present application can be a pickup truck, a sedan, an SUV (Sport Utility Vehicle), a van, a truck, etc. in terms of its functional form, and can be a fuel vehicle or a new energy vehicle (e.g., a hybrid vehicle, an electric vehicle, a hydrogen energy vehicle, a methanol energy vehicle, etc.) in terms of its power form. The specific form of the vehicle is not limited in the present application. In addition, the occupant 12 in the cabin can be a driver sitting in the driver's seat, and at least one passenger sitting in other positions can also be included in the vehicle. The number of occupants and their seating positions are not limited in the present application.

[0037] The assisted driving function described in the present application is used to assist the driver in driving the vehicle, such as Figure 1 The vehicle 11 provides the driver 12 with an assisted driving function based on data collected by various vehicle-mounted sensors, and details are not repeated. The assisted driving function can be adaptive cruise control (ACC), or intelligence cruise control (ICC), etc. Of course, the function can be implemented by L2, L3, or L4 assisted driving technology, and the present application does not limit this. In addition, the assisted driving function is also called intelligent driving in some scenarios, and the assisted driving system is also called a high-level driving assistance system, which is hereby explained.

[0038] However, it should be noted that the assisted driving function implemented by the assisted driving system described in the present application should comply with the relevant laws, regulations and standards of the corresponding country and region (e.g., the sales and / or use place of the vehicle), and provide corresponding operation interfaces for relevant personnel (e.g., the driver) to select authorization or refuse to use.

[0039] Figure 2 is a software architecture diagram of an assisted driving system according to an embodiment of the present application. As shown in Figure 2As shown, the driver assistance system includes a visibility ODD detection module and a driver assistance control module, both deployed within the vehicle's Automated Driving Control Unit (ADCU). The visibility ODD detection module acquires map information (i.e., a map MAP, such as a high-precision map) and environmental information collected by sensors (such as road images captured by image acquisition equipment, position information of objects ahead detected by ranging radar, and information on the type and severity of rain and fog detected by rain and fog sensors). Based on this information, it determines the vehicle's maximum visible distance at the current moment and then sends control commands (such as deactivation commands or downgrade commands) to the driver assistance control module based on the relative magnitude between this distance and the minimum safe recognition distance. Correspondingly, the driver assistance control module can respond to these commands by controlling the driver assistance function (such as downgrading or deactivating the function) and prompting the driver to take appropriate action.

[0040] Figure 3 This is a flowchart illustrating an exemplary embodiment of an assisted driving control method based on line-of-sight distance detection. This method is applied to vehicles equipped with image acquisition devices and supporting assisted driving functions, such as those used in… Figure 1 Vehicle 11 is shown. (As shown) Figure 3 As shown, the method includes steps 302-306. Step 302 can be executed by the visibility ODD detection module in the driver assistance system, and steps 304-306 can be executed by the driver assistance control module.

[0041] Step 302: When the vehicle has its assisted driving function activated, acquire the road image captured by the image acquisition device for the current road, and determine the maximum visible distance of the vehicle at the current moment based on the road image.

[0042] During vehicle operation, the driver assistance function can be activated by default or by a passenger (such as the driver or front passenger). Once activated, the vehicle is in driver assistance mode. This driver assistance function can include multiple levels, and the implementation logic of different levels can differ. For example, the vehicle's cruise speed (i.e., the speed at which it automatically maintains a constant speed) at different levels can be positively correlated with the level; for instance, a relatively higher cruise speed can be used at higher levels, while a relatively lower cruise speed is used at lower levels. And / or, the vehicle's minimum safe recognition distance at different levels can be positively correlated with the level; for instance, a relatively larger minimum safe recognition distance can be set for higher levels, and a relatively lower minimum safe recognition distance can be set for lower levels, etc., which will not be elaborated further.

[0043] After the auxiliary driving function is turned on, the image acquisition device can acquire a road image of the current road during the vehicle is driving according to any level, so that the auxiliary driving system can extract corresponding road information based on the image, and then determine the maximum visible distance of the vehicle according to the road information. It can be understood that the image acquisition device can take pictures at a preset interval, or continuously record videos at a preset sampling rate, and the auxiliary driving system can continuously process each image in turn and continuously determine the corresponding maximum visible distance, so the maximum visible distance determined according to any road image can be regarded as the maximum visible distance of the vehicle at the time when the image is taken.

[0044] The maximum visible distance (or simply visible distance) of the vehicle at the current time refers to the effective perception distance of the visual perception algorithm of the vehicle under the current environment (i.e. the external environment of the vehicle at the current time), that is, the distance between the farthest object that can be effectively recognized by the visual perception algorithm and the vehicle. In short, it is the farthest distance that the vehicle (specifically the image acquisition device) can "see" in the current external environment.

[0045] The visual perception algorithm can include various algorithms, for example, lane line recognition algorithms such as CNN (Convolutional Neural Network) and U-Net (U-Shaped Convolutional Neural Network), target detection algorithms such as YOLO and Faster R-CNN, and map matching algorithms.

