Accumulated water detection method, device and equipment and storage medium

Abstract

The invention provides a ponding detection method, device and equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical field of map navigation and automatic driving. According to the specific implementation scheme, a target road section is recognized from a navigation route of a vehicle based on map data; determining a water accumulation risk of the target road section based on the weather data; under the condition that it is determined that sensing equipment of the vehicle needs to be turned on based on the ponding risk of the target road section, the ponding condition of the target road section is determined through sensing data collected by the sensing equipment.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to the field of map navigation and autonomous driving technology. Background Art

[0002] In-vehicle navigation systems can be installed in vehicles and use satellite positioning technology and electronic maps to provide navigation guidance and related information services, helping passengers reach their destination more conveniently and quickly. In-vehicle navigation systems often rely on weather data, such as rainfall, to provide warnings about road hazards such as flooding. Summary of the Invention

[0003] The present disclosure provides a method, apparatus, device, and storage medium for detecting water accumulation.

[0004] According to one aspect of the present disclosure, a method for detecting water accumulation is provided, comprising:

[0005] Based on the map data, the target road section is identified from the vehicle's navigation route;

[0006] Determine the flooding risk of the target road section based on weather data;

[0007] In a case where it is determined that the sensing device of the vehicle needs to be turned on based on the water accumulation risk of the target road section, the water accumulation situation of the target road section is determined through the sensing data collected by the sensing device.

[0008] According to another aspect of the present disclosure, there is provided a water accumulation detection device, comprising:

[0009] An identification module, configured to identify a target road section from a vehicle's navigation route based on map data;

[0010] A risk determination module is used to determine the waterlogging risk of the target road section based on weather data;

[0011] The water accumulation determination module is used to determine the water accumulation situation of the target road section through the perception data collected by the perception device when it is necessary to turn on the vehicle's perception device based on the water accumulation risk of the target road section.

[0012] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any method in the embodiments of the present disclosure.

[0016] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any method according to the embodiments of the present disclosure.

[0017] According to another aspect of the present disclosure, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the computer program implements any one of the methods according to the embodiments of the present disclosure.

[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0020] Figure 1 is a flow chart of a method for detecting water accumulation according to an embodiment of the present disclosure;

[0021] Figure 2 is a flow chart of a method for detecting water accumulation according to another embodiment of the present disclosure;

[0022] Figure 3 is a flow chart of a method for detecting water accumulation according to another embodiment of the present disclosure;

[0023] Figure 4 is a flow chart of a method for detecting water accumulation according to another embodiment of the present disclosure;

[0024] Figure 5 is a flow chart of a method for detecting water accumulation according to another embodiment of the present disclosure;

[0025] Figure 6 is a flow chart of a method for detecting water accumulation according to another embodiment of the present disclosure;

[0026] Figure 7 is a structural schematic diagram of a water accumulation detection device according to an embodiment of the present disclosure;

[0027] Figure 8 is a structural schematic diagram of a water accumulation detection device according to another embodiment of the present disclosure;

[0028] Figure 9 is a block diagram of an electronic device for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be appreciated by those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0030] Figure 1 FIG. 1 is a flow chart of a method 100 for detecting water accumulation according to an embodiment of the present disclosure, the method comprising:

[0031] S110, identifying a target road section from the vehicle's navigation route based on map data;

[0032] S120. Determine the flooding risk of the target road section based on weather data;

[0033] S130. When it is determined that the sensing device of the vehicle needs to be turned on based on the water accumulation risk of the target road section, the water accumulation condition of the target road section is determined through the sensing data collected by the sensing device.

[0034] In the disclosed embodiments, map data may include the relationships between data sets of various elements of the map content and the arrangement and organization of data records, and is a computer-readable form converted from various map elements. Examples include geocoding data, topographic data, shared data between different organizations, and regional data shared by users. Map data can be obtained from in-vehicle map software such as navigation software, high-precision maps, and in-vehicle GPS. A vehicle's navigation route may include a route for guiding the vehicle's travel, such as a route for guiding the vehicle from its current starting point to its destination (end point). One or more target sections in the navigation route, such as sections prone to flooding, can be obtained through map data. For example, the total length of the navigation section is 35 kilometers, and the section from kilometer 4 to kilometer 5 is the first section prone to flooding, and the section from kilometer 21 to kilometer 21.5 is the second section prone to flooding. Marking sections prone to flooding with kilometers is merely an example and not a limitation. In practice, other methods, such as latitude and longitude, length, width, and height, can be used to mark sections prone to flooding.

[0035] In the disclosed embodiments, weather data may include data obtained through observation, recording, and analysis of atmospheric conditions and meteorological phenomena, such as rainfall, temperature, humidity, wind direction, and wind speed. Weather data can be obtained from meteorological data application programming interfaces (APIs), meteorological department websites, and meteorological data platforms. This weather data can be used to obtain rainfall and radar images of target road sections, thereby determining the risk of flooding on the target road sections.

[0036] In the disclosed embodiment, the risk of water accumulation in the target road section can be divided into risk levels. For example, high risk, medium risk, low risk, etc. For example, level one, level two, and level three. It can be determined whether to turn on the vehicle's perception equipment, as well as the type and number of perception equipment to be turned on, based on different risk levels. For example, when the risk of water accumulation in the target road section is level one, the perception equipment may not be turned on; when the risk of water accumulation in the target road section is level two, one or more on-board cameras in the perception equipment may be turned on; when the risk of water accumulation in the target road section is level three, all perception equipment such as on-board cameras and radars may be turned on. The perception equipment can collect perception data related to the target road section, such as road surface images and / or point cloud data, and the water accumulation situation of the target road section can be determined through the perception data. For example, the water accumulation area of the current road section L1 is 5m 2 , the water depth is 5cm.

[0037] According to the embodiment of the present disclosure, the target road section can be directly identified based on map data, the water accumulation risk of the target road section can be judged based on weather data, and then it can be determined whether it is necessary to turn on the sensing equipment to collect sensing data. The water accumulation situation of the road where the vehicle is located can be accurately obtained, thereby improving the safety of vehicle driving.

[0038] Figure 2 2 is a flow chart of a water accumulation detection method 200 according to another embodiment of the present disclosure. The method 200 can be used to implement step S110 of the water accumulation detection method 100. In one embodiment, the method 200 includes: identifying a target road section from a vehicle's navigation route based on map data, and further includes:

[0039] S210, determining a navigation route of the vehicle based on the map data and the starting point and end point of the vehicle;

[0040] S220: Based on the navigation route and waterlogging-related data in the map data, identify the target road section from the navigation route.

[0041] In the disclosed embodiments, the vehicle's starting point can be obtained through a positioning service, and the vehicle's destination can be obtained in response to a destination input by a user. Based on map data and the vehicle's starting and ending points, a navigation route can be generated for the vehicle from the starting point to the destination. For example, if the vehicle's starting point is A and its destination is B, a navigation route from A to B can be determined based on the route in the map data.

