Vehicle lamp control method, vehicle-mounted electronic device and vehicle machine system

Abstract

The invention relates to a vehicle lamp control method, a vehicle-mounted electronic device and a vehicle machine system, and the method comprises the steps: obtaining a real-time image obtained by collecting a road environment through a camera in response to an environment request signal; wherein the environment request signal is generated based on the current meteorological information; according to the type of the road environment, performing corresponding target identification on the live image, and extracting environment visibility information based on a target identification result; wherein the target object corresponding to the target identification result comprises a traffic facility and / or a vehicle; under the condition that the safety level corresponding to the environment visibility information is lower than a preset level, a first vehicle lamp signal is triggered to turn on a vehicle lamp; and the intellectualization of vehicle lamp control is improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle safe driving, and in particular to a vehicle light control method, a vehicle-mounted electronic device and a vehicle computer system. Background Art

[0002] With the development of automotive electronic technology, the safety protection measures of automobiles are becoming more and more perfect. During the driving process, the vehicle's automatic sensing headlights can automatically light up before the ambient light becomes dark, and automatically turn off when the ambient light becomes brighter. This helps to reduce the driver's vehicle control intensity and reduce driving safety hazards.

[0003] At present, headlight control mainly evaluates the visibility of the road environment by sensing the ambient light intensity, thereby deciding whether to turn on the headlights. The ambient light intensity is mainly sensed by the photosensitive element, which sends an electronic signal to the controller to decide whether to turn on or off the vehicle headlights. Since the photosensitive element only obtains light intensity information and has a low recognition rate of the light source, it is easy to cause the headlight control to be wrong, which may cause the headlights to be turned on too late or too much in some cases.

[0004] Currently, no effective solution has been proposed for the insufficiently intelligent method of headlight control in related technologies. Summary of the invention

[0005] Based on this, it is necessary to provide a more intelligent vehicle light control method, vehicle-mounted electronic device and vehicle computer system to address the above technical issues.

[0006] In a first aspect, the present application provides a vehicle light control method, comprising:

[0007] In response to an environment request signal, obtaining a live image of a road environment acquired by a camera; wherein the environment request signal is generated based on current meteorological information;

[0008] According to the type of the road environment, corresponding target recognition is performed on the live image, and environmental visibility information is extracted based on the target recognition result; wherein the target object corresponding to the target recognition result includes traffic facilities and / or vehicles;

[0009] When the safety level corresponding to the environmental visibility information is lower than a preset level, a first vehicle light signal is triggered to turn on the vehicle lights.

[0010] In some embodiments, according to the type of the road environment, corresponding target recognition is performed on the live image, and environmental visibility information is extracted based on the target recognition result, including:

[0011] In the case that no other vehicles exist within the field of view of the camera, performing semantic recognition processing on the live image;

[0012] In the case where the characters are recognized, determining that the traffic facility is a road sign;

[0013] The visible distance of the vehicle relative to the road sign is detected, and first environmental visibility information is generated according to the visible distance.

[0014] In some embodiments, performing semantic recognition processing on the live image includes:

[0015] Performing OCR recognition and skeleton recognition on the live image to obtain an OCR recognition result and a skeleton recognition result respectively;

[0016] Determine whether the OCR recognition result is consistent with the skeleton recognition result;

[0017] If the OCR recognition result is consistent with the skeleton recognition result, it is determined that the current semantic recognition process is valid, and the corresponding character information is output;

[0018] If the OCR recognition result is inconsistent with the skeleton recognition result, it is determined that the current semantic recognition process is invalid, and the semantic recognition process is performed again based on the next frame of live image.

[0019] In some embodiments, detecting the visible distance of the vehicle relative to the road sign includes:

[0020] The visual distance is obtained by measuring the live image based on the left and right aberration positions using a binocular camera carried by the vehicle; or,

[0021] The distance of the space high-reflectivity target is measured by the radar module carried by the vehicle, and the distance of the space high-reflectivity target closest to the vehicle is used as the visible distance.

[0022] In some embodiments, according to the type of the road environment, corresponding target recognition is performed on the live image, and environmental visibility information is extracted based on the target recognition result, including:

[0023] In the case that there are other vehicles within the field of view of the camera, vehicle recognition is performed on the live image to determine a first vehicle that is traveling in the same direction as the vehicle and is following the vehicle;

[0024] Calculating the following distance between the first vehicle and other vehicles, and determining whether the following distance is increasing within a preset time;

[0025] When it is determined that the following distance shows an increasing trend within a preset time, it is determined that the following distance of the first vehicle increases, and second environmental visibility information is generated according to the determination result.

[0026] In some embodiments, when there are other vehicles within the field of view of the camera, vehicle recognition is performed on the live image to determine the first vehicle that is traveling in the same direction as the vehicle and has a following behavior, including:

[0027] When it is identified that there are a plurality of vehicles in a single lane that are traveling in the same direction as the own vehicle and are following the own vehicle, the vehicle closest to the own vehicle among the plurality of vehicles is determined as the first vehicle.

[0028] In some embodiments, when it is identified that the first vehicle exists in multiple lanes, and when it is determined that the following distance of the first vehicle is increasing within a preset time, it is determined that the following distance of the first vehicle is increasing, and second environmental visibility information is generated according to the determination result, including:

[0029] Determining a first confidence level of each lane according to the distance between each lane and the lane of the vehicle;

[0030] Determining a second confidence level of each relative position relationship according to the relative position relationship between each of the first vehicles and the host vehicle;

[0031] The following vehicle confidence of the target vehicle is calculated according to the first confidence and the second confidence, and the second environmental visibility information is generated according to the following vehicle confidence of the target vehicle; wherein the target vehicle is the first vehicle for which the following distance is determined to increase.

