Vehicle wading early warning method, device and system and computer readable storage medium

Abstract

The invention discloses a vehicle wading early warning method, device and system and a computer readable storage medium, and the method comprises the steps: obtaining the real-time image data of a wading risk point located in a preset range of the current position of a vehicle, and judging whether the wading risk point has accumulated water or not according to the real-time image data; when it is judged that ponding exists at the wading risk point, the ponding depth of the wading risk point is calculated according to the real-time image data and historical image data of the same wading risk point, and the ponding depth is compared with the safe wading depth of the vehicle; and when the accumulated water depth exceeds the safe wading depth, giving out an early warning prompt. Existing camera equipment of the vehicle is fully utilized, effective early warning of wading high-risk points can be achieved without additionally arranging a sensor for the vehicle, the modification cost is reduced, and usability and universality are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent driving, and particularly to a vehicle wading warning method, device, system and computer-readable storage medium. Background Art

[0002] Automobile wading may cause vehicle damage and even threaten the lives of passengers. Therefore, it is very necessary to give an effective early warning of automobile wading. Automobile wading warning mainly makes a warning after detecting the water level. At present, it is relatively mature to use ultrasonic radar for detection and make a reminder or warning. There are also solutions that use methods such as pressure or capacitance for detection, but they have not been applied in mass production.

[0003] For example, an existing warning scheme uses a water accumulation measurement unit installed in a bridge opening to detect whether there is water accumulation in real time, a water level sensor installed at the bottom of the vehicle to detect the water accumulation level on the road surface of the bridge opening, and an infrared ranging camera installed inside the vehicle to detect whether there is water accumulation within a set distance. The analysis and judgment module analyzes whether the vehicle is suitable to pass and gives a warning by receiving the above information and combining the built-in wading passing height information. This scheme needs to rely on the water accumulation measurement unit installed in the bridge opening or the water level sensor on the vehicle to detect the water level, which will increase additional costs. The infrared ranging camera is only used to identify whether there is water accumulation and does not detect the water level. Summary of the Invention

[0004] The technical problem to be solved by the embodiments of the present invention is to provide a vehicle wading warning method, device, system and computer-readable storage medium to achieve vehicle wading warning without adding extra sensors to the vehicle and improve driving safety.

[0005] To solve the above technical problem, the present invention provides a vehicle wading warning method, including the following steps: Obtain real-time image data of a wading risk point within a preset range of the current position of the vehicle, and judge whether there is water accumulation at the wading risk point according to the real-time image data; When it is judged that there is water accumulation at the wading risk point, calculate the water accumulation depth at the wading risk point according to the real-time image data and the historical image data of the same wading risk point, and compare the water accumulation depth with the safe wading depth of the vehicle; When the water accumulation depth exceeds the safe wading depth, issue a warning prompt.

[0006] Preferably, when it is judged that there is water accumulation at the wading risk point, the vehicle terminal triggers the server to select the historical non-water accumulation image with the largest image comparison weight W from the historical image data of the wading risk point stored in the server for calculating the water accumulation depth with the real-time image; or The vehicle terminal obtains the historical non-flooded image with the largest image comparison weight W from the historical image data of the wading risk point from the server, and calculates the water accumulation depth by comparing it with the real-time image; or The vehicle terminal selects the historical non-flooded image with the largest image comparison weight W from the historical image data of the wading risk point stored in itself, and calculates the water accumulation depth by comparing it with the real-time image.

[0007] Preferably, the image comparison weight is obtained by summing the time weight and the image clarity weight. The time weight is determined according to the time of the historical image data of the stored wading risk point, and the image clarity weight is calculated and determined according to the gray variance product method.

[0008] Preferably, calculating the water accumulation depth of the wading risk point specifically includes: Identifying the lowest point on the road surface in the historical non-flooded image of the same wading risk point as the reference point; Drawing a ray in the direction perpendicular to the road surface from the reference point, and forming a set of feature points with the pixel points on the ray; Aligning the coordinates of the real-time image and the historical non-flooded image; Obtaining the overlapping pixel points of the water surface and the reference point in the set of feature points in the aligned image, and calculating the pixel distance between the overlapping pixel points and the reference point; According to the real-time distance between the vehicle and the wading risk point, converting the pixel distance into the water accumulation depth according to the image scale relationship.

[0009] Preferably, the method further includes: obtaining the geographical location information of the wading risk points within a preset range of the current position of the vehicle through the electronic map integrated in the vehicle navigation system, and triggering the vehicle-mounted camera to collect real-time image data when the vehicle approaches or enters the preset range.