[0042] In the disclosed embodiment, map data may include data related to waterlogging, such as historical records of waterlogging, roads prone to waterlogging, and terrain prone to waterlogging. Based on this data, sections of the navigation route prone to waterlogging can be identified. Geographical locations prone to waterlogging can be determined based on the waterlogging-related data, and a determination can be made as to whether the navigation route passes through these geographical locations. If a section of the navigation route passes through a geographical location prone to waterlogging, this section can be marked as a section prone to waterlogging or a target section. Through the aforementioned identification process of sections prone to waterlogging, some target sections that may be flooded can be preliminarily screened out from the navigation route.

[0043] According to the embodiment of the present disclosure, a navigation route can be determined based on map data, and target sections prone to waterlogging can be identified from the navigation route without performing full section processing on the navigation section. This can improve the efficiency of waterlogging detection, improve the accuracy of waterlogging detection, and thereby improve the safety of vehicle driving.

[0044] In one embodiment, the target road section includes a road section prone to waterlogging determined based on one or more of the following waterlogging-prone areas on the navigation route in the map data: low-lying areas, passages under bridges, and areas with a high incidence of historical waterlogging.

[0045] In the disclosed embodiments, low-lying areas may include areas with lower terrain than the surrounding area; underpasses may include areas located under bridges for pedestrian and / or vehicular traffic; and historically flood-prone areas may include areas with a history of frequent flooding as shown in map data. These geographical locations are prone to flooding and may be referred to as flood-prone areas. A flood-prone area within a navigation route may also be understood as a flood-prone area that passes through the navigation route or overlaps with the navigation route. If a section of the navigation route passes through any of these flood-prone areas or overlaps with any of these flood-prone areas, the section may be designated as a flood-prone section or a target section. For example, if the route from point P1 to point P2 passes through a low-lying area, the section from point P1 to point P2 is a flood-prone section or a target section. For another example, if the route from point P3 to point P4 passes through an underpass, the section from point P3 to point P4 is a flood-prone section or a target section. For another example, if the navigation route from point P5 to point P6 passes through a historically high-incidence area of flooding, then the section from point P5 to point P6 is a section prone to flooding or a target section. For another example, if the navigation route from point P5 to point P6 overlaps with a historically high-incidence area of flooding, then the section from point P5 to point P6 is a section prone to flooding or a target section. A navigation route may have no sections prone to flooding, or may have one or more sections prone to flooding. If a navigation route has no sections prone to flooding, then the subsequent steps for determining the risk of flooding will not be executed; if a navigation route has one or more sections prone to flooding, then the subsequent steps for determining the risk of flooding will be executed.

[0046] According to an embodiment of the present disclosure, a target section in a navigation route is determined based on one or more water-prone areas in the navigation route in map data, so that the target section prone to water accumulation can be accurately identified, thereby improving the accuracy of water accumulation detection results.

[0047] Figure 3 3 is a flow chart of a waterlogging detection method 300 according to another embodiment of the present disclosure. The method 300 can be used to implement step S120 in the waterlogging detection method 100. In one embodiment, the method 300 includes: determining the waterlogging risk of the target road section based on weather data, and further includes:

[0048] S310: Obtaining a first waterlogging depth and / or a waterlogging-prone weight of a target road section based on the weather data;

[0049] S320: Determine the waterlogging risk of the target road section based on the first waterlogging depth and / or the waterlogging susceptibility weight.

[0050] In an embodiment of the present disclosure, a first flood depth of a target road section can be calculated based on weather data. The flood risk of the target road section can be determined based on the first flood depth. For example, if the first flood depth exceeds a first depth threshold, the flood risk is high; if it is below the first depth threshold, the flood risk is low.

[0051] In the disclosed embodiments, a waterlogging risk weight for a target road section can be calculated based on weather data. The waterlogging risk for the target road section can be determined based on the waterlogging risk weight. For example, if the waterlogging risk weight exceeds a first weight threshold, it indicates a high waterlogging risk; if it falls below the first weight threshold, it indicates a low waterlogging risk.

[0052] In the disclosed embodiment, the water accumulation risk of the target road section can be determined based on the first water accumulation depth and the water accumulation risk weight. For example, when the first water accumulation depth is greater than or equal to the first depth threshold, such as 5 cm, the water accumulation risk can be determined in combination with the water accumulation risk weight. When the weight exceeds the first weight threshold, such as 0.5, the water accumulation risk of the target road section can be determined to be high. When the weight is lower than the first weight threshold, such as 0.5, the water accumulation risk of the target road section can be determined to be low.

[0053] The high and low waterlogging risks in the above examples are merely examples and are not intended to be limiting. In practice, other classifications can be used. For example, waterlogging risk can be classified as high, medium, medium, or low. Another example is waterlogging risk classifications of level 1, level 2, level 3, or level 4. Another example is waterlogging risk classifications of 0.9, 0.7, 0.5, or 0.3.

[0054] According to the embodiment of the present disclosure, the first water accumulation depth and / or water accumulation weight can be obtained based on weather data. According to the first water accumulation depth and / or water accumulation weight, the water accumulation risk of the target road section can be determined more accurately, thereby improving the safety of vehicle driving.

[0055] Figure 4 FIG4 is a flow chart of a water accumulation detection method 400 according to another embodiment of the present disclosure. The method 400 can be used to implement step S310 in the water accumulation detection method 300. In one embodiment, the method 400 includes: obtaining a first water accumulation depth of a target road section based on the weather data, and further includes:

[0056] S410: Obtain a first waterlogging depth of the target road section based on current weather data and a waterlogging empirical coefficient, wherein the waterlogging empirical coefficient is obtained based on historical weather data and historically measured waterlogging depths.

[0057] In the disclosed embodiment, the historical weather data of the target road section can reflect the weather conditions of the target road section in the past. An empirical waterlogging coefficient for the target road section can be first obtained based on the historical weather data of the target road section, and then the empirical waterlogging coefficient can be used to assist the current weather data to more accurately determine the first waterlogging depth of the target road section.

[0058] In the disclosed embodiment, the rainfall in the weather data has a greater impact on the depth of waterlogging, and the historical rainfall in the historical weather data, for example, the rainfall at the same detection point at the same historical time, can be used to calculate the waterlogging experience coefficient. The historical same time can be the same time or period of the previous year, the same time or period of the previous month, etc. relative to the current time, and there is no specific limitation. The same detection point can be a detection point at the same position in the target section or the area prone to waterlogging where the target section is located. If the target section or the area prone to waterlogging where the target section is located has multiple detection points, different detection points can correspond to different detection samples. The same detection point may also correspond to detection samples at multiple different times within a time period. The waterlogging experience coefficient can be comprehensively calculated based on these detection samples.

