Driving environment safety assessment method, vehicle lamp control method and vehicle-mounted electronic device

Abstract

The invention relates to a driving environment safety assessment method, a vehicle lamp control method and a vehicle-mounted electronic device. The method comprises the following steps: acquiring a live image obtained by acquiring a road environment by a camera and an actual shooting distance of the camera; performing target identification on the live image, and extracting environment visibility information based on a target identification result and an actual shooting distance; wherein the environment visibility information comprises the definition of the first traffic facility and / or the visibility of the second traffic facility; wherein the first traffic facility is provided with characters; determining the safety level of the road environment according to the environment visibility information; and the accuracy of driving environment safety assessment is improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle safe driving, and in particular to a driving environment safety assessment method, a vehicle light control method and a vehicle-mounted electronic device. 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 photosensitive elements, which send electronic signals to the controller to decide whether to turn on or off the vehicle headlights. Since photosensitive elements only obtain light intensity information and have low recognition of light sources, it is easy to cause errors in headlight control. Therefore, a more accurate driving environment safety assessment method is needed to guide the operating status of headlights.

[0004] Currently, no effective solution has been proposed to address the problem that the driving environment safety assessment methods of related technologies are not accurate enough. Summary of the invention

[0005] Based on this, it is necessary to provide a relatively accurate driving environment safety assessment method, a vehicle light control method and a vehicle-mounted electronic device to address the above technical issues.

[0006] In a first aspect, the present application provides a driving environment safety assessment method, comprising:

[0007] Acquire a real-time image of the road environment captured by a camera, and an actual shooting distance of the camera;

[0008] Performing target recognition on the live image, and extracting environmental visibility information based on the target recognition result and the actual shooting distance; wherein the environmental visibility information includes the clarity of the first traffic facility and / or the visibility of the second traffic facility; wherein the first traffic facility is provided with characters;

[0009] A safety level of the road environment is determined according to the environmental visibility information.

[0010] In one embodiment, performing target recognition on the live image and extracting environmental visibility information based on the target recognition result and the actual shooting distance includes:

[0011] When the first traffic facility is recognized in the live image, acquiring characters on the first traffic facility in the live image based on semantic recognition, and determining a first stroke continuity degree of the characters;

[0012] Acquire a first visible distance of the vehicle relative to the first traffic facility according to the actual shooting distance;

[0013] The first stroke continuity degree and the first visible distance are substituted into a first mapping function to calculate the clarity of the first traffic facility.

[0014] In one of the embodiments, when the first traffic facility is recognized in the live image, acquiring characters on the first traffic facility in the live image based on semantic recognition and determining a first stroke continuity degree of the characters includes:

[0015] Extracting a first stroke feature of the character, and extracting a second stroke feature of the character in full size;

[0016] The second stroke feature is used as a reference object to determine the stroke continuity degree of the first stroke feature relative to the second stroke feature.

[0017] In one embodiment, acquiring characters on the first traffic facility in the live image based on semantic recognition includes:

[0018] Performing OCR recognition and skeleton recognition on the live image to obtain an OCR recognition result and a skeleton recognition result respectively;

[0019] Determine whether the OCR recognition result is consistent with the skeleton recognition result;

[0020] 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;

[0021] 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.

[0022] In one of the embodiments, before performing target recognition on the live image and extracting environmental visibility information based on the target recognition result and the actual shooting distance, the method further includes:

[0023] Obtaining different stroke continuity degrees of the vehicle relative to the first traffic facility at different visual distances and different clarity;

[0024] Performing two-dimensional fitting on each of the visible distances, each of the clarity and each of the stroke continuity degrees to obtain a first fitting parameter;

[0025] The first mapping function is constructed according to the first fitting parameter.

[0026] In one embodiment, performing target recognition on the live image and extracting environmental visibility information based on the target recognition result and the actual shooting distance includes:

[0027] When the second traffic facility is identified in the live image, obtaining a second visible distance of the vehicle relative to the farthest second traffic facility in the live image according to the actual shooting distance;

[0028] Substitute the second visible distance into the second mapping function to calculate the visibility of the second traffic facility.

[0029] In one of the embodiments, before performing target recognition on the live image and extracting environmental visibility information based on the target recognition result and the actual shooting distance, the method further includes:

[0030] Obtaining different visibility of the vehicle relative to the second traffic facility at different visual distances;

[0031] Perform one-dimensional fitting on each of the visual distances and each of the visibility to obtain a second fitting parameter;

[0032] The second mapping function is constructed according to the second fitting parameter.

[0033] In one embodiment, the first traffic facility includes a road sign or a ground sign; the second traffic facility includes a road guardrail or a speed bump.

