Vehicle wading mode exit control method and device and vehicle

Abstract

The invention discloses a quit control method and device for a vehicle wading mode of a vehicle and the vehicle. The quit control method comprises the steps that after the vehicle enters the wading mode, water area information of a preset area behind the vehicle in the driving direction is obtained; and when the water area information of the preset area meets a preset condition, determining that the vehicle exits the wading mode.

Description

Technical Field

[0001] The present application relates to the field of transportation vehicles, and more specifically to a method for controlling the exit of a vehicle wading mode and a device and vehicle thereof. Background Art

[0002] At present, most vehicles are equipped with a driving control strategy for a wading mode. When a vehicle enters a body of water, the driving mode of the vehicle is switched to the wading mode to control the vehicle to travel in the water. In the related art, there is a problem of mistaken exit of the wading mode in controlling when the vehicle exits the wading mode. Summary of the invention

[0003] The present application is proposed to solve at least one of the above problems. According to a first aspect of the present application, a method for controlling the exit of a vehicle wading mode is provided, the method comprising: after the vehicle enters the wading mode, obtaining water area information of a preset area behind the vehicle in the driving direction; when the water area information of the preset area meets a preset condition, determining that the vehicle exits the wading mode.

[0004] In one embodiment of the present application, the obtaining of water area information of a preset area behind the vehicle in the driving direction includes: obtaining the water surface area of ​​the preset area behind the vehicle in the driving direction, and using the water surface area of ​​the preset area as the water area information of the preset area.

[0005] In one embodiment of the present application, obtaining the water surface area of ​​the preset area behind the vehicle in the driving direction includes: obtaining first image information of the image acquisition area behind the vehicle in the driving direction through at least one device selected from the group consisting of an electronic rearview mirror, an imaging lidar, a side view camera, a front view camera, and a streaming media rearview mirror on the vehicle; wherein the image acquisition area at least includes the preset area; and obtaining the water surface area of ​​the preset area behind the vehicle in the driving direction based on the first image information.

[0006] In one embodiment of the present application, obtaining the water surface area of ​​the preset area behind the vehicle in the driving direction based on the first image information includes: identifying the water surface area in the first image information; and calculating the water surface area of ​​the preset area based on the preset area and the water surface area in the first image information.

[0007] In one embodiment of the present application, obtaining the water surface area of ​​the preset area behind the vehicle in the driving direction based on the first image information includes: cropping out the second image information of the preset area based on the first image information; identifying the water surface area in the second image information, and calculating the water surface area of ​​the preset area.

[0008] In one embodiment of the present application, the exit control method further includes: when the water surface area of ​​the preset area is less than a preset area threshold, determining that the water area information of the preset area meets the preset condition.

[0009] In one embodiment of the present application, the obtaining of water area information of a preset area behind the vehicle in the driving direction includes: obtaining second image information of the preset area behind the vehicle in the driving direction, and using the second image information as the water area information of the preset area.

[0010] In one embodiment of the present application, the exit control method also includes: inputting the second image information into a decision classification algorithm, and the decision classification algorithm determines whether the preset area is a water area; when the output result of the decision classification algorithm is: the preset area is not a water area, determining that the water area information of the preset area meets the preset condition.

[0011] In one embodiment of the present application, after the vehicle enters the wading mode, the water area information of a preset area behind the vehicle in the driving direction is obtained, including: after the vehicle enters the wading mode, periodically obtaining the water area information of a preset area behind the vehicle in the driving direction.

[0012] In one embodiment of the present application, when the water area information of the preset area meets the preset condition, determining that the vehicle exits the wading mode includes: when the water area information of the preset area obtained at least twice in a row meets the preset condition, determining that the vehicle exits the wading mode.

[0013] In one embodiment of the present application, the obtaining of water area information of a preset area behind the vehicle in the driving direction includes: obtaining water area information of a first preset area directly behind the vehicle in the driving direction; when the water area information in the preset area satisfies a preset condition, determining that the vehicle exits the wading mode includes: when the water area information in the first preset area satisfies the preset condition, determining that the vehicle exits the wading mode.

[0014] In one embodiment of the present application, the acquiring of water area information of a preset area behind the vehicle in the driving direction further includes: acquiring water area information of a second preset area to the side and rear of the vehicle in the driving direction; determining that the vehicle exits the wading mode when the water area information in the preset area satisfies a preset condition, further includes: determining that the vehicle exits the wading mode when both the water area information in the first preset area and the water area information in the second preset area satisfy the preset condition.

[0015] According to the second aspect of the present application, there is also provided a vehicle wading mode exit control device, the exit control device comprising: a storage medium and a processor, the storage medium storing a computer program run by the processor, the computer program, when run by the processor, enables the processor to execute any one of the above-mentioned vehicle wading mode exit control methods.

[0016] According to a third aspect of the present application, a vehicle is further provided, comprising: an exit control device for a vehicle wading mode as described above.

[0017] According to the vehicle wading mode exit control method and device and vehicle provided in the embodiment of the present application, after the vehicle enters the wading mode, water area information of a preset area behind the vehicle in the driving direction is obtained; and when the water area information of the preset area meets the preset conditions, the vehicle is determined to exit the wading mode. Whether the water area information of the preset area behind the vehicle in the driving direction meets the preset conditions is used as the basis for judging whether to exit the wading mode, thereby preventing the problem of erroneous exit from the wading mode. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0019] Figure 1 This is a flow chart of a method for controlling the exit of a vehicle wading mode according to an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of a preset area behind a vehicle in a driving direction according to an embodiment of the present invention;

[0021] Figure 3 A schematic diagram showing the relationship between a preset area and an image acquisition area according to another embodiment of the present invention;

[0022] Figure 4 A schematic diagram of a preset area behind a vehicle in the driving direction according to another embodiment of the present invention;

[0023] Figure 5 This is a flow chart of a method for controlling the exit of a vehicle wading mode according to another embodiment of the present invention;

[0024] Figure 6 A schematic diagram of the installation position of an ultrasonic radar according to an embodiment of the present invention.