[0059] In one embodiment, obtaining a first waterlogging depth for a target road section based on current weather data and an empirical waterlogging coefficient includes: calculating the first waterlogging depth based on current rainfall and the empirical waterlogging coefficient; wherein the empirical waterlogging coefficient is obtained through regression calculation based on historical rainfall and historically measured waterlogging depths. For example, the regression calculation process may include: obtaining an estimated first waterlogging depth based on historical rainfall at the same detection point and an initial empirical waterlogging coefficient; calculating a minimum mean square error based on the historically measured waterlogging depth and the estimated first waterlogging depth, adjusting the empirical waterlogging coefficient used to calculate the estimated first waterlogging depth to reduce the minimum mean square error; and outputting the optimized empirical waterlogging coefficient if output conditions are met.

[0060] In the disclosed embodiment, the current rainfall of the target road section can be obtained from current weather data, and the historical rainfall of the target road section can be obtained from historical weather data. Based on the current rainfall of the target area and the empirical waterlogging coefficient, etc., the first waterlogging depth of the target road section can be calculated according to the waterlogging depth formula.

[0061] An example of a ponding depth formula is as follows:

[0062] D=α*R

[0063] Where α is the empirical coefficient of water accumulation, and R is the current rainfall. The empirical coefficient of water accumulation α can be obtained by regression calculation based on historical weather data.

[0064] An example of the calculation process of a water accumulation empirical coefficient is as follows:

[0065] (1) Collect the rainfall R at the same historical time and point (geographic location or trajectory point, etc.).

[0066] (2) An example of a minimum mean square error (MSE) formula is as follows:

[0067]

[0068] Where n is the number of samples; D real_i is the historical measured water depth of the i-th group of data (or called the historical actual water depth); α*R i : is the first water depth D of the i-th group of data calculated based on the above water depth formula.

[0069] (3) Using the MSE formula, with the initial α = 1, the calculated depth of water D is based on the historical measured depth of water D. real And the first water depth D estimated previously, gradually adjust α and continuously reduce MSE until MSE converges to the minimum, or the α update change is very small (less than a threshold, such as 0.0001), then the optimal α value can be output.

[0070] According to the embodiment of the present disclosure, rainfall has a great influence on the depth of water accumulation. The water accumulation empirical coefficient can be calculated based on historical rainfall and historical measured water accumulation depth, and then a more accurate water accumulation depth can be estimated based on the current rainfall and the water accumulation empirical coefficient.

[0071] In one embodiment, obtaining a first waterlogging depth for a target road section based on current weather data and a waterlogging empirical coefficient includes: calculating the first waterlogging depth based on current rainfall, road characteristic data, and the waterlogging empirical coefficient; wherein the waterlogging empirical coefficient is obtained through regression calculation based on historical rainfall, road characteristic data, and historically measured waterlogging depths. For example, the regression calculation process may include: obtaining an estimated first waterlogging depth based on historical rainfall, road characteristic data, and an initial waterlogging empirical coefficient; calculating a minimum mean square error based on the historically measured waterlogging depths and the estimated first waterlogging depth, adjusting the waterlogging empirical coefficient used to calculate the estimated first waterlogging depth to reduce the minimum mean square error; and outputting an optimized waterlogging empirical coefficient if output conditions are met.

[0072] In the disclosed embodiment, the current rainfall and historical rainfall of the target road section can be obtained from weather data. Road characteristic data such as terrain slope, soil permeability, etc. can be obtained from map data, weather data or other data sources. Road characteristic data usually does not change much, and either historical road characteristic data or current road characteristic data can be used to calculate the water accumulation empirical coefficient. The water accumulation empirical coefficient can be determined based on historical measured water accumulation depth, road characteristic data and historical rainfall. Based on the current rainfall, terrain slope, soil permeability, etc. of the target road section, the first water accumulation depth of the target road section can be calculated according to the water accumulation depth formula.

[0073] An example of a ponding depth formula is as follows:

[0074] D=α*R*(1-P) / tan(θ)

[0075] Where α is the empirical coefficient for waterlogging, R is the current rainfall, θ is the terrain slope, P is the soil permeability, and D is the depth of waterlogging. The empirical coefficient α represents the permeability of the road soil and may vary for different roads. For example, urban roads with low soil permeability have a lower empirical coefficient α; rural roads with high soil permeability have a higher empirical coefficient α. The empirical coefficient can be calculated through regression based on historical weather data.

[0076] An example of the calculation process of a water accumulation empirical coefficient is as follows:

[0077] (1) Collect the rainfall R, terrain slope θ, soil permeability P, and measured water depth D at the same historical time and point (geographic location or trajectory point, etc.) real , each set of data includes R i ,θ i 、P i 、D real_i ; i represents the i-th group of data.

[0078] (2) An example of a minimum mean square error (MSE) formula is as follows:

[0079]

[0080] Where n is the number of samples; D real_i is the historical measured water depth of the i-th group of data; is the first water depth D of the i-th group of data calculated based on the above water depth formula.

[0081] (3) Using the MSE formula, the initial α = 1 is used for calculation, based on the measured water depth D real And the first water depth D estimated previously, gradually adjust α and continuously reduce MSE until MSE converges to the minimum, or the α update change is very small (less than a threshold, such as 0.0001), then the optimal α value can be output.

[0082] According to the embodiment of the present disclosure, rainfall and road characteristic data have a greater impact on the depth of water accumulation. The water accumulation empirical coefficient can be calculated based on historical rainfall, road characteristic data and historical measured water accumulation depth, and then the water accumulation depth can be calculated based on current rainfall, road characteristic data and the water accumulation empirical coefficient, which can improve the accuracy of the water accumulation depth estimation results.

[0083] In one embodiment, the method 400 further includes: obtaining a waterlogging weight of the target road section based on the weather data, further including:

[0084] S420. Calculate the current waterlogging weight based on one or more of the historical waterlogging weight, the current rainfall, the minimum rainfall resulting in waterlogging, and a dynamic adjustment coefficient; wherein the dynamic adjustment coefficient is obtained based on the rainfall in the weather data.

[0085] In the embodiment of the present disclosure, the waterlogging weight may be calculated using a waterlogging weight formula based on the weather data of the target road section.

[0086] An example of a calculation or adjustment formula for the waterlogging weight is as follows:

[0087] W new =W old +β*(RR threshold )

[0088] Another example of a calculation or adjustment formula for the waterlogging weight is as follows:

[0089] W new =W old +β*R

[0090] An example of a calculation or adjustment formula for the waterlogging weight is as follows:

[0091] Wnew =W old +(RR threshold )

[0092] Among them, R is the current rainfall, R threshold is the minimum rainfall for water accumulation, β is the dynamic adjustment coefficient, W old is the weight to be adjusted (or called the historical water accumulation weight), W new is the waterlogging weight. The historical waterlogging weight may be a historical waterlogging weight previously calculated for the current target road section; the current rainfall may be the real-time rainfall for the target road section obtained from weather data; and the minimum rainfall required for waterlogging may be the minimum rainfall required for waterlogging obtained from statistical or empirical data, which may also be obtained from weather data.