[0010] The present invention also provides a vehicle wading warning device, including: A water accumulation judgment module, configured to obtain real-time image data of wading risk points within a preset range of the current position of the vehicle, and judge whether there is water accumulation at the wading risk points according to the real-time image data; A water accumulation depth calculation module, configured to calculate the water accumulation depth of the wading risk point according to the real-time image data and the historical image data of the same wading risk point when it is judged that there is water accumulation at the wading risk point, and compare the water accumulation depth with the safe wading depth of the vehicle; A warning prompt module, configured to issue a warning prompt when the water accumulation depth exceeds the safe wading depth.

[0011] Preferably, the water accumulation depth calculation module calculates the water accumulation depth of the wading risk point in the following way: Identify the lowest point on the road surface in the historical non-flooded images at the same wading risk point as the reference point; Make a ray in the direction perpendicular to the road surface from the reference point, and form a set of feature points for the pixel points on the ray; Align the coordinates of the real-time image and the historical non-flooded image; Obtain the overlapping pixel points of the flooded surface and the reference point in the set of feature points in the aligned image, and calculate the pixel distance between the overlapping pixel points and the reference point; According to the real-time distance between the vehicle and the wading risk point, convert the pixel distance into the water depth according to the image scale relationship.

[0012] The present invention also provides a vehicle wading warning system, including a vehicle terminal and a server communicating through vehicle-cloud. The vehicle terminal is used to obtain real-time image data of wading risk points within a preset range of the current position of the vehicle, and judge whether there is water accumulation at the wading risk point according to the real-time image data; the server is used to calculate the water depth of the wading risk point according to the real-time image data and the historical image data of the same wading risk point when it is judged that there is water accumulation at the wading risk point, and compare the water depth with the safe wading depth of the vehicle; the vehicle terminal is also used to issue a warning prompt when the water depth exceeds the safe wading depth.

[0013] The present invention also provides a vehicle wading warning device, including: One or more processors; A memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to execute the vehicle wading warning method described above.

[0014] The present invention also provides a computer-readable storage medium, which includes a stored computer program; wherein, the computer program controls the device where the computer-readable storage medium is located to execute the vehicle wading warning method when running.

[0015] Implementing the present invention has the following beneficial effects: The present invention makes full use of the existing camera equipment of the vehicle, and can realize effective warning of high-risk wading points without adding additional sensors to the vehicle, which not only reduces the transformation cost, but also improves the usability and popularity. By accurately judging the wading risk and issuing a timely warning to the driver when necessary, the driving safety is significantly increased, providing a safe and intelligent driving environment for the driver. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0017] Figure 1 It is a schematic flowchart of a vehicle wading warning method according to Embodiment 1 of the present invention.

[0018] Figure 2 It is a schematic flowchart of calculating the water accumulation depth in the embodiments of the present invention.

[0019] Figure 3 It is a schematic architecture diagram of a vehicle wading warning system according to Embodiment 3 of the present invention. Detailed implementation manners

[0020] The following descriptions of the embodiments are with reference to the accompanying drawings to exemplify specific embodiments in which the present invention can be implemented.

[0021] Please refer to Figure 1 As shown, Embodiment 1 of the present invention provides a vehicle wading warning method, including the following steps: Obtain real-time image data of wading risk points within a preset range of the current position of the vehicle, and determine whether there is water accumulation at the wading risk points according to the real-time image data; When it is determined that there is water accumulation at the wading risk points, calculate the water accumulation depth at the wading risk points according to the real-time image data and the historical image data of the same wading risk point, and compare the water accumulation depth with the safe wading depth of the vehicle; Send a warning prompt when the water accumulation depth exceeds the safe wading depth.

[0022] From the above steps, it can be seen that the present invention uses the image data collected by the existing camera, compares it with the historical image data of the same location pre-stored, determines whether the water accumulation depth exceeds the safe wading depth value, and gives a warning prompt to the driver when the water accumulation depth exceeds the safe wading depth value, so as to realize vehicle wading warning without adding additional sensors, improving driving safety.

