Vehicle control method, device and vehicle based on ADAS camera

Abstract

The present application relates to the field of automobile technology, and discloses a vehicle control method, device and vehicle based on an ADAS camera, wherein the method includes: obtaining an actual image of the environment in which the vehicle is located captured by the ADAS camera; identifying the current rainfall and / or current brightness of the environment according to the actual image; when the current rainfall is greater than a preset rainfall threshold, controlling the vehicle's windshield wipers to scrape, and / or when the current brightness is less than a preset brightness threshold, controlling the vehicle's lighting equipment to turn on. Thus, the problem that the related art requires the use of both a rain sensor and a light sensor to realize the automatic headlight and automatic wiper functions, which wastes the layout space of the entire vehicle, increases the cost of the entire vehicle, and reduces driving comfort is solved.

Description

Technical Field

[0001] The present application relates to the field of automobile technology, and in particular to a vehicle control method, device and vehicle based on an ADAS camera. Background Art

[0002] With the development trend of the automobile industry, intelligent configuration has been widely used in automobiles, and each type of sensor has its unique advantages and application scenarios. Among them, rain sensors and light sensors are currently commonly used sensors. Rain sensors can control the wipers to start and stop according to the detected rainfall information, and light sensors can control the opening and closing of car lights according to the detected brightness of the external environment light source.

[0003] However, the related technology requires the use of rain sensors and light sensors at the same time to realize the automatic headlight and automatic wiper functions, which greatly increases the cost of the entire vehicle. In addition, the sensors installed in smart driving vehicles have high requirements for environmental perception, and need to meet their own layout requirements under the overall layout to enable various sensors in the perception system to exert maximum energy efficiency. Not only does it take up layout space, causing difficulties in vehicle layout, but the sensors installed on the front windshield will also affect the driver's line of sight and reduce driving comfort.

[0004] Application Contents

[0005] The present application provides a vehicle control method, device and vehicle based on an ADAS camera to solve the problems in the related technology that a rain sensor and a light sensor are needed to realize the automatic headlight and automatic wiper functions, which wastes the layout space of the whole vehicle, increases the cost of the whole vehicle, and reduces driving comfort.

[0006] The first aspect of the present application provides a vehicle control method based on an ADAS camera, comprising the following steps: acquiring an actual image of the vehicle's environment captured by the ADAS camera; identifying the current rainfall and / or current brightness of the environment based on the actual image; controlling the vehicle's wipers to scrape when the current rainfall is greater than the preset rainfall threshold, and / or controlling the vehicle's lighting equipment to turn on when the current brightness is less than a preset brightness threshold.

[0007] Furthermore, identifying the current rainfall and / or current brightness of the environment based on the actual image includes: extracting at least one rainfall feature and / or at least one brightness feature from the actual image; and obtaining the current rainfall and / or the current brightness using a pre-trained recognition model based on the at least one rainfall feature and / or the at least one brightness feature.

[0008] Furthermore, the controlling of the wiper wiping of the vehicle includes: determining a current rainfall level based on a difference between the current rainfall and the preset rainfall threshold; calculating a target wiping frequency of the wiper based on the current rainfall level, and controlling the wiper to wipe at the target wiping frequency.

[0009] Furthermore, the controlling of turning on the lighting equipment of the vehicle includes: determining a current light level according to a difference between the current brightness and the preset brightness threshold; calculating a target brightness of the lighting equipment according to the current light level, and controlling the low beam of the lighting equipment to illuminate according to the target brightness.

[0010] Furthermore, the controlling of turning on the lighting equipment of the vehicle further includes: judging whether the environment in which the vehicle is located meets the high beam condition based on the actual image; when the environment in which the vehicle is located meets the high beam condition, turning on the high beam of the lighting equipment and controlling the high beam to illuminate according to the target brightness.

[0011] A second aspect of the present application provides a vehicle control device based on an ADAS camera, including: an acquisition module, used to acquire an actual image of the vehicle's environment captured by the ADAS camera; an identification module, used to identify the current rainfall and / or current brightness of the environment based on the actual image; a control module, used to control the vehicle's wipers to wipe when the current rainfall is greater than the preset rainfall threshold, and / or control the vehicle's lighting equipment to turn on when the current brightness is less than a preset brightness threshold.