[0032] In some of the embodiments, when there are other vehicles within the field of view of the camera, the method further includes:

[0033] Performing headlight recognition on the vehicle to determine a second vehicle with headlights turned on;

[0034] Determine the ratio of surrounding vehicles with lights on according to the ratio of the second vehicle in the identified vehicles;

[0035] The third environment visibility information is generated according to the ratio of the surrounding vehicles with lights on.

[0036] In some embodiments, after generating the third environmental visibility information according to the ratio of lights on of surrounding vehicles, the method further includes:

[0037] When the safety level corresponding to the third environmental visibility information is lower than a preset level, the type of lights of the host vehicle waiting to be turned on is determined according to the type of lights turned on by the second vehicle.

[0038] In some embodiments, after performing headlight recognition on the vehicle and determining a second vehicle with headlights turned on, the method further includes:

[0039] Determining a relative position relationship between the second vehicle and the host vehicle;

[0040] The type of the corresponding headlight of the second vehicle is identified according to the relative position relationship.

[0041] In some embodiments, when the safety level corresponding to the environmental visibility information is lower than a preset level, after triggering the first vehicle light signal to turn on the vehicle light, the method further includes:

[0042] Controlling the vehicle lighting system to remain in an on state within a preset time period;

[0043] After the preset time period has passed, the vehicle light is turned off in response to a second vehicle light signal.

[0044] In some embodiments, after the preset time period has elapsed, responding to the second vehicle light signal to turn off the vehicle light comprises:

[0045] When it is detected that the safety level corresponding to the environmental visibility information is higher than a preset level, the second vehicle light signal is triggered; wherein the environmental visibility information includes visible distance, following distance or the proportion of surrounding vehicles with lights on.

[0046] In a second aspect, the present application provides a vehicle-mounted electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in the first aspect are implemented.

[0047] In a third aspect, the present application provides a vehicle system, comprising: the vehicle-mounted electronic device, sensor, execution controller and vehicle light system described in the second aspect above;

[0048] Wherein, the sensor and the execution controller are respectively connected to the vehicle-mounted electronic device, and the execution controller is also connected to the vehicle light system;

[0049] The vehicle-mounted electronic device executes the vehicle light control method by receiving the sensing data collected by the sensor, generates and sends a control signal to the execution controller, and the execution controller controls the operating state of the vehicle light system.

[0050] The above-mentioned vehicle light control method, vehicle-mounted electronic device and vehicle computer system collect real-time images of the road environment on the premise of receiving an environment request signal that preliminarily indicates that the current road environment is not conducive to driving, and decide whether to turn on the vehicle lights by identifying the target in the real-time image, thereby avoiding the misjudgment and missed judgment problems that may occur in traditional methods. Furthermore, according to the type of road environment, the corresponding target recognition is performed on the real-time image, so that the vehicle light control method can evaluate the road environment more intelligently and comprehensively, further improving the rationality of the decision. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A hardware structure block diagram of a vehicle-mounted electronic device in one embodiment;

[0052] Figure 2 A schematic diagram of the structure of a vehicle system in an embodiment;

[0053] Figure 3 is a flow chart of a vehicle light control method in one embodiment;

[0054] Figure 4 is a flow chart of a method for identifying a target when there are no vehicles around the vehicle in one embodiment;

[0055] Figure 5 A flowchart of an OCR recognition method combined with a skeleton recognition method in one embodiment;

[0056] Figure 6 A live image including a road sign in one embodiment;

[0057] Figure 7 is a flow chart of a target recognition method for a situation where there are vehicles around the vehicle in one embodiment;

[0058] Figure 8 is an exploded schematic diagram of an overtaking process between a vehicle and a neighboring vehicle in one embodiment;

[0059] Fig. 9 is a schematic diagram of a lane in an embodiment;

[0060] Fig.10 is a flow chart of a target recognition method for a situation where there are vehicles around the vehicle in another embodiment;