[0023] Specifically, in the embodiments of the present invention, the geographical location information of the water-crossing risk points is known and can be obtained by the vehicle end in combination with its own positioning information. For example, the geographical location information of the water-crossing risk points can be pre-integrated into the electronic map of the in-vehicle navigation system. When the vehicle is driving, the in-vehicle navigation system will detect the vehicle's position in real time and compare it with the electronic map. Once the vehicle approaches or enters the area where the water-crossing risk points are located, the vehicle end will collect the real-time image data of the water-crossing risk points within a preset range of the vehicle's current position through the camera on the vehicle. The geographical location information of the water-crossing risk points can also be stored on a remote server. The vehicle establishes real-time communication with the server through the in-vehicle system. When the vehicle drives to a certain area, the vehicle end requests the water-crossing risk point information of this area from the server. The server returns the corresponding geographical location information of the water-crossing risk points according to the vehicle's current position, and the vehicle end then judges and triggers the camera to collect the real-time image data of these water-crossing risk points based on these data.

[0024] It can be understood that in this embodiment, the preset range of the vehicle's current position can be set at a specific distance L from the vehicle itself along the driving direction of the vehicle. When the vehicle drives into this preset range, the camera on the vehicle is triggered to collect the real-time image data of the water-crossing risk points within the preset range of the vehicle's current position. The specific distance L can be set to different values according to different locations. Specifically, low-lying areas such as underpasses are prone to water accumulation, and L can be set shorter, such as 50 meters, to ensure that real-time image data is quickly collected when approaching these high-risk areas. Of course, it is also necessary to consider leaving enough reaction time and time for taking emergency measures for the driver once it is determined that there is a water-crossing risk, so L cannot be set too short; similarly, from the perspective of reducing unnecessary system activation and driver interference, L cannot be set too long.

[0025] After the vehicle end obtains the real-time image data of the water-crossing risk points within the preset range of the vehicle's current position, it will judge whether there is water accumulation at the water-crossing risk points based on these real-time image data. The specific implementation method is not limited in the present invention. The following are several common solutions: 1. Image processing solution based on computer vision That is, through computer vision technology, the collected real-time image data is processed and analyzed, such as edge detection, color analysis, texture recognition, etc. By identifying the water surface features in the image, such as reflection, ripple, color difference, etc., to judge whether there is water accumulation.

[0026] 2. Image recognition solution based on deep learning That is, a deep learning model (such as convolutional neural network CNN) that has been trained on a large number of labeled water-crossing images is used to identify and classify the real-time images to judge whether there is water accumulation.

[0027] 3. 3D reconstruction solution based on stereo vision That is, a stereoscopic image of the scene where the wading risk point is located is captured using multiple cameras or depth cameras, a three-dimensional model of the scene is generated through three-dimensional reconstruction technology, and the height information in the three-dimensional model is analyzed to determine whether there is a water accumulation area.

[0028] When it is determined that there is water accumulation at the wading risk point, the vehicle end triggers the server to calculate the water accumulation depth based on the real-time image data and the historical image data of the same wading risk point. It should be noted that, in specific implementation, the historical image data of each wading risk point can be pre-stored in the server. These historical image data can be captured by each vehicle during daily driving, identified by location numbers, and uploaded to the server through vehicle-cloud communication. The server stores a certain number of image data for each wading risk point according to the time sequence, and sets the image comparison weight according to the time and image clarity. Specifically, the time weight can be sequentially valued 1, 0.7, 0.5, 0.2, 0.1 for the same day, within 3 days, within 7 days, within 30 days, and more than 30 days, denoted as W1. The image clarity weight can be calculated by the method of the product of gray variance SMD2, and the result is normalized to the interval [0, 1] and denoted as W2. In this embodiment, the image comparison weight W = W1 + W2.

[0029] Generally speaking, recent images are more likely to reflect the current situation of the wading risk point. At the same time, clearer images can also provide more accurate information during comparison. Therefore, the server selects the historical non-water-accumulation image with the largest image comparison weight W from the stored historical image data of this wading risk point to calculate the water accumulation depth (i.e., the water level value) with the real-time image collected by the vehicle end.

[0030] Please refer to Figure 2 As shown, the specific calculation method of the water accumulation depth is as follows: First, identify the lowest point on the road surface: The lowest point on the road surface is identified in the historical non-water-accumulation image of the same wading risk point and marked as D1, thus establishing a reference point for subsequent calculation of the water accumulation depth.

[0031] Then, establish a set of feature points: Taking the reference point D1 as the origin, a ray is made along the direction perpendicular to the road surface (i.e., the upward direction), and the pixel points on the ray form the set of feature points C1. These feature points are used for subsequent comparison with the corresponding points in the real-time image.