[0034] In a second aspect, the present application provides a vehicle light control method, comprising:

[0035] Determine the road environment safety level according to the driving environment safety assessment method described in the first aspect above;

[0036] The operating state of the vehicle headlights is controlled according to the road environment safety level.

[0037] In a third aspect, the present application provides a vehicle-mounted electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the method described in the first aspect above when executing the computer program.

[0038] The above-mentioned driving environment safety assessment method, vehicle light control method and vehicle-mounted electronic device obtain the actual shooting distance of the camera by collecting real-time images of the road environment, and extract environmental visibility information based on the target recognition results of the real-time images and the actual shooting distance. The environmental visibility information adaptively selects clarity or visibility indicators for different types of traffic facilities, and provides data support for evaluating the safety level of the road environment in different driving scenarios, making the driving environment safety assessment more intelligent and comprehensive, and can avoid the problem of light source recognition errors, thereby improving the accuracy of the driving environment safety assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a hardware structure block diagram of a vehicle-mounted electronic device in one embodiment;

[0040] Figure 2 A schematic diagram of the structure of a vehicle system in an embodiment;

[0041] Figure 3 A flowchart of a driving environment safety assessment method in one embodiment;

[0042] Figure 4 is a flow chart of a target identification method for a first traffic facility in one embodiment;

[0043] Figure 5 is a character schematic diagram in one embodiment;

[0044] Figure 6 A flowchart of an OCR recognition method combined with a skeleton recognition method in one embodiment;

[0045] Figure 7 FIG. 4 is a flow chart of a target recognition method for a second transportation facility in one embodiment. DETAILED DESCRIPTION

[0046] 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.

[0047] 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.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] 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 headlight 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 headlight 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 headlight system 400 includes but is not limited to a fog lamp, a high beam, a low beam, and a flash. The on-board electronic device 100 receives the sensor data (such as a live image, an actual shooting distance) collected by the sensor 200, executes the headlight control method, extracts the environmental visibility information, and determines the corresponding safety level based on the environmental visibility information. When the safety level is lower than the preset level, the first headlight signal is triggered. After receiving the first headlight signal, the execution controller 300 starts the headlight system 400, for example, turning on the high and low beams or intelligently adjusting the lighting range and angle, etc., to improve the driving field of vision.

[0052] In actual applications, after the vehicle-mounted electronic device 100 controls and starts the vehicle lighting system 400, 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.

[0053] Figure 3 Flowchart of the driving environment safety assessment method of this embodiment is shown in FIG. 1 , which is described by taking the method applied to the above-mentioned vehicle-mounted electronic device as an example, and includes the following steps:

[0054] Step S101, obtaining a real-time image of the road environment captured by a camera and an actual shooting distance of the camera.

[0055] The actual shooting distance of the camera is the distance between the camera or the vehicle and the traffic facilities. The actual shooting distance can be obtained in the following ways:

[0056] In the actual environment, after the vehicle recognizes the traffic facilities through the pictures collected by the camera, it uses the binocular vision imaging module or Lidar, Radar and other sensors to measure the position of the traffic facilities. For example, the character information on the road sign is recognized by the binocular vision imaging module, and based on the visual recognition result, the distance between the first traffic facility and the vehicle is calculated using the binocular vision left and right aberration position. Alternatively, the distance to the spatial high-reflection target (such as road guardrail) is directly measured by Lidar.

[0057] Step S102, performing target recognition on the live image, and extracting environmental visibility information based on the target recognition result and the actual shooting distance; wherein the environmental visibility information includes the clarity of the first traffic facility and / or the visibility of the second traffic facility; wherein characters are set on the first traffic facility.

[0058] The characters include, but are not limited to, classical Chinese (which may be in various languages), Arabic numerals, and symbols. The live image may include images of traffic facilities, such as road signs, ground signs, road guardrails, speed bumps, etc. In this embodiment, traffic facilities containing characters such as road signs and ground signs are defined as first traffic facilities, and traffic facilities without characters such as road guardrails and speed bumps are defined as second traffic facilities.

[0059] The clarity of the first traffic facility is related to whether the driver can quickly and accurately read the characters on the traffic sign, understand its meaning and respond correctly. In complex road conditions or high-speed driving, the clarity of the first traffic facility can help the driver prepare in advance and reduce the occurrence of unexpected situations.

[0060] The visibility of the second traffic facility is related to whether the traffic facility can still be clearly seen in low light or bad weather conditions, which is crucial to preventing accidents. Especially at night or in low light conditions, sufficient visibility is a key factor in preventing traffic accidents.