[0046] It can be understood that rainfall, snowfall, fog, haze, dust, moonlight, street lamp lighting and other factors can affect the visibility under the current environment, and then affect the maximum visible distance of the vehicle. Among them, the worse the current environment, the lower the visibility, the smaller the determined maximum visible distance, and vice versa. For example, in the rainfall / snowfall scenario, the smaller the rain / snow (i.e. the smaller the rainfall / snowfall, the same below), the greater the visibility, and the greater the determined maximum visible distance; on the contrary, the greater the rain / snow, the smaller the visibility, and the smaller the determined maximum visible distance. Similarly, in the fog / haze / dust scenario, the smaller the fog / haze / dust concentration, the greater the visibility, and the greater the determined maximum visible distance; on the contrary, the greater the fog / haze / dust concentration, the smaller the visibility, and the smaller the determined maximum visible distance.

[0047] In addition, in the case that the vehicle travels at a certain speed, its deceleration capability is generally stable (i.e., the brake distance generally fluctuates little), and thus the smaller the maximum visible distance under the current environment, the lower the success rate of the vehicle to avoid obstacles through emergency braking (i.e., deceleration), i.e., the more dangerous; and the larger the minimum safe recognition distance, the higher the success rate of the vehicle to avoid obstacles through emergency braking, i.e., the safer. Conversely, in order to achieve safe driving, the vehicle can travel at a relatively high speed in the case that the maximum visible distance is large; and in the case that the maximum visible distance is small, the vehicle should travel at a relatively low speed to avoid the risk of failure of emergency obstacle avoidance due to too high speed under the current environment, and even cause an accident.

[0048] As mentioned above, the speed of the vehicle under different levels of assisted driving functions is generally different, and the ODD of the assisted driving function generally declares the minimum safe recognition distance suitable for different levels (i.e., in any level, the maximum visible distance of the vehicle is not greater than the minimum safe recognition distance of the level, which generally can ensure the safety of the vehicle driving). Therefore, the present scheme needs to detect the maximum visible distance of the vehicle to determine whether the current environment has exceeded the ODD of the assisted driving function, and to downgrade or even close the assisted driving function (after being closed, the vehicle can be slowed down and parked or taken over by the driver) when the maximum visible distance is not greater than the minimum safe recognition distance (i.e., indicating that the current environment has exceeded the ODD of the assisted driving function), so as to ensure the safety of driving.

[0049] The current road described in the present application is the road where the vehicle is located at the current time, which can be any type of road. For example, it can be a city ordinary road, a city viaduct, a highway, a ramp / bridge of a city viaduct or a highway, a rural road with physical lane lines or guide objects, etc., which is not limited in the present application. In addition, the image acquisition device can acquire road images in the direction of vehicle travel (such as forward direction or reverse direction) of the current road to ensure that the physical lane lines or guide objects on the current road are captured into the road images for subsequent identification.

[0050] In an embodiment, in order to ensure the accuracy of the subsequent identification result, after receiving the road image acquired by the image acquisition device, the assisted driving system can first determine whether the image can be used to determine the maximum visible distance of the vehicle.

[0051] For example, the image acquisition device can first determine whether it is malfunctioning based on the road image collected by the image acquisition device. For example, the image acquisition device can determine whether it is malfunctioning based on the image of the front of the road captured by the front-facing camera. Then, if it is determined that the image acquisition device is not malfunctioning, the maximum visible distance of the vehicle can be determined based on the road image. In this way, the problem of inaccurate subsequent recognition results caused by image distortion due to malfunction of the image acquisition device can be avoided, which helps to improve the accuracy of determining the maximum visible distance and the precision of functional control.

[0052] For example, the image acquisition device can first determine whether it is malfunctioning based on the road image collected by the image acquisition device. For example, the image acquisition device can determine whether it is malfunctioning based on the image of the front of the road captured by the front-facing camera. Then, if it is determined that the image acquisition device is not malfunctioning, the maximum visible distance of the vehicle can be determined based on the road image. In this way, the problem of inaccurate subsequent recognition results caused by image distortion due to malfunction of the image acquisition device can be avoided, which helps to improve the accuracy of determining the maximum visible distance and the precision of functional control.

[0053] Through the above two types of filtering principles, abnormal situations that temporarily or long-term affect visual perception such as reflection, backlight, glare, etc. can be effectively avoided, and data preparation for subsequent processing based on road images is done. Typical road images in a rain environment and a glare environment can be seen in FIG. 1, and will not be described again. Figure 4

[0054] In an embodiment, when determining the maximum visible distance of the vehicle at the current time based on the road image, the assisted driving system can use multiple ways.

[0055] ​For example, a guide line of the current road can be identified in the road image first (this step can directly use the identification result of the foregoing embodiment), and in the case that the guide line is identified, the farthest effective pixel points on the guide line and their position information in the image can be further determined. The farthest effective pixel points can be a preset number of adjacent pixel points (such as 4 or 10 adjacent pixel points) on the guide line farthest from the vehicle, which can accurately reflect the farthest position on the guide line that can be identified (i.e., “seen”) by the auxiliary driving system. The position information of the farthest effective pixel points in the road image can be that these pixel points are located in which row and which column of the image, and the like. Further, the maximum visible distance of the vehicle at the current time can be calculated based on the position information and the device parameters of the image acquisition device, that is, the distance between the position of the object represented by the farthest effective pixel points in the three-dimensional space and the position of the image acquisition device in the three-dimensional space. The specific calculation method is determined by the internal structure principle (such as optical path diagram, device size, and the like) of the image acquisition device, and the present application does not limit this. In this way, the auxiliary driving system can accurately calculate the maximum visible distance by means of the position information of the farthest effective pixel points in the road image.