[0025] Figure 7A schematic diagram showing the arrangement positions and connections of various components on a vehicle according to an embodiment of the present invention;

[0026] Figure 8 A flowchart of exiting the wading mode is shown as another embodiment of the present invention;

[0027] Fig. 9 A schematic diagram of the connection of a data communication module on a vehicle according to an embodiment of the present invention;

[0028] Fig.10 This is a schematic block diagram of an exit control device for a vehicle wading mode according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical scheme and advantages of the present invention more obvious, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described in the present invention, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present invention.

[0030] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0031] It should be understood that the present invention can be implemented in different forms and should not be interpreted as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to make the disclosure thorough and complete and to fully convey the scope of the present invention to those skilled in the art.

[0032] The purpose of the terms used herein is only to describe specific embodiments and is not intended to be limiting of the present invention. When used herein, the singular forms "one", "an" and "said / the" are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "consisting of" and / or "comprising", when used in this specification, confirm the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0033] With the extreme and severe changes in the global climate and environment, the melting of global glaciers is accelerating under the trend of global warming, the sea level is rising, and the variability and frequency of severe weather such as floods and droughts may cause stationary vehicles to be stranded and unable to move due to floods. For example, floods in some cities in recent years have led to huge compensation payments from vehicle insurance companies, and more seriously, the lives of vehicle drivers and passengers are in danger. In previous years, urban flooding occurred every year in southern cities: 184 cities were flooded in 2012, 234 cities in 2013, and 125 cities in 2014; the flood situation was such as the 3,610 flooded vehicles in Huangshan City on July 7, 2020 due to urban flooding, with an estimated loss of 47.71 million; in July 2021, the insurance industry in Henan received 180,000 vehicle claims due to flooding, with an estimated loss of 5.2 billion, etc.; in 657 cities across the country, as many as 300 cities have drainage systems or flood control infrastructure that do not meet national standards.

[0034] Even if we ignore the threats to property or life brought about by climate change, off-road vehicles usually encounter rivers of varying depths, wading grass, wading potholes and uneven roads in the wild environment. Therefore, whether from a practical perspective or from a future trend, the research on safe and reliable wading and floating systems is becoming increasingly important.

[0035] At present, the sensors based on the vehicle body perception system include millimeter wave radar, ultrasonic radar, camera, laser radar, etc., which are mainly used for land ranging, image acquisition and other functions. The existing vehicle sensor systems are basically based on the consideration of road autonomous driving or intelligent driving, and their sensor networks are composed of millimeter wave radar, ultrasonic radar, laser radar and camera. The operating frequencies of millimeter wave radar, ultrasonic radar, etc. are in the frequency range of tens of kHz and GHz. Such high-frequency signals are extremely easy to attenuate in water, resulting in a short propagation distance, and the received effective signal will be very weak, which greatly increases the difficulty of signal processing. The use of underwater cameras is limited by the visibility in the water, and a simple underwater camera cannot provide distance information. It needs to be explained that: Ultrasonic (Ultra-Sonic radar) is a sound wave signal with a frequency range of 20kHz to hundreds of MHz, which belongs to the category of sound waves that cannot be heard by the human ear.

[0036] There are already vehicle products equipped with wading systems, but the known products are basically in a state that requires manual opening or closing of the wading system mode. At the same time, such products are based on a sensor called ultrasonic radar to measure the distance from the rearview mirror to the water surface. However, the technology of ultrasonic radar for wading distance measurement often results in great target misjudgment and false alarms; that is, when encountering road obstacles, it is likely to be misjudged as wading; or in complex outdoor environments, the ultrasonic radar on the rearview mirror may misreport as a wading section when passing through bushes and other plant areas, or even give an erroneous warning message that the water depth exceeds the threshold.

[0037] At present, some vehicles are also equipped with systems based on wading and floating functions, but their technical development only uses the ultrasonic radar mounted on the rearview mirror to perform a simple measurement of the height of the rearview mirror to the water surface when wading or floating. Since the acoustic impedance of air is relatively small compared to that of other media, the ultrasonic radar mounted on the rearview mirror cannot identify the target in an air environment. Therefore, the relevant ultrasonic radar technology for wading ranging often results in great target misjudgment and false alarms. That is, when encountering road obstacles, it is likely to be misjudged as wading; or in a complex outdoor environment, the ultrasonic radar on the rearview mirror may be misreported as a wading section when passing through bushes and other plant areas, or even give an erroneous warning message that the water depth exceeds the threshold.

[0038] In the related art, a method of taking images based on the front-view and left and right side-view fisheye cameras is proposed. Through the image recognition method, the road type in front of the vehicle is input to the side-view ultrasonic height detection system, thereby assisting some vehicles' passive wading detection to automatically switch to the active wading mode. However, in actual applications, when driving from water areas such as wild rivers to land, the active wading mode exit mechanism of the front-view and side-view cameras exposes its defects. That is, when the vehicle exits the water area by going uphill, even if the vehicle is still in the water area, the front-view camera sees the land. Or when the front wheels of the vehicle leave the water area and reach the land, the front-view camera also sees the land. At this time, the vehicle is actually still in the water area, but the input type given to the ultrasonic system by the front-view and side-view camera systems is non-water area, and the active wading mode is exited (that is, the rear half of the vehicle body is still in the water area, but the driving mode has exited the active wading mode). Therefore, it can be seen that the exit mechanism of the active wading height detection system based on the fusion of the front-view camera, the left and right side-view cameras and the ultrasonic wave has the problem of mistaken exit from the wading mode.