[0093] In the embodiment of the present disclosure, a dynamic adjustment coefficient can be used to adjust the waterlogging weight. A dynamic adjustment coefficient can be determined based on the current rainfall R. An example of a determination method is as follows:

[0094] (1) When R<the first threshold, it can be determined that β=the first value.

[0095] (2) When the first threshold ≤ R < the second threshold, it can be determined that β = the second value.

[0096] (3) When the second threshold ≤ R < the third threshold, it can be determined that β = the third value.

[0097] (4) When R≥the third threshold, it can be determined that β=the fourth value.

[0098] According to the embodiment of the present disclosure, the current waterlogging weight can be adjusted by one or more of the historical waterlogging weight, the current rainfall, the minimum rainfall resulting in waterlogging, and the dynamic adjustment coefficient, so that a waterlogging weight that is more in line with the road waterlogging situation can be obtained, thereby improving the accuracy of road waterlogging risk assessment.

[0099] In one embodiment, determining the flooding risk of the target road section based on the first flooding depth and / or the flooding susceptibility weight includes:

[0100] Determine the waterlogging risk level of the target road section based on the current waterlogging risk weight; or

[0101] Determining a flood risk level of the target road section based on the first flood depth; or

[0102] When the first waterlogging depth is greater than or equal to a first depth threshold and / or the current rainfall is greater than a rainfall threshold, the waterlogging risk level of the target road section is determined based on the current waterlogging weight.

[0103] In the disclosed embodiments, the waterlogging risk of a target road section can be determined using only the first waterlogging depth or the waterlogging susceptibility weight. Alternatively, the first waterlogging depth and the waterlogging susceptibility weight can be combined to determine the waterlogging risk of the target road section. For example, if the first waterlogging depth exceeds the first depth threshold, it indicates a high waterlogging risk; if it is between the first and second depth thresholds, it indicates a medium waterlogging risk; and if it is below the second depth threshold, it indicates a low waterlogging risk. For another example, if the waterlogging susceptibility weight exceeds the first weight threshold, it indicates a high waterlogging risk; if it is between the first and second weight thresholds, it indicates a medium waterlogging risk; and if it is below the second weight threshold, it indicates a low waterlogging risk. For another example, if the first waterlogging depth is greater than or equal to the first depth threshold and the current rainfall is greater than the rainfall threshold, the waterlogging risk of the target road section can be determined based on the waterlogging susceptibility weight and the weight threshold. If the waterlogging susceptibility weight exceeds the first weight threshold, the waterlogging risk of the target road section can be determined to be high. If the waterlogging susceptibility weight is lower than the first weight threshold but higher than the second weight threshold, the waterlogging risk of the target road section can be determined to be medium. If the waterlogging susceptibility weight is lower than the second weight threshold, the waterlogging risk of the target road section can be determined to be low.

[0104] The various thresholds and risk levels in the above examples are merely examples and not limitations, and can be flexibly adjusted in actual applications according to the needs of specific application scenarios.

[0105] According to the embodiment of the present disclosure, the water accumulation risk of the target road section can be determined by multiple parameters such as the water accumulation weight, water accumulation depth, and current rainfall, thereby improving the accuracy and flexibility of the water accumulation detection method.

[0106] Figure 5 is a flow chart of a water accumulation detection method 500 according to another embodiment of the present disclosure. The method may include one or more features of the water accumulation detection method described above. In one embodiment, the method 500 includes: determining that a sensing device of the vehicle needs to be activated based on the water accumulation risk, and further includes:

[0107] S510: When the water accumulation risk level meets the level requirements, turn on the vehicle's sensing device.

[0108] In the disclosed embodiment, the flooding risk level can be a clear level parameter such as high, medium, low, or one, two, three, etc. In this case, the level requirement can be a specific level. For example, the level requirement can be medium-high. If the flooding risk level is medium or high, one or more sensing devices of the vehicle are turned on. For another example, the level requirement can be no less than level two. If the flooding risk level is level two or three, one or more sensing devices of the vehicle are turned on.

[0109] In the disclosed embodiment, the water accumulation risk level may not have specific parameters, but it is considered to meet the level requirements under certain circumstances. For example, the first water accumulation depth is greater than a certain water accumulation threshold. In this case, the vehicle's perception device can be turned on to collect perception data (the default water accumulation risk level meets the level requirements). For another example, the water accumulation weight is greater than a certain weight threshold. In this case, the vehicle's perception device can be turned on to collect perception data (the default water accumulation risk level meets the level requirements). The vehicle's perception device may include on-board cameras, radars, and other on-board sensors. Only the camera can be turned on, or only the radar can be turned on, or both the camera and the radar can be turned on at the same time, and other sensors can also be turned on. Perception data may include one or more of images, point cloud data, temperature, video, audio, and the like.

[0110] According to the embodiment of the present disclosure, the switch of the vehicle-mounted sensing device can be controlled based on the water accumulation risk level, and then the vehicle-mounted sensing device can be used to collect sensing data. Based on the sensing data, it can be more accurately determined whether there is water accumulation on the road, thereby improving the safety of vehicle driving.

[0111] In one embodiment, the method 500 further includes: determining the waterlogging condition of the target road section using the sensing data collected by the sensing device, further including:

[0112] S520: Using the camera on the vehicle to collect images of the road around the vehicle;

[0113] S530: Determine a waterlogged area in the target road section based on the road image.

[0114] In the disclosed embodiments, after the onboard camera is turned on, it can capture road images around the road section the vehicle is currently on, such as images of the target road section the vehicle is about to enter. The road images captured by the camera are processed using, for example, computer vision and image processing techniques to determine whether the road image of the target road section contains any areas of accumulated water. If no areas of accumulated water are present, subsequent water accumulation detection can be omitted and the vehicle can proceed normally. If no areas of accumulated water are present, subsequent water accumulation detection can be continued using data measured by the onboard radar.

[0115] According to the embodiment of the present disclosure, the waterlogged area is determined by the road image captured by the vehicle-mounted camera. The vehicle-mounted camera can be used to perform real-time waterlogging detection on the road around the current location of the vehicle, and the detection result is more accurate.

[0116] In one embodiment, determining the waterlogged area in the target road section based on the road image includes:

[0117] Recognize the road image based on computer vision technology to obtain a water surface reflection ratio and / or a color shift pixel value;

[0118] Based on the water surface reflection ratio and / or the color shift pixel value, a waterlogged area in the target road section is determined.

[0119] In the disclosed embodiments, computer vision technology, a multidisciplinary field encompassing computer science, image processing, pattern recognition, and machine learning, enables computers to understand and interpret the content in images or videos. Road images captured by vehicle-mounted cameras are preprocessed using computer vision technology, for example by grayscale conversion and edge detection. The preprocessed road is then segmented, for example by semantic segmentation, to obtain the reflectance ratio and / or color-shifted pixel values of water surface areas within the road image.