[0056] The algorithm for identifying the farthest effective pixel points can be calibrated in advance by a specific marker to ensure that the auxiliary driving system 1 accurately identifies the farthest position on the guide line. The calibration can be completed in the design and development stage of the vehicle. For example, the design / development personnel can first perform basic calibration on the device parameters of the image acquisition device, such as calibrating its intrinsic parameters (i.e., given parameters of the device, such as camera focal length, lens distortion, and the like) and extrinsic parameters (such as camera installation height / ground clearance, pitch angle, yaw angle, and the like), to ensure that the system can accurately convert “planar distance between pixel points in the road image” into “spatial distance in the real world (i.e., the foregoing three-dimensional space)”. The foregoing conversion can be achieved by using related algorithms such as inverse perspective transformation (IPM), 3D space back calculation algorithm, camera projection model, and the like. For example, a lane line pixel point in the calibrated image is located in the 300th row, and the system can calculate its corresponding position 70 meters away from the ground.

[0057] It is assumed that the specific marker is a cone, and a mapping relationship between the lane line recognition distance and the cone recognition distance can be established in the calibration stage. For example, a standard cone with a height of 30 cm can be placed every 10 m on the test road (the color, size, shape, etc. of these cones need to be kept as consistent as possible). The test vehicle drives along the test road, and according to the shooting results of the camera installed on the test vehicle, the minimum distance at which the cone can be recognized (i.e. "how far can the cone be recognized at the shortest distance") and the maximum recognizable distance of the lane line are determined. For example, if the conclusion is "when the lane line recognition distance is less than or equal to 50 m, the cone is not clear at a distance of 50 m" after multiple tests, it can be set that as long as the lane line recognition distance is less than 50 m, the small target is also considered to be not clear. For example, lane line recognition can be equated to cone recognition (e.g. 4 pixel points at the far end of the lane line and 15 pixel points on the long side of the cone are calibrated and verified to confirm that the maximum visible distance under the same environment is the farthest end of the lane line, and beyond this distance is no longer effective).

[0058] Finally, the minimum safe recognition distance under different conditions is determined and recorded in the local production vehicle (i.e. the vehicle described above). The alarm threshold can be determined according to relevant laws, regulations and safety redundancy, for example, as shown in Table 1:

[0059] Table 1

[0060]

[0061] In the above embodiment, the guide line of the current road recognized from the road image can take different forms according to actual conditions. For example, it can be a real lane line actually drawn on the current road (such as a solid lane line, a lane dashed line, a lane guide line, etc.), which is suitable for roads with clear, complete and standard lane lines. Using a real lane line as a guide line can help improve the accuracy of subsequent recognition.

[0062] Alternatively, the guide line can also be a virtual guide line fitted according to guide objects arranged on the current road, wherein the guide objects can be water marks, guardrails, cones, road rocks, and isolation belts, etc. At this time, the virtual guide line can be generated by fitting feature points of the same part of multiple guide objects on the current road, such as for cones placed in sequence on the road surface, the vertices of each cone can be connected using a smooth curve to obtain a virtual guide line. This method is suitable for current roads that do not have real lane lines but have guide objects placed according to certain rules. This method can still relatively accurately fit a virtual guide line for subsequent determination of the maximum visible distance without using a real lane line.

[0063] Alternatively, if the vehicle is currently located on a preset section of the current road and the real lane lines or the virtual guide lines are interrupted, a compensated guide line obtained by compensating for the real lane lines or the virtual guide lines can be used as the guide line for the current road. For example, the preset section can be a section within a preset distance after an intersection or turn (i.e., in the direction of oncoming traffic). Since lane lines on the road are usually interrupted at intersections and turns, if the recognition logic for ordinary road sections is still used at intersections and turns, the vehicle may mistakenly believe that visibility is too low and forcibly disengage from assisted driving because it cannot see lane lines at a distance in front of it. This method, by generating compensated lane lines in the road image for special road sections (i.e., intersections, turns, etc.) lacking lane lines (real lane lines or virtual lane lines) and using them as guide lines, ensures that the assisted driving system can still see the guide lines in these road sections, thereby effectively avoiding the abnormal situation where the vehicle forcibly disengages from assisted driving when passing through the aforementioned special road sections. Understandably, this solution aims to make the driver assistance system "smarter," enabling it to recognize that "lane lines shouldn't exist here in the first place." In other words, it teaches the system "not to panic at the sight of a broken lane line, but to first check if it's at an intersection or turn—if there are guide lines or signs, it indicates normal design and not reduced visibility due to excessive rain / fog; only when nothing can be seen is there truly low visibility." This method compensates for lane line breaks during subsequent processing, rather than immediately triggering an alarm or suspending driver assistance upon detection of a broken lane line, thus improving the continuity and stability of the vehicle's driver assistance system.

[0064] The aforementioned embodiment determines the maximum visibility distance by identifying the guide lines of the current road. In practice, it is also possible to determine the maximum visibility distance directly based on the road image without identifying the guide lines of the current road.

[0065] In one embodiment, road images can be input into a pre-trained visibility distance prediction model for analysis and inference, and the maximum visibility distance of the vehicle at the current moment can be received from the model's inference output. This approach is logically simple and efficient in actual operation, and its powerful inference capabilities enable more accurate prediction of the maximum visibility distance, thus improving the efficiency and accuracy of distance determination.