[0032] Next, align the real-time image and the historical image: The real-time image and the historical non-water-accumulation image are coordinate-aligned through some fixed features (such as the edge of a bridge opening) to ensure that the corresponding points in the two images are located at the same position, thus facilitating accurate comparison.

[0033] Calculate the pixel distance again: In the aligned image, find the coincident pixel point Cr (or the closest coincident pixel point) of the water accumulation area and the reference point D1 in the feature point set C1, and then calculate the pixel distance H1 between the coincident pixel point Cr and the reference point D1. It can be understood that H1 is the pixel representation of the water accumulation depth in the image.

[0034] Finally, convert the pixel distance to the actual distance: The server converts the pixel distance H1 to the actual water accumulation depth H2 according to the real-time distance S between the vehicle and the wading risk point according to the image scale relationship. It can be understood that the real-time distance S between the vehicle and the wading risk point can also directly use the specific distance L within the preset range of the current vehicle position set above.

[0035] After the server calculates the water accumulation depth H2, it determines whether it exceeds the safe wading depth of the vehicle, and when the water accumulation depth H2 exceeds the safe wading depth of the vehicle, it sends a warning signal to the vehicle terminal. It can be understood that the server stores the safe wading depth data of different types of vehicles, and these data are determined based on parameters such as the chassis height and electrical system layout of the vehicle. The server compares the calculated water accumulation depth H2 with the safe wading depth of the corresponding vehicle to determine whether the water accumulation depth at the current wading risk point poses a threat to the vehicle.

[0036] After the vehicle terminal receives the warning signal sent by the server, it gives a warning prompt to the driver through sound, light, etc. For example, it displays prominent warning icons and text information on the dashboard, plays a pre-recorded or synthesized voice warning, or flashes through the LED light strip or other lighting devices in the vehicle to attract the driver's visual attention. These sound and light warnings are designed to quickly and effectively convey the wading danger information to the driver, and can be detected in time even when their attention is distracted or the environmental noise is large. Further, the vehicle terminal can also take automatic or semi-automatic emergency measures according to the severity of the warning signal, such as decelerating, changing lanes to avoid, or even automatically braking emergently in extreme cases, to ensure the safety of the driver and the vehicle. The implementation of these measures will be based on the current driving state of the vehicle, the surrounding environment, and the driver's input to achieve the best risk avoidance effect.

[0037] It should also be noted that the calculation of the above water accumulation depth and the judgment of whether it exceeds the safe wading depth of the vehicle can also be performed at the vehicle end. On the one hand, historical image data of each wading risk point can be stored at the vehicle end. In this way, when it is determined that there is water accumulation at the wading risk point, the vehicle end can select the historical water-free image with the largest image comparison weight W from the historical image data of this wading risk point stored by itself and perform the calculation of the water accumulation depth with the real-time image collected by itself, and then compare the calculated water accumulation depth with the safe wading depth of the vehicle. On the other hand, when it is determined that there is water accumulation at the wading risk point, the vehicle end can also obtain the historical water-free image with the largest image comparison weight W from the historical image data of this wading risk point from the server, perform the calculation of the water accumulation depth with the real-time image collected by itself, and then compare the calculated water accumulation depth with the safe wading depth of the vehicle.

[0038] Corresponding to the vehicle wading warning method described in the foregoing Embodiment 1 of the present invention, Embodiment 2 of the present invention further provides a vehicle wading warning device, including: A water accumulation judgment module, configured to obtain real-time image data of a wading risk point within a preset range of the current position of the vehicle, and judge whether there is water accumulation at the wading risk point according to the real-time image data; A water accumulation depth calculation module, configured to calculate the water accumulation depth of the wading risk point according to the real-time image data and the historical image data of the same wading risk point when it is judged that there is water accumulation at the wading risk point, and compare the water accumulation depth with the safe wading depth of the vehicle; A warning prompt module, configured to issue a warning prompt when the water accumulation depth exceeds the safe wading depth.

[0039] Preferably, the way for the water accumulation depth calculation module to calculate the water accumulation depth of the wading risk point is: Identify the lowest point on the road surface in the historical water-free image of the same wading risk point as the reference point; Make a ray in the direction perpendicular to the road surface with the reference point, and form a set of feature points with the pixel points on the ray; Align the coordinates of the real-time image and the historical water-free image; Obtain the overlapping pixel points of the water surface and the reference point in the set of feature points in the aligned image, and calculate the pixel distance between the overlapping pixel points and the reference point; According to the real-time distance between the vehicle and the wading risk point, convert the pixel distance into the water accumulation depth according to the image scale relationship.