[0039] In the related art, there is also a dual-mode active wading mode entry and exit system. However, when the dual-mode active wading height detection entry system is activated and the vehicle enters the water area, there are two situations when the vehicle wants to leave the water area: 1. The front wheels go uphill to land, and the rear wheels are in the water area; at this time, the image of the front camera is land, and the original system will prompt to exit the wading mode; however, the vehicle is still in the water. 2. The front wheels pass through flat land and enter dry land. The front camera may have water and dry land; if the judgment result is most likely land, the system will mistakenly trigger the exit of the wading mode. In order to solve at least some of the problems shown above, the present application proposes the following embodiments.

[0040] In order to fully understand the present invention, a detailed structure will be presented in the following description to illustrate the technical solution proposed by the present invention. The optional embodiments of the present invention are described in detail as follows, but in addition to these detailed descriptions, the present invention may also have other implementations.

[0041] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0042] First, an application scenario of the vehicle wading mode exit control method illustrated in the example of the present application is introduced. The vehicle wading mode exit control method is applied to the process of monitoring when the vehicle exits the wading mode after the vehicle enters the wading mode.

[0043] refer to Figure 1 and Figure 2 , an embodiment of the present application provides an exit control method for a vehicle wading mode, the exit control method comprising:

[0044] Step 1: After the vehicle enters the wading mode, obtain water area information of a preset area behind the vehicle in the driving direction;

[0045] Step 2: When the water area information of the preset area meets the preset conditions, determine that the vehicle exits the wading mode.

[0046] In the above scheme, after the vehicle enters the wading mode, the water area information of the preset area behind the vehicle in the driving direction is obtained; and when the water area information of the preset area meets the preset conditions, it is determined that the vehicle exits the wading mode. Compared with the active wading mode exit mechanism of the front and side view cameras in the related art, and the dual-mode active wading mode exit system, the present application does not use the front wheel position of the vehicle, or the water area information in front of or in front of the side of the vehicle as the basis for judging whether the vehicle exits the wading mode, but uses whether the water area information of the preset area behind the vehicle in the driving direction meets the preset conditions as the basis for judging whether to exit the wading mode. In the scenario where the front wheels of the vehicle go uphill to the land and the rear wheels are in the water, the problem of erroneous triggering of exiting the wading mode will occur in the related art, but according to the scheme of the embodiment of the present application, the vehicle will not be judged as exiting the wading mode in this scenario, thereby preventing the problem of erroneous exit of the wading mode. The above steps are described in detail below in conjunction with the accompanying drawings.

[0047] First, refer to Figure 1 and Figure 2 After the vehicle enters the wading mode, the water area information of the preset area behind the vehicle in the driving direction is obtained. It should be explained that the driving direction of the vehicle refers to the current driving direction of the vehicle. For example, when the vehicle is moving forward, the driving direction of the vehicle is the front direction of the vehicle. When the vehicle is reversing, the driving direction of the vehicle is the rear direction of the vehicle. For example, refer to Figure 4 , the preset area behind the vehicle refers to: a first preset area directly behind the vehicle in the driving direction of the vehicle, the first preset area is located directly behind the current position of the vehicle in the driving direction; and / or a second preset area behind the side of the vehicle in the driving direction of the vehicle, the second preset area is located behind the current position of the vehicle in the driving direction. Specifically, the second preset area may include only the left rear of the vehicle in the driving direction, or only the right rear of the vehicle in the driving direction, or both the left rear and the right rear of the vehicle in the driving direction. Exemplarily, the first preset area may be a rectangular area of ​​3 meters * 8 meters directly behind the vehicle in the driving direction, wherein 3 meters refers to the side length of the first preset area in the width direction of the vehicle, and 8 meters refers to the side length of the first preset area in the length direction of the vehicle. Exemplarily, the second preset area can be a rectangular area of ​​1.5 meters * 8 meters on the side and rear of the vehicle in the direction of travel, where 1.5 meters refers to the side length of the second preset area in the width direction of the vehicle, and 8 meters refers to the side length of the second preset area in the length direction of the vehicle.

[0048] After the vehicle enters wading mode, refer to Figure 1 and Figure 2During the driving process, the vehicle can obtain water area information of a preset area behind the vehicle in the driving direction. The water area information can be any information that can identify or carry the water surface area, water surface area, water surface size, etc. of the preset area. Exemplarily, the water area information can be the water area of ​​the preset area. Exemplarily, the water area information can also be the second image information of the preset area. The second image information can carry the image of the water surface area such as the water surface position and water surface size of the preset area. Therefore, the second image information of the preset area can be directly used as the water area information of the preset area.

[0049] When obtaining the water area information of the preset area behind the vehicle in the driving direction, a variety of methods can be used. Exemplarily, the water surface area of ​​the preset area can be used as the water area information of the preset area. Specifically, when obtaining the water area information of the preset area behind the vehicle in the driving direction, the water surface area of ​​the preset area behind the vehicle in the driving direction can be obtained, and the water surface area of ​​the preset area can be used as the water area information of the preset area. It should be explained that the water surface area refers to the area of ​​the water surface of the preset area, and the water surface area does not represent the depth information of the water area.

[0050] At this time, when obtaining the water surface area of ​​the preset area behind the vehicle in the driving direction, various methods can be used.