[0061] Fig.11 FIG. 4 is a flow chart of a vehicle light control method in another embodiment. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0063] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0064] In one embodiment, a vehicle-mounted electronic device is provided. The vehicle-mounted electronic device may be a vehicle central control unit (SOC), a vehicle-mounted electronic terminal or a similar computing device. The method embodiments provided in the present application may be executed in the vehicle-mounted electronic device. Figure 1 1 is a hardware structure block diagram of a vehicle-mounted electronic device according to an embodiment of the present application. Figure 1 As shown, the vehicle-mounted electronic device may include one or more ( Figure 1 Only one is shown in the figure) processor 101 and memory 102 for storing data, wherein processor 101 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above-mentioned vehicle-mounted electronic device may also include a transmission device 103 and an input and output device 104 for communication functions. It can be understood by ordinary technicians in this field that Figure 1 The structure shown is for illustration only and does not limit the structure of the above-mentioned vehicle-mounted electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0065] The memory 102 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the vehicle light control method in this embodiment. The processor 101 executes various functional applications and data processing by running the computer program stored in the memory 102, that is, to implement the above method. The memory 102 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 102 may further include a memory remotely arranged relative to the processor 101, and these remote memories may be connected to the vehicle-mounted electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0066] The transmission device 103 is used to receive or send data via a network. The above network includes a wireless network provided by a communication provider of the vehicle-mounted electronic device. In one embodiment, the transmission device 103 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one embodiment, the transmission device 103 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0067] In one embodiment, a vehicle system is provided. Figure 2 It is a structural diagram of the vehicle system. Figure 2 As shown, the vehicle system includes: an on-board electronic device 100, a sensor 200, an execution controller 300 and a vehicle light system 400; the sensor 200 and the execution controller 300 are respectively connected to the on-board electronic device 100, and the execution controller 300 is also connected to the vehicle light system 400. Among them, the sensor 200 includes but is not limited to a light sensor, a camera (monocular and / or binocular), and a radar (Lidar and / or Radar); the execution controller 300 includes but is not limited to a motor and an optical mechanism; the vehicle light system 400 includes but is not limited to a fog lamp, a high beam lamp, a low beam lamp, and a flash lamp. The on-board electronic device 100 executes the vehicle light control method by receiving the sensor data (such as a live image, an actual shooting distance) collected by the sensor 200, generates and sends a control signal to the execution controller 300, and the execution controller 300 controls the operating state of the vehicle light system 400.

[0068] Exemplarily, the vehicle-mounted electronic device 100 extracts environmental visibility information by executing the vehicle light control method, and determines the corresponding safety level based on the environmental visibility information. When the safety level is lower than the preset level, the first vehicle light signal is triggered, and after the execution controller 300 receives the first vehicle light signal, the vehicle light system 400 is turned on, such as turning on the high and low beam lights or intelligently adjusting the lighting range and angle, etc., to improve driving visibility. For another example, when the safety level is higher than the preset level, the second vehicle light signal is triggered, and after the execution controller 300 receives the second vehicle light signal, the vehicle light system 400 is turned off.

[0069] In actual applications, when the vehicle-mounted electronic device 100 controls the vehicle lighting system 400 to turn on, it can automatically switch between high and low beams or intelligently adjust the lighting range and angle. Among them, the automatic switching between high and low beams can be when the safety level is lower than a preset level, the high and low beams are automatically switched to avoid interfering with other road users. Intelligent adjustment of the lighting range and angle can be when the safety level is lower than a preset level, the lighting angle and lighting range of the headlights are automatically adjusted to provide the best lighting effect. In this embodiment, by effectively extracting environmental visibility information, determining the corresponding safety level based on the environmental visibility information, and automatically controlling the operating state of the vehicle system 400 based on the safety level, the driver's field of vision can be improved and driving safety can be improved.

[0070] Figure 3 Flowchart of the vehicle light control method of this embodiment is shown in FIG. 1 , which is described by taking the method applied to the above-mentioned vehicle electronic device as an example, and includes the following steps:

[0071] Step S101, in response to an environment request signal, obtaining a real-time image of a road environment captured by a camera; wherein the environment request signal is generated based on current meteorological information.

[0072] Meteorological information refers to a series of environmental information that will affect the visibility of vehicles, such as heavy rain, heavy snow, heavy fog, and strong sandstorms. The driving area within a certain distance range centered on the vehicle can be determined as a driving geofence. The driving geofence corresponds to a certain range on the map. This part of the area can obtain local real-time or weather forecasts for a period of time from the map or the cloud. When the weather forecast in the driving geofence shows that the current weather will affect the visibility of vehicles, the system will output an environmental request signal. At the same time, considering that the weather information in the cloud is limited by the update frequency and network signal strength, the vehicle also provides environmental information obtained through the vehicle's own sensing device for system-assisted judgment. For example, through the sunlight and rain sensors configured in the vehicle, the vehicle can obtain real-time sunlight and rainfall parameters during the driving process, and can accurately judge whether the vehicle is driving in the dark or rainy environment. For example, through the temperature and humidity sensors configured in the vehicle, the temperature and humidity in the vehicle's driving environment can be evaluated to assist in foggy judgment, that is, when the vehicle finds that the clarity of the target of the vehicle in front drops below a certain level, the rain sensor has no input signal, the humidity is higher than a certain threshold, and the temperature is within a certain range, it is judged as a heavy fog. For example, the vehicle's PM2.5 environmental sensor senses the content of particulate matter in the environment. When the PM2.5 outside the vehicle seriously exceeds the standard, the humidity is very low, and the wind speed in the driving area is high, it is judged as a sandstorm.

[0073] When the system analyzes the current weather information and finds that it is not conducive to driving, it will trigger an environmental request signal to preliminarily instruct to turn on the headlight system to improve the driving field of vision. However, not all unfavorable analyses of weather information require turning on the headlight system. For example, when a vehicle is driving in a tunnel environment on a rainy day, although the analysis result of the weather information is not conducive to driving, there are usually street lights in the tunnel, and there is no need to turn on the headlights to supplement the light during driving. Therefore, in order to avoid erroneous control of the headlights, this embodiment will not turn on the headlights immediately after receiving the environmental request signal, but will perform further analysis by acquiring the real-time image of the road environment captured by the camera.

[0074] Step S102, according to the type of road environment, corresponding target recognition is performed on the live image, and environmental visibility information is extracted based on the target recognition result; wherein the target object corresponding to the target recognition result includes traffic facilities and / or vehicles.