[0066] The visual distance prediction model can be built based on any form of neural network framework and trained in a supervised or unsupervised manner. Taking supervised training as an example, sample data corresponding to driving cases can be obtained in advance, and each sample data includes a sample road image collected during vehicle driving and a sample maximum visual distance confirmed for authenticity (the sample distance can be manually labeled by a technician or generated by other labeling software and used as a label of the sample data). Through the above training, the obtained visual distance prediction model can accurately and efficiently predict the maximum visual distance of the vehicle at the current time based on the road image.

[0067] In addition, the visual distance prediction model can be trained by using any type of large multimodal model (Large Multimodal Model, LMM, which can identify and process visual, text, audio, and other multi-modal data) to ensure that the visual distance prediction model can output accurate reasoning results based on multi-modal data. For example, a vision language model (Vision-Language Model, VLM) can be used, which is a multi-modal artificial intelligence model combining computer vision (Computer Vision, CV) and natural language processing (Natural Language Processing, NLP) capabilities, capable of understanding and processing image (or video) and text information simultaneously, and establishing a connection between the two, thereby achieving more complex tasks. The visual distance prediction model implemented by the VLM can accurately determine the maximum visual distance based on its powerful image recognition and analysis capabilities.

[0068] In step 304, the minimum safe recognition distance of the vehicle at the current time is determined according to the road information of the current road and the current driving information of the vehicle.

[0069] It is not written in this step that the current driving information needs to obtain the road information of the current road and the current driving information of the vehicle. The road information can include the road type of the current road, the speed limit information of the current section (such as the maximum speed limit of 120 km / h and the minimum speed limit of 80 km / h on a highway section, the maximum speed limit of 60 km / h on a highway ramp, etc.), the turning radius of the front intersection / turning, etc. The current driving information of the vehicle can include the current speed, the maximum braking distance, etc.

[0070] In an embodiment, when determining the minimum safe recognition distance according to the road information of the current road and the current driving information of the vehicle, a plurality of ways can be used. For example, the vehicle can maintain locally or obtain from the cloud (such as Figure 1The server 13 shown acquires a safe distance mapping relationship (such as a pre-calibrated mapping table), and then queries the minimum safe recognition distance in the mapping relationship that matches the road type of the current road and / or the current speed of the vehicle. In the case where the safe distance mapping relationship records the mapping relationship between road information (such as road type) and minimum safe recognition distance, the minimum safe recognition distance matching the current road information (i.e. the current road type) in the mapping relationship can be queried as the minimum safe recognition distance of the vehicle at the current time according to the road information of the current road. Or, in the case where the safe distance mapping relationship records the mapping relationship between driving information (such as speed) and minimum safe recognition distance, the minimum safe recognition distance matching the current driving information (i.e. the current speed) in the mapping relationship can be queried as the minimum safe recognition distance of the vehicle at the current time according to the current driving information of the vehicle. And in the case where the safe distance mapping relationship records the mapping relationship between road type and speed and minimum safe recognition distance, the corresponding minimum safe recognition distance in the mapping relationship can be queried as the minimum safe recognition distance of the vehicle at the current time according to the road type of the current road and the current speed of the vehicle.

[0071] For example, in the case where the safe distance mapping relationship records the mapping relationship between road type and speed and minimum safe recognition distance, the mapping relationship can be as shown in Table 2 below;

[0072] Table 2

[0073]

[0074] And / or, the minimum safe recognition distance can also be calculated according to the maximum speed limit of the current road (i.e. the maximum speed of the vehicle when driving on the current road) and the maximum deceleration of the vehicle during deceleration on the current road (i.e. the deceleration of the vehicle when the maximum braking force is applied to the tires), and the specific calculation formula is not repeated. This mode refers to the maximum speed limit of the current road, and can determine a suitable minimum safe recognition distance while ensuring that the vehicle does not exceed the speed (in accordance with relevant regulations).

[0075] Of course, similar to the aforementioned maximum visible distance, the minimum safe recognition distance can also be predicted based on the road information of the current road and / or the current driving information of the vehicle by calling a pre-trained model, or predicted based on the maximum speed limit of the current road and the maximum deceleration of the vehicle by calling a model. In the prediction process, various information such as road slope, tire material, road surface water / icing conditions, etc. can also be referred to, which is not repeated.

[0076] Step 306, at least in the case where the maximum visible distance is not greater than the minimum safe recognition distance, the auxiliary driving function is degraded or closed.

[0077] As can be known from the meanings of the maximum visible distance and the minimum safe recognition distance, the maximum visible distance is equal to the minimum safe recognition distance, which indicates that the current environment where the vehicle is located is just at the ODD boundary of the assisted driving function (specifically, the ODD boundary corresponding to the current level); if the maximum visible distance is less than the minimum safe recognition distance, it indicates that the current environment where the vehicle is located has exceeded the ODD of the assisted driving function. Therefore, when the maximum visible distance is not greater than (i.e., less than or equal to) the minimum safe recognition distance, the processing of downgrading (i.e., running the assisted driving function at a lower level) or shutting down (i.e., directly exiting the assisted driving function) the assisted driving function can effectively ensure that the vehicle stops providing the assisted driving service in an inappropriate environment or ensures that the assisted driving service is provided according to the appropriate level matched to the current environment, thereby improving the driving safety.