[0120] An example of a reflectance ratio formula is as follows:

[0121] Reflection ratio = number of pixels in the reflective area / total number of pixels.

[0122] An example formula for color shift is as follows:

[0123] Color shift = blue channel pixel mean - red channel pixel mean.

[0124] In the disclosed embodiment, the waterlogged area in the target road section can be determined based on either the reflection ratio or the color shift pixel value of the water surface area. The waterlogged area can also be determined based on both the reflection ratio and the color shift pixel value of the water surface area. For example, if the reflection ratio is higher than a threshold, it indicates that the water surface reflection is strong and there may be a waterlogged area. For another example, if the color shift is higher than a threshold, it may indicate that the pixel value of the blue channel in the road image is significantly higher than that of other channels, indicating that the reflection in the image is strong and there may be a waterlogged area.

[0125] According to the embodiment of the present disclosure, by using computer vision technology to process images and determining the water accumulation area through the image's reflective ratio and color shift pixel value, more accurate water accumulation detection results can be obtained, thereby improving the accuracy of real-time water accumulation detection results on roads.

[0126] In one embodiment, the method 500 further includes: determining the waterlogging condition of the target road section using the sensing data collected by the sensing device, including:

[0127] S540: Using the radar on the vehicle to measure the water level and the ground level of the flooded area in the target road section;

[0128] S550: Calculate a second water depth of the waterlogged area based on the difference between the ground height and the water surface height.

[0129] In the disclosed embodiment, the LiDAR can be activated simultaneously with the camera for simultaneous detection. Alternatively, the LiDAR can be activated only after the camera captures images that indicate a high risk of water accumulation in an area. After the vehicle's radar is activated, it scans the surrounding environment to determine the water level and ground level of the flooded area.

[0130] In the disclosed embodiment, the second water depth of the flooded area can be calculated using the water surface height and the ground height. The water surface height can be the distance between the radar and the water surface of the flooded area. The ground height can be the distance between the radar and the ground. An example formula for calculating the second water depth is as follows:

[0131] The second water depth = ground height - water surface height.

[0132] For example, if the radar measured ground height at 3 meters and the water surface height at 1.5 meters, the second water depth is: second water depth = 3.0 meters - 1.5 meters = 1.5 meters. The second water depth can be used as the measured water depth to update the empirical coefficient α in the above water detection method.

[0133] According to the embodiment of the present disclosure, the ground height and water surface height of the flooded area in the target road section can be measured by radar, so as to obtain the water depth of the target road section, which can improve the accuracy of real-time detection of road water depth.

[0134] In one embodiment, using the radar to measure the water surface height and the ground height of the flooded area in the target road section includes:

[0135] When the target road section includes a waterlogged area, the radar is used to scan the environment around the vehicle to obtain point cloud data;

[0136] The point cloud data is corrected based on the iterative closest point (ICP) algorithm to obtain the water surface height and ground height of the flooded area.

[0137] In the disclosed embodiments, a radar scans the environment around the road where the vehicle is located to obtain point cloud data. Point cloud data is a type of three-dimensional spatial data consisting of a large number of points, each of which contains spatial coordinates and possibly other attribute information. For example, point cloud data may include position coordinates (X, Y, Z), where coordinates X and Y may represent the horizontal position measured by the radar, and coordinate Z may represent the vertical height measured by the radar.

[0138] In the embodiment of the present disclosure, an iterative closest point (Iterative Closest Point eThe Closest Point (ICP) algorithm is used to process the point cloud data. The ICP algorithm is an algorithm for matching and aligning two point clouds. The ICP algorithm can be used to match a source point cloud data set with a target point cloud data set. Through rigid body transformation (such as rotation and translation), the source point cloud is transformed to achieve the best alignment with the target point cloud at a specific angle. In addition, the mean square error (MSE) and other metrics can be used. The point cloud data corrected by the ICP algorithm can obtain the point coordinates of multiple water surfaces and multiple ground points in the flooded area. The water surface height of the flooded area is obtained by averaging the depth of each water surface point coordinate; the ground height of the flooded area is obtained by averaging the depth of each ground point coordinate.

[0139] According to the embodiment of the present disclosure, point cloud data can be obtained through radar scanning, and the point cloud data can be corrected through algorithms to obtain more accurate water surface height and ground height, which can improve the accuracy of the accumulated water depth calculated based on the point cloud data.

[0140] Figure 6 FIG. 6 is a flow chart of a method 600 for detecting water accumulation according to another embodiment of the present disclosure. The method may include one or more features of the aforementioned method for detecting water accumulation. In one embodiment, the method 600 further includes:

[0141] S610: Obtain driving advice for the vehicle based on the water accumulation condition of the target road section and the type of the vehicle.

[0142] In the disclosed embodiments, vehicle types may include sedans, SUVs, MPVs, and trucks. Different vehicle types result in different capabilities for navigating flooded areas; for example, sedans are less capable than SUVs. Based on the water accumulation conditions determined by the aforementioned water accumulation detection method and the current vehicle model, corresponding driving recommendations can be derived.

[0143] For example, if the car model is a sedan, the water depth can be divided into levels 1-3, and corresponding driving suggestions are given:

[0144] (Water accumulation level 1) Water accumulation depth <5cm: Normal traffic.

[0145] (Water Level 2) Water depth is between 5-15 cm: It is recommended to slow down and provide a detour route.

[0146] (Water accumulation level 3) Water accumulation depth > 15cm: It is recommended to detour or stop and wait to prevent vehicle damage.

[0147] For example, if the vehicle type is an SUV, the water depth can be divided into levels 1-3, and corresponding driving advice is given:

[0148] (Water accumulation level 1) Water accumulation depth <5cm: Normal traffic.

[0149] (Water Level 2) Water depth is between 5-20 cm: It is recommended to slow down and provide a detour route.

[0150] (Water accumulation level 3) Water accumulation depth > 20cm: It is recommended to detour or stop and wait to prevent vehicle damage.

[0151] The numerical values of the water depth levels in the above examples and the water depth thresholds corresponding to each level are only examples and not limitations, and can be flexibly set according to the needs of actual application scenarios.

[0152] According to the embodiment of the present disclosure, driving suggestions that are more suitable for the vehicle are generated based on the water accumulation situation and the type of vehicle, thereby giving accurate driving suggestions to passengers and improving the safety of vehicle driving.

[0153] In one embodiment, the method 600 further includes:

[0154] S620: Upload the vehicle's sensing data and / or the water accumulation situation to the cloud.

[0155] In the disclosed embodiment, the vehicle can upload the perception data collected by its own perception equipment and the water accumulation conditions and other data related to water accumulation to the cloud server of the navigation system for storage as historical data. Depending on the needs, only one of the perception data or the water accumulation conditions can be uploaded, or all the data can be uploaded. The vehicle can upload the relevant data of a target road section after passing the target road section, or it can upload it directly after obtaining the relevant data of the target road section. A vehicle can download the water accumulation-related data uploaded by other vehicles from the cloud through map software, weather software, etc.

