Snowfall detection method, device, computer equipment and readable storage medium

Abstract

The present application relates to a snowfall detection method, device, computer equipment and readable storage medium. The method comprises: obtaining a target image of a target area through a high-sensitivity imaging component, and detecting whether the target image includes snowfall; if the target image includes snowfall, classifying the target image using a snow amount classification model to obtain a snow amount level corresponding to the target area, the snow amount level is used to characterize the snowfall intensity of the target area; based on the snow amount level, obtaining a snowfall visibility value corresponding to the target area. The method can provide all-weather multi-dimensional snowfall detection data to reduce safety accidents.

Description

Technical Field

[0001] The present application relates to the field of meteorological detection technology, and in particular to a snowfall detection method, device, computer equipment and readable storage medium. Background Art

[0002] Snow is solid water in the form of snowflakes that falls to the ground from mixed clouds. It is precipitation composed of a large number of white opaque ice crystals (snow crystals) and their polymers (snow balls). Snow only appears under very cold temperatures and the influence of temperate cyclones.

[0003] The traditional snowfall observation method is generally to observe the snowfall manually. The snowfall is measured by meteorological observers who collect snow from the rain gauge at the observation site and melt it into water indoors, then pour it into the measuring cylinder to obtain the precipitation. Just like rainfall, snowfall refers to the amount of snowfall in a certain period of time.

[0004] However, the above-mentioned method of manual observation of snowfall cannot provide all-weather multi-dimensional snowfall detection data for areas with high safety requirements such as airports and highways, which can easily lead to safety accidents. Summary of the invention

[0005] Based on this, it is necessary to provide a snowfall detection method, device, computer equipment and readable storage medium that can provide multi-dimensional snowfall detection data around the clock and reduce safety accidents in response to the above-mentioned technical problems.

[0006] In a first aspect, an embodiment of the present application provides a snowfall detection method, the method comprising:

[0007] Acquire a target image of a target area through a high-sensitivity imaging component, and detect whether the target image includes snowfall;

[0008] If the target image includes snowfall, the target image is classified using a snow amount classification model to obtain a snow amount level corresponding to the target area, where the snow amount level is used to characterize the snowfall intensity of the target area;

[0009] Based on the snow level, a snowfall visibility value corresponding to the target area is obtained.

[0010] In one embodiment, the target area includes at least one target object, and obtaining the snowfall visibility value corresponding to the target area based on the snow level includes:

[0011] Intercepting imaging images corresponding to each of the targets from the target image, and acquiring a clarity level corresponding to each of the targets according to each of the imaging images and a clarity classification model, wherein the clarity level is used to characterize the clarity of the imaging of the corresponding target in the target image;

[0012] Based on the snow amount level and the clarity level corresponding to each of the target objects, the snowfall visibility value corresponding to the target area is obtained.

[0013] In one embodiment, obtaining the snowfall visibility value corresponding to the target area based on the snow amount level and the clarity level corresponding to each target object includes:

[0014] For each of the target objects, according to the snow amount level and the clarity level corresponding to the target object, searching for a visibility coefficient corresponding to the target object, wherein the visibility coefficient is negatively correlated with the snowfall intensity of the target area represented by the snow amount level, and the visibility coefficient is positively correlated with the clarity level corresponding to the target object;

[0015] Detecting the target distance between the target object and the high-sensitivity imaging component;

[0016] According to the target distance corresponding to each of the target objects and the visibility coefficient corresponding to each of the target objects, the snowfall visibility value corresponding to the target area is obtained.

[0017] In one embodiment, obtaining the snowfall visibility value corresponding to the target area according to the target distance corresponding to each target object and the visibility coefficient corresponding to each target object includes:

[0018] For each target object, multiply the target distance corresponding to the target object and the visibility coefficient corresponding to the target object to obtain a multiplication result;

[0019] The average value of the multiplication results corresponding to each of the target objects is calculated to obtain the snowfall visibility value corresponding to the target area.

[0020] In one embodiment, after obtaining the snow visibility value corresponding to the target area based on the snow level, the method further includes:

[0021] Acquire snowfall data corresponding to the target area through a snow depth sensor, wherein the snowfall data includes at least one of snowfall depth and precipitation corresponding to the target area;

[0022] According to a preset snow level classification standard, detecting whether the snow level matches the snowfall data, and detecting whether the snow level matches the snowfall visibility value, the snow level classification standard including a matching relationship between a standard snow level and a standard snowfall visibility value, and the snow level classification standard also including a matching relationship between a standard snow level and a standard snowfall data;

[0023] If the snow level matches the snowfall data, and the snow level matches the snowfall visibility value, then the snowfall visibility value is output.

[0024] In one embodiment, the method further comprises:

[0025] Acquiring environmental data corresponding to the target area through an environmental sensor;

[0026] Detecting whether the environmental data meets a preset condition, wherein the preset condition is related to a meteorological factor causing snowfall;

[0027] Correspondingly, the step of acquiring a target image of a target area by using a high-sensitivity imaging component includes:

[0028] If the environmental data meets the preset conditions, a target image of the target area is acquired through a high-sensitivity imaging component.