[0061] By setting clarity and visibility indicators for different types of traffic facilities, data support can be provided for evaluating the safety level of the road environment in different driving scenarios.

[0062] Step S103, determining the safety level of the road environment according to the environmental visibility information.

[0063] 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.

[0064] In some embodiments, the clarity of the first traffic facility and the visibility of the second traffic facility can be normalized to the safety level respectively, and the decision to turn on the headlights is made based on a single indicator, which is convenient to calculate and has a fast decision speed. For example, the higher the clarity of the first traffic facility, the higher the corresponding safety level; the higher the visibility of the second traffic facility, the higher the corresponding safety level. Alternatively, the clarity of the first traffic facility and the visibility of the second traffic facility can be transformed into the [0, 1] interval after data standardization, and the weights can be 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 clarity of the first traffic facility and the visibility of the second traffic facility meets the preset conditions (the clarity of the first traffic facility is lower than the first threshold, and the visibility of the second traffic facility is lower than the second threshold), the system determines that the safety level is lower than the preset level and the headlights need to be turned on.

[0065] In the above steps S101 to S103, by collecting real-time live images of the road environment, the actual shooting distance of the camera is obtained, and environmental visibility information is extracted based on the object recognition results of the live images and the actual shooting distance. This environmental visibility information adaptively selects clarity or visibility indicators for different types of traffic facilities, providing data support for evaluating the safety level of the road environment in different driving scenarios, making the driving environment safety assessment more intelligent and comprehensive, and can avoid the problem of incorrect light source recognition. Therefore, the accuracy of the driving environment safety assessment can be improved.

[0066] In one embodiment, a method for object recognition of a first traffic facility is provided. Figure 4 The flowchart of the method for object recognition of the first traffic facility in this embodiment is as Figure 4 shown. When performing object recognition on the live image and extracting environmental visibility information based on the object recognition results and the actual shooting distance, it can be achieved through the following steps:

[0067] Step S201, when the first traffic facility is recognized in the live image, based on semantic recognition, obtain the characters on the first traffic facility in the live image and determine the first stroke continuity degree of the characters.

[0068] The first stroke feature of the character can be extracted through semantic recognition, and the second stroke feature of the character in the complete size can also be extracted; taking the second stroke feature as the reference object, determine the stroke continuity degree of the first stroke feature relative to the second stroke feature.

[0069] Both the first stroke feature and the second stroke feature are the total stroke lengths of the character. Among them, the first stroke feature is the total stroke length actually calculated for the character in the live image, and the second stroke feature is the total stroke length theoretically calculated for the character in the complete size. When the clarity is low (weak ambient light, turbid air, or far distance), the characters recognized in the visual imaging will have defects, resulting in discontinuous stroke order. For easy understanding, Figure 5 a character schematic diagram is provided, as Figure 5 shown. Assume that the character "Tian" is recognized based on the live image. The left part represents the defective shape of the character, and the right part represents the complete shape of the character. Then the first stroke feature L1 is the total length of the discontinuous stroke order in the actual situation, and the second stroke feature L2 is the total length of the continuous stroke order in the imaginary situation.

[0070] For the recognized character, divide the total stroke length L1 actually calculated by the total stroke length L2 theoretically calculated to obtain the stroke continuity degree of the character. The more serious the character defect, the lower its stroke continuity degree; conversely, the less serious the character defect, the higher its stroke continuity degree.

[0071] Step S202: acquiring a first visible distance of the vehicle relative to a first traffic facility according to the actual shooting distance.

[0072] In the actual environment, after the vehicle recognizes the traffic facilities through the pictures collected by the camera, it uses the binocular vision imaging module or Lidar, Radar and other sensors to measure the location of the traffic facilities. For example, the character information on the road sign is recognized by the binocular vision imaging module, and based on the visual recognition results, the distance between the first traffic facility and the vehicle is calculated using the binocular vision left and right aberration position. Alternatively, the distance to the nearest high-reflectivity target in space is directly measured by Lidar.

[0073] Step S203: Substitute the first stroke continuity degree and the first visible distance into the first mapping function to calculate the clarity of the first traffic facility.

[0074] Before performing target recognition on the live image and extracting environmental visibility information based on the target recognition result and the actual shooting distance, the clarity calibration of the first traffic facility can be performed as follows:

[0075] Obtain different stroke continuity degrees of the vehicle relative to the first traffic facility at different visual distances and different definitivities; perform two-dimensional fitting on each visual distance, each definitivity and each stroke continuity degree to obtain a first fitting parameter; and construct a first mapping function according to the first fitting parameter.