[0075] Since vehicles travel on diverse road environments, they may travel on urban roads and highways with heavy traffic, or on rural roads and field roads with light traffic. To adapt to target recognition in different driving scenarios, this embodiment divides target recognition for different road environments into the following two categories:

[0076] Target recognition scheme 1: For a road environment where there are no other vehicles around the vehicle, the vehicle can perform target recognition based on the traffic facilities contained in the road environment, such as identifying guardrails or road signs, and obtain the visible distance based on the recognition of guardrails or road signs.

[0077] Target recognition scheme 2: When there are other vehicles around the vehicle, the vehicle can perform target recognition based on the vehicle, such as identifying a first vehicle that is following the vehicle in the same direction as the vehicle and monitoring the following distance of the first vehicle. Or identify a second vehicle with its lights on and determine the proportion of surrounding vehicles with their lights on based on the proportion of the second vehicle in the identified vehicles.

[0078] These two target recognition methods can be performed simultaneously or one by one.

[0079] Step S103 : when the safety level corresponding to the environmental visibility information is lower than a preset level, triggering a first vehicle light signal to turn on the vehicle lights.

[0080] Environmental visibility information can be quantified into a safety level, and then the safety level is compared with the preset level. If the safety level is lower than the preset level, it means that the current road environment is not conducive to driving, and the lights need to be turned on to improve the driving vision. On the contrary, if the safety level is not lower than the preset level, it means that the current road environment is acceptable and there is no need to turn on the lights.

[0081] Environmental visibility information can be one of the following information, or a combination of multiple information, including visible distance, following distance, and the percentage of surrounding vehicles with lights on. The visible distance, following distance, and the percentage of surrounding vehicles with lights on can be normalized into safety levels, respectively. The decision to turn on the lights is based on a single indicator, which is convenient to calculate and has a fast decision speed. For example, the larger the visible distance, the higher the corresponding safety level; the smaller the following distance, the higher the corresponding safety level; the smaller the percentage of surrounding vehicles with lights on, the higher the corresponding safety level. Alternatively, the visible distance, following distance, and the percentage of surrounding vehicles with lights on can be normalized and transformed into the [0, 1] interval, and weights are assigned according to the importance of each indicator in the comprehensive evaluation. The standardized indicator values ​​are multiplied by their corresponding weights and summed to obtain the final comprehensive value, which is the safety level. This multi-indicator decision is more accurate than a single indicator decision. Alternatively, as long as one of the visible distance, following distance, and proportion of surrounding vehicles with lights on meets the preset conditions (visible distance is lower than the first threshold, following distance is greater than the second threshold, and proportion of surrounding vehicles with lights on is greater than the third threshold), the system will determine that the safety level is lower than the preset level and the lights need to be turned on.

[0082] In the above steps S101 to S103, on the premise of receiving the environment request signal indicating that the current road environment is not conducive to driving, the real-time image of the road environment is collected in real time, and the decision on whether to turn on the headlights is made by identifying the target of the real-time image, thereby avoiding the misjudgment and missed judgment problems that may occur in the traditional method. Further, according to the type of the road environment, the corresponding target recognition is performed on the real-time image, so that the headlight control method can evaluate the road environment more intelligently and comprehensively, and further improve the rationality of the decision.

[0083] In the following embodiments, the two target recognition schemes mentioned above will be further introduced.

[0084] In one embodiment, Figure 4 A flow chart of a target recognition method for a vehicle without any vehicles around it is given. Figure 4 As shown, the process includes the following steps:

[0085] Step S201: When there are no other vehicles within the field of view of the camera, semantic recognition processing is performed on the live image.

[0086] In some embodiments, characters may be recognized only by OCR recognition, or only by skeleton recognition, or by both OCR and skeleton recognition. These different situations will be described below.

[0087] (1) OCR recognition method: For Chinese recognition solutions, optical character recognition (OCR) algorithm can be used. Through machine learning or pattern recognition algorithm, the extracted features are matched with known characters to identify the characters.

[0088] (2) Skeleton recognition method: For image recognition of digital information and letter information, the acquired real-time image can be used to first perform image shape recognition and distinguish image continuity; for those whose colors have not changed, they are classified as features belonging to a region; the position median of each feature is extracted and the image inflection point is identified, and the nearest bone feature points are connected in sequence at the inflection point to obtain the skeleton information of the regional feature; each skeleton information recognized in the image is processed by digital nesting of numbers (0-9) and letters (AZ, az), and for each bone point in the image, the nearest other bone point is found, and vector operations are performed point by point to obtain the formation route of the entire feature, that is, the "stroke order"; after comparing the "stroke order" feature of the regional feature with the numbers and letters, the corresponding semantic information can be obtained.

[0089] (3) OCR recognition method combined with skeleton recognition method:

[0090] In one embodiment, Figure 5A flowchart of combining OCR recognition method with skeleton recognition method is provided, such as Figure 5 As shown, the following steps are included:

[0091] Step S301, performing OCR recognition on the live image to obtain an OCR recognition result; for details, please refer to the above OCR recognition method;

[0092] Step S302, performing skeleton recognition on the live image to obtain a skeleton recognition result; for details, reference may be made to the above-mentioned skeleton recognition method;

[0093] Step S303, determining whether the OCR recognition result and the skeleton recognition result are consistent; if they are consistent, executing step S304; if they are inconsistent, executing step S305;

[0094] Step S304, determining that the current semantic recognition process is effective, and outputting corresponding character information;

[0095] Step S305: determine that the current semantic recognition process is invalid, and re-perform the semantic recognition process based on the next frame of live image.