[0156] According to the embodiment of the present disclosure, the perception data and water accumulation conditions and other water accumulation-related data collected by the vehicle are uploaded to the cloud server of the navigation system as historical data, which can provide data reference for other vehicles and thus improve the driving safety of other vehicles.

[0157] Most navigation systems rely solely on weather data to provide road risk warnings, but cannot detect water depth in real time or provide accurate driving advice. The disclosed embodiments can provide a system that combines map data, onboard intelligent hardware, and real-time image analysis to improve driving safety in rainy weather.

[0158] The disclosed embodiment proposes a vehicle water accumulation detection and driving suggestion system. The system is based on map data, smart cameras, vehicle-mounted sensors and artificial intelligence algorithms. It can detect the depth of water accumulation on the road in real time and provide drivers with detour, deceleration or passage suggestions.

[0159] In the disclosed embodiment, the in-vehicle map can determine the possibility of waterlogging by combining third-party weather data with map data of the specific route slope or construction, to alert the driver and provide detailed driving advice.

[0160] The water accumulation detection method based on the above system may include one or more of the following steps:

[0161] S1. Obtain map data and initialize the warning system

[0162] The specific implementation process of S1 may further include one or more steps from S11 to S13:

[0163] S11. After the user enters their destination, the vehicle loads the current route (navigation route) through an online navigation system (such as a high-precision map or onboard GPS). Using basic road data, the system identifies sections prone to flooding, including those passing through low-lying areas, underpasses, and areas with a history of high flooding.

[0164] S12. The vehicle connects to a weather API (such as the Meteorological Bureau's open data interface) to obtain the current regional rainfall and radar images, and calculates the relationship between rainfall and the possibility of waterlogging.

[0165] 1. Calculate the depth of water accumulation

[0166] For example, set up a waterlogging model, see formula 1-1. Input rainfall R (mm / h), terrain slope θ, and soil permeability P into the model to calculate the waterlogging depth D:

[0167] D=α*R*(1-P) / tan(θ) 1-1

[0168] Where α is the empirical coefficient for water accumulation, which may vary for different roads. For example, for urban roads (asphalt / concrete): α ≈ 0.6-0.9; for rural dirt roads (highly permeable): α ≈ 0.3-0.6; and for viaducts / tunnels (areas prone to water accumulation): α ≈ 0.8-1.2. The empirical coefficient for water accumulation α can be calculated by regression analysis of historical data.

[0169] An example of a historical data regression calculation method is as follows:

[0170] (1) First, the rainfall R, terrain slope θ, soil permeability P, and measured water depth D at the same time and point are collected. real , each set of data is Ri, θ i 、Pi 、D real_i .

[0171] (2) Using the minimum mean square error (MSE) formula:

[0172]

[0173] Where n is the number of samples, D real_i is the measured water depth of the i-th data, It is the water depth D calculated based on S12 formula 1-1.

[0174] (3) Using formula 1-2, with initial α = 1, the calculated value is based on the measured water depth D. real And the water depth D estimated by formula 1-1, gradually adjust α and continuously reduce MSE until MSE converges to the minimum, or the α update changes very little (less than a threshold, such as 0.0001), then the optimal α value can be output.

[0175] 2. Dynamically adjust the weight of waterlogging points (also known as waterlogging point weights)

[0176] For example, using the weighted average algorithm, the weight W is dynamically adjusted according to the current rainfall, see formula 1-3:

[0177] W new =W old +β*(RR threshold ) 1-3

[0178] Among them, R threshold is the minimum rainfall that causes waterlogging, and β is the dynamic adjustment coefficient.

[0179] An example of a method for determining the dynamic adjustment coefficient is as follows:

[0180] (1) When the rainfall is low (R<5 mm / h), β=0.1 (i.e., the weight increases by only 0.1 for every 1 mm / h increase in rainfall).

[0181] (2) When the rainfall is moderate (5≤R<20mm / h), β=0.3.

[0182] (3) In case of heavy rain (20≤R<50mm / h), β=0.5.

[0183] (4) In case of heavy rain (R≥50mm / h), β=0.8.

[0184] S13. If in S12, the water depth D ≥ 5 cm, and the current rainfall R ≥ R threshold(such as 5mm / h), the risk is determined based on the dynamically adjusted weight W. For example, W≥0.8 indicates high risk, 0.5≤W<0.8 indicates medium risk, and W<0.5 indicates low risk. If W exceeds 0.5, the route is determined to be a high-risk section in water. When the vehicle is about to reach the section, the body sensing equipment such as the body camera and / or lidar will be triggered to turn on and enter step S2. If the water depth D<5cm, the body camera and / or lidar will not be triggered to turn on when the vehicle is about to reach the section. In addition, the water depth D can be ignored, and the route can be directly determined to be a high-risk section in water based on W. When the vehicle is about to reach the section, the body camera and / or lidar will be triggered to turn on.

[0185] S2. Use on-board cameras and sensors to collect detailed road data

[0186] The specific implementation process of S2 may further include one or more steps from S21 to S25:

[0187] S21. If the conditions for triggering the vehicle sensing device in S13 are met, the front camera automatically begins capturing road images a certain distance (e.g., 500 meters) before entering a road section at risk of flooding. Computer vision techniques (such as the object detection algorithm YOLO and the Mask R-CNN) are used to analyze reflections and color changes on the water surface and identify areas of flooding.

[0188] (1) Preprocess the image (perform operations such as grayscale conversion and edge detection on the image);

[0189] (2) Use computer vision technology such as Mask R-CNN to perform semantic segmentation on the image and distinguish the water surface area;

[0190] (3) Calculate the reflectivity of the water surface area and combine it with color shift (blue enhancement) to determine the degree of water accumulation. For example, calculate the distribution of brightness values in the image of the water surface area and set a threshold to separate the reflective area. Assuming that the brightness value range is 0 to 255 (a common grayscale range), you can choose a suitable threshold (for example, 160 or above is a reflective area). The formula for the reflectivity ratio is as follows:

[0191] Reflection ratio = number of pixels in the reflective area / total number of pixels.

[0192] If the reflectivity ratio is high, it means that the water surface is highly reflective and there may be accumulated water.

[0193] Color shift is to decompose the image into red, green, and blue channels and analyze the changes in each color channel separately. The water surface usually has a significant enhancement in the blue channel, so we can focus on the pixel values in the blue channel. The formula for color shift is as follows:

[0194] Color shift = blue channel pixel mean - red channel pixel mean.

[0195] If the pixel values of the blue channel are significantly higher than those of the other channels, it means that the reflections in the image are stronger and the water surface is more prominent.