[0012] Furthermore, the recognition module includes: an extraction unit, used to extract at least one rainfall feature and / or at least one brightness feature from the actual image; and a recognition unit, used to obtain the current rainfall and / or the current brightness based on the at least one rainfall feature and / or the at least one brightness feature using a pre-trained recognition model.

[0013] Furthermore, the control module includes: a wiper control unit, used to determine the current rainfall level according to the difference between the current rainfall and the preset rainfall threshold, calculate the target wiping frequency of the wiper according to the current rainfall level, and control the wiper to wipe according to the target wiping frequency.

[0014] Furthermore, the control module includes: a low beam control unit, used to determine the current light level according to the difference between the current brightness and the preset brightness threshold, calculate the target brightness of the lighting device according to the current light level, and control the low beam of the lighting device to illuminate according to the target brightness; a high beam control unit, used to determine whether the environment in which the vehicle is located meets the high beam condition according to the actual image, and when the environment in which the vehicle is located meets the high beam condition, turn on the high beam of the lighting device and control the high beam to illuminate according to the target brightness.

[0015] A third aspect of the present application provides a vehicle, comprising the vehicle control device based on the ADAS camera described in the above embodiment.

[0016] Therefore, this application has at least the following beneficial effects:

[0017] Using ADAS cameras to replace rain sensors and light sensors, automatic headlights and automatic wipers can be realized without rain sensors and light sensors, effectively reducing the number of sensors in the vehicle, reducing the cost of the vehicle, and effectively saving the layout space of the vehicle, reducing the impact of sensors on the driver's line of sight, and improving driving comfort. This solves the technical problems in related technologies that require the use of rain sensors and light sensors at the same time to realize automatic headlights and automatic wipers, wasting the layout space of the vehicle, increasing the cost of the vehicle, and reducing driving comfort.

[0018] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0020] Figure 1 It is a working schematic diagram of an infrared sunlight rainfall sensor in the related art;

[0021] Figure 2 A schematic diagram of a process of a vehicle control method based on an ADAS camera provided according to an embodiment of the present application;

[0022] Figure 3 A schematic diagram of the arrangement position of an ADAS camera according to an embodiment of the present application;

[0023] Figure 4 A schematic diagram of deep learning simulation of an ADAS camera provided according to an embodiment of the present application;

[0024] Figure 5A schematic diagram of the operation of an ADAS camera according to an embodiment of the present application;

[0025] Figure 6 This is an example diagram of a vehicle control device based on an ADAS camera provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0027] With the development trend of the automotive industry, intelligent configuration has been widely used in automobiles, and each type of sensor has its unique advantages and application scenarios. Among them, rain sensors and light sensors are currently commonly used sensors.

[0028] At present, a rain sensor that detects rainfall and a light sensor that detects the brightness of the external environment light source are usually set together as a sunlight rain sensor. The sunlight rain sensor is used to realize the automatic headlight and automatic wiper functions, but its essence is still the automatic headlight and automatic wiper functions realized by the use of two sensors. Among them, the sunlight rain sensors mainly include flow sensors, electrostatic sensors, capacitive sensors, and infrared sensors. By comparison, the mainstream sensors on the market are infrared sensors. Figure 1 As shown, its working principle is:

[0029] The light emitted by the light-emitting diode is adjusted by the lens system and irradiated onto the windshield in a parallel light state; the rainfall is calculated by the received reflection signal. Ambient light sensing is to sense the brightness of the external ambient light source through infrared rays. When the ambient light brightness is lower than the required brightness (the brightness is a calibration quantity and can be calibrated according to each OEM), the headlights are controlled to turn on and off. The sunlight and rainfall sensor needs to be placed in an area that is easy to sense ambient light and wipers, and at the same time needs to be placed within the wiper range.

[0030] However, the sensors installed in smart driving vehicles have high requirements for environmental perception. They need to meet their own layout requirements under the overall layout to maximize the energy efficiency of various sensors in the perception system. The use of each sensor in its own way not only makes the layout of the whole vehicle difficult and occupies a large space, but also increases the cost of the whole vehicle. With the rapid development of my country's automobile technology and the promotion of national standards, Ministry of Transport standards and other regulatory requirements, the country and the automobile industry are also gradually paying attention to assisted driving technology. For example, forward-facing ADAS (Advanced Driving Assistance System) cameras can be widely used in the field of commercial vehicles.