[0078] In an embodiment, as can be known from the description of step 306, the "maximum visible distance not greater than the minimum safe recognition distance" is a necessary condition for downgrading or shutting down the assisted driving function. In addition, other preset associated conditions can also be considered to achieve more stringent function control. For example, the assisted driving function can be downgraded or shut down when the maximum visible distance is not greater than the minimum safe recognition distance, and the preset associated conditions of the current road are met.

[0079] The preset associated conditions can include that the map information indicates that the current position of the vehicle is located in a preset road section of the current road, and the distance between the current position and the end point of the guide line of the current road is greater than the minimum safe recognition distance. The map information is the map information of the vehicle. Figure 2The map MAP shown can be a high-precision map stored in a cloud server or a low-precision map maintained locally by a vehicle, and the present application does not limit this. If the distance between the vehicle and the end of the guide line of the current road is greater than the minimum safe recognition distance, it means that the vehicle is far enough from the break point of the guide line, such as a distance from the intersection. On the contrary, if the distance between the vehicle and the end of the guide line of the current road is not greater than the minimum safe recognition distance, it means that the vehicle has approached the intersection. As mentioned earlier, the position of the intersection or the turn will definitely have a guide line, so the maximum visible distance determined according to the guide line is less than the real maximum visible distance in the current environment, which leads to the necessary condition that the maximum visible distance is not greater than the minimum safe recognition distance being met, but the real maximum visible distance may not be less than the minimum safe recognition distance at this time, so only in the case where the above necessary condition is met, the auxiliary driving function is directly degraded or closed, which may cause a false judgment, resulting in the vehicle suddenly degrading or exiting the auxiliary driving in good visibility, seriously affecting the user's experience of the auxiliary driving function. Through the above setting and judgment of the preset associated condition, further judgment is made on the basis of the foregoing necessary condition, which can effectively avoid the abnormal situation of forcibly degrading or closing the auxiliary driving function due to the disappearance of the lane line near the intersection or the turn in good visibility, and improve the user's experience of the auxiliary driving function.

[0080] And / or, the preset associated condition can also include: the duration of the maximum visible distance being not greater than the minimum safe recognition distance, reaching a time threshold corresponding to the road information of the current road and the current driving information of the vehicle. In other words, the foregoing necessary condition needs to be continuously met for a certain duration before the auxiliary driving function is controlled to be closed or degraded, rather than being immediately closed or degraded as soon as the condition is met. The time threshold can be determined according to the lane and the speed, and can be set to 2.4s, for example, that is, after the necessary condition of "the maximum visible distance being less than the minimum safe recognition distance" is continuously met for 2.4s, the auxiliary driving function is degraded or closed. In this way, false judgments caused by reflection, backlight, glare, and alternating light and dark caused by streetlights can be effectively avoided, and the running stability of the auxiliary driving function is improved.

[0081] In an embodiment, when the auxiliary driving function is degraded or turned off, a closing prompt information of the function can be output to the driver of the vehicle, such as "current visibility is low, will slow down soon" or "current visibility is too low, will exit the auxiliary driving, please take over the vehicle immediately". The closing prompt information can be output to the driver in the form of displaying text (such as pop-up reminder on the instrument screen, central control screen, etc.), playing voice, or outputting a vibration signal of a specific frequency through the steering wheel or seat to remind the driver, and the like, which will not be described herein. After receiving the closing prompt information, if the driver can take over the vehicle in time (such as holding the steering wheel, stepping on the brake, etc.), the vehicle will run in response to the operation of the driver; otherwise, if the driver still does not take over the vehicle after a preset time (such as 10s), the auxiliary driving function can be degraded (such as forced to slow down) automatically. The vehicle can also be controlled to automatically park on the roadside, turn on the double flash and fog lights, and the like in the auxiliary driving mode, but should not be directly exited from the auxiliary driving function, so as to avoid accidents caused by out-of-control vehicle without human control.

[0082] In an embodiment, the auxiliary driving level of the vehicle at the current time can be referred to as the current auxiliary driving level, and when the auxiliary driving function is degraded, the expected auxiliary driving level corresponding to the maximum visible distance can be determined first, and the first cruise speed of the current auxiliary driving level is higher than the second cruise speed of the expected auxiliary driving level; then the vehicle is degraded from the current auxiliary driving level to the expected auxiliary driving level, and the degradation includes controlling the vehicle to slow down from the current speed to the second cruise speed. The first cruise speed and the second cruise speed can be a certain speed value or a certain speed interval, and the current speed can be the first cruise speed or not. However, it can be understood that the current speed should be greater than the second cruise speed, and then it is necessary to slow down. This way can control the vehicle to degrade the auxiliary driving function by slowing down, thereby improving the driving safety of the vehicle in the low-visibility environment.

[0083] In an embodiment, the vehicle is equipped with multiple sensors, each of which can provide its own detection result for the current environment (i.e. multi-sensor fusion technology), and the assistant driving system can control the assistant driving function using the fusion result of these detection results. In this case, if no front object is identified in the road image and the ranging radar detects a front object, the assistant driving function can be degraded to a level matched with the front object. In this way, the target detection result is actually revised according to the side detection result that is too large: if both Lidar and Radar sensors have target output, and the camera does not perceive any target, only lane lines, then the target is taken as the object, and the speed is reduced to a stable operating speed to avoid collision with the target.