[0040] Such as Figure 3As shown, corresponding to the vehicle wading warning method described in the first embodiment of the present invention, the third embodiment of the present invention further provides a vehicle wading warning system, including a vehicle terminal and a server communicating through vehicle-cloud communication. The vehicle terminal is used to obtain real-time image data of wading risk points within a preset range of the current position of the vehicle, and determine whether there is water accumulation at the wading risk points based on the real-time image data. The server is used to calculate the water accumulation depth of the wading risk points according to the real-time image data and the historical image data of the same wading risk point when it is determined that there is water accumulation at the wading risk point, and compare the water accumulation depth with the safe wading depth of the vehicle. The vehicle terminal is further used to issue a warning prompt when the water accumulation depth exceeds the safe wading depth.

[0041] The vehicle wading warning system of this embodiment combines the functions of the vehicle terminal and the server, and realizes the real-time transmission and processing of data through efficient vehicle-cloud communication, ensuring that a warning can be issued in a timely manner when the vehicle faces wading risks. Among them, the server, as a data processing and storage center, is equipped with a wading risk point database and a vehicle safe wading depth database. The wading risk point database is used to store the historical image data of each wading risk point, providing a reference for the calculation of the water accumulation depth. The vehicle safe wading depth database stores the safe wading depth information of different types of vehicles, which is determined based on parameters such as the chassis height and electrical system layout of the vehicle, and serves as the basis for judging whether the vehicle can safely pass through the wading risk point. The vehicle terminal, as the front-end perception part of the system, is equipped with image acquisition devices such as cameras, which are used to collect real-time image data of wading risk points within a preset range of the current position of the vehicle in real time and make a water accumulation judgment. If the vehicle terminal determines that there is water accumulation at the wading risk point, it will upload the real-time image data and related information to the server through vehicle-cloud communication. After receiving the data uploaded by the vehicle terminal, the server extracts the corresponding historical image data from the wading risk point database and calculates the water accumulation depth with the real-time image data. The specific calculation method refers to the introduction in the first embodiment of the present invention. If the calculated water accumulation depth exceeds the safe wading depth of the vehicle, the server will immediately send a warning signal to the vehicle terminal through vehicle-cloud communication. After receiving the warning signal, the vehicle terminal will start the warning prompt mechanism and issue a clear warning prompt to the driver through sound, light, etc., to ensure that the driver can timely perceive the wading risk and take corresponding measures.

[0042] Corresponding to the vehicle wading warning method described in the first embodiment of the present invention, the fourth embodiment of the present invention further provides a vehicle wading warning device, including: One or more processors; A memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to execute the vehicle wading warning method described in Embodiment 1 of the present invention.

[0043] Corresponding to the vehicle wading warning method described in Embodiment 1 of the foregoing present invention, Embodiment 5 of the present invention provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the vehicle wading warning method described in Embodiment 1 of the present invention.

[0044] Preferably, the computer program can be divided into one or more modules / units (such as computer program 1, computer program 2,...), and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of completing specific functions, and these instruction segments are used to describe the execution process of the computer program in the device.

[0045] The processor can be a Central Processing Unit (CPU), or can also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or the processor can also be any conventional processor. The processor is the control center of the device, and connects various parts of the device through various interfaces and lines.

[0046] The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, applications required for at least one function, etc., and the data storage area can store related data, etc. In addition, the memory can be a high-speed random access memory, or can also be a non-volatile memory, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., or the memory can also be other volatile solid-state storage devices.

[0047] It should be noted that the above device may include but is not limited to a processor and a memory, which can be understood by those skilled in the art.

[0048] Regarding the working principle and process of the above embodiments, refer to the description of Embodiment 1 of the present invention above, and details will not be repeated here.

[0049] It can be seen from the above description that, compared with the prior art, the beneficial effects of the present invention are as follows: The present invention makes full use of the existing camera devices of the vehicle, and can achieve effective early warning of high-risk wading points without adding additional sensors to the vehicle, which not only reduces the transformation cost, but also improves the usability and popularity. By accurately judging the wading risk and issuing timely warnings to the driver when necessary, the driving safety is significantly increased, providing a safe and intelligent driving environment for the driver.

[0050] The above-disclosed are only the preferred embodiments of the present invention, and of course, the scope of the rights of the present invention cannot be limited thereby. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope covered by the present invention.