[0029] In one embodiment, the method further comprises:

[0030] Measuring the target brightness value corresponding to the target area by using a light meter brightness meter;

[0031] Searching a preset parameter adjustment table according to the target brightness value to obtain a target imaging parameter corresponding to the target brightness value, wherein the parameter adjustment table includes a mapping relationship between each brightness value and each imaging parameter;

[0032] The target imaging parameters are set as working parameters of the high-sensitivity imaging component.

[0033] In a second aspect, an embodiment of the present application provides a snowfall detection device, the device comprising:

[0034] A first acquisition module, used to acquire a target image of a target area through a high-sensitivity imaging component, and detect whether the target image includes snowfall;

[0035] A classification module, for classifying the target image using a snow amount classification model if the target image includes snowfall, to obtain a snow amount level corresponding to the target area, wherein the snow amount level is used to characterize the snowfall intensity of the target area;

[0036] The second acquisition module is used to acquire the snowfall visibility value corresponding to the target area based on the snow level.

[0037] In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method of the first aspect when executing the computer program.

[0038] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method of the first aspect described above.

[0039] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least:

[0040] A target image of a target area is acquired through a high-sensitivity imaging component, and it is detected whether the target image includes snowfall; if the target image includes snowfall, a snow amount classification model is used to classify the target image to obtain the snow amount level corresponding to the target area; based on the snow amount level, a snowfall visibility value corresponding to the target area is acquired; thus, the target image of the target area is acquired through a high-sensitivity imaging component. Due to its high-sensitivity characteristics, the high-sensitivity imaging component can collect target images similar to daytime imaging effects even at night or in poor light environments, thereby avoiding the problem of obstructed vision at night and inability to observe manually, thereby realizing all-weather snowfall detection in the target area; in addition, in the case that the target image includes snowfall, a snow amount classification model is used to obtain a snow amount level for characterizing the snowfall intensity in the target area, and the snowfall visibility value of the target area is obtained based on the snow amount level, thereby obtaining the snow amount level and snowfall visibility value of the target area; the problem of only manually observing the snow amount in traditional technology, failing to provide multi-dimensional snowfall detection data for areas with high safety requirements such as airports and highways, which is prone to safety accidents, is avoided. The embodiment of the present application can obtain all-weather multi-dimensional snowfall detection data for the target area, which is helpful to reduce the probability of safety accidents in the target area. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 1 is a schematic diagram of a process of a snowfall detection method in an embodiment;

[0042] Figure 2 is a schematic diagram of detailed steps of step S300 in another embodiment;

[0043] Figure 3 is a schematic diagram of detailed steps of step S302 in another embodiment;

[0044] Figure 4 is a schematic flow chart of a snowfall detection method in another embodiment;

[0045] Figure 5 is a schematic flow chart of a snowfall detection method in another embodiment;

[0046] Figure 6 is a schematic flow chart of a snowfall detection method in another embodiment;

[0047] Figure 7is a structural block diagram of a snowfall detection device in one embodiment;

[0048] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] The snowfall detection method, device, computer equipment, and readable storage medium provided in the embodiments of the present application are intended to solve the technical problem that the traditional technology cannot provide all-weather multi-dimensional snowfall detection data for areas with high safety requirements such as airports and highways through manual observation of snowfall, which is easy to cause safety accidents. The technical solution of the present application will be described in detail below through embodiments and in conjunction with the accompanying drawings. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0051] It should be noted that the snowfall detection method provided in the embodiment of the present application may be executed by a snowfall detection device, which may be implemented as part or all of a computer device through software, hardware, or a combination of software and hardware, and the computer device may be a server. In the following method embodiments, the execution subject is a computer device as an example for explanation. It is understandable that the snowfall detection method provided in the following method embodiments may also be applied to a terminal, and may also be applied to a system including a terminal and a server, and may be implemented through the interaction between the terminal and the server.

[0052] In one embodiment, Figure 1 As shown, a snowfall detection method is provided, comprising the following steps:

[0053] Step S100, acquiring a target image of a target area through a high-sensitivity imaging component, and detecting whether the target image includes snowfall.

[0054] In the embodiment of the present application, the target area may be an area where snowfall detection is required, for example, an airport, a highway, or other area with high safety requirements. The computer device controls the high-sensitivity imaging component to collect a target image of the target area. The high-sensitivity imaging component may be a high-sensitivity imager deployed in the target area. The high-sensitivity imaging component may be installed on a rotatable pan / tilt in the target area.