[0031] It is precisely for the above reasons that the embodiments of the present application can realize the sunlight and rain sensor function through the forward ADAS camera, reduce the layout space of the whole vehicle, and at the same time reduce the cost of the whole vehicle, thereby achieving cost-effective car manufacturing while meeting the functions of the whole vehicle.

[0032] The following will describe the vehicle control method, device and vehicle based on the ADAS camera of the embodiment of the present application with reference to the accompanying drawings. In view of the problem that the related technology mentioned in the background technology center mentioned above needs to use both the rain sensor and the light sensor to realize the automatic headlight and automatic wiper functions, which wastes the layout space of the whole vehicle, increases the cost of the whole vehicle, and reduces the driving comfort, the present application provides a vehicle control method based on the ADAS camera, in which the ADAS camera is used to replace the rain sensor and the light sensor, and the automatic headlight and automatic wiper functions can be realized without the rain sensor and the light sensor, which effectively reduces the number of sensors in the whole vehicle, reduces the cost of the whole vehicle, and can effectively save the layout space of the whole vehicle, reduce the influence of the sensor on the driving line of sight, and improve driving comfort. As a result, the technical problems such as the need to use both the rain sensor and the light sensor in the related technology to realize the automatic headlight and automatic wiper functions, waste the layout space of the whole vehicle, increase the cost of the whole vehicle, and reduce driving comfort are solved.

[0033] Specifically, Figure 2 A schematic flow chart of a vehicle control method based on an ADAS camera provided in an embodiment of the present application.

[0034] like Figure 2 As shown, the vehicle control method based on the ADAS camera includes the following steps:

[0035] In step S101, an actual image of the vehicle's environment captured by an ADAS camera is obtained.

[0036] Among them, the embodiment of the present application can specifically arrange the position of the ADAS camera according to the vehicle model to comprehensively obtain the road and environmental information in front of the vehicle.

[0037] As an example of an arrangement, Figure 3 As shown, the forward ADAS camera can be arranged at the central axis of the windshield inside the vehicle, and the error during arrangement can be within a first preset range from the central axis. For example, the first preset range can be set to be within 50 mm left and right deviation from the central axis; the installation height range can be within a second preset range. For example, the second preset range can be set to 1.2 meters to 2.5 meters, which can be determined according to the actual vehicle model; at the same time, the installation of other components on the front windshield cannot cause the emitted light to enter the camera's field of view.

[0038] In step S102, the current rainfall and / or current brightness of the environment is identified according to the actual image.

[0039] In this embodiment, the current rainfall and / or current brightness of the environment is identified according to the actual image, including: extracting at least one rainfall feature and / or at least one brightness feature from the actual image; and obtaining the current rainfall and / or current brightness according to the at least one rainfall feature and / or at least one brightness feature using a pre-trained recognition model.

[0040] Among them, the pre-trained recognition model can be a model obtained through deep learning and other methods. For example, it can be through CNN (Convolutional Neural Network) or other deep neural networks in deep learning, by simulating neural network data for a large number of rainy days / cloudy days / dark ambient light and other similar scenes, so as to train to achieve judgment and prediction, and realize automatic wiper and automatic headlight functions.

[0041] It is understandable that if Figure 4 As shown, the embodiment of the present application can use a forward ADAS camera to obtain the road and environment information in front of the vehicle in real time, classify and process the captured images through deep learning and other methods, and output the corresponding control logic, so that the forward ADAS camera can perform a large amount of simulation training through deep learning and other methods, and can correctly determine whether it is raining in front of the vehicle or the ambient light is dim, and automatically turn on the wiper and headlight functions. The specific control logic refers to step S103, which is not elaborated here.