[0076] It can be understood that the first mapping function is used to represent the mapping relationship between the visual distance, clarity, and stroke continuity. Among them, the stroke continuity is positively correlated with the clarity. The higher the clarity, the higher the stroke continuity. The stroke continuity is also related to the visual distance. The closer the visual distance, the higher the stroke continuity.

[0077] In one embodiment, Figure 6 A flowchart of a semantic recognition processing method is provided, such as Figure 6 As shown, obtaining the characters on the first traffic facility in the live image based on semantic recognition can be achieved through the following steps:

[0078] Step S301, performing OCR recognition on the live image to obtain an OCR recognition result.

[0079] In the live image, a first area whose color does not change and is continuous is determined; shape recognition is performed on the first area or a second area obtained by combining the first areas, and a corresponding character is determined according to the recognized shape.

[0080] Step S302, performing skeleton recognition on the live image to obtain a skeleton recognition result.

[0081] Identify pixel blocks with color jumps in the live image; determine the median coordinates based on the maximum and minimum values ​​of the pixel coordinates in the pixel block on the X-axis and Y-axis, and determine the pixels at the median coordinates as inflection points; connect every two closest inflection points in sequence to obtain skeleton information; and determine the corresponding characters based on the skeleton information.

[0082] Step S303, determine whether the OCR recognition result and the skeleton recognition result are consistent; if they are consistent, execute step S304; if they are inconsistent, execute step S305.

[0083] Step S304, determining whether the current semantic recognition process is valid, and outputting corresponding character information.

[0084] 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.

[0085] 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.

[0086] In one embodiment, a target recognition method for a second transportation facility is provided. Figure 7 is a flow chart of the target recognition method for the second traffic facility in this embodiment. Figure 7As shown, when performing target recognition on a live image and extracting environmental visibility information based on the target recognition result and the actual shooting distance, it can be achieved through the following steps:

[0087] Step S401 : when a second traffic facility is identified in the live image, a second visible distance of the vehicle relative to the farthest second traffic facility in the live image is obtained according to the actual shooting distance.

[0088] In an actual environment, after the vehicle recognizes traffic facilities through images captured by the camera, it can directly measure the distance to the farthest high-reflectivity target in space through Lidar.

[0089] Step S402: Substitute the second visible distance into the second mapping function to calculate the visibility of the second traffic facility.

[0090] Before performing target recognition on the live image and extracting environmental visibility information based on the target recognition result and the actual shooting distance, the visibility of the second traffic facility can be calibrated as follows:

[0091] Obtain different visibility of the vehicle relative to the second traffic facility at different visible distances; perform one-dimensional fitting on each visible distance and each visibility to obtain a second fitting parameter; and construct a second mapping function according to the second fitting parameter.

[0092] It can be understood that the second mapping function is used to represent the mapping relationship between the visual distance and the visibility. The visual distance and the visibility are positively correlated, and the shorter the visual distance, the higher the visibility.

[0093] The following will take road signs and guardrails as examples to further introduce clarity and visibility calibration.

[0094] In actual applications, the vehicle is parked in a test site with road signs and road guardrails. Real-time images of road signs and road guardrails are collected under different visibility environments. The visibility, the stroke continuity of the characters on the road signs at different distances, and the visible distance of the road guardrails are calculated through the real-time images.

[0095] Construct a database. The database contains two functions: one is a function for the continuity of character strokes corresponding to road signs at different visibility and different viewing distances (i.e., the first mapping function); the other is a function for the viewing distance corresponding to road guardrails at different visibility (i.e., the second mapping function).

[0096] Specifically, when the continuity of character strokes at different clarity and different visible distances is obtained, a two-dimensional fitting is performed to obtain the first mapping function Y1=MX1+NX2. At this time, the sampling points X1 and X2 correspond to the visible distance and the continuity of character strokes respectively, and Y1 corresponds to the clarity under this two-dimensional parameter, and [M, N] is the corresponding first fitting parameter. When the visible distance under different visibility is obtained, a one-dimensional fitting is performed to obtain the second mapping function Y2=AX1+B function. At this time, the sampling point X1 is the visible distance, Y1 is the visibility, and [A, B] is the corresponding second fitting parameter. The two parameters Y1 and Y2 are benchmarked based on the actual environment, that is, in the two-level ranking of Y1 and Y2, some levels correspond to each other, such as one or several levels of Y1 correspond to one or several levels of Y2.