[0196] Using the reflectivity ratio and color shift together, you can accurately determine the extent of water accumulation. For example, if the reflectivity ratio is high and the blue channel shift is large, you can determine that the water surface is deeper and the risk of water accumulation is higher.

[0197] S22. Start the LiDAR sensor to measure distance. The LiDAR can be started at the same time as the camera, or it can be started after the camera identifies a high risk of water accumulation in the waterlogged area in the image captured by the camera. The LiDAR scans the environment and records the surrounding spatial position information to form a point cloud. For example, each point in the point cloud has a position coordinate (X, Y, Z), where X and Y represent the horizontal position and Z represents the vertical height (such as the height of the water surface). The points on the water surface are horizontal, so their Z values do not change much.

[0198] S23. Use the ICP algorithm to align point clouds. Because lidar scans can occur at multiple angles, the data obtained may have some deviations. To ensure accuracy, a method called the ICP algorithm is used to "align" the data obtained from different scan angles. This allows the point clouds obtained from different angles to perfectly match, eliminating errors and ensuring measurement accuracy.

[0199] S24. Extract the water surface height. After the ICP algorithm adjusts the point cloud data, the points on the water surface should be relatively flat. By finding these points and calculating the average of their Z coordinates, the water surface height can be determined. For example, there are many points on the water surface with Z coordinates of 1.2 meters, 1.3 meters, 1.1 meters, 1.25 meters, and so on. The average value can be calculated, assuming it is 1.2 meters, which is the water surface height. The water surface height can be understood as the distance between the radar and the water surface.

[0200] S25. Calculate water depth. Ground height is also calculated using the point cloud generated by the LiDAR. Ground height can be understood as the distance between the radar and the ground. The ground and water heights are calculated based on the difference between the reflected signal from the ground and the reflected signal from the water. Therefore, water depth = ground height - water height. For example, if the ground height is 2 meters and the water height is 1.2 meters, the water depth is: Water depth = 2.0 meters - 1.2 meters = 0.8 meters.

[0201] S3. Provide driving tips based on the data from S2

[0202] The further specific implementation process of S3 may include one or more steps from S31 to S32:

[0203] S31. Use the water depth data measured in S2 to classify the water level. The example is as follows:

[0204] (1) If the vehicle is a sedan, the depth of the water can be divided into the following levels and corresponding driving advice is given:

[0205] (Water accumulation level 1) Water accumulation depth <5cm: Normal traffic.

[0206] (Water Level 2) Water depth is between 5-15 cm: It is recommended to slow down and provide a detour route.

[0207] (Water accumulation level 3) Water accumulation depth > 15cm: It is recommended to detour or stop and wait to prevent vehicle damage.

[0208] (2) If the vehicle is an SUV, the following water levels can be classified based on the depth of the water and corresponding driving advice will be given:

[0209] (Water accumulation level 1) Water accumulation depth <5cm: Normal traffic.

[0210] (Water Level 2) Water depth is between 5-20 cm: It is recommended to slow down and provide a detour route.

[0211] (Water accumulation level 3) Water accumulation depth > 20cm: It is recommended to detour or stop and wait to prevent vehicle damage.

[0212] S32. After a vehicle passes a road section, it uploads water detection data to the cloud and shares it with other vehicles to improve overall road safety.

[0213] Figure 7 FIG. 7 is a schematic structural diagram of a water accumulation detection device 700 according to an embodiment of the present disclosure. The device 700 may include:

[0214] An identification module 710 is configured to identify a target road segment from a navigation route of the vehicle based on map data;

[0215] a risk determination module 720 for determining the flooding risk of the target road section based on weather data;

[0216] The water accumulation determination module 730 is used to determine the water accumulation situation of the target road section through the perception data collected by the perception device when it is determined that the vehicle's perception device needs to be turned on based on the water accumulation risk of the target road section.

[0217] Figure 88 is a schematic diagram of a water accumulation detection device 800 according to another embodiment of the present disclosure. The device 800 includes: an identification module 810, a risk determination module 820, and a water accumulation determination module 830. The functions of the above modules can refer to the functions of the modules of the water accumulation detection device in the above embodiment. In one embodiment, the identification module 810 may include:

[0218] Route determination submodule 811, for determining the navigation route of the vehicle based on the map data and the starting point and end point of the vehicle;

[0219] The identification submodule 812 is configured to identify the target road section from the navigation route based on the navigation route and waterlogging-related data in the map data.

[0220] In one embodiment, the target road section includes a road section prone to waterlogging determined based on one or more of the following waterlogging-prone areas on the navigation route in the map data: low-lying areas, passages under bridges, and areas with a high incidence of historical waterlogging.

[0221] In one embodiment, the risk determination module 820 includes:

[0222] A first calculation submodule 821 is configured to obtain a first waterlogging depth and / or a waterlogging-prone weight of a target road section based on the weather data;

[0223] The risk determination submodule 822 is configured to determine the waterlogging risk of the target road section based on the first waterlogging depth and / or the waterlogging susceptibility weight.

[0224] In one embodiment, the first calculation submodule 821 is used to obtain a first water depth of the target road section based on current weather data and a water experience coefficient; wherein the water experience coefficient is obtained based on historical weather data and historical measured water depths.

[0225] In one embodiment, the first calculation submodule 821 is used to calculate the first ponding depth based on the current rainfall and the water accumulation empirical coefficient; wherein the water accumulation empirical coefficient is obtained by regression calculation based on historical rainfall and historical measured water accumulation depth; or

[0226] In one embodiment, the first calculation submodule 821 is used to calculate the first water depth based on one or more of the current rainfall, road characteristic data and water accumulation experience coefficient; wherein, the water accumulation experience coefficient is obtained through regression calculation based on historical rainfall, road characteristic data and historical measured water depth.

[0227] In one embodiment, the first calculation submodule 821 is used to calculate the current waterlogging weight based on one or more of the historical waterlogging weight, the current rainfall, the minimum rainfall for waterlogging, and a dynamic adjustment coefficient; wherein the dynamic adjustment coefficient is obtained based on the rainfall in the weather data.

[0228] In one embodiment, the first calculation submodule 821 is further configured to:

[0229] Determine the waterlogging risk level of the target road section based on the current waterlogging risk weight; or

[0230] Determining a flood risk level of the target road section based on the first flood depth; or

[0231] When the first waterlogging depth is greater than or equal to a first depth threshold and / or the current rainfall is greater than a rainfall threshold, the waterlogging risk level of the target road section is determined based on the current waterlogging weight.

[0232] In one embodiment, the water accumulation determination module 830 includes:

[0233] The activation submodule 831 is used to activate the sensing device of the vehicle when the water accumulation risk level meets the level requirements.

[0234] In one embodiment, the water accumulation determination module 830 includes:

[0235] The acquisition submodule 832 is configured to use a camera on the vehicle to acquire images of the road surrounding the vehicle;

[0236] The waterlogged area determining submodule 833 is configured to determine the waterlogged area in the target road section based on the road image.