[0042] The following will take the CNN deep learning model as an example to explain the model training process in detail:

[0043] The deep learning model consists of four main components: low-level feature extraction network, mid-level feature extraction network, global feature extraction network and colorization network. These components are tightly coupled and trained in an end-to-end manner. By comparing the chromaticity, brightness and other information of the captured image, these factors are successfully separated through multi-layer nonlinear mapping, so that each factor becomes a simple linear relationship and no longer interferes with each other to determine whether there are raindrops in front of the vehicle, whether the ambient light in front of the vehicle is insufficient, and other scenes.

[0044] At the same time, in order for the ADAS camera to make correct judgments, the ADAS camera needs to perform a large amount of neural network training and learning, neural network implementation and inference operations, and comparative analysis of the execution of the neural network's CNN algorithm on the image and the classification results to ensure the accuracy of the output results.

[0045] In step S103, when the current rainfall is greater than a preset rainfall threshold, the vehicle's windshield wipers are controlled to wipe, and / or when the current brightness is less than a preset brightness threshold, the vehicle's lighting equipment is controlled to turn on.

[0046] Among them, the preset rainfall threshold and the preset brightness threshold can be specifically set according to the results of model training, and there is no specific limitation on this; the lighting equipment can be the headlights of a vehicle, etc.

[0047] It can be understood that the embodiment of the present application uses a forward-facing ADAS camera instead of a sunlight and rain sensor, and can recognize the rainfall and the brightness of the external environment based on the image acquired by the ADAS camera to automatically control the operation of the wipers and headlights, thereby realizing automatic wiper and headlight functions, saving space for the entire vehicle layout and reducing the cost of the entire vehicle, thereby achieving cost-effective vehicle manufacturing while meeting the functions of the entire vehicle.

[0048] In this embodiment, controlling the wiping of the vehicle's wipers includes: determining the current rainfall level based on the difference between the current rainfall and a preset rainfall threshold; calculating the target wiping frequency of the wipers based on the current rainfall level, and controlling the wipers to wipe at the target wiping frequency.

[0049] Among them, the embodiment of the present application can pre-establish a rainfall level and difference correspondence table, so that the current rainfall level can be quickly and accurately determined according to the difference between the current rainfall and the preset rainfall threshold; the target scraping frequency corresponds to the current rainfall level, the greater the rainfall, the higher the scraping frequency.

[0050] Therefore, the embodiment of the present application can utilize the image acquired by the ADAS camera to identify the amount of rainfall and realize automatic control of the wiper, thereby realizing the automatic wiper function without the need for a rain sensor.

[0051] In this embodiment, controlling the vehicle's lighting equipment to turn on includes: determining the current light level based on the difference between the current brightness and a preset brightness threshold; calculating the target brightness of the lighting equipment based on the current light level, and controlling the low beam of the lighting equipment to illuminate according to the target brightness.

[0052] Among them, the embodiment of the present application can pre-establish a light level and difference correspondence table, so that the current light level can be quickly and accurately determined based on the difference between the current brightness and the preset rainfall threshold; the target brightness corresponds to the current light level, and the higher the current light level, the higher the corresponding brightness.

[0053] Therefore, the embodiment of the present application can utilize the image acquired by the ADAS camera to recognize the brightness of the external environment and realize automatic control of the lighting equipment, thereby realizing the automatic headlight function without the need for a light sensor.

[0054] In this embodiment, controlling the vehicle's lighting equipment to turn on further includes: determining whether the vehicle's environment meets the high beam condition based on the actual image; when the vehicle's environment meets the high beam condition, turning on the high beam of the lighting equipment and controlling the high beam to illuminate according to the target brightness.

[0055] It is understandable that after calculating the target brightness of the lighting equipment, the embodiment of the present application also determines whether the high beam needs to be turned on according to the actual image. If not, the low beam is turned on. If yes, the high beam is turned on and illuminated according to the target brightness. Therefore, the embodiment of the present application can use the image obtained by the ADAS camera to control the automatic turning on of the low beam and the high beam, thereby improving the intelligence of the control.

[0056] The following will be combined Figure 5 The working principle of the vehicle control method based on ADAS camera is explained as follows:

[0057] The forward assisted driving function obtains information within the forward field of view through the forward ADAS camera and other perception systems, performs data analysis and outputs corresponding content for comprehensive control; the ADAS camera is arranged in a position to fully obtain the road and environmental information in front of the vehicle, and can process and analyze rainfall information and ambient light information through deep learning or other methods, and send out corresponding control signals to control the opening and closing of the lights and wipers, thereby realizing automatic headlights and automatic wiper functions.