[0055] The embodiment of the present application uses a high-sensitivity imaging component to acquire the target image. The computer device adjusts the working parameters of the high-sensitivity imaging component so that the high-sensitivity imaging component can also collect target images with similar imaging effects during the day at night or in poor light environments. This can achieve all-weather snowfall detection in the target area, expand the time range of snowfall detection, and avoid the problem of manual observation of snow volume in traditional technologies due to obstructed vision at night.

[0056] After acquiring the target image of the target area, the computer device detects whether the target image includes snowfall. In a possible implementation, the computer device may input the target image into a pre-trained snowfall classification model, and classify the target image using the snowfall classification model, which is used to classify whether the target image includes snowfall, thereby determining whether the target image includes snowfall.

[0057] As an implementation method, a computer device may obtain multiple snowfall sample images at different historical moments, and the multiple snowfall sample images may include positive samples and negative samples, wherein the positive samples include snowfall and the negative samples do not include snowfall. Corresponding positive and negative category labels are manually added to the positive and negative samples, and the computer device uses the multiple snowfall sample images with added positive and negative category labels to train an initial snowfall classification model, and obtains a snowfall classification model after the model converges. The initial snowfall classification model can be a classification network model such as a Resnet residual network, a VGG network, etc., and is not specifically limited here.

[0058] Step S200: If the target image includes snowfall, a snow amount classification model is used to classify the target image to obtain a snow amount level corresponding to the target area.

[0059] If the computer device detects that the target image includes snowfall, the target image is classified using a snow amount classification model to obtain the snow amount level corresponding to the target area. The snow amount level is used to characterize the snowfall intensity in the target area. The snow amount levels include "light snow", "moderate snow", "heavy snow", etc.

[0060] In the embodiment of the present application, a plurality of snowfall sample images including snowfall can be manually labeled with snow level according to their corresponding snow intensity, such as a "light snow" label, a "medium snow" label, a "heavy snow" label, and a "blizzard" label. The computer device uses the plurality of snowfall sample images with snow level labels added to train an initial snow classification model. During the training process, the snow level labels corresponding to each snowfall sample image are used as supervision, and the model parameters are iteratively updated. After the model converges, a snow classification model is obtained.

[0061] The computer device inputs the target image into the snow classification model, and obtains the snow level corresponding to the target image output by the snow classification model, that is, the snow level corresponding to the target area. Therefore, the computer device can automatically classify the snow level corresponding to the target area through the snow classification model, avoiding the problem of low automation of snowfall detection and waste of manpower in traditional technology, where meteorological observers need to take the snow collected in the rain gauge of the observation field indoors to melt it into water, and then pour it into the measuring cylinder to obtain precipitation to measure the snow amount.

[0062] Step S300, based on the snow level, obtain the snowfall visibility value corresponding to the target area.

[0063] After the computer device obtains the snow level corresponding to the target area, the snowfall visibility value corresponding to the target area is obtained based on the snow level. In a possible implementation, there may be a target object in the target area, and the target object may be a landmark building. The computer device may obtain the snowfall visibility value corresponding to the target area according to the snow level of the target area and the clarity of the image of the target object in the target image; it can be understood that the greater the snowfall intensity represented by the snow level of the target area, and the less clear the image of the target object in the target image, the smaller the snowfall visibility value corresponding to the target area, and vice versa, the greater the snowfall visibility value corresponding to the target area.

[0064] In another possible implementation, the computer device can also obtain multiple historical snow levels of the target area at different historical moments and the manually observed visibility at each historical moment, and fit the mapping relationship between the historical snow level and the visibility. The computer device searches for the visibility corresponding to the snow level of the target area from the mapping relationship to obtain the snowfall visibility value corresponding to the target area.

[0065] Visibility is an indicator that reflects the transparency of the atmosphere and has important reference significance for flight safety and traffic safety. In the embodiment of the present application, the computer device obtains the snowfall visibility value corresponding to the target area based on the snow level, which can provide more valuable snowfall observation data (snowfall visibility value) for the target area, which is beneficial to the safety control of the target area.

[0066] In this embodiment, a target image of a target area is acquired through a high-sensitivity imaging component, and whether the target image includes snowfall is detected; if the target image includes snowfall, a snow amount classification model is used to classify the target image to obtain a snow amount level corresponding to the target area; based on the snow amount level, a snowfall visibility value corresponding to the target area is acquired; thus, a target image of the target area is acquired through a high-sensitivity imaging component. Due to its high-sensitivity characteristic, the high-sensitivity imaging component can capture a target image similar to the imaging effect during the day even at night or in an environment with poor light, thereby avoiding the problem of obstructed vision at night and inability to observe manually, thereby achieving All-weather snowfall detection; in addition, when the target image includes snowfall, a snow amount classification model is used to obtain the snow amount level used to characterize the snowfall intensity in the target area, and the snowfall visibility value of the target area is obtained based on the snow amount level, so that the snow amount level and snowfall visibility value of the target area can be obtained; this avoids the problem of only manually observing the snow amount in traditional technologies, and failing to provide multi-dimensional snowfall detection data for areas with high safety requirements such as airports and highways, which easily leads to safety accidents. The embodiments of the present application can provide all-weather multi-dimensional snowfall detection data for the target area, which is beneficial to reducing the probability of safety accidents in the target area.

