Pit identification method and system

Abstract

The invention discloses a water pit identification method and system, and the method comprises the steps: obtaining the latitude and longitude data, elevation data, temperature data, time data, environment light intensity data, reflectivity data, image data and laser radar data of a to-be-measured target region, and calculating the current elevation angle, the current main light source position information, the current calibration matrix and the current vehicle lamp light intensity data, and substituting the data into a pre-established water pit detection model and / or an ice surface detection model for processing so as to determine whether the target area to be detected is a water pit or an ice surface. According to the method provided by the invention, the accurate recognition of the puddle under all-weather conditions in summer and winter is realized by fusing various sensing data, and effective information is provided for an unmanned driving system.

Description

Technical Field

[0001] The present invention relates to the field of intelligent detection technology, and more specifically, to a puddle recognition method and system. Background Art

[0002] When a puddle is deep or large in an open-pit mine, it may cause the vehicle to get stuck, posing a safety risk to the mine vehicles and affecting the production efficiency. Compared with humans, it is more difficult for unmanned vehicles to identify puddles, especially when the temperature drops suddenly in winter and the water surface is covered with ice. The surface characteristics of the puddle are quite different from those in summer when the sediment content is high, making it more difficult to identify.

[0003] Traditional liquid puddle recognition is mainly based on visual recognition and segmentation. Generally, the puddle area and non-puddle area have clear edges and large color differences. However, the robustness of this recognition method is relatively poor under different lighting environments.

[0004] For puddles covered with ice, the thickness of the ice layer and whether there is liquid water under the ice can be determined by measuring the temperature difference, but this is only applicable to areas that are not easily changed and are deep. The reflectivity of the puddle surface can also be measured by roadside equipment to determine the ice layer and liquid water in the puddle. However, the above two methods are only applicable to fixed areas, and the measurement speed is slow, which is difficult to meet the needs of unmanned driving real-time measurement.

[0005] In summary, at this stage, there is an urgent need to develop a puddle identification method and system to solve the above-mentioned technical problems. Summary of the invention

[0006] An object of the present invention is to provide a new technical solution for a puddle identification method and system.

[0007] According to a first aspect of the present invention, a method for identifying a puddle is provided, the method comprising:

[0008] Step S1: Acquire the latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data and lidar data of the target area to be measured;

[0009] Step S2: Calculate the current altitude angle of the target area to be measured based on the acquired latitude and longitude data and time data;

[0010] Step S3: determining the current main light source position information according to the acquired ambient light intensity data and reflectivity data;

[0011] Step S4: calibrate the collected camera data and lidar data to obtain a current calibration matrix;

[0012] Step S5: The longitude and latitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data are brought into a pre-established puddle detection model and / or ice surface detection model for processing to determine whether the target area to be measured is a puddle or an ice surface.

[0013] According to the method of the first aspect of the present invention, step S5 specifically comprises:

[0014] Step S51: determining the current icing probability according to the acquired latitude and longitude data, elevation data, temperature data and time data;

[0015] Step S52: if the current icing probability is less than the first threshold, the latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data are brought into the puddle detection model for processing to determine whether the target area to be detected is a puddle or an ice surface;

[0016] Step S53: if the current probability of icing is greater than the second threshold, the latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data are brought into the ice surface detection model for processing to determine whether the target area to be detected is a puddle or an ice surface;

[0017] Step S54: If the current probability of icing is greater than the first threshold and less than the second threshold, the longitude and latitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, camera data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data are respectively brought into the puddle detection model and the ice surface detection model for processing to determine whether the target area to be measured is a puddle or an ice surface.

[0018] According to the method of the first aspect of the present invention, step S54 further comprises:

[0019] If the current icing probability is less than the third threshold, the detection processing sequence is: puddle detection model, ice surface detection model;

[0020] If the current probability of the puddle being frozen is greater than the third threshold, the order of detection processing is: ice surface detection model, puddle detection model.

[0021] According to the method of the first aspect of the present invention, in step S2, the calculation formula of the current altitude angle is expressed as:

[0022] sin X= sin G sin δ+cos G cosδ cos T (1)

[0023] Among them, X represents the altitude angle, δ represents the solar declination, G represents the geographical latitude of the observation site, and T represents the local time.