[0058] In summary, the embodiments of the present application can save space for the entire vehicle layout and improve driving comfort; save the cost of the entire vehicle and achieve cost-effective vehicle manufacturing; realize automatic headlights and automatic wiper functions through deep learning and other methods, and the working reliability is better than that of traditional infrared sunlight and rainfall sensors.

[0059] According to the vehicle control method based on ADAS camera proposed in the embodiment of the present application, ADAS camera is used to replace rain sensor and light sensor, and automatic headlight and automatic wiper functions can be realized without rain sensor and light sensor, thereby effectively reducing the number of sensors in the whole vehicle, reducing the cost of the whole vehicle, and effectively saving the layout space of the whole vehicle, reducing the influence of sensors on driving vision, and improving driving comfort.

[0060] Next, a vehicle control device based on an ADAS camera according to an embodiment of the present application is described with reference to the accompanying drawings.

[0061] Figure 6 It is a block diagram of a vehicle control device based on an ADAS camera according to an embodiment of the present application.

[0062] like Figure 6 As shown, the vehicle control device 10 based on the ADAS camera includes: an acquisition module 100 , a recognition module 200 and a control module 300 .

[0063] Among them, the acquisition module 100 is used to obtain the actual image of the vehicle's environment captured by the ADAS camera; the recognition module 200 is used to identify the current rainfall and / or current brightness of the environment based on the actual image; the control module 300 is used to control the vehicle's wipers to scrape when the current rainfall is greater than a preset rainfall threshold, and / or control the vehicle's lighting equipment to turn on when the current brightness is less than a preset brightness threshold.

[0064] Furthermore, the recognition module 200 includes: an extraction unit and a recognition unit. The extraction unit is used to extract at least one rainfall feature and / or at least one brightness feature from the actual image; the recognition unit is used to obtain the current rainfall and / or current brightness according to the at least one rainfall feature and / or at least one brightness feature using a pre-trained recognition model.

[0065] Furthermore, the control module 300 includes a wiper control unit, which is used to determine the current rainfall level according to the difference between the current rainfall and a preset rainfall threshold, calculate the target wiping frequency of the wiper according to the current rainfall level, and control the wiper to wipe according to the target wiping frequency.

[0066] Furthermore, the control module 300 includes: a low beam control unit and a high beam control unit. The low beam control unit is used to determine the current light level according to the difference between the current brightness and the preset brightness threshold, calculate the target brightness of the lighting device according to the current light level, and control the low beam of the lighting device to illuminate according to the target brightness; the high beam control unit is used to determine whether the environment where the vehicle is located meets the high beam condition according to the actual image, and when the environment where the vehicle is located meets the high beam condition, turn on the high beam of the lighting device and control the high beam to illuminate according to the target brightness.

[0067] It should be noted that the aforementioned explanation of the embodiment of the vehicle control method based on the ADAS camera is also applicable to the vehicle control device based on the ADAS camera of this embodiment, and will not be repeated here.

[0068] According to the vehicle control device based on ADAS camera proposed in the embodiment of the present application, ADAS camera is used to replace rain sensor and light sensor, and automatic headlight and automatic wiper functions can be realized without rain sensor and light sensor, thereby effectively reducing the number of sensors in the whole vehicle, reducing the cost of the whole vehicle, and effectively saving the layout space of the whole vehicle, reducing the influence of sensors on the driving line of sight, and improving driving comfort.

[0069] In addition, this embodiment also provides a vehicle, including the vehicle control device based on the ADAS camera of the above embodiment. The vehicle uses the ADAS camera to replace the rain sensor and the light sensor, and can realize the automatic headlight and automatic wiper functions without the rain sensor and the light sensor, effectively reducing the number of sensors in the whole vehicle, reducing the cost of the whole vehicle, and can effectively save the layout space of the whole vehicle, reduce the influence of the sensor on the driving line of sight, and improve driving comfort.