[0097] When the vehicle is driving and there are no other vehicles around it, the vehicle uses the camera configured on the vehicle to collect road images in real time; analyze the information in the image, first identify the road sign as the target, and when the information in the image does not include the road sign information, identify the road guardrail as the target. If both of the above targets do not exist, collect the next frame of image and make a new judgment. If it is found that the image only contains guardrail information during the image recognition process, the farthest end of the guardrail in the image is measured by the binocular ranging solution, and the visibility Y2 is calculated in the database for the measured distance. If it is found that the image contains road sign information during the image recognition process, the speed information on the road sign is read, which includes but is not limited to speed limit signs, ground speed limits (digital information: speed limit 80, G92 Hangzhou Bay Loop), highway names (text information: G92 Hangzhou Bay Loop), etc., and the classical Chinese information on the road sign is identified and the degree of stroke continuity of the classical Chinese is obtained; based on the measured estimate and the degree of stroke continuity, the clarity Y1 can be calculated in the database. Comprehensive result output: When the corresponding relationship is satisfied between the two matrices Y1 and Y2, the corresponding road environment safety level is output, and the safety level is input into the vehicle hardware control unit to control the lights.

[0098] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0099] Obtain the real-time image of the road environment captured by the camera, as well as the actual shooting distance of the camera;

[0100] Performing target recognition on the live image, and extracting environmental visibility information based on the target recognition result and the actual shooting distance; wherein the environmental visibility information includes the clarity of the first traffic facility and / or the visibility of the second traffic facility; wherein characters are arranged on the first traffic facility;

[0101] Determine the safety level of the road environment based on environmental visibility information.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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 driving environment safety assessment method, characterized in that: include: Acquire a real-time image of the road environment captured by a camera, and an actual shooting distance of the camera; Performing target recognition on the live image, and extracting environmental visibility information based on the target recognition result and the actual shooting distance; wherein the environmental visibility information includes the clarity of the first traffic facility and / or the visibility of the second traffic facility; wherein the first traffic facility is provided with characters; A safety level of the road environment is determined according to the environmental visibility information.

2. The driving environment safety assessment method according to claim 1, characterized in that: Performing target recognition on the live image, and extracting environmental visibility information based on the target recognition result and the actual shooting distance, including: When the first traffic facility is recognized in the live image, acquiring characters on the first traffic facility in the live image based on semantic recognition, and determining a first stroke continuity degree of the characters; According to the actual shooting distance, obtaining a first visible distance of the vehicle relative to the first traffic facility; The first stroke continuity degree and the first visible distance are substituted into a first mapping function to calculate the clarity of the first traffic facility.

3. The driving environment safety assessment method according to claim 2, characterized in that: In the case where the first traffic facility is recognized in the live image, acquiring a character on the first traffic facility in the live image based on semantic recognition and determining a first stroke continuity degree of the character includes: Extracting a first stroke feature of the character, and extracting a second stroke feature of the character in full size; The second stroke feature is used as a reference object to determine the stroke continuity degree of the first stroke feature relative to the second stroke feature.

4. The driving environment safety assessment method according to claim 3, characterized in that: Acquiring characters on the first traffic facility in the live image based on semantic recognition 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.

5. The driving environment safety assessment method according to claim 2, characterized in that: Before performing target recognition on the live image and extracting environmental visibility information based on the target recognition result and the actual shooting distance, the method further includes: Obtaining different stroke continuity degrees of the vehicle relative to the first traffic facility at different visual distances and different clarity; Performing two-dimensional fitting on each of the visible distances, each of the clarity and each of the stroke continuity degrees to obtain a first fitting parameter; The first mapping function is constructed according to the first fitting parameter.

6. The driving environment safety assessment method according to claim 1, characterized in that: Performing target recognition on the live image, and extracting environmental visibility information based on the target recognition result and the actual shooting distance, including: When the second traffic facility is identified in the live image, obtaining a second visible distance of the vehicle relative to the farthest second traffic facility in the live image according to the actual shooting distance; Substitute the second visible distance into the second mapping function to calculate the visibility of the second traffic facility.

7. The driving environment safety assessment method according to claim 6, characterized in that: Before performing target recognition on the live image and extracting environmental visibility information based on the target recognition result and the actual shooting distance, the method further includes: Obtaining different visibility of the vehicle relative to the second traffic facility at different visual distances; Perform one-dimensional fitting on each of the visual distances and each of the visibility to obtain a second fitting parameter; The second mapping function is constructed according to the second fitting parameter.

8. The driving environment safety assessment method according to claim 1, characterized in that: The first traffic facility includes road signs or ground markings; the second traffic facility includes road guardrails or speed bumps.

9. A vehicle light control method, characterized in that: include: Determining the road environment safety level according to the driving environment safety assessment method described in any one of claims 1 to 8; The operating state of the vehicle headlights is controlled according to the road environment safety level.

10. 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 8 are implemented.

Images