[0084] Alternatively, if the vehicle is also equipped with a ranging radar, if a front object is identified in the road image and the ranging radar detects a front object, and the first distance between the front object identified from the road image and the vehicle is greater than the second distance between the front object detected by the ranging radar and the vehicle, the weight value of the detection result of the ranging radar in the fusion result can be increased. Specifically, according to the radar point cloud output by the Lidar, the target identified by the Lidar is determined, and this result is fused with the target obtained by other sensors. If the distance between this target and the vehicle exceeds the maximum distance of visual recognition (i.e. greater than the maximum visible distance), and visual recognition fails to detect this target, the confidence of the rain / mist scene recognition result is increased to speed up the reduction to a stable operating speed.

[0085] Alternatively, if the vehicle is also equipped with a rain and mist sensor, if the rain and mist detection result of the rain and mist sensor indicates that there is currently rain and mist, and the guide line of the current road identified from the road image has no loss, the weight value of the detection result of the rain and mist sensor in the fusion result can be increased to speed up the reduction to a stable operating speed.

[0086] For example, corresponding to the above Table 2, the speed reduction process can be performed in the manner shown in Table 3 below:

[0087] Table 3

[0088]

[0089] Through the above embodiments, in the case that the auxiliary driving function is started, the vehicle can acquire the road image collected by the image collection device for the current road, and determine the maximum visible distance of the vehicle at the current time based on the road image; then determine the minimum safe recognition distance of the vehicle at the current time according to the road information of the current road and the current driving information of the vehicle; and finally, at least in the case that the maximum visible distance is not greater than the minimum safe recognition distance, degrade or close the auxiliary driving function.

[0090] It can be understood that the present scheme does not distinguish various factors affecting visibility, but directly collects images of the current road as the object (various factors may affect the image content and quality) and determines the maximum visible distance at this time through image recognition and other related algorithms, so as to accurately determine whether the current environment exceeds the ODD of the auxiliary driving function. The present scheme not only does not need a rain sensor to directly detect the amount of rain, but also does not need the preceding vehicle to always maintain a distance similar to the visibility distance (even completely does not need to exist the preceding vehicle, suitable for non-following vehicle scenes), which not only simplifies the determination logic and accuracy of the maximum visible distance, but also helps to improve the control accuracy of the closing and degradation of the auxiliary driving function.

[0091] Please refer to Figure 5 , Figure 5 is an exemplary embodiment showing a hardware structure diagram of a vehicle on which an auxiliary driving control device based on visible distance detection is located. At the hardware level, the device includes a processor 502, an internal bus 504, a network interface 506, a memory 508, and a non-volatile memory 510, and of course can also include other hardware required by the business. One or more embodiments of the present application can be implemented in a software manner, such as reading a corresponding computer program from the non-volatile memory 510 into the memory 508 by the processor 502 and then running. Of course, in addition to the software implementation, one or more embodiments of the present application do not exclude other implementation manners, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to the logical unit, but can also be hardware or a logic device.

[0092] Please refer to Figure 6 , Figure 6 is a block diagram of an auxiliary driving control device based on visible distance detection according to an exemplary embodiment. The device can be applied to the vehicle shown in Figure 5 to implement the technical scheme of the present application. Wherein, the device can include:

[0093] The visible distance determination unit 601 is configured to, in the case that the auxiliary driving function is started, acquire the road image collected by the image collection device for the current road, and determine the maximum visible distance of the vehicle at the current time based on the road image;

[0094] The safety distance determination unit 602 is configured to determine a minimum safety recognition distance of the vehicle at the current time according to the road information of the current road and the current driving information of the vehicle.

[0095] The auxiliary driving control unit 603 is configured to degrade or close the auxiliary driving function at least in the case that the maximum visible distance is not greater than the minimum safety recognition distance.

[0096] Optionally, the visible distance determination unit 601 is specifically configured to:

[0097] If a guide line of the current road is recognized from the road image, the maximum visible distance of the vehicle at the current time is determined based on the road image; and / or,

[0098] If the road image indicates that the image acquisition device is not faulty, the maximum visible distance of the vehicle at the current time is determined based on the road image.

[0099] Optionally, the visible distance determination unit 601 is specifically configured to:

[0100] The guide line of the current road is recognized in the road image, and position information of the farthest effective pixel point on the guide line in the road image is determined;

[0101] The maximum visible distance of the vehicle at the current time is calculated based on the position information and the device parameters of the image acquisition device.

[0102] Optionally, the guide line of the current road comprises at least one of:

[0103] A real lane line drawn on the current road;

[0104] A virtual guide line fitted according to a guide object placed on the current road;

[0105] In the case that the vehicle is located at a preset road section of the current road at the current time, and the real lane line or the virtual guide line is interrupted, a compensation guide line obtained by compensating the real lane line or the virtual guide line.

[0106] Optionally, the safety distance determination unit 602 is specifically configured to:

[0107] The minimum safety recognition distance matched with the road type of the current road and / or the current speed of the vehicle is queried in a safety distance mapping relationship; and / or,

[0108] The minimum safety recognition distance is calculated according to the highest speed limit of the current road and the maximum deceleration in the deceleration process of the vehicle on the current road.