[0067] In one embodiment, in the above Figure 1 Based on the embodiment shown, see Figure 2 , this embodiment relates to a process of how a computer device obtains a snowfall visibility value corresponding to a target area based on the snow level. In this embodiment, the target area includes at least one target object, such as Figure 2 As shown, step S300 in this embodiment may include step S301 and step S302:

[0068] Step S301 , capturing imaging images corresponding to respective target objects from the target image, and obtaining the clarity level corresponding to respective target objects according to the imaging images and the clarity classification model.

[0069] As an implementation method, when the high-sensitivity imaging component is deployed in the target area, one or more landmark buildings can be selected in the target area as target objects. The landmark buildings may be houses, signal towers, mountains, etc., which do not obstruct each other in the imaging picture of the high-sensitivity imaging component. The distance between each target object and the high-sensitivity imaging component may be different.

[0070] In a possible implementation, the computer device may use a target detection algorithm to detect and obtain the position frame coordinates corresponding to each target object from the target image, each position frame coordinate corresponds to the position of the imaging area of ​​each target object in the target image, and the computer device intercepts the area corresponding to each position frame coordinate from the target image to obtain the imaging image corresponding to each target object. In another possible implementation, the position frame coordinates corresponding to each target object may also be manually input into the computer device, which is not specifically limited here.

[0071] The computer device adjusts the size of each captured image so that the size of each adjusted image meets the input size of the clarity classification model; the computer device inputs each adjusted image into the clarity classification model to obtain the clarity level corresponding to each target object, and the clarity level is used to characterize the clarity of the corresponding target object in the target image. For example, the clarity level "3" means clearly visible, "2" means visible appearance, "1" means visible outline or "0" means invisible, wherein the clarity of the corresponding targets in the target image corresponding to clearly visible, visible appearance, visible outline and invisible decreases in sequence.

[0072] In a possible implementation, a computer device may collect multiple clarity sample images of different visibility during snowfall, each clarity sample image including manually annotated clarity level labels of each target object imaged in the clarity sample image and the position of each target object; for example, a clarity level label "0" indicates that the target object is not visible in the clarity sample image, a clarity level label "1" indicates that the outline of the target object is visible in the clarity sample image, a clarity level label "2" indicates that the appearance of the target object is visible in the clarity sample image, and a clarity level label "3" indicates that the target object is clearly visible in the clarity sample image, and the position of each target object may be a position box coordinate. The computer device trains an initial clarity classification model based on the multiple clarity sample images, and the initial clarity classification model may be a classification network model such as a Resnet residual network, which is not specifically limited here.

[0073] In a possible implementation, the initial clarity classification model can be a Resnet classification network structure constructed by 21 convolutional layers, 21 batchnorm layers, 21 scale layers, 17 relu activation layers, 8 eltwise layers, 2 pooling layers, and 1 fully connected layer. The computer device intercepts the image corresponding to each target object from multiple clarity sample images according to the position of each target object, and normalizes each intercepted image, such as subtracting 104, 117, and 124 from the three-channel pixel values ​​of each pixel point of each intercepted image, and scaling each intercepted image to a preset size to obtain an input image, and then input each input image and the corresponding clarity level label into the initial clarity classification model, and the computer device calculates the loss value CE according to formula 1:

[0074]

[0075] Where c represents the number of clarity levels, s i represents the predicted probability that the input image belongs to the i-th category, t i It represents the actual probability that the input image belongs to the i-th category. The computer device calculates the back propagation gradient according to the loss value and iteratively updates the model parameters. When the loss value tends to stabilize to about 0.01 or a smaller value, it is determined that the model converges and a clarity classification model is obtained.

[0076] Step S302, based on the snow level and the clarity level corresponding to each target object, obtain the snowfall visibility value corresponding to the target area.

[0077] The computer device obtains the snowfall visibility value corresponding to the target area based on the snow amount level in the target area and the clarity level corresponding to each target object.

[0078] In a possible implementation of step S302, see Figure 3 , the computer device can execute Figure 3 Steps S3021, S3022 and S3023 shown in the figure implement the process of obtaining the snowfall visibility value corresponding to the target area based on the snow level and the clarity level corresponding to each target object:

[0079] Step S3021, for each target object, according to the snow level and the clarity level corresponding to the target object, find the visibility coefficient corresponding to the target object.

[0080] In an embodiment of the present application, a mapping relationship among snow amount level, clarity level and visibility coefficient is stored in a computer device. The mapping relationship among the three is as follows: when the snow amount level is "light snow" and the clarity level is "3" (clearly visible), the corresponding visibility coefficient is 2.5; when the snow amount level is "medium snow" and the clarity level is "2" (visible in appearance), the corresponding visibility coefficient is 1.5; when the snow amount level is "heavy snow" and the clarity level is "1" (visible in outline), the corresponding visibility coefficient is 1; when the snow amount level is "blizzard" and the clarity level is "0" (invisible), the corresponding visibility coefficient is 0.