[0024] According to the method of the first aspect of the present invention, the main light source position information includes whether the main light source is the sun or the car lights, and the positional relationship between the sun, the car lights and the target area to be measured.

[0025] According to the method of the first aspect of the present invention, the puddle detection model includes an R1 sub-model, an R2 sub-model and an R3 sub-model; the R1 sub-model is applicable to detection scenarios including: the main light source is a car light and the car light is located between the sun and the target area to be measured, or the main light source is the sun and the sun is located between the car light and the target area to be measured; the R2 sub-model is applicable to detection scenarios including: the main light source is a car light and the sun is located between the car light and the target area to be measured, or the main light source is the sun and the car light is located between the target area to be measured and the sun; the R3 sub-model is applicable to detection scenarios including: the main light source is a car light and the target area to be measured is located between the car light and the sun, or the main light source is the sun and the target area to be measured is located between the car light and the sun;

[0026] The ice surface detection model includes a P1 sub-model, a P2 sub-model and a P3 sub-model; the applicable detection scenarios of the P1 sub-model include: the main light source is a car light and the car light is located between the sun and the target area to be measured, or the main light source is the sun and the sun is located between the car light and the target area to be measured; the applicable detection scenarios of the P2 sub-model include: the main light source is a car light and the sun is located between the car light and the target area to be measured, or the main light source is the sun and the car light is located between the target area to be measured and the sun; the applicable detection scenarios of the P3 sub-model include: the main light source is a car light and the target area to be measured is located between the car light and the sun, or the main light source is the sun and the target area to be measured is located between the car light and the sun.

[0027] According to the method of the first aspect of the present invention, the puddle detection model and the ice surface detection model are trained using a pre-collected training data set;

[0028] The training data set includes the latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data and lidar data of the target puddle / target ice surface obtained at different time points and different geographical locations, the calculated altitude angle data, main light source position information, calibration matrix and vehicle light intensity data, as well as the empirical values ​​of puddle reflectivity, ice surface reflectivity and ground reflectivity obtained by testing.

[0029] According to a second aspect of the present invention, there is provided a puddle identification system, the system comprising:

[0030] The first processing module is configured to obtain latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data and laser radar data of the target area to be measured;

[0031] The second processing module is configured to calculate the current altitude angle of the target area to be measured based on the acquired latitude and longitude data and time data;

[0032] A third processing module is configured to determine the current main light source position information according to the acquired ambient light intensity data and reflectivity data;

[0033] A fourth processing module is configured to calibrate the collected camera data and lidar data to obtain a current calibration matrix;

[0034] The fifth processing module is configured to bring the longitude and latitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data into a pre-established puddle detection model and / or ice surface detection model for processing to determine whether the target area to be measured is a puddle or an ice surface.

[0035] According to a third aspect of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a puddle identification method as described in the first aspect of the present invention are implemented.

[0036] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of a puddle identification method as described in the first aspect of the present invention are implemented.

[0037] According to an embodiment disclosed in the present invention, a puddle identification method and system of the present invention have the following beneficial effects:

[0038] A puddle recognition method of the present invention realizes accurate recognition of puddles in all-weather conditions in summer and winter by fusing multiple sensor data, thereby providing effective information for an unmanned driving system.

[0039] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0041] Figure 1 A schematic diagram of a process of a puddle identification method provided according to an embodiment;

[0042] Figure 2 A schematic diagram of the structure of a puddle identification system provided according to an embodiment;

[0043] Figure 3 A schematic diagram of an electronic device. DETAILED DESCRIPTION

[0044] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0045] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0046] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0047] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0048] Embodiment 1:

[0049] See also Figure 1 As shown, an embodiment of the present invention provides a puddle identification method, the method comprising:

[0050] Step S1: Acquire the latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data and lidar data of the target area to be measured.