[0051] Exemplary, reference Figure 3 , Figure 5 and Figure 7 When obtaining the water surface area of ​​the preset area behind the vehicle in the driving direction, the first image information of the image acquisition area behind the vehicle in the driving direction can be obtained through at least one device of the electronic rearview mirror, imaging laser radar, side view camera, front view camera and streaming media rearview mirror on the vehicle, wherein the image acquisition area at least includes the preset area. Then, according to the first image information, the water surface area of ​​the preset area behind the vehicle in the driving direction is obtained.

[0052] Among them, reference Figure 3 , Figure 6 and Figure 7 There are multiple implementation methods for obtaining first image information of an image acquisition area behind the vehicle in the driving direction through at least one of an electronic rearview mirror, an imaging laser radar, a side view camera, a front view camera, and a streaming media rearview mirror on the vehicle. Specifically, the first image information of an image acquisition area behind the vehicle in the driving direction can be obtained through one, two, or more of the electronic rearview mirror, an imaging laser radar, a side view camera, a front view camera, and a streaming media rearview mirror on the vehicle. For example, referring to Figure 7When an electronic rearview mirror, an imaging laser radar, a side-view camera, a front-view camera, and a streaming media rearview mirror are installed on a vehicle at the same time, the image acquisition areas of some devices can completely include the preset area, while the image acquisition areas of some devices cannot completely include the preset area. Devices whose image acquisition areas can completely include the preset area can be used to acquire the first image information of the image acquisition areas of these devices, thereby obtaining the second image information that at least includes the preset area. Figure 5 to Figure 7 The CMS in it represents an electronic rearview mirror; the front-view camera can be any type of camera, specifically, it can be a front-view binocular (or monocular) camera; the side-view camera can be a fisheye side-view camera arranged on the left and right sides of the vehicle body. Exemplarily, the first image information can be two-dimensional image information or three-dimensional image information of the image acquisition area. The above-mentioned multiple devices can be used together to assist each other, so as to improve the accuracy of target recognition and judgment. Of course, when a 360-degree surround-view camera is provided on the vehicle, the second image information of the preset area at the rear can be obtained through the 360-degree surround-view camera, so as to improve the accuracy of the wading mode exit mechanism.

[0053] Exemplarily, the vehicle's traveling direction is the front direction of the vehicle, and the preset area is located within the image acquisition area of ​​the vehicle's electronic rearview mirror and / or streaming media rearview mirror. At this time, the first image information of the electronic rearview mirror and / or streaming media rearview mirror in the image acquisition area of ​​each device can be directly obtained, thereby obtaining the first image information that at least contains the second image information of the preset area.

[0054] Exemplarily, the vehicle's traveling direction is the rear direction of the vehicle, and the preset area is located within the image acquisition area of ​​the vehicle's front-view camera. At this time, the first image information of the image acquisition area of ​​the front-view camera can be directly obtained, thereby obtaining the first image information that at least includes the second image information of the preset area.

[0055] Exemplarily, if the image acquisition area of ​​the vehicle's imaging lidar and side-view camera can include a preset area, the first image information of the respective devices acquired by the vehicle's imaging lidar and side-view camera can be used.

[0056] After obtaining the first image information, refer to Figure 5 , according to the first image information, the water surface area of ​​the preset area behind the vehicle in the driving direction is obtained. There are many ways to obtain the water surface area of ​​the preset area according to the first image information.

[0057] For example, reference 3 and Figure 5When obtaining the water surface area of ​​the preset area behind the vehicle in the driving direction according to the first image information, the water surface area in the first image information can be identified first; then, the water surface area of ​​the preset area can be calculated according to the preset area and the water surface area in the first image information. Exemplarily, there is a difference between the grayscale value of the water surface area in the first image information and the grayscale value of the non-water surface area. When identifying the water surface area in the first image information, all the water surface areas in the first image information can be identified by the difference in grayscale values. And the position of the preset area in the first image information is known, so that the water surface area of ​​the preset area can be obtained by accumulating and summing the areas of the water surface areas in the preset area in the first image information. In this way, there is no need to crop the first image information, thereby reducing the complexity of processing the first image information and facilitating operation.

[0058] Exemplarily, there is a difference between the grayscale value of the water surface area in the first image information and the grayscale value of the non-water surface area. When identifying the water surface area in the first image information, all the water surface areas in the first image information can be identified by the difference in grayscale values. Exemplarily, when identifying the water surface area in the first image information, a target detection algorithm can be used to detect the water surface pixels in the first image information by taking the water surface as the target object, thereby detecting the water surface area in the first image information. The target detection algorithm can use any algorithm that can detect the water surface in the image information. Exemplarily, the target detection algorithm can be a target detection model trained by methods such as but not limited to neural network training. Exemplarily, the algorithm can be used as follows Figure 5 The YOLO neural network model (You Only Look Once, a name of a deep learning neural network model) in the image processing method is used as the target detection model. For example, after the first image information is input into the target detection algorithm, the water surface area on the first image information can be directly identified and marked, so as to facilitate user viewing.

[0059] After identifying the water surface area in the first image information, the water surface area of ​​the preset area can be calculated based on the preset area and the water surface area in the first image information. The calculation method can be adopted in a variety of ways. After identifying the water surface area in the first image information, the positions of all water surface areas in the image acquisition area of ​​the first image information can be known, and the image acquisition area of ​​the first image information includes the preset area. After knowing the preset area, the area of ​​the overlapping area between the preset area and the water surface area in the first image information can be directly calculated, so that the area of ​​the overlapping area between the preset area and the water surface area in the first image information is used as the water surface area of ​​the preset area. Exemplarily, the position of the preset area in the first image information is known, so that the water surface area of ​​the preset area can be obtained by accumulating and summing the areas of the water surface areas in the preset area in the first image information.