[0081] For each target object, the computer device searches for the visibility coefficient corresponding to the snow amount level of the target area and the clarity level of the target object from the mapping relationship between the three, and obtains the visibility coefficient corresponding to the target object, wherein the visibility coefficient is negatively correlated with the snowfall intensity in the target area represented by the snow amount level, and the visibility coefficient is positively correlated with the clarity level corresponding to the target object, that is, the smaller the snowfall intensity in the target area and the clearer the image of the target object in the target image, the larger the visibility coefficient corresponding to the target object.

[0082] Step S3022, detecting the target distance between the target object and the high-sensitivity imaging component.

[0083] For each target object, the computer device measures the distance between each target object and the high-sensitivity imaging component through a rangefinder or a total station to obtain the target distance between each target object and the high-sensitivity imaging component.

[0084] In a possible implementation, the computer device can control a rangefinder or a total station to measure the target distance between each target object and a high-sensitivity imaging component under good weather conditions, such as a sunny day, thereby helping to improve the accuracy of the measurement.

[0085] Step S3023, obtaining the snowfall visibility value corresponding to the target area according to the target distance corresponding to each target object and the visibility coefficient corresponding to each target object.

[0086] Taking the case where the target area includes a target object, the computer device calculates the product of the target distance corresponding to the target object and the visibility coefficient corresponding to the target object, and the product is the snowfall visibility value corresponding to the target area.

[0087] In another possible implementation of step S3023, taking the target area including multiple targets as an example, step S3023 may include the following steps A1 and A2:

[0088] Step A1: for each target object, multiply the target distance corresponding to the target object and the visibility coefficient corresponding to the target object to obtain a multiplication result.

[0089] Step A2, calculating the average value of the multiplication results corresponding to each target object to obtain the snowfall visibility value corresponding to the target area.

[0090] When the target area includes multiple target objects, for each target object, the computer device calculates the product of the target distance corresponding to the target object and the visibility coefficient corresponding to the target object, and obtains the multiplication result corresponding to the target object; the computer device further calculates the arithmetic mean of the multiplication results corresponding to each target object, and obtains the snowfall visibility value corresponding to the target area.

[0091] This embodiment captures imaging images corresponding to each target object from the target image, obtains the clarity level corresponding to each target object based on each imaging image and a clarity classification model, and obtains the snowfall visibility value corresponding to the target area based on the snow amount level and the clarity level corresponding to each target object. Thus, the visibility value of the target area can be accurately calculated in combination with the snow amount level of the target area and the clarity level corresponding to the target object. Visibility is an indicator reflecting the transparency of the atmosphere and has important reference significance for flight safety and traffic safety. By calculating the snowfall visibility value of the target area, the computer equipment can provide the target area with more valuable snowfall visibility values ​​as snowfall detection data, which is beneficial to the safety control of the target area.

[0092] In one embodiment, in the above Figure 1 Based on the embodiment shown, see Figure 4 This embodiment relates to a process of how a computer device verifies the accuracy of the snow visibility value in a target area. Figure 4 As shown, the snowfall detection method of this embodiment further includes step S401, step S402 and step S403:

[0093] Step S401, obtaining snowfall data corresponding to the target area through a snow depth sensor.

[0094] The snow depth sensor may be deployed in the target area. The snow depth sensor may be deployed at the junction of the bottom of the high-sensitivity imaging component and the ground. The initial value of the snow depth sensor may be set to 0. The computer device obtains the snowfall data corresponding to the target area through the snow depth sensor. The snowfall data may include at least one of the snowfall depth and precipitation corresponding to the target area. The precipitation may be measured after the snowfall in a preset time period (e.g., 24 hours) is melted into water. Taking the snowfall data including the snowfall depth and precipitation corresponding to the target area as an example, for example, the computer device obtains the snowfall depth (ground snow depth) of the target area through the snow depth sensor as 2 cm and the precipitation as 2 mm.

[0095] Step S402, based on the preset snow level classification standard, detect whether the snow level matches the snowfall data, and detect whether the snow level matches the snowfall visibility value.

[0096] Among them, the snow level classification standard includes the matching relationship between the standard snow level and the standard snowfall visibility value. The snow level classification standard also includes the matching relationship between the standard snow level and the standard snowfall data. For example, the standard snow level "light snow" matches the standard snowfall visibility value equal to or greater than 1000 meters, and the matching standard snowfall data is snowfall depth less than 3 cm and precipitation between 0.1 and 2.4 mm; the standard snow level "medium snow" matches the standard snowfall visibility value between 500 and 1000 meters, and the matching standard snowfall data is snowfall depth of 3 to 5 cm and precipitation between 2.5 and 4.9 mm; the standard snow level "heavy snow" matches the standard snowfall visibility value less than 500 meters, and the matching standard snowfall data is snowfall depth equal to or greater than 5 cm and precipitation between 5.0 and 9.9 mm, and so on.