[0096] In the present embodiment, the characters identified by the skeleton recognition method are compared with the characters identified by the OCR recognition method. When the recognition results of the two algorithms are the same, it is determined that the recognition is valid and the character information is output. The character information can be the character itself (classical Chinese, Arabic numerals, symbols), or the boundary point of the character, wherein the boundary point refers to the coordinates of the stroke boundary points of a complete character. When the recognition results of the two algorithms are different, the semantic recognition will use the next frame of live image to re-recognize until the correct character information is output, or the target object in the road environment moves out of the visual field of the camera projection. This arrangement is to take into account that the skeleton recognition method performs better when processing complex backgrounds and partial occlusions, while the OCR recognition method is more accurate when processing clear and standard characters. When the recognition results of the two algorithms are consistent, it can be considered that the recognition results are reliable, thereby outputting character information, and this dual verification mechanism significantly reduces the probability of misidentification. If the results of the two algorithms are inconsistent, the next frame of image will continue to be used for re-recognition until the results of the two methods are consistent or the target object moves out of the visual field, and this dynamic adjustment and continuous verification process further improves the accuracy of recognition. In practical applications, characters in road environments may be affected by a variety of factors, such as lighting changes, occlusion, and contamination. The multi-algorithm fusion method can better cope with these complex situations and improve the robustness of the system. This embodiment significantly improves the accuracy of semantic recognition through the design of multi-algorithm fusion, complementarity, double verification, robustness, and real-time performance, ensuring that character information can be reliably recognized in various complex environments.

[0097] Step S202: when characters are recognized, determining that the traffic facility is a road sign.

[0098] Considering that there are no cars around the vehicle, the existing traffic facilities may be guardrails or road signs. For guardrails and road signs at the same distance, when the human eye can see the guardrail, it may not be able to see the characters on the road sign clearly, and the visible distance should be based on the ability to see the characters on the road sign clearly. Therefore, this embodiment first determines whether there is a road sign by identifying the characters in the live image, and then measures the visible distance through the road sign.

[0099] Step S203 , detecting the visible distance of the vehicle relative to the road sign, and generating first environmental visibility information according to the visible distance.

[0100] The visible distance can be obtained by measuring the left and right image aberration positions of the live image through the binocular camera carried by the vehicle; or, the distance of the high-reflective target in space can be measured through the radar module carried by the vehicle, and the distance of the high-reflective target in space closest to the vehicle can be taken as the visible distance. The first environmental visibility information can be the measured visible distance itself, or it can be information obtained after data processing of the visible distance, such as transforming the visible distance into the interval [0, 1] after data standardization processing, which is not limited in this embodiment.

[0101] For example, Figure 6 is a live image containing road signs, such as Figure 6 As shown, when the vehicle is driving and there are no other vehicles around it, the vehicle will use the onboard camera to read the content in the live image in real time, such as the speed information on the road sign, which includes but is not limited to the information on the speed limit sign, the ground speed limit information (such as digital information: speed limit 80, G92 Hangzhou Bay Ring Road), the name of the expressway (text information: G92 Hangzhou Bay Ring Road), etc. For classical Chinese, numbers, and symbols, any of the above semantic recognition processing methods can be used to identify the corresponding semantic information.

[0102] After the vehicle recognizes the above semantic information through the image collected by the camera, it then uses the vehicle's forward binocular vision imaging or the vehicle's radar (Lidar and / or Radar) to measure the position of the semantic information carrier and obtain the visible distance. Figure 6 When the high-speed navigation signal on the road sign is valid, the vehicle uses the left and right image difference position of binocular vision to measure the distance between the road sign and the vehicle. Alternatively, the distance between the nearest high-reflection target in space and the vehicle is directly measured by Lidar. The distance between the road sign and the vehicle is the visible distance.

[0103] When the visual distance is less than a certain threshold, the vehicle is considered to have obstructed vision by default, and a signal of obstructed vision can be output. This threshold can be configured by the parking lot after calibration based on the vehicle model, road conditions, and vehicle usage mode.

[0104] In one embodiment, Figure 7 A flow chart of a target recognition method for the case where there are vehicles around the vehicle is given. Figure 7 As shown, the process includes the following steps:

[0105] Step S401: When there are other vehicles within the field of view of the camera, vehicle recognition is performed on the live image to determine the first vehicle that has the same driving direction as the vehicle and is following the vehicle.

[0106] During driving, the vehicle camera monitors other vehicles in the lanes around the vehicle in real time, and first determines whether the other vehicles are traveling in the same direction as the vehicle; if they are traveling in the same direction, it determines whether the other vehicles are following the vehicle, that is, whether there is a car in front of the other vehicles. If there is a car, it is determined to be following the vehicle.

[0107] When multiple vehicles are identified in a single lane that are traveling in the same direction as the vehicle and following the vehicle, the vehicle closest to the vehicle is determined as the first vehicle. This is because in a multi-vehicle scenario, for multiple target vehicles at different locations and different lane distances around the vehicle, the error in the distance measurement by the sensor will increase with the increase of distance, so only the vehicle closest to the vehicle is tracked in each adjacent lane as the tracking target.