[0051] It should be noted that, in this embodiment, the longitude and latitude data and elevation data can be obtained through the GNSS positioning system; the ambient temperature data can be obtained in real time through the temperature sensor on the unmanned vehicle; the time data can be obtained through the clock on the unmanned vehicle; the ambient light intensity data can be obtained through the light tester on the unmanned vehicle; the reflectivity data of the target area to be tested can be obtained through the reflectivity tester on the unmanned vehicle; and the image data and lidar data can be obtained in real time through the camera and lidar sensor on the unmanned vehicle.

[0052] Step S2: Calculate the current altitude angle of the target area to be measured based on the acquired longitude and latitude data and time data.

[0053] Optionally, in step S2 of the method of this embodiment, the calculation formula of the current altitude angle is expressed as:

[0054] sin X= sin G sin δ+cos G cosδ cos T (1)

[0055] Among them, X represents the altitude angle, δ represents the solar declination, G represents the geographical latitude of the observation site, and T represents the local time. Specifically, the solar declination is equal to the latitude of the sun's direct point. Both the solar declination and the geographical latitude are positive in the north latitude and negative in the south latitude.

[0056] Step S3: Determine the current main light source position information based on the acquired ambient light intensity data and reflectivity data.

[0057] Optionally, in the method of this embodiment, the main light source position information includes whether the main light source is the sun or a car light, and the position relationship between the sun, the car light and the target area to be measured.

[0058] It should be noted that in this embodiment, there are three types of positional relationships between the sun, the headlights, and the target area to be measured: the sun is located between the headlights and the target area to be measured, the headlights are located between the sun and the target area to be measured, and the target area to be measured is located between the headlights and the sun. Generally, at night or when the sunlight is very weak, the headlights are the main light source, and otherwise, the sun is mostly the main light source.

[0059] Step S4: Calibrate the collected camera data and lidar data to obtain a current calibration matrix.

[0060] Step S5: The longitude and latitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data are brought into a pre-established puddle detection model and / or ice surface detection model for processing to determine whether the target area to be measured is a puddle or an ice surface.

[0061] It should be noted that, in this embodiment, the current vehicle light intensity data is calculated based on the vehicle light power and the vehicle light viewing angle.

[0062] Optionally, step S5 in the method of this embodiment specifically includes:

[0063] Step S51: determining the current icing probability according to the acquired latitude and longitude data, elevation data, temperature data and time data;

[0064] Step S52: if the current icing probability is less than the first threshold, the latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data are brought into the puddle detection model for processing to determine whether the target area to be detected is a puddle or an ice surface;

[0065] Step S53: if the current probability of icing is greater than the second threshold, the latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data are brought into the ice surface detection model for processing to determine whether the target area to be detected is a puddle or an ice surface;

[0066] Step S54: If the current probability of icing is greater than the first threshold and less than the second threshold, the longitude and latitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, camera data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data are respectively brought into the puddle detection model and the ice surface detection model for processing to determine whether the target area to be measured is a puddle or an ice surface.

[0067] Optionally, step S54 in the method of this embodiment further includes:

[0068] If the current icing probability is less than the third threshold, the detection processing sequence is: puddle detection model, ice surface detection model;

[0069] If the current probability of the puddle being frozen is greater than the third threshold, the order of detection processing is: ice surface detection model, puddle detection model.

[0070] It should be noted that, in this embodiment, the first threshold, the second threshold and the third threshold can be determined according to empirical data or test data, and are not specifically limited here.

[0071] For example, the first threshold is 10%, the second threshold is 90%, and the third threshold is 50%; when the current icing probability is less than 10%, the puddle detection model is used for detection; when the current icing probability is greater than 10%, the ice surface detection model is used for detection; when the current icing probability is between the first threshold and the second threshold, and is less than 50%, the order of detection processing is: puddle detection model, ice surface detection model; when the current icing probability is between the first threshold and the second threshold, and is greater than 50%, the order of detection processing is: ice surface detection model, puddle detection model.