[0097] The computer device detects whether the snow level of the target area matches the snowfall data of the target area according to the snow level classification standard, and detects whether the snow level of the target area matches the snowfall visibility value of the target area. For example, the snow level corresponding to the target area obtained by the computer device is "light snow", the snowfall visibility value of the target area is 1200 meters, the snowfall depth of the target area is 2 centimeters and the precipitation is 2 millimeters. The computer device matches the standard snowfall visibility value equal to or greater than 1000 meters according to the standard snow level "light snow" in the snow level classification standard, and the matching standard snowfall data is that the snowfall depth is less than 3 centimeters and the precipitation is between 0.1 and 2.4 millimeters. The computer device determines that the snow level corresponding to the target area matches the snowfall data, and determines that the snow level of the target area matches the snowfall visibility value.

[0098] Step S403: If the snow level matches the snowfall data, and the snow level matches the snowfall visibility value, then the snowfall visibility value is output.

[0099] If the computer device determines that the snow level of the target area matches the snowfall data of the target area, and the snow level of the target area matches the snowfall visibility value of the target area, then the snowfall visibility value and snow level of the target area calculated by the computer device are accurate, and the computer device outputs the snowfall visibility value, or can also output the snowfall visibility value and snow level.

[0100] In this embodiment, in order to avoid the computer device capturing the target image with a single high-sensitivity imaging component, the snow accumulation on the lens of the high-sensitivity imaging component may affect the observation quality, resulting in accidental errors in the snowfall visibility values ​​corresponding to the target area detected by the computer device. Therefore, the computer device verifies the accuracy of the snowfall visibility values ​​corresponding to the target area in combination with the snow depth sensor, which can improve the accuracy of the snowfall visibility values ​​corresponding to the target area.

[0101] In one embodiment, in the above Figure 1 Based on the embodiment shown, see Figure 5 , this embodiment relates to a process of how a computer device detects snowfall in a target area in combination with environmental data of the target area. In this embodiment, Figure 5 As shown, the snowfall detection method of this embodiment further includes step S501 and step S502:

[0102] Step S501: Acquire environmental data corresponding to a target area through an environmental sensor.

[0103] In the embodiment of the present application, the environmental data may include, for example, the temperature and air humidity corresponding to the target area, and the computer device obtains the environmental data corresponding to the target area through the environmental sensor.

[0104] Step S502, detecting whether the environmental data meets a preset condition, wherein the preset condition is related to the meteorological factors causing snowfall.

[0105] The computer device determines the preset condition that the temperature included in the environmental data is lower than the preset temperature threshold and the air humidity included is greater than the preset humidity threshold based on the meteorological factors that make snowfall easy to form. The computer device detects whether the temperature included in the environmental data is lower than the preset temperature threshold and whether the air humidity is greater than the preset humidity threshold.

[0106] Correspondingly, step S100 includes:

[0107] Step S101, if the environmental data meets the preset conditions, a target image of the target area is acquired through a high-sensitivity imaging component, and it is detected whether the target image includes snowfall.

[0108] If the computer device detects that the temperature included in the environmental data is lower than a preset temperature threshold and the air humidity is greater than a preset humidity threshold, it is determined that the environmental data meets the preset conditions. The environmental data meeting the preset conditions indicates that the environment corresponding to the target area is prone to snowfall. When the environmental data meets the preset conditions, the computer device controls the high-sensitivity imaging component to obtain a target image of the target area and detects whether the target image includes snowfall, thereby extending the life of the high-sensitivity imaging component and improving the accuracy of snowfall detection.

[0109] In one embodiment, in the above Figure 1 Based on the embodiment shown, see Figure 6 This embodiment relates to a process of how a computer device automatically adjusts the working parameters of a high-sensitivity imaging component. Figure 6 As shown, the snowfall detection method of this embodiment also includes:

[0110] Step S601, measuring a target brightness value corresponding to a target area by using a light meter.

[0111] The computer device measures the target brightness value corresponding to the target area through a photometer brightness meter. Different target brightness values ​​represent different light intensities in the target area. The larger the target brightness value, the higher the light intensity of the target area.

[0112] Step S602: searching a preset parameter adjustment table according to the target brightness value to obtain a target imaging parameter corresponding to the target brightness value.

[0113] The parameter adjustment table includes the mapping relationship between each brightness value and each imaging parameter.

[0114] In an embodiment of the present application, the mapping relationship between each brightness value and each imaging parameter can be obtained by a computer device fitting the brightness value of the light meter and the imaging parameters of the corresponding high-sensitivity imaging component at multiple historical moments, and the imaging parameters include exposure, gain, noise reduction, etc.