[0108] Step S402, calculating the following distance between the first vehicle and the remaining vehicles, and determining whether the following distance is increasing within a preset time.

[0109] Determining whether the following distance shows an increasing trend within a preset time may be determining whether the following distance between the first vehicle and the preceding vehicle continues to increase within a certain period of time, or may be determining whether a rate of increase in the vehicle distance exceeds a certain threshold.

[0110] Step S403 : when it is determined that the following distance of the first vehicle is increasing within a preset time, it is determined that the following distance of the first vehicle is increasing, and second environment visibility information is generated according to the determination result.

[0111] For the first vehicle that has following behavior, this vehicle monitors the following distance between the first vehicle and the vehicle in front of it in real time. When it is found that the following distance between the first vehicle and the vehicle in front continues to increase within a certain period of time, or the rate of increase of the vehicle distance exceeds a certain threshold, it is determined that the following distance of the first vehicle has increased, and an increase signal of the vehicle distance of the first vehicle is output.

[0112] Exemplarily, inter-camera target tracking calibration will be further introduced below.

[0113] Figure 8 is a decomposition diagram of the overtaking process between the vehicle and the neighboring vehicle, as shown in Figure 8 As shown, the left side shows the scene of the first vehicle overtaking on the right, and the right side shows the scene of the first vehicle overtaking on the left. Overtaking can be divided into two driving processes:

[0114] The first process: from the time when the first vehicle appears in the front camera image of the vehicle until the first vehicle exits the front camera image during the overtaking process;

[0115] The second process: from the time when the first vehicle appears in the side camera image of the vehicle until the first vehicle drives to a certain distance behind the rear of the vehicle during the overtaking process.

[0116] Taking the first process mentioned above as an example, vehicle reference point recognition is performed. When the vehicle approaches from the right rear and enters a certain area behind the first vehicle, the first vehicle enters the front camera screen of the vehicle. The front camera of the vehicle will capture the target in the screen. At this time, the forward binocular system can achieve the distance measurement of the front vehicle target. Through the target recognition method, the center point (feature point) of the upper edge of the first vehicle is located, and the first vehicle is simulated as a feature point for continuous tracking. Using this method, in the case of multiple vehicles behind, each vehicle model is fitted as a feature point, and each vehicle feature point is continuously tracked for a period of time to obtain the motion trajectory of each vehicle. The same treatment is applied to the multi-vehicle mode, and a parallel target recognition strategy can be adopted.

[0117] In one embodiment, when it is identified that there are multiple lanes with the first vehicle, when it is determined that the following distance of the first vehicle is increasing within a preset time, it is determined that the following distance of the first vehicle is increasing, and second environmental visibility information is generated according to the determination result, including:

[0118] A first confidence level of each lane is determined based on the distance between each lane and the lane of the host vehicle; a second confidence level of each relative position relationship is determined based on the relative position relationship between each first vehicle and the host vehicle; a following confidence level of a target vehicle is calculated based on the first confidence level and the second confidence level, and second environmental visibility information is generated based on the following confidence level of the target vehicle; wherein the target vehicle is the first vehicle for which an increase in following distance is determined.

[0119] In this embodiment, a first confidence level is set for the following distance increase results outputted from different lanes, and a second confidence level is set for the relative positional relationship between each first vehicle and the host vehicle. The first confidence level changes in a gradient as the distance between each lane and the host lane changes, that is, the closer a lane is to the host lane, the higher the first confidence level of the lane; otherwise, the opposite is true. Fig. 9is a schematic diagram of the lanes of this embodiment, as shown in Fig. 9 As shown, assuming that the current road environment has 4 lanes, from left to right they are lane 1, lane 2, lane 3, and lane 4, and the vehicle is driving in lane 2. If the confidence of lane 2 is a, then the confidences of lane 1, lane 3, and lane 4 are a / 2, a / 2, and a / 3 respectively. The first vehicle can be located in front of, behind, on the left, or on the right of the vehicle, and each relative position relationship corresponds to a second confidence, which can be 1 / 2.

[0120] Continue to refer Fig. 9 , assuming that the vehicle is in lane 2, and there is a first vehicle in lane 2, and the first vehicle is behind the vehicle, then the following confidence of the first vehicle is 1 / 2(a / (a+a / 2+a / 2+a / 3))×100%. For another example, on this basis, there is a first vehicle in lane 4, and the first vehicle is located on the right side of the vehicle, then the following confidence of the first vehicle in lane 4 is 1 / 2(a / 3 / (a+a / 2+a / 2+a / 3))×100%. The sum of the following confidences of lanes 2 and 3 is accumulated. For multiple target vehicles, the sum of the following confidences of all target vehicles around the vehicle is accumulated. When the sum of the following confidences is greater than a certain threshold, a vehicle distance increase signal is output.

[0121] In one embodiment, Fig.10 A flowchart of another target recognition method for the case where there are vehicles around the vehicle is given, such as Fig.10 As shown, the process includes the following steps:

[0122] Step S501, performing headlight recognition on a vehicle to determine a second vehicle with headlights turned on;

[0123] Step S502, determining the ratio of surrounding vehicles with lights on according to the ratio of the second vehicle in the identified vehicles;

[0124] Step S503: generating third environmental visibility information according to the ratio of surrounding vehicles with lights on.