[0072] Optionally, the puddle detection model in the method of this embodiment includes an R1 sub-model, an R2 sub-model and an R3 sub-model; the R1 sub-model is applicable to detection scenarios including: the main light source is a car light and the car light is located between the sun and the target area to be measured, or the main light source is the sun and the sun is located between the car light and the target area to be measured; the R2 sub-model is applicable to detection scenarios including: the main light source is a car light and the sun is located between the car light and the target area to be measured, or the main light source is the sun and the car light is located between the target area to be measured and the sun; the R3 sub-model is applicable to detection scenarios including: the main light source is a car light and the target area to be measured is located between the car light and the sun, or the main light source is the sun and the target area to be measured is located between the car light and the sun;

[0073] The ice surface detection model includes P1 sub-model, P2 sub-model and P3 sub-model; the applicable detection scenarios of the P1 sub-model include: the main light source is the car lights and the car lights are located between the sun and the target area to be measured, or the main light source is the sun and the sun is located between the car lights and the target area to be measured; the applicable detection scenarios of the P2 sub-model include: the main light source is the car lights and the sun is located between the car lights and the target area to be measured, or the main light source is the sun and the car lights are located between the target area to be measured and the sun; the applicable detection scenarios of the P3 sub-model include: the main light source is the car lights and the target area to be measured is located between the car lights and the sun, or the main light source is the sun and the target area to be measured is located between the car lights and the sun.

[0074] It should be noted that due to the different main light sources and the different positional relationships between the sun, car lights and the target area to be measured, the surface features of the target area to be measured (puddles or ice surfaces) are different. Therefore, a single detection model cannot be used for detection and processing. Therefore, in order to improve the robustness of the model, in this embodiment, the puddle detection model is divided into R1 sub-model, R2 sub-model and R3 sub-model according to the position information of the main light source, and the ice surface detection model is divided into P1 sub-model, P2 sub-model and P3 sub-model.

[0075] Specifically, when the main light source is the car light and the calculation error exceeds 10%, the detection is performed in the order of R1 sub-model, R3 sub-model, and R2 sub-model, and whether the target is a puddle is confirmed based on the final recognition rate; if the models cannot be clearly distinguished, the puddle and ice surface are fused and recognized, and the detection order is R1 sub-model, P1 sub-model, R3 sub-model, P3 sub-model, R2 sub-model, and P2 sub-model, and whether the target is an ice surface or a puddle is confirmed based on the final recognition rate.

[0076] Optionally, in the method of this embodiment, the puddle detection model and the ice surface detection model are trained by means of a pre-collected training data set; the training data set includes latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data and lidar data of the target puddle / target ice surface acquired at different time points and different geographical locations, calculated altitude angle data, main light source position information, calibration matrix and vehicle light intensity data, as well as empirical values ​​of puddle reflectivity, ice surface reflectivity and ground reflectivity obtained by testing.

[0077] The following is a detailed description of the process of establishing the puddle detection model and the ice surface detection model:

[0078] 1. First, collect GNSS information (i.e. longitude and latitude data G, elevation data H), and collect temperature data O and time data T;

[0079] 2. Calculate the current altitude angle based on the latitude and longitude data G and time data T;

[0080] 3. Collect the ambient light intensity data L1, and calculate the headlight intensity data L2 based on the headlight power and viewing angle;

[0081] 4. According to the on-site environment, reflectivity data at different time nodes are collected to obtain the empirical value K1 of puddle reflectivity, the empirical value K2 of ice surface reflectivity and the empirical value K3 of ground reflectivity. The three values ​​can be range values.

[0082] 5. Based on the reflectivity data and the above light intensity data, we can know whether the main light source is sunlight or car lights, as well as the positional relationship between the light source, car lights and the target area to be measured;

[0083] When the main light source is a car light and the car light is between the sun and the target area to be measured, or the main light source is the sun and the sun is between the car light and the target area to be measured, it is marked as R1; when the main light source is a car light and the sun is between the car light and the target area to be measured, or the main light source is the sun and the car light is between the target area to be measured and the sun, it is marked as R2; when the main light source is a car light and the target area to be measured is between the car light and the sun, or the main light source is the sun and the target area to be measured is between the car light and the sun, it is marked as R3;

[0084] Similarly, in the case where the surface of the puddle is frozen, when the main light source is the car light and the car light is between the sun and the target area to be measured, or the main light source is the sun and the sun is between the car light and the target area to be measured, it is marked as P1; when the main light source is the car light and the sun is between the car light and the target area to be measured, or the main light source is the sun and the car light is between the target area to be measured and the sun, it is marked as P2; when the main light source is the car light and the target area to be measured is between the car light and the sun, or the main light source is the sun and the target area to be measured is between the car light and the sun, it is marked as P3.