[0070] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0071] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0072] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0073] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0074] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

Claims

1. A vehicle control method based on an ADAS camera, characterized in that: The following steps are involved: Obtain the actual image of the vehicle's environment captured by the ADAS camera; Identify the current rainfall and / or current brightness of the environment according to the actual image; as well as When the current rainfall is greater than a preset rainfall threshold, controlling the wipers of the vehicle to wipe, and / or when the current brightness is less than a preset brightness threshold, controlling the lighting equipment of the vehicle to turn on; The step of identifying the current rainfall and / or current brightness of the environment according to the actual image includes: Extracting at least one rainfall feature and / or at least one brightness feature from the actual image; The current rainfall and / or the current brightness are obtained according to the at least one rainfall feature and / or the at least one brightness feature using a pre-trained recognition model, wherein the pre-trained recognition model is a model obtained by deep learning, including: a low-level feature extraction network, a mid-level feature extraction network, a global feature extraction network and a coloring network, the low-level feature extraction network, the mid-level feature extraction network, the global feature extraction network and the coloring network are tightly coupled and trained in an end-to-end manner, and the chromaticity and brightness of the captured image are separated through multi-layer nonlinear mapping, so that various factors become linear relationships.

2. The method according to claim 1, characterized in that The controlling of the wiper of the vehicle comprises: Determining a current rainfall level according to a difference between the current rainfall and the preset rainfall threshold; The target wiping frequency of the wiper is calculated according to the current rainfall level, and the wiper is controlled to wipe according to the target wiping frequency.

3. The method according to claim 1, characterized in that The controlling the lighting device of the vehicle to turn on comprises: Determining a current light level according to a difference between the current brightness and the preset brightness threshold; The target brightness of the lighting device is calculated according to the current light level, and the low beam of the lighting device is controlled to illuminate according to the target brightness.

4. The method according to claim 3, characterized in that The controlling the lighting device of the vehicle to turn on further comprises: Determining whether the environment in which the vehicle is located meets the high beam condition according to the actual image; When the environment in which the vehicle is located meets the high beam condition, the high beam of the lighting device is turned on and the high beam is controlled to illuminate according to the target brightness.

5. A vehicle control device based on an ADAS camera, characterized in that: include: An acquisition module is used to obtain the actual image of the vehicle's environment captured by the ADAS camera; An identification module, used for identifying the current rainfall and / or current brightness of the environment according to the actual image; as well as A control module, configured to control the wipers of the vehicle to wipe when the current rainfall is greater than a preset rainfall threshold, and / or control the lighting equipment of the vehicle to turn on when the current brightness is less than a preset brightness threshold; The identification module comprises: An extraction unit, configured to extract at least one rainfall feature and / or at least one brightness feature from the actual image; An identification unit is used to obtain the current rainfall and / or the current brightness according to the at least one rainfall feature and / or the at least one brightness feature using a pre-trained identification model, wherein the pre-trained identification model is a model obtained by deep learning, including: a low-level feature extraction network, a mid-level feature extraction network, a global feature extraction network and a coloring network, wherein the low-level feature extraction network, the mid-level feature extraction network, the global feature extraction network and the coloring network are tightly coupled and trained in an end-to-end manner, and the chromaticity and brightness of the captured image are separated through multi-layer nonlinear mapping, so that various factors become linearly related.

6. The device according to claim 5, characterized in that The control module comprises: A wiper control unit is used to determine a current rainfall level according to a difference between the current rainfall and the preset rainfall threshold, calculate a target wiping frequency of the wiper according to the current rainfall level, and control the wiper to wipe according to the target wiping frequency.

7. The device according to claim 5, characterized in that The control module comprises: A low beam control unit, configured to determine a current light level according to a difference between the current brightness and the preset brightness threshold, calculate a target brightness of the lighting device according to the current light level, and control the low beam of the lighting device to illuminate according to the target brightness; A high beam control unit is used to determine whether the environment in which the vehicle is located meets the high beam condition based on the actual image, and when the environment in which the vehicle is located meets the high beam condition, turn on the high beam of the lighting device and control the high beam to illuminate according to the target brightness.

8. A vehicle, characterized in that: A vehicle control device based on an ADAS camera as described in any one of claims 5 to 7.

Images