[0125] In the following vehicle scenario, the vehicle will use the camera to detect the status of the lights of other vehicles around it, and use the status of the lights of the surrounding vehicles as a reference to decide whether to turn on the lights of the vehicle. When the proportion of lights on in the surrounding vehicles is higher than a certain percentage, it means that the current road environment is poor and the lights need to be turned on. Therefore, the first light signal will be triggered to turn on the lights of the vehicle. This setting can maximize the accuracy of light control.

[0126] In some embodiments, after step S503, when the safety level corresponding to the third environmental visibility information is lower than the preset level, the type of lights to be turned on by the vehicle can be determined according to the type of lights turned on by the second vehicle. By using the lights of surrounding vehicles as a reference to determine the type of lights to be turned on by the vehicle, the control of the lights of the vehicle can be more reasonable.

[0127] In one embodiment, the relative position relationship between the second vehicle and the vehicle may be determined first, and the type of headlights corresponding to the second vehicle may be identified according to the relative position relationship. The following will introduce headlight type identification solutions for different relative position relationships.

[0128] (1) When a second vehicle is located behind the vehicle, the second vehicle is identified as having its headlights turned on.

[0129] (2) When a second vehicle is located in front of the vehicle, the second vehicle is identified as having its fog lights turned on.

[0130] (3) When a second vehicle is located in front of and behind the vehicle, the second vehicle is identified by turning on the hazard lights.

[0131] In this embodiment, the visual image target difference frame method can be used for identification. Within a preset period, the same target object is selected for comparison. For example, for the flashing of the target double flash warning light, a cyclic yellow light can be recognized at the vehicle headlight position through difference frame recognition, which is used as a determination requirement for the activation of the double flash warning light. For the headlights and fog lights, a long cycle of highlight appears at the corresponding light position of the vehicle body as a determination requirement for the activation of the headlights. The multi-vehicle headlight type recognition scenario can be similar to the following vehicle scenario processing method, and the confidence of the activation of periodic vehicle headlights in the road environment is calculated based on the confidence gradient.

[0132] In one embodiment, Fig.11 A flow chart of another vehicle light control method is provided, such as Fig.11 As shown, the process includes the following steps:

[0133] Step S601, in response to the environment request signal, obtain the real-time image obtained by the camera collecting the road environment. When the vehicle is driving in a geographical fence area with extreme weather, when the vehicle receives the environment request signal, the vehicle will collect the real-time image and make further judgment on the conditions for turning on the headlights. Before this, a corresponding user operation switch can be set on the vehicle's on-board electronic terminal. When the user turns on this function switch, the function of judging the conditions for turning on the headlights is effective, and the vehicle begins to monitor the driving environment in real time.

[0134] Step S602: According to the type of road environment, corresponding target recognition is performed on the live image, and environmental visibility information is extracted based on the target recognition result. The environmental visibility information can be one of the following information: visible distance, following distance, and the ratio of surrounding vehicles with lights on, or a combination of multiple information.

[0135] Step S603, when the safety level corresponding to the environmental visibility information is lower than the preset level, trigger the first headlight signal to turn on the headlights. When the vehicle meets the headlight turn-on judgment conditions, the vehicle is ready to automatically turn on the headlights. And based on visual judgment, the surrounding vehicles' headlights are turned on accordingly, and a certain type of headlight (headlight, fog light or double flash warning light) is turned on. Optionally, as long as one of the visible distance, following distance, and the proportion of surrounding vehicles with lights on meets the preset conditions (visible distance is lower than the first threshold, following distance is greater than the second threshold, and the proportion of surrounding vehicles with lights on is greater than the third threshold), it is considered that the safety level is lower than the preset level, and the headlights can be turned on at this time.

[0136] Step S604, controlling the vehicle light system to remain on for a preset time period.

[0137] Step S605: after a preset time period, when it is detected that the safety level corresponding to the environmental visibility information is higher than a preset level, trigger a second vehicle light signal to turn off the vehicle lights.

[0138] In this embodiment, when the safety level corresponding to the environmental visibility information is lower than the preset level, after the first headlight signal is triggered to turn on the headlights, the headlight system can be controlled to maintain the on state within the preset time; after the preset time, the headlights are turned off in response to the second headlight signal. The second headlight signal can be triggered when it is detected that the safety level corresponding to the environmental visibility information is higher than the preset level, or it can be triggered by the user's input operation (button, screen gesture, voice command); wherein the environmental visibility information includes the visible distance, the following distance, or the proportion of surrounding vehicles with lights on. Such a setting can avoid system misjudgment resulting in frequent headlight turn-off / turn-on signals, resulting in poor user experience. Therefore, a delay switch can be set at the system level, and the vehicle will not accept the headlight turn-off signal issued by the system within a period of time after the headlight turn-on signal is issued. When the delay is over, when the vehicle outputs the headlight turn-off signal again, the headlight responds and turns off.

[0139] Optionally, when the vehicle meets one of the following two conditions, the corresponding headlight system light group shutdown signal is output: (1) the vehicle's forward visibility is higher than a threshold; (2) one or more of the other vehicle light systems in the driving environment are turned off. In the above process, when the user intervenes in the light adjustment, the vehicle responds with the highest priority to the human intervention request, and enters the next detection cycle after the response is completed.

[0140] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0141] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0142] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0143] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle light control method, characterized in that: include: In response to an environment request signal, obtaining a real-time image of a road environment acquired by a camera; wherein the environment request signal is generated based on current meteorological information; According to the type of the road environment, corresponding target recognition is performed on the live image, and environmental visibility information is extracted based on the target recognition result; wherein the target object corresponding to the target recognition result includes traffic facilities and / or vehicles; When the safety level corresponding to the environmental visibility information is lower than a preset level, a first vehicle light signal is triggered to turn on the vehicle lights.

2. The vehicle light control method according to claim 1, characterized in that: According to the type of the road environment, corresponding target recognition is performed on the live image, and environmental visibility information is extracted based on the target recognition result, including: In the case that no other vehicles exist within the field of view of the camera, performing semantic recognition processing on the live image; In the case where the characters are recognized, determining that the traffic facility is a road sign; The visible distance of the vehicle relative to the road sign is detected, and first environmental visibility information is generated according to the visible distance.

3. The vehicle light control method according to claim 2, characterized in that: Performing semantic recognition processing on the live image includes: Performing OCR recognition and skeleton recognition on the live image to obtain an OCR recognition result and a skeleton recognition result respectively; Determine whether the OCR recognition result is consistent with the skeleton recognition result; If the OCR recognition result is consistent with the skeleton recognition result, it is determined that the current semantic recognition process is valid, and the corresponding character information is output; If the OCR recognition result is inconsistent with the skeleton recognition result, it is determined that the current semantic recognition process is invalid, and the semantic recognition process is performed again based on the next frame of live image.

4. The vehicle light control method according to claim 2, characterized in that: Detecting the visible distance of the vehicle relative to the road sign, including: The visual distance is obtained by measuring the live image based on the left and right aberration positions using a binocular camera carried by the vehicle; or, The distance of the space high-reflectivity target is measured by the radar module carried by the vehicle, and the distance of the space high-reflectivity target closest to the vehicle is used as the visible distance.

5. The vehicle light control method according to claim 1, characterized in that: According to the type of the road environment, corresponding target recognition is performed on the live image, and environmental visibility information is extracted based on the target recognition result, including: In the case where there are other vehicles within the field of view of the camera, the live image is used to identify a first vehicle that is traveling in the same direction as the vehicle and is following the vehicle, or when multiple vehicles that are traveling in the same direction as the vehicle and are following the vehicle are identified in a single lane, the vehicle that is closest to the vehicle among the multiple vehicles is identified as the first vehicle; Calculating the following distance between the first vehicle and other vehicles, and determining whether the following distance is increasing within a preset time; When it is determined that the following distance shows an increasing trend within a preset time, it is determined that the following distance of the first vehicle increases, and second environmental visibility information is generated according to the determination result.

6. The vehicle light control method according to claim 5, characterized in that: When it is identified that the first vehicle exists in a plurality of lanes, and when it is determined that the following distance shows an increasing trend within a preset time, it is determined that the following distance of the first vehicle increases, and second environmental visibility information is generated according to the determination result, including: Determining a first confidence level of each lane according to the distance between each lane and the lane of the vehicle; Determining a second confidence level of each relative position relationship according to the relative position relationship between each of the first vehicles and the host vehicle; The following vehicle confidence of the target vehicle is calculated according to the first confidence and the second confidence, and the second environmental visibility information is generated according to the following vehicle confidence of the target vehicle; wherein the target vehicle is the first vehicle for which the following distance is determined to increase.

7. The vehicle light control method according to claim 5, characterized in that: In the case that there are other vehicles within the field of view of the camera, the method further includes: Performing headlight recognition on the vehicle to determine a second vehicle with headlights turned on; Determine the ratio of surrounding vehicles with lights on according to the ratio of the second vehicle in the identified vehicles; The third environment visibility information is generated according to the ratio of the surrounding vehicles with lights on.

8. The vehicle light control method according to claim 7, characterized in that: After generating the third environmental visibility information according to the ratio of lights on of surrounding vehicles, the method further includes: When the safety level corresponding to the third environmental visibility information is lower than a preset level, determining the type of lights to be turned on by the host vehicle according to the type of lights turned on by the second vehicle; and / or, Determining a relative position relationship between the second vehicle and the host vehicle; The type of the corresponding headlight of the second vehicle is identified according to the relative position relationship.

9. The vehicle light control method according to claim 1, characterized in that: When the safety level corresponding to the environmental visibility information is lower than a preset level, after triggering the first vehicle light signal to turn on the vehicle light, the method further includes: Controlling the vehicle lighting system to remain in an on state within a preset time period; After the preset time period has passed, the vehicle light is turned off in response to a second vehicle light signal.

10. The vehicle light control method according to claim 9, characterized in that: After the preset time has passed, responding to a second vehicle light signal to turn off the vehicle light comprises: When it is detected that the safety level corresponding to the environmental visibility information is higher than a preset level, the second vehicle light signal is triggered; wherein the environmental visibility information includes visible distance, following distance or the proportion of surrounding vehicles with lights on.

11. An in-vehicle electronic device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 10 are implemented.

12. A vehicle computer system, characterized in that: include: The vehicle-mounted electronic device, sensor, actuator controller and vehicle lighting system as claimed in claim 11; Wherein, the sensor and the execution controller are respectively connected to the vehicle-mounted electronic device, and the execution controller is also connected to the vehicle light system; The vehicle-mounted electronic device executes the vehicle light control method by receiving the sensing data collected by the sensor, generates and sends a control signal to the execution controller, and the execution controller controls the operating state of the vehicle light system.

Images