Claims

1. A vehicle wading warning method, characterized in that, Including the following steps: Obtain real-time image data of a wading risk point within a preset range of the current vehicle position, and determine whether there is water accumulation at the wading risk point according to the real-time image data; When it is determined that there is water accumulation at the wading risk point, calculate the water accumulation depth of the wading risk point according to the real-time image data and the historical image data of the same wading risk point, and compare the water accumulation depth with the safe wading depth of the vehicle; Send a warning prompt when the water accumulation depth exceeds the safe wading depth.

2. The method according to claim 1, wherein When it is determined that there is water accumulation at the wading risk point, the vehicle terminal triggers the server to select the historical water-free image with the largest image comparison weight W from the historical image data of the wading risk point stored in the server for calculating the water accumulation depth with the real-time image; or The vehicle terminal obtains the historical water-free image with the largest image comparison weight W from the historical image data of the wading risk point from the server, and calculates the water accumulation depth by comparing it with the real-time image; or The vehicle terminal selects the historical water-free image with the largest image comparison weight W from the historical image data of the wading risk point stored in itself for calculating the water accumulation depth with the real-time image.

3. The method according to claim 2, wherein The image comparison weight is obtained by summing the time weight and the image clarity weight. The time weight is determined according to the time of the historical image data of the stored wading risk point, and the image clarity weight is calculated and determined according to the gray variance product method.

4. The method according to claim 2, characterized in that, Specifically, calculating the water accumulation depth of the wading risk point includes: Identify the lowest point on the road surface in the historical water-free image of the same wading risk point as the reference point; Make a ray in the direction perpendicular to the road surface from the reference point, and form a set of feature points with the pixel points on the ray; Align the coordinates of the real-time image and the historical water-free image; Obtain the overlapping pixel points of the water surface and the reference point in the set of feature points in the aligned image, and calculate the pixel distance between the overlapping pixel points and the reference point; According to the real-time distance between the vehicle and the wading risk point, convert the pixel distance into the water accumulation depth according to the image scale relationship.

5. The method according to claim 1, wherein It also includes: Obtain the geographical location information of the wading risk point within a preset range of the current vehicle position through the electronic map integrated in the in-vehicle navigation system, and trigger the in-vehicle camera to collect real-time image data when the vehicle approaches or enters the preset range.

6. A vehicle wading warning device, characterized in that, Including: A water accumulation judgment module, configured to obtain real-time image data of a wading risk point within a preset range of the current vehicle position, and determine whether there is water accumulation at the wading risk point according to the real-time image data; A water accumulation depth calculation module, configured to calculate the water accumulation depth of the wading risk point according to the real-time image data and the historical image data of the same wading risk point when it is determined that there is water accumulation at the wading risk point, and compare the water accumulation depth with the safe wading depth of the vehicle; A warning prompt module, configured to send a warning prompt when the water accumulation depth exceeds the safe wading depth.

7. The device according to claim 6, characterized in that, The way for the water accumulation depth calculation module to calculate the water accumulation depth of the wading risk point is: Identify the lowest point on the road surface in the historical water-free image of the same wading risk point as the reference point; Make a ray in the direction perpendicular to the road surface from the reference point, and form a set of feature points for the pixel points on the ray; Align the coordinates of the real-time image and the historical image without water accumulation; Obtain the overlapping pixel points of the water surface and the reference point in the set of feature points in the aligned image, and calculate the pixel distance between the overlapping pixel points and the reference point; According to the real-time distance between the vehicle and the wading risk point, convert the pixel distance into the water depth according to the image scale relationship.

8. A vehicle wading warning system, characterized in that, It includes a vehicle terminal and a server communicating through vehicle-cloud. The vehicle terminal is used to obtain real-time image data of wading risk points within a preset range of the current vehicle position, and determine whether there is water accumulation at the wading risk points according to the real-time image data; The server is used to calculate the water depth of the wading risk point according to the real-time image data and the historical image data of the same wading risk point when it is determined that there is water accumulation at the wading risk point, and compare the water depth with the safe wading depth of the vehicle; the vehicle terminal is also used to issue a warning prompt when the water depth exceeds the safe wading depth.

9. A vehicle wading warning device, characterized in that, It includes: One or more processors; A memory; One or more applications, wherein the one or more applications are stored in the memory and are configured to be executed by the one or more processors, and the one or more applications are configured to execute the vehicle wading warning method according to any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program; wherein, the computer program controls the device where the computer-readable storage medium is located to execute the vehicle wading warning method according to any one of claims 1 to 5 when running.

Images