[0060] Of course, in other embodiments, other methods may be used to obtain the water surface area of ​​the preset area of ​​the vehicle in the driving direction according to the first image information. Figure 3 and Figure 5 , when obtaining the water surface area of ​​the preset area behind the vehicle in the driving direction according to the first image information, the second image information of the preset area can be firstly cut out according to the first image information; then, the water surface area in the second image information is identified, and the water surface area of ​​the preset area is calculated. The difference between this embodiment and the previous embodiment is mainly that after obtaining the first image information, the water surface area on the first image information is not directly identified, but the second image information of the preset area is firstly cut out from the first image information, that is, the first image with a larger size is firstly cut to obtain the second image containing only the preset area. Then, the water surface area of ​​the second image information is identified, and the water surface area of ​​the preset area is calculated. In this way, although the first image information needs to be cut out to obtain the second image information, when identifying the water surface area, the image information input into the target detection algorithm is the second image information containing only the preset area, and does not contain other image information, so that the amount of image information input into the target detection algorithm can be reduced, thereby improving the speed of identifying the water surface area. And after identifying the water surface area in the second image information, the identified water surface area can be directly summed and accumulated to obtain the water surface area of ​​the preset area.

[0061] Of course, it should be noted that, during the processing of the first image information and the second image information, image preprocessing may be performed, and the image preprocessing method may include, but is not limited to, normalization, resizing, rotation, image enhancement, and the like.

[0062] Exemplarily, the exit control method may also include: when the water surface area of ​​the preset area is less than the preset area threshold, determining that the water area information of the preset area meets the preset condition. That is, the preset condition is that the water surface area of ​​the preset area is less than the preset area threshold. If the water surface area of ​​the preset area is less than the preset area threshold, it means that the water surface area of ​​the preset area is small, and there may be only small puddles in the preset area, and the vehicle does not need to enter the wading mode, then it can be determined that the water area information of the preset area meets the preset condition, thereby triggering the vehicle to exit the wading mode. Of course, in other embodiments, if the water surface area of ​​the preset area is not less than the preset area threshold, it can be determined that the water area information of the preset area does not meet the preset condition, and the vehicle is not triggered to exit the wading mode, that is, the vehicle maintains the current wading mode unchanged.

[0063] In other embodiments, the image of the preset area may be used as the water area information of the preset area. Figure 2When obtaining water area information of a preset area behind the vehicle in the driving direction, second image information of the preset area behind the vehicle in the driving direction can be obtained, and the second image information of the preset area can be used as the water area information of the preset area.

[0064] When obtaining the second image information of the preset area behind the vehicle in the driving direction, various methods may be used. Figure 3 , Figure 5 and Figure 7 , you can first obtain the first image information of the image acquisition area behind the vehicle in the driving direction through at least one device among the electronic rearview mirror, imaging laser radar, side view camera, front view camera and streaming media rearview mirror on the vehicle, wherein the first image information at least includes the second image information of the preset area. Afterwards, the second image information of the preset area is cropped out according to the first image information. At this time, it can be judged whether the preset conditions are met based on the second image information of the preset area. Since when there is water surface in the preset area, it will be carried on the second image information, so it can be determined whether the preset conditions are met based on the water surface information carried on the second image information. Exemplarily, the preset conditions can be used as the classification basis, and the second image information can be classified in a classification manner to determine whether the preset area is a water area.

[0065] Specifically, the exit control method may further include: inputting the second image information of the preset area into a decision classification algorithm, and the decision classification algorithm determines whether the preset area is a water area. When the output result of the decision classification algorithm is: the preset area is not a water area, it is determined that the water area information of the preset area meets the preset condition. It should be noted that the decision classification algorithm can use any classification algorithm that can determine whether the area reflected by the input image is a water area. In this way, there is no need to identify the water surface area on the image, thereby simplifying the amount of calculation.

[0066] Exemplary, reference Figure 8 After the vehicle enters the wading mode, in the process of obtaining the water area information of the preset area behind the vehicle in the driving direction, the water area information of the preset area behind the vehicle in the driving direction can be periodically obtained after the vehicle enters the wading mode. That is, the water area information of the preset area behind the vehicle in the driving mode is obtained multiple times at intervals, so as to timely monitor whether the vehicle meets the conditions for exiting the wading mode.

[0067] Exemplarily, when the water area information of the preset area meets the preset conditions, in the process of determining that the vehicle exits the wading mode, reference Figure 5 and Figure 8, when the water area information of the preset area obtained at least twice in succession meets the preset conditions, it can be determined that the vehicle exits the wading mode. Exemplarily, when the water area information of the preset area obtained twice in succession meets the preset conditions, it can be determined that the vehicle exits the wading mode. Alternatively, when the water area information of the preset area obtained three times in succession meets the preset conditions, it can be determined that the vehicle exits the wading mode. Alternatively, when the water area information of the preset area obtained four times in succession meets the preset conditions, it can be determined that the vehicle exits the wading mode. If the water area information of the preset area obtained only once meets the preset conditions, and the water area information of the preset area obtained before and after the acquisition does not meet the preset conditions, it can be determined that the vehicle maintains the wading mode unchanged, thereby preventing interference in the judgment of whether to exit the wading mode due to errors, accidental situations, etc.

[0068] Exemplary, reference Figure 4 , when obtaining the water area information of the preset area behind the vehicle in the driving direction, the water area information of the first preset area directly behind the vehicle in the driving direction can be obtained. At this time, when the water area information of the preset area meets the preset conditions, determining that the vehicle exits the wading mode includes: when the water area information of the first preset area meets the preset conditions, determining that the vehicle exits the wading mode. By using the water area information of the first preset area directly behind the vehicle in the driving direction as a basis for judging whether to exit the wading mode, it is possible to quickly determine whether to exit the wading mode, thereby improving the judgment efficiency. It should be explained that directly behind the vehicle refers to the direction covered within the body width range behind the vehicle in the driving direction.