[0085] 6. Collect a large amount of camera data C and lidar data D of puddles and ice surfaces in different seasons, calibrate them at the same time to form a calibration matrix N, and classify them according to the collection parameters to form data matrices {G, H, T, X, O, L1, L2, K1, K2, K3, R1, C, D, N}, {G, H, T, X, O, L1, L2, K1, K2, K3, R2, C, D, N}, {G, H , T, X, O, L1, L2, K1, K2, K3, R3, C, D, N}, {G, H, T, ,H,T,X,O,L1,L2,K1,K2,K3,P2,C,D,N},{G,H,T,X,O,L1,L2,K1,K2,K3,P3,C,D,N}.

[0086] 7. Due to the large difference in gradients of related data, fusion training is difficult to converge. Therefore, according to different data matrix sets, the related data are trained separately through convolutional neural networks and large model algorithms to generate training models R1 sub-model, R2 sub-model, R3 sub-model, P1 sub-model, P2 sub-model, and P3 sub-model.

[0087] The puddle identification method of the embodiment of the present invention has the following advantages:

[0088] 1. Capable of real-time detection and meeting the needs of unmanned driving;

[0089] 2. Dynamic and stable recognition can be achieved under different lighting angles and temperature conditions;

[0090] 3. Multi-source data fusion, high robustness.

[0091] In summary, the puddle recognition method of the embodiment of the present invention realizes accurate recognition of puddles in all weather conditions in summer and winter by fusing multiple sensor data, thereby providing effective information for the unmanned driving system.

[0092] Embodiment 2:

[0093] The embodiment of the present invention provides a puddle identification system 100, see Figure 2 As shown, the system 100 includes:

[0094] The first processing module 10 is configured to obtain latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data and laser radar data of the target area to be measured;

[0095] The second processing module 20 is configured to calculate the current altitude angle of the target area to be measured based on the acquired latitude and longitude data and time data;

[0096] The third processing module 30 is configured to determine the current main light source position information according to the acquired ambient light intensity data and reflectivity data;

[0097] The fourth processing module 40 is configured to calibrate the collected camera data and lidar data to obtain a current calibration matrix;

[0098] The fifth processing module 50 is configured to bring the longitude and latitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data into a pre-established puddle detection model and / or ice surface detection model for processing to determine whether the target area to be measured is a puddle or an ice surface.

[0099] Optionally, the fifth processing module 50 in the puddle identification system of this embodiment specifically includes:

[0100] A first processing unit is configured to determine a current icing probability based on the acquired latitude and longitude data, elevation data, temperature data, and time data;

[0101] The second processing unit is configured to bring the latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data into the puddle detection model for processing if the current icing probability is less than the first threshold value, so as to determine whether the target area to be detected is a puddle or an ice surface;

[0102] The third processing unit is configured to bring the latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data into the ice surface detection model for processing if the current icing probability is greater than the second threshold value, so as to determine whether the target area to be detected is a puddle or an ice surface;

[0103] The fourth processing unit is configured to bring the longitude and latitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, camera data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data into the puddle detection model and ice surface detection model for processing respectively if the current probability of icing is greater than the first threshold and less than the second threshold, so as to determine whether the target area to be measured is a puddle or an ice surface.

[0104] Optionally, the fourth processing unit in the puddle identification system of this embodiment is further configured to:

[0105] If the current icing probability is less than the third threshold, the detection processing sequence is: puddle detection model, ice surface detection model;

[0106] If the current probability of the puddle being frozen is greater than the third threshold, the order of detection processing is: ice surface detection model, puddle detection model.