[0237] In one embodiment, the water accumulation area determination submodule 833 is used to identify the road image based on computer vision technology to obtain the water surface reflection ratio and / or the color shift pixel value; based on the water surface reflection ratio and / or the color shift pixel value, determine the water accumulation area in the target road section.

[0238] In one embodiment, the water accumulation determination module 830 includes:

[0239] The measurement submodule 834 is configured to use the radar on the vehicle to measure the water level and ground level of the flooded area in the target road section;

[0240] The second calculation submodule 835 is configured to calculate a second water depth of the waterlogged area based on the difference between the ground height and the water surface height.

[0241] In one embodiment, the measurement submodule 834 is used to use the radar to scan the environment around the vehicle to obtain point cloud data when the target road section includes a flooded area; and to correct the point cloud data based on the iterative closest point (ICP) algorithm to obtain the water surface height and ground height of the flooded area.

[0242] In one embodiment, it further includes:

[0243] The suggestion module 840 is used to obtain driving suggestions for the vehicle based on the water accumulation condition of the target road section and the type of the vehicle.

[0244] In one embodiment, it further includes:

[0245] The uploading module 850 is used to upload the sensing data of the vehicle and / or the water accumulation situation to the cloud.

[0246] For the description of specific functions and examples of each module and submodule of the device in the embodiment of the present disclosure, please refer to the relevant description of the corresponding steps in the above method embodiment, which will not be repeated here.

[0247] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0248] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0249] Figure 9 A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0250] like Figure 9As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. Various programs and data required for the operation of the device 900 can also be stored in the RAM 903. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0251] Various components in the device 900 are connected to the I / O interface 905, including an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a magnetic disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0252] The computing unit 901 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as the water accumulation detection method. For example, in some embodiments, the water accumulation detection method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the water accumulation detection method described above can be performed. Alternatively, in other embodiments, the computing unit 901 can be configured to perform the water accumulation detection method by any other suitable means (e.g., via firmware).

[0253] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0254] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0255] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0256] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0257] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0258] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0259] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0260] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for detecting accumulated water, comprising: Based on the map data, the target road section is identified from the vehicle's navigation route; Determining the flooding risk of the target road section based on weather data; In a case where it is determined that the sensing device of the vehicle needs to be turned on based on the water accumulation risk of the target road section, the water accumulation condition of the target road section is determined through the sensing data collected by the sensing device.

2. The method according to claim 1, wherein Based on the map data, the target road segment is identified from the vehicle's navigation route, including: determining a navigation route for the vehicle based on the map data and a starting point and an end point of the vehicle's travel; The target road section is identified from the navigation route based on the navigation route and the water accumulation related data in the map data.

3. The method according to claim 2, wherein: The target road section includes a road section prone to waterlogging determined based on one or more of the following waterlogging-prone areas on the navigation route in the map data: a low-lying area, a passage under a bridge, and an area with a high incidence of historical waterlogging.

4. The method according to any one of claims 1 to 3, wherein Determine the flooding risk of the target road section based on weather data, including: Based on the weather data, obtaining a first waterlogging depth and / or a waterlogging-prone weight of a target road section; The waterlogging risk of the target road section is determined based on the first waterlogging depth and / or the waterlogging susceptibility weight.

5. The method according to claim 4, wherein Obtaining a first flood depth of a target road section based on the weather data includes: Based on current weather data and an empirical waterlogging coefficient, a first waterlogging depth of the target road section is obtained; wherein the empirical waterlogging coefficient is obtained based on historical weather data and historically measured waterlogging depths.

6. The method according to claim 5, wherein: Based on the current weather data and the empirical coefficient of waterlogging, the first waterlogging depth of the target road section is obtained, including: Calculating the first waterlogging depth based on current rainfall and a waterlogging empirical coefficient; wherein the waterlogging empirical coefficient is obtained by regression calculation based on historical rainfall and historical measured waterlogging depths; or The first waterlogging depth is calculated based on current rainfall, road characteristic data and a waterlogging empirical coefficient; wherein the waterlogging empirical coefficient is obtained by regression calculation based on historical rainfall, road characteristic data and historical measured waterlogging depths.

7. The method according to any one of claims 4 to 6, wherein Based on the weather data, the waterlogging weight of the target road section is obtained, including: The current waterlogging weight is calculated based on one or more of the historical waterlogging weight, the current rainfall, the minimum rainfall resulting in waterlogging, and a dynamic adjustment coefficient; wherein the dynamic adjustment coefficient is obtained based on the rainfall in the weather data.

8. The method according to claim 7, wherein: Determining the waterlogging risk of the target road section based on the first waterlogging depth and / or the waterlogging susceptibility weight includes: Determining the waterlogging risk level of the target road section based on the current waterlogging risk weight; or Determining a flood risk level of the target road section based on the first flood depth; or When the first waterlogging depth is greater than or equal to a first depth threshold and / or the current rainfall is greater than a rainfall threshold, the waterlogging risk level of the target road section is determined based on the current waterlogging weight.

9. The method according to claim 8, wherein Determining that a sensing device of the vehicle needs to be turned on based on the water accumulation risk includes: When the water accumulation risk level meets the level requirement, the sensing device of the vehicle is turned on.

10. The method according to any one of claims 1 to 9, wherein Determining the waterlogging condition of the target road section using the sensing data collected by the sensing device includes: Using a camera on the vehicle to collect images of the road around the vehicle; A waterlogged area in the target road section is determined based on the road image.

11. The method according to claim 10, wherein: Determining a waterlogged area in the target road section based on the road image includes: Recognizing the road image based on computer vision technology to obtain a water surface reflection ratio and / or a color shift pixel value; Based on the water surface reflection ratio and / or the color shift pixel value, a water accumulation area in the target road section is determined.

12. The method according to any one of claims 1 to 11, wherein Determining the waterlogging condition of the target road section using the sensing data collected by the sensing device includes: Using the radar on the vehicle to measure the water level and ground level of the flooded area in the target road section; A second water depth of the waterlogged area is calculated based on the difference between the ground height and the water surface height.

13. The method according to claim 12, wherein: Measuring the water surface height and the ground height of the flooded area in the target road section using the radar includes: When the target road section includes a waterlogged area, scanning the environment around the vehicle using the radar to obtain point cloud data; The point cloud data is corrected based on an iterative closest point (ICP) algorithm to obtain the water surface height and the ground height of the waterlogged area.

14. A water accumulation detection device, comprising: An identification module, configured to identify a target road section from a vehicle's navigation route based on map data; a risk determination module, configured to determine the waterlogging risk of the target road section based on weather data; The water accumulation determination module is used to determine the water accumulation situation of the target road section through the perception data collected by the perception device when it is determined that the vehicle's perception device needs to be turned on based on the water accumulation risk of the target road section.

15. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 13.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-13.

17. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 13.

Images