[0069] Of course, in some embodiments, reference Figure 4 , the second preset area behind the vehicle in the driving direction can also be used as an auxiliary judgment basis. Specifically, when obtaining the water area information of the preset area behind the vehicle in the driving direction, the water area information of the second preset area behind the vehicle in the driving direction can also be obtained. At this time, when the water area information of the preset area meets the preset conditions, in the process of determining that the vehicle exits the wading mode, when the water area information of the first preset area and the water area information of the second preset area both meet the preset conditions, it is determined that the vehicle exits the wading mode. By using the first preset area directly behind and the second preset area behind the side as the judgment basis for determining whether to exit the wading mode, the accuracy of the judgment can be improved. It should be explained that the side and rear of the vehicle refers to the direction outside the coverage of the vehicle body width behind the vehicle in the driving direction, that is, although the second preset area is also located behind the vehicle in the driving direction, it is not covered by the vehicle body width.

[0070] like Figure 5 , Figure 7 and Fig. 9 As shown, the present invention is based on the domain control 4.0 architecture ( Fig. 9 ) based on the streaming media rearview mirror, possible CMS electronic rearview mirror, front and side view cameras, and ultrasonic radars at the base of the left and right rearview mirrors to accurately exit the wading mode. Fig. 9 The domain control 4.0 architecture shown in the figure is based on the streaming media rearview mirror, the possible CMS electronic rearview mirror, the front binocular (or monocular) camera and the side (fisheye) camera, and the ultrasonic radar at the base of the left and right rearview mirrors. Compared with the wading vehicle sensor system in the related art, a more accurate function fusion technology is proposed. Specifically, Fig. 9 The domain control 4.0 architecture shown includes the DILINK smart cockpit and smart driving domain control as the main control. The DILINK smart cockpit and smart driving domain control are connected to the DCM in the front smart domain control through the left body DCM and the right body DCM; and the DILINK smart cockpit and smart driving domain control are also connected to the DCM in the rear smart domain control through the left body DCM and the right body DCM. Thus, it can receive image information in the image acquisition area obtained by the CMS electronic rearview mirror, the front and side view cameras, and the ultrasonic radars at the base of the left and right rearview mirrors.

[0071] Exemplarily, a camera near the rearview mirror and an ultrasonic radar installed at the bottom of the rearview mirror can be used for functional-level fusion to obtain water information in a preset area behind the vehicle in the direction of travel, and determine whether the water information in the preset area meets preset conditions. The vehicle is controlled to exit the wading mode only when the preset conditions are met, thereby preventing accidental exit from the wading mode and improving the accuracy of the vehicle's active wading exit.

[0072] Specifically, the video stream collected by the camera is stored in the vehicle's SD memory card in real time. When a signal to start image analysis is received, the video stream information starting at this time point is transmitted to the vehicle's image processing chip. The YOLO neural network model and parameters are deployed on the image processing chip in advance. When the trigger signal is received, the first image information can be preprocessed including normalization, resizing, rotation, image enhancement, etc., and the existing training model parameters are called to test the image and output the classification test results. If there are types such as water surface or slippery in the classification, this result is output to the domain control to verify the judgment of the ultrasonic radar and improve the robustness of the system judgment. If there are no categories such as water areas, PAD (display screen) and pre-alarm functions can be omitted. If there are water areas, the image processing unit and the ultrasonic radar system will output the height and image information to the PAD or HUD (head-up display) end respectively, and the water surface of the wading area, the height of the rearview mirror, and the real-time display of the scene near the water area will be displayed. If the height of the water area exceeds the threshold, a dual alarm of sound and image will be issued. At the same time, the vehicle automatically switches between master and slave modes.

[0073] Therefore, the vehicle's existing streaming media rearview mirror and CMS electronic rearview mirror are combined. The streaming media rearview mirror obtains the image situation within a larger field of view behind the vehicle, including the image information of the first preset area behind the vehicle's driving direction. The CMS electronic rearview mirror can obtain the image information of the second preset area on both sides of the vehicle. According to the first two scenarios of exiting the water area, the algorithm model needs to fuse the image analysis results of the rear view and the rear side. When the original images obtained by the streaming media rearview mirror and the CMS electronic rearview mirror enter the image recognition training model, the image information needs to be processed by image algorithms such as distortion correction, image enhancement, HDR, and AWR white balance in advance. When the rear view image is verified by the image recognition model to be non-water area, the vehicle system exits the active wading system. This algorithm, combined with the streaming media rearview mirror and the CMS image processing algorithm, can further improve the accuracy of the exit mechanism of active wading and reduce the false exit rate of this system.

[0074] Exemplary, reference Figure 6 , ultrasonic radars can be installed under the rearview mirrors on both sides of the vehicle body, and two ultrasonic radars installed on the rearview mirrors on both sides of the vehicle body can be used in a master-slave manner, based on the following example: Fig. 9 The architecture of vehicle domain control 4.0 shown is referenced Figure 7 Two ultrasonic radars are placed at the bottom of the rearview mirrors on both sides. The echo signals obtained by the ultrasonic radars are transmitted to the adjacent domain controller for subsequent signal data processing and analysis, and their output is used as the input for subsequent vehicle control.