[0109] Optionally, the auxiliary driving control unit 603 is specifically configured to:

[0110] in a case where the maximum visible distance is not greater than the minimum safe recognition distance, and a preset associated condition of the auxiliary driving function is met, degrading or closing the auxiliary driving function; wherein the preset associated condition comprises at least one of the following:

[0111] the map information indicates that the current position of the vehicle is located in a preset section of the current road, and the distance between the current position and the end point of the guide line of the current road is greater than the minimum safe recognition distance;

[0112] the duration that the maximum visible distance is not greater than the minimum safe recognition distance reaches a time threshold corresponding to the road information of the current road and the current driving information of the vehicle.

[0113] Optionally, the auxiliary driving control unit 603 is specifically configured to:

[0114] outputting closing prompt information for the auxiliary driving function to the driver of the vehicle, and degrading the auxiliary driving function if the driver does not take over the vehicle within a preset time.

[0115] Optionally, the vehicle is in a current auxiliary driving level at the current time, and the auxiliary driving control unit 603 is specifically configured to:

[0116] determining an expected auxiliary driving level corresponding to the maximum visible distance, wherein a first cruise speed of the current auxiliary driving level is higher than a second cruise speed of the expected auxiliary driving level;

[0117] degrading the vehicle from the current auxiliary driving level to the expected auxiliary driving level, including: controlling the vehicle to decelerate from a current speed to the second cruise speed.

[0118] Optionally, the fusion result of the detection results of the plurality of sensors is used to control the auxiliary driving function, and the apparatus further comprises a multi-sensor fusion module 604, configured to:

[0119] in a case where the vehicle is also equipped with a ranging radar, if no front object is recognized in the road image and the ranging radar detects a front object, triggering the auxiliary driving function to be degraded to a level matched with the front object;

[0120] In the case that the vehicle is further equipped with a ranging radar, if a front object is identified in the road image and the ranging radar detects a front object, and a first distance between the front object identified in the road image and the vehicle is greater than a second distance between the front object detected by the ranging radar and the vehicle, the weight value of the detection result of the ranging radar in the fusion result is increased.

[0121] In the case that the vehicle is further equipped with a rain and fog sensor, if the rain and fog detection result of the rain and fog sensor indicates that there is currently rain and fog, and the guide line of the current road identified from the road image has no loss, the weight value of the detection result of the rain and fog sensor in the fusion result is increased.

[0122] The implementation process of the functions and roles of the units in the device is specifically described in the implementation process of the corresponding steps in the method, which will not be repeated here.

[0123] Correspondingly, the application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the auxiliary driving control method based on visual distance detection according to any one of the preceding embodiments.

[0124] Correspondingly, the present specification also provides a computer program product, which includes computer programs / instructions, and the computer programs / instructions are executed by a processor to implement the steps of the auxiliary driving control method based on visual distance detection according to any one of the preceding embodiments.

[0125] For the device embodiment, since it basically corresponds to the method embodiment, the related parts are described in the part of the method embodiment. The device embodiments described above are only illustrative, and the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, that is, they can be located in one place or distributed on multiple network units. According to actual needs, part or all of the modules can be selected to achieve the purpose of the application scheme. Those skilled in the art can understand and implement without creative labor.

[0126] The system, device, module or unit illustrated in the embodiments can be specifically implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer, and the specific form of the computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0127] In a typical configuration, a computer includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0128] Memory can include non-persistent memory and / or volatile memory, random access memory (RAM), and / or non-volatile memory, e.g., read only memory (ROM) or flash memory, among others. Memory is an example of computer readable media.

[0129] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disks (DVDs) or other optical storage, magnetic cassettes, magnetic disks storage, quantum memory, graphene-based storage media, or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to computing devices. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0130] It is also important to note that the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0131] The particular embodiments described herein describe the present application. Other embodiments are within the scope of the following claims. In some cases, operations or steps described in the claims can be performed in a different order than described in the embodiments and still achieve desirable results. Additionally, the processes depicted in the accompanying figures do not necessarily require the particular order shown or sequential order in order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0132] The terminology used by the term in the implementation of the application one or more embodiments for the purpose of describing a specific embodiment, rather than intended to limit one or more embodiments of the application. In one or more embodiments of the application and the appended claims used in the singular "a", "said" and "this" are intended to include the plural form, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein means and includes any or all possible combinations of one or more associated listed items.

[0133] It should be understood that although the first, second, third, etc. may be employed in the description of one or more embodiments of the application, such terms are not intended to limit the information to these terms. These terms are used only to distinguish one type of information from another type of information. For example, without departing from the scope of one or more embodiments of the application, the first information can also be called the second information, and similarly, the second information can also be called the first information. Depending on the context, the word "if" as used herein can be interpreted as "when" or "upon" or "in response to determining".

[0134] The above description is only the preferred embodiment of one or more embodiments of the application, and is not intended to limit one or more embodiments of the application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of the application shall be included in the scope of protection of one or more embodiments of the application.

[0135] The user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the application are information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

Claims

1. A driver assistance control method based on line-of-sight distance detection, characterized in that, Applied to vehicles equipped with image acquisition devices and supporting driver assistance functions, the method includes: When the vehicle has its assisted driving function activated, the image acquisition device acquires a road image of the current road, and the maximum visible distance of the vehicle at the current moment is determined based on the road image. The maximum visible distance is the distance between the vehicle and the farthest object that its visual perception algorithm can effectively identify. The minimum safe identification distance of the vehicle at the current moment is determined based on the road information of the current road and the current driving information of the vehicle. If the maximum visibility distance is not greater than the minimum safe recognition distance, the driver assistance function will be downgraded or turned off, and the driver will be reminded to take appropriate action.