[0115] The computer device searches a preset parameter adjustment table according to the target brightness value to obtain the target imaging parameter corresponding to the target brightness value.

[0116] Step S603, setting the target imaging parameters as the working parameters of the high-sensitivity imaging component.

[0117] In a possible implementation manner, the parameter adjustment table is shown in Table 1:

[0118] Luminance agc mshutter denoise 0 0x00 0x4f 0x07 (0，750] 0x0c 0x49 0x05 (750，2700] 0x00 0x40 0x00 (2700，∞) 0x00 0x4a 0x05

[0119] Table 1

[0120] Among them, Luminance is the lumen value (brightness value) of the light meter, agc is gain, mshutter is exposure, and denoise is noise reduction.

[0121] As shown in Table 1, when the target brightness value is 0, the computer device adjusts the AGC of the high-sensitivity imaging component to 0x00, mshutter to 0x4f, and denoise to 0x07; when the target brightness value is 0-750, the computer device adjusts the AGC of the high-sensitivity imaging component to 0x0c, mshutter to 0x49, and denoise to 0x05; when the target brightness value is 750-2700, the computer device adjusts the AGC of the high-sensitivity imaging component to 0x00, mshutter to 0x40, and denoise to 0x00; when the target brightness value is greater than 2700, the computer device adjusts the AGC of the high-sensitivity imaging component to 0x00, mshutter to 0x0f, and denoise to 0x07.

[0122] Therefore, the computer equipment can adaptively adjust the working parameters of the high-sensitivity imaging component based on the target brightness value corresponding to the target area measured by the light meter brightness meter, without the need for manual adjustment, thereby improving the timeliness of the adjustment of the working parameters of the high-sensitivity imaging component, thereby ensuring the effect of the target image captured by the high-sensitivity imaging component, and further improving the accuracy of snowfall detection.

[0123] It should be understood that although Figure 1-6 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1-6 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0124] In one embodiment, Figure 7 As shown, a snowfall detection device is provided, comprising:

[0125] A first acquisition module 10 is used to acquire a target image of a target area through a high-sensitivity imaging component, and detect whether the target image includes snowfall;

[0126] A classification module 20, for classifying the target image using a snow amount classification model if the target image includes snowfall, to obtain a snow amount level corresponding to the target area, wherein the snow amount level is used to characterize the snowfall intensity of the target area;

[0127] The second acquisition module 30 is used to acquire the snowfall visibility value corresponding to the target area based on the snow level.

[0128] In one embodiment, the target area includes at least one target object, and the second acquisition module 30 includes:

[0129] A clarity acquisition unit, used to intercept imaging images corresponding to each of the targets from the target image, and acquire a clarity level corresponding to each of the targets according to each of the imaging images and a clarity classification model, wherein the clarity level is used to characterize the clarity of the imaging of the corresponding target in the target image;

[0130] The visibility acquisition unit is used to acquire the snowfall visibility value corresponding to the target area based on the snow amount level and the clarity level corresponding to each of the target objects.

[0131] In one embodiment, the visibility acquisition unit is specifically used to find the visibility coefficient corresponding to each target object according to the snow amount level and the clarity level corresponding to the target object, the visibility coefficient is negatively correlated with the snowfall intensity of the target area represented by the snow amount level, and the visibility coefficient is positively correlated with the clarity level corresponding to the target object; detect the target distance between the target object and the high-sensitivity imaging component; and acquire the snowfall visibility value corresponding to the target area according to the target distance corresponding to each target object and the visibility coefficient corresponding to each target object.

[0132] In one embodiment, the visibility acquisition unit is specifically used to multiply the target distance corresponding to the target object and the visibility coefficient corresponding to the target object for each target object to obtain a multiplication result; calculate the average value of the multiplication results corresponding to each target object to obtain the snowfall visibility value corresponding to the target area.

[0133] In one embodiment, the apparatus further comprises:

[0134] A third acquisition module is used to acquire snowfall data corresponding to the target area through a snow depth sensor, wherein the snowfall data includes at least one of snowfall depth and precipitation corresponding to the target area;

[0135] a first detection module, configured to detect whether the snow level matches the snowfall data and whether the snow level matches the snowfall visibility value according to a preset snow level classification standard, wherein the snow level classification standard includes a matching relationship between a standard snow level and a standard snowfall visibility value, and the snow level classification standard also includes a matching relationship between a standard snow level and a standard snowfall data;

[0136] A matching confirmation module is used to output the snowfall visibility value if the snow level matches the snowfall data and the snow level matches the snowfall visibility value.

[0137] In one embodiment, the apparatus further comprises:

[0138] A fourth acquisition module, used to acquire environmental data corresponding to the target area through an environmental sensor;

[0139] A second detection module is used to detect whether the environmental data meets a preset condition, wherein the preset condition is related to a meteorological factor causing snowfall;

[0140] Correspondingly, the first acquisition module 10 is specifically configured to acquire a target image of a target area through a high-sensitivity imaging component if the environmental data meets the preset condition.