[0075] Exemplary, reference Figure 6 and Figure 7 Ultrasonic radars are installed on both rearview mirrors on the left and right sides of the vehicle body to measure the distance from the rearview mirror to the water surface in the wading area. The cameras on the left and right sides of the vehicle body take images and videos of the scenes on both sides. The specific parameters of the ultrasonic radar are as follows: measurement range, 20cm-150cm; measurement accuracy, + / -2cm; static water depth measurement accuracy, + / -4cm; the protection level of its sensor is IP6K9K, the water depth display update time is <300ms, the controller response time is <100ms, and the sensor response time is <50ms.

[0076] Exemplary, reference Figure 6 and Figure 7The ultrasonic radars on the left and right sides of the vehicle body can generate pulsed ultrasonic waves through pulse coding. The sound waves generated in the coding method have a relatively stronger anti-interference ability during propagation. The ultrasonic beams it transmits have transverse and longitudinal beam angles of approximately 60° and 45°. The ultrasonic signal will encounter scattering or refraction during propagation, and eventually reach the air-water interface layer, or the air-ground interface layer, and the air-other medium interface layer. The reflected echo in the case of total reflection is received by the receiving end. The 50kHz main frequency ultrasonic radar system, through the main ultrasonic radar embedded in the MCU of the left intelligent domain, transmits ultrasonic waves with a bandwidth of approximately 4kHz in the form of coded pulses. This signal will experience propagation attenuation, scattering, and total reflection in the air propagation process in the interface layer formed by air and other media. Due to the fact that the air acoustic impedance is very small compared to any other medium, the ultrasonic signal will experience total reflection during vertical incidence. The left and right ultrasonic radars are in a master-slave relationship. Assume that the left radar is the MASTER and the right radar is the SLAVE. The data of the SLAVE radar is transmitted to the left radar MASTER. The master radar transmits the echo data collected by the two radars to the domain control MCU through the CAN bus for digital signal processing. The echo signal of the time domain signal arrives in the form of a pulse. The waveform of the pulse wave can be extracted by the envelope detection method, so that the initial reflection and secondary reflection of the target object can be judged by the peaks and troughs of the waveform. In digital signal processing, there are digital filtering, digital-to-analog conversion, etc. The output signal may include wading, wading depth, etc. 0 and 1 can represent wading and non-wading respectively. If it is predicted to be wading at this stage, the controller needs to send a signal to start the image recognition captured by the camera in this corresponding area.

[0077] The height of the ultrasonic radar from the water surface can be calculated by obtaining the time of the first echo. The calculation formula is as follows:

[0078] d=0.5*C free *t*cos(θ)

[0079] Where, d is the depth distance measured by a single transducer and a single beam, C free is the propagation speed of sound waves in water medium, t is the time for the receiving transducer to transmit the sound wave. θ is the inclination angle formed between the horizontal plane and the transducer transmitting head during the vehicle's driving process. This inclination angle can be measured by other sensors such as IMU on the vehicle body.

[0080] In the various embodiments shown above, after the vehicle enters the wading mode, the water area information of the preset area behind the vehicle in the driving direction is obtained; and when the water area information of the preset area meets the preset conditions, it is determined that the vehicle exits the wading mode. Compared with the active wading mode exit mechanism of the front and side view cameras in the related art, and the dual-mode active wading mode exit system, the present application does not use the front wheel position of the vehicle, or the water area information in front of or in front of the side of the vehicle as the basis for judging whether the vehicle exits the wading mode, but uses whether the water area information of the preset area behind the vehicle in the driving direction meets the preset conditions as the basis for judging whether to exit the wading mode. In the scenario where the front wheels of the vehicle go uphill to the land and the rear wheels are in the water, the problem of erroneous triggering of exiting the wading mode will occur in the related art, but according to the solution of the embodiment of the present application, the vehicle will not be judged as exiting the wading mode in this scenario, thereby preventing the problem of erroneous exit from the wading mode.

[0081] In some embodiments, the difference compared to the related art mainly lies in: utilizing a camera near the rearview mirror and an ultrasonic radar installed at the bottom of the rearview mirror for functional-level fusion to obtain water information in a preset area behind the vehicle in the direction of travel, and determine whether the water information in the preset area meets preset conditions, so that the vehicle is controlled to exit the wading mode only when the preset conditions are met, thereby preventing accidental exit from the wading mode and improving the accuracy of the vehicle's active wading exit.

[0082] The functional-level fusion of the ultrasonic radars at the base of the left and right rearview mirrors, the side-view cameras, and the front-view cameras means that when the ultrasonic detection gives depth information and wading target information feedback, the image analysis in the camera video stream is triggered, and the YOLO model (You Only Look Once, the name of a deep learning neural network model) neural network is combined to identify scene targets. The categories of targets can include grass, roads, water surfaces, steps, mud, etc. The output type after model analysis assists the ranging function of the ultrasonic radar in the wading system, thereby reducing the false alarm rate caused by the failure of a single radar system to identify the target. The external environment of the water area and the depth information can be displayed simultaneously on the PAD (display) or HUD (head-up display), and the vehicle can be assisted in the automatic switching of the wading master-slave mode. Therefore, combined with the existing streaming media rearview mirror and CMS electronic rearview mirror on the vehicle body, plus different distortion correction algorithms and image signal processing algorithms such as ISP (such as low-light enhancement / HDR) and deep learning image classification, the water area information of the preset area behind the vehicle in the driving direction is obtained, and it is determined whether the water area information of the preset area meets the preset conditions. The vehicle is controlled to exit the wading mode only when the preset conditions are met, thereby preventing the wading mode from being accidentally exited and improving the accuracy of the vehicle's active wading exit.

[0083] Furthermore, an embodiment of the present application also provides an exit control device for a vehicle wading mode, the exit control device comprising: a storage medium and a processor, the storage medium storing a computer program run by the processor, and when the computer program is run by the processor, the processor executes any one of the above-mentioned exit control methods for the vehicle wading mode.