2. The method according to claim 1, characterized in that, Determining the maximum visible distance of the vehicle at the current moment based on the road image includes: If the guide lines of the current road are identified from the road image, then the maximum visible distance of the vehicle at the current moment is determined based on the road image; and / or, If the road image indicates that the image acquisition device is functioning correctly, then the maximum visible distance of the vehicle at the current moment is determined based on the road image.

3. The method according to claim 1, characterized in that, Determining the maximum visible distance of the vehicle at the current moment based on the road image includes: Identify the guide line of the current road in the road image, and determine the position information of the farthest valid pixel on the guide line in the road image; The maximum visible distance of the vehicle at the current moment is calculated based on the location information and the device parameters of the image acquisition device.

4. The method according to claim 3, characterized in that, The guide lines of the current road include at least one of the following: The actual lane lines drawn on the current road; A virtual guide line fitted based on the guide objects currently placed on the road; When the vehicle is currently located on a preset section of the current road and the real lane line or the virtual guide line is interrupted, a compensation guide line is obtained by compensating the real lane line or the virtual guide line.

5. The method according to claim 1, characterized in that, Determining the minimum safe identification distance of the vehicle at the current moment based on the road information of the current road and the current driving information of the vehicle includes: In the safe distance mapping relationship, query the minimum safe identification distance that matches the road type of the current road and / or the current speed of the vehicle; and / or, The minimum safe identification distance is calculated based on the current road's maximum speed limit and the vehicle's maximum deceleration during deceleration on the current road.

6. The method according to claim 1, characterized in that, The step of downgrading or disabling the driver assistance function when the maximum visibility distance is not greater than the minimum safe recognition distance includes: If the maximum visibility distance is not greater than the minimum safe recognition distance, and the preset association conditions of the driver assistance function are met, the driver assistance function is downgraded or turned off; wherein, the preset association conditions include at least one of the following: The map information indicates that the vehicle's current location is within a preset section of the current road, and the distance between it and the end point of the guide line of the current road is greater than the minimum safe identification distance; The duration for which the maximum visible distance is not greater than the minimum safe identification distance reaches the duration threshold corresponding to the road information of the current road and the current driving information of the vehicle.

7. The method according to claim 1, characterized in that, The downgrading or disabling of the driver assistance function includes: The driver of the vehicle is prompted to disable the driver assistance function. If the driver does not take over the vehicle within a preset time, the driver assistance function is downgraded.

8. The method according to claim 1, characterized in that, The vehicle is currently at the current level of driver assistance, and downgrading the driver assistance function includes: Determine the expected level of driver assistance corresponding to the maximum visibility distance, wherein the first cruise speed of the current level of driver assistance is higher than the second cruise speed of the expected level of driver assistance; Degrading the vehicle from the current level of driver assistance to the expected level of driver assistance includes: controlling the vehicle to decelerate from the current speed to the second cruise speed.

9. The method according to claim 1, characterized in that, The method further includes using the fusion of detection results from multiple sensors to control the assisted driving function, and the fusion result from each sensor is used to control the assisted driving function. If the vehicle is also equipped with a ranging radar, and if no object is detected in the road image but the ranging radar detects an object, the driver assistance function will be downgraded to a level that matches the object in front. If the vehicle is also equipped with a ranging radar, and if an object is identified in the road image and the ranging radar detects the object, and if the first distance between the object identified in the road image and the vehicle is greater than the second distance between the object detected by the ranging radar and the vehicle, then the weight of the detection result of the ranging radar in the fusion result is increased. If the vehicle is also equipped with a rain and fog sensor, and the rain and fog detection result of the rain and fog sensor indicates that rain and fog are present, and the guide lines of the current road identified from the road image are not lost, then the weight value of the detection result of the rain and fog sensor in the fusion result is increased.

10. A driver assistance control device based on line-of-sight distance detection, characterized in that, The device, applicable to vehicles equipped with image acquisition devices and supporting driver assistance functions, includes: The visible distance determination unit is used to acquire road images captured by the image acquisition device for the current road when the vehicle's assisted driving function is activated, and to determine the maximum visible distance of the vehicle at the current moment based on the road images. The maximum visible distance is the distance between the vehicle and the farthest object that its visual perception algorithm can effectively identify. A safe distance determination unit is used to determine the minimum safe identification distance of the vehicle at the current moment based on the road information of the current road and the current driving information of the vehicle; The driver assistance control unit is used to downgrade or disable the driver assistance function, and remind the driver to take appropriate action, at least when the maximum visibility distance is not greater than the minimum safe recognition distance.

11. A vehicle equipped with an image acquisition device and supporting driver assistance functions, the vehicle comprising: processor; Memory used to store processor-executable instructions; The processor implements the method as described in any one of claims 1-9 by executing the executable instructions.

12. A computer-readable storage medium having stored thereon computer instructions that, when executed by a processor, implement the steps of the method as claimed in any one of claims 1-9.

13. A computer program product comprising a computer program and / or instructions, characterized in that, When the computer program and / or instructions are executed by a processor, they implement the steps of the method as described in any one of claims 1-9.

Images