[0107] Optionally, the calculation formula of the current altitude angle in the puddle recognition system of this embodiment is expressed as:

[0108] sin X= sin G sin δ+cos G cosδ cos T (1)

[0109] Among them, X represents the altitude angle, δ represents the solar declination, G represents the geographical latitude of the observation site, and T represents the local time.

[0110] Optionally, the main light source position information in the puddle recognition system of this embodiment includes whether the main light source is the sun or a car light, and the positional relationship between the sun, the car light and the target area to be measured.

[0111] Optionally, the puddle detection model in the puddle recognition system of the present embodiment includes an R1 sub-model, an R2 sub-model and an R3 sub-model; the R1 sub-model is applicable to detection scenarios including: the main light source is a car light and the car light is located between the sun and the target area to be measured, or the main light source is the sun and the sun is located between the car light and the target area to be measured; the R2 sub-model is applicable to detection scenarios including: the main light source is a car light and the sun is located between the car light and the target area to be measured, or the main light source is the sun and the car light is located between the target area to be measured and the sun; the R3 sub-model is applicable to detection scenarios including: the main light source is a car light and the target area to be measured is located between the car light and the sun, or the main light source is the sun and the target area to be measured is located between the car light and the sun;

[0112] The ice surface detection model includes P1 sub-model, P2 sub-model and P3 sub-model; the applicable detection scenarios of the P1 sub-model include: the main light source is the car lights and the car lights are located between the sun and the target area to be measured, or the main light source is the sun and the sun is located between the car lights and the target area to be measured; the applicable detection scenarios of the P2 sub-model include: the main light source is the car lights and the sun is located between the car lights and the target area to be measured, or the main light source is the sun and the car lights are located between the target area to be measured and the sun; the applicable detection scenarios of the P3 sub-model include: the main light source is the car lights and the target area to be measured is located between the car lights and the sun, or the main light source is the sun and the target area to be measured is located between the car lights and the sun.

[0113] Optionally, in the puddle recognition system of the present embodiment, the puddle detection model and the ice surface detection model are trained using a pre-collected training data set; the training data set includes longitude and latitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data and lidar data of the target puddle / target ice surface acquired at different time points and geographical locations, calculated altitude angle data, main light source position information, calibration matrix and vehicle light intensity data, as well as empirical values ​​of puddle reflectivity, ice surface reflectivity and ground reflectivity obtained by testing.

[0114] Embodiment three:

[0115] The present invention discloses an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a puddle identification method in any one of the embodiments of the present invention are implemented.

[0116] Figure 3 is a structural diagram of an electronic device according to an embodiment of the present invention, such as Figure 3 As shown, the electronic device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, near field communication (NFC) or other technologies. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covered on the display screen, or a button, a trackball or a touch pad set on the housing of the electronic device, or an external keyboard, touch pad or mouse, etc.

[0117] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a structural diagram of the part related to the technical solution of the present disclosure, and does not constitute a limitation on the electronic device to which the technical solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0118] Embodiment 4:

[0119] The embodiment of the present invention discloses a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a puddle identification method in any one of the embodiments of the present invention are implemented.

[0120] Please note that the technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. The above embodiments only express several implementation methods of the present application, and their descriptions are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present application, several variations and improvements can be made, which all belong to the scope of protection of the present application. Therefore, the scope of protection of the patent in this application shall be based on the attached claims.

[0121] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0122] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will be appreciated by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A puddle identification method, characterized in that: The method comprises: Step S1: Acquire the latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data and lidar data of the target area to be measured; Step S2: Calculate the current altitude angle of the target area to be measured based on the acquired latitude and longitude data and time data; Step S3: determining the current main light source position information according to the acquired ambient light intensity data and reflectivity data; Step S4: calibrate the collected camera data and lidar data to obtain a current calibration matrix; Step S5: The longitude and latitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data are brought into a pre-established puddle detection model and / or ice surface detection model for processing to determine whether the target area to be measured is a puddle or an ice surface.