[0084] Fig.10 FIG. 1 is a schematic block diagram of an exit control device 100 for a vehicle in a wading mode according to an embodiment of the present application. Fig.10 As shown, the vehicle wading mode exit control device 100 according to the embodiment of the present application may include a storage medium 110 and a processor 120, the storage medium 110 stores a computer program executed by the processor 120, and when the computer program is executed by the processor 120, the processor 120 executes the vehicle wading mode exit control method according to the embodiment of the present application described above. Those skilled in the art can understand the specific operation of the vehicle wading mode exit control device 100 deployment device according to the embodiment of the present application in combination with the above content, and for the sake of brevity, it will not be repeated here.

[0085] The storage medium 110 may include, for example, a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0086] In addition, the present application embodiment also provides a vehicle, referring to Figures 1 to 10 , the vehicle includes: any one of the above-mentioned vehicle wading mode exit control devices. Exemplarily, the vehicle can be, for example, but not limited to, an electric vehicle, a fuel vehicle, a hybrid vehicle, a gas-electric hybrid vehicle, etc. That is, as long as the vehicle is provided with a wading mode, it is within the scope of the vehicle shown in this patent.

[0087] The present invention has been described by the above embodiments, but it should be understood that the above embodiments are only for the purpose of example and description, and are not intended to limit the present invention to the scope of the described embodiments. In addition, it can be understood by those skilled in the art that the present invention is not limited to the above embodiments, and more variations and modifications can be made according to the teachings of the present invention, and these variations and modifications all fall within the scope of the protection claimed by the present invention. The protection scope of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for controlling the exit of a vehicle wading mode, characterized in that: include: After the vehicle enters the wading mode, obtaining water area information of a preset area behind the vehicle in the driving direction; When the water area information of the preset area meets a preset condition, it is determined that the vehicle exits the wading mode.

2. The exit control method according to claim 1, characterized in that: The obtaining of water area information of a preset area behind the vehicle in the driving direction includes: The water surface area of ​​the preset area behind the vehicle in the driving direction is obtained, and the water surface area of ​​the preset area is used as the water area information of the preset area.

3. The exit control method according to claim 2, characterized in that: The obtaining of the water surface area of ​​the preset area behind the vehicle in the driving direction includes: Acquire first image information of an image acquisition area behind the vehicle in the driving direction through at least one of an electronic rearview mirror, an imaging laser radar, a side view camera, a front view camera, and a streaming media rearview mirror on the vehicle; wherein the image acquisition area at least includes the preset area; The water surface area of ​​the preset area behind the vehicle in the driving direction is acquired according to the first image information.

4. The exit control method according to claim 3, characterized in that: The step of acquiring the water surface area of ​​the preset area behind the vehicle in the driving direction according to the first image information includes: identifying a water surface area in the first image information; The water surface area of ​​the preset area is calculated according to the preset area and the water surface area in the first image information.

5. The exit control method according to claim 3, characterized in that: The step of acquiring the water surface area of ​​the preset area behind the vehicle in the driving direction according to the first image information includes: According to the first image information, cropping the second image information of the preset area; Identify the water surface area in the second image information, and calculate the water surface area of ​​the preset area.

6. The exit control method according to any one of claims 2 to 5, characterized in that: Also includes: When the water surface area of ​​the preset area is less than a preset area threshold, it is determined that the water area information of the preset area meets the preset condition.

7. The exit control method according to claim 1, characterized in that: The obtaining of water area information of a preset area behind the vehicle in the driving direction includes: Second image information of the preset area behind the vehicle in the driving direction is obtained, and the second image information is used as the water area information of the preset area.

8. The exit control method according to claim 7, characterized in that: Also includes: Inputting the second image information into a decision classification algorithm, and allowing the decision classification algorithm to determine whether the preset area is a water area; When the output result of the decision classification algorithm is: when the preset area is not a water area, it is determined that the water area information of the preset area meets the preset condition.

9. The exit control method according to any one of claims 1 to 8, characterized in that: After the vehicle enters the wading mode, obtaining water area information of a preset area behind the vehicle in the driving direction includes: After the vehicle enters the wading mode, water area information of the preset area behind the vehicle in the driving direction is periodically obtained.

10. The exit control method according to claim 9, characterized in that: When the water area information of the preset area meets a preset condition, determining that the vehicle exits the wading mode includes: When the water area information of the preset area obtained at least twice in succession meets the preset condition, it is determined that the vehicle exits the wading mode.

11. The exit control method according to claim 1, characterized in that: The obtaining of water area information of a preset area behind the vehicle in the driving direction includes: obtaining water area information of a first preset area directly behind the vehicle in the driving direction; When the water area information of the preset area meets the preset condition, determining that the vehicle exits the wading mode includes: when the water area information of the first preset area meets the preset condition, determining that the vehicle exits the wading mode.

12. The exit control method according to claim 11, characterized in that: The obtaining of water area information of a preset area behind the vehicle in the driving direction further includes: obtaining water area information of a second preset area behind the vehicle in the driving direction; The method of determining that the vehicle exits the wading mode when the water area information of the preset area meets a preset condition also includes: determining that the vehicle exits the wading mode when both the water area information of the first preset area and the water area information of the second preset area meet the preset condition.

13. A vehicle wading mode exit control device, characterized in that: include: A storage medium and a processor, wherein the storage medium stores a computer program executed by the processor, and when the computer program is executed by the processor, the processor executes the vehicle wading mode exit control method according to any one of claims 1 to 12.

14. A vehicle, characterized in that: include: The vehicle wading mode exit control device as claimed in claim 13.

Images