[0141] In one embodiment, the apparatus further comprises:

[0142] A measuring module, used for measuring a target brightness value corresponding to the target area by using a photometer brightness meter;

[0143] A search module, used to search a preset parameter adjustment table according to the target brightness value to obtain a target imaging parameter corresponding to the target brightness value, wherein the parameter adjustment table includes a mapping relationship between each brightness value and each imaging parameter;

[0144] A setting module is used to set the target imaging parameters as working parameters of the high-sensitivity imaging component.

[0145] The specific definition of the snowfall detection device can be found in the definition of the snowfall detection method above, which will not be repeated here. Each module in the above-mentioned snowfall detection device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0146] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data of the snowfall detection method. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a snowfall detection method is implemented.

[0147] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0148] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0149] Acquire a target image of a target area through a high-sensitivity imaging component, and detect whether the target image includes snowfall;

[0150] If the target image includes snowfall, the target image is classified using a snow amount classification model to obtain a snow amount level corresponding to the target area, where the snow amount level is used to characterize the snowfall intensity of the target area;

[0151] Based on the snow level, a snowfall visibility value corresponding to the target area is obtained.

[0152] In one embodiment, the target area includes at least one target object, and the processor further implements the following steps when executing the computer program:

[0153] Intercepting imaging images corresponding to each of the targets from the target image, and acquiring a clarity level corresponding to each of the targets according to each of the imaging images and a clarity classification model, wherein the clarity level is used to characterize the clarity of the imaging of the corresponding target in the target image;

[0154] Based on the snow amount level and the clarity level corresponding to each of the target objects, the snowfall visibility value corresponding to the target area is obtained.

[0155] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0156] For each of the target objects, according to the snow amount level and the clarity level corresponding to the target object, searching for a visibility coefficient corresponding to the target object, wherein the visibility coefficient is negatively correlated with the snowfall intensity of the target area represented by the snow amount level, and the visibility coefficient is positively correlated with the clarity level corresponding to the target object;

[0157] Detecting the target distance between the target object and the high-sensitivity imaging component;

[0158] According to the target distance corresponding to each of the target objects and the visibility coefficient corresponding to each of the target objects, the snowfall visibility value corresponding to the target area is obtained.

[0159] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0160] For each target object, multiply the target distance corresponding to the target object and the visibility coefficient corresponding to the target object to obtain a multiplication result;

[0161] The average value of the multiplication results corresponding to each of the target objects is calculated to obtain the snowfall visibility value corresponding to the target area.

[0162] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0163] Acquire snowfall data corresponding to the target area through a snow depth sensor, wherein the snowfall data includes at least one of snowfall depth and precipitation corresponding to the target area;

[0164] According to a preset snow level classification standard, detecting whether the snow level matches the snowfall data, and detecting whether the snow level matches the snowfall visibility value, the snow level classification standard including a matching relationship between a standard snow level and a standard snowfall visibility value, and the snow level classification standard also including a matching relationship between a standard snow level and a standard snowfall data;

[0165] If the snow level matches the snowfall data, and the snow level matches the snowfall visibility value, then the snowfall visibility value is output.

[0166] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0167] Acquiring environmental data corresponding to the target area through an environmental sensor;

[0168] Detecting whether the environmental data meets a preset condition, wherein the preset condition is related to a meteorological factor causing snowfall;

[0169] Correspondingly, the step of acquiring a target image of a target area by using a high-sensitivity imaging component includes:

[0170] If the environmental data meets the preset conditions, a target image of the target area is acquired through a high-sensitivity imaging component.

[0171] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0172] Measuring the target brightness value corresponding to the target area by using a light meter brightness meter;

[0173] Searching a preset parameter adjustment table according to the target brightness value to obtain a target imaging parameter corresponding to the target brightness value, wherein the parameter adjustment table includes a mapping relationship between each brightness value and each imaging parameter;

[0174] The target imaging parameters are set as working parameters of the high-sensitivity imaging component.

[0175] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0176] Acquire a target image of a target area through a high-sensitivity imaging component, and detect whether the target image includes snowfall;

[0177] If the target image includes snowfall, the target image is classified using a snow amount classification model to obtain a snow amount level corresponding to the target area, where the snow amount level is used to characterize the snowfall intensity of the target area;

[0178] Based on the snow level, a snowfall visibility value corresponding to the target area is obtained.

[0179] In one embodiment, the target area includes at least one target object, and the computer program, when executed by a processor, further implements the following steps:

[0180] Intercepting imaging images corresponding to each of the targets from the target image, and acquiring a clarity level corresponding to each of the targets according to each of the imaging images and a clarity classification model, wherein the clarity level is used to characterize the clarity of the imaging of the corresponding target in the target image;

[0181] Based on the snow amount level and the clarity level corresponding to each of the target objects, the snowfall visibility value corresponding to