2. The puddle identification method according to claim 1, characterized in that: The step S5 specifically includes: Step S51: determining the current icing probability according to the acquired latitude and longitude data, elevation data, temperature data and time data; Step S52: if the current icing probability is less than the first threshold, the latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data are brought into the puddle detection model for processing to determine whether the target area to be detected is a puddle or an ice surface; Step S53: if the current probability of icing is greater than the second threshold, the latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data are brought into the ice surface detection model for processing to determine whether the target area to be detected is a puddle or an ice surface; Step S54: If the current probability of icing is greater than the first threshold and less than the second threshold, the longitude and latitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, camera data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data are respectively brought into the puddle detection model and the ice surface detection model for processing to determine whether the target area to be measured is a puddle or an ice surface.

3. The puddle identification method according to claim 2, characterized in that: The step S54 further comprises: If the current icing probability is less than the third threshold, the detection processing sequence is: puddle detection model, ice surface detection model; If the current probability of the puddle being frozen is greater than the third threshold, the order of detection processing is: ice surface detection model, puddle detection model.

4. The puddle identification method according to claim 1, characterized in that: In step S2, the calculation formula of the current altitude angle is expressed as: sin X= sin G sin δ+cos G cosδ cos T (1) Among them, X represents the altitude angle, δ represents the solar declination, G represents the geographical latitude of the observation site, and T represents the local time.

5. The puddle identification method according to claim 1, characterized in that: The main light source position information includes whether the main light source is the sun or a car light, and the position relationship between the sun, the car light and the target area to be measured.

6. The puddle identification method according to claim 5, characterized in that: The puddle detection model includes an R1 sub-model, an R2 sub-model and an R3 sub-model; the R1 sub-model is applicable to detection scenarios including: the main light source is a car light and the car light is located between the sun and the target area to be measured, or the main light source is the sun and the sun is located between the car light and the target area to be measured; the R2 sub-model is applicable to detection scenarios including: the main light source is a car light and the sun is located between the car light and the target area to be measured, or the main light source is the sun and the car light is located between the target area to be measured and the sun; the R3 sub-model is applicable to detection scenarios including: the main light source is a car light and the target area to be measured is located between the car light and the sun, or the main light source is the sun and the target area to be measured is located between the car light and the sun; The ice surface detection model includes a P1 sub-model, a P2 sub-model and a P3 sub-model; the applicable detection scenarios of the P1 sub-model include: the main light source is a car light and the car light is located between the sun and the target area to be measured, or the main light source is the sun and the sun is located between the car light and the target area to be measured; the applicable detection scenarios of the P2 sub-model include: the main light source is a car light and the sun is located between the car light and the target area to be measured, or the main light source is the sun and the car light is located between the target area to be measured and the sun; the applicable detection scenarios of the P3 sub-model include: the main light source is a car light and the target area to be measured is located between the car light and the sun, or the main light source is the sun and the target area to be measured is located between the car light and the sun.

7. The puddle identification method according to any one of claims 1 to 6, characterized in that: Training the puddle detection model and the ice surface detection model using a pre-collected training data set; The training data set includes the latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data and lidar data of the target puddle / target ice surface obtained at different time points and different geographical locations, the calculated altitude angle data, main light source position information, calibration matrix and vehicle light intensity data, as well as the empirical values ​​of puddle reflectivity, ice surface reflectivity and ground reflectivity obtained by testing.

8. A puddle identification system, characterized in that: The system comprises: The first processing module is configured to obtain latitude and longitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data and laser radar data of the target area to be measured; The second processing module is configured to calculate the current altitude angle of the target area to be measured based on the acquired latitude and longitude data and time data; A third processing module is configured to determine the current main light source position information according to the acquired ambient light intensity data and reflectivity data; A fourth processing module is configured to calibrate the collected camera data and lidar data to obtain a current calibration matrix; The fifth processing module is configured to bring the longitude and latitude data, elevation data, temperature data, time data, ambient light intensity data, reflectivity data, image data, lidar data, current altitude angle, current main light source position information, current calibration matrix and current vehicle light intensity data into a pre-established puddle detection model and / or ice surface detection model for processing to determine whether the target area to be measured is a puddle or an ice surface.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps in a puddle identification method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the puddle identification method described in any one of claims 1 to 7 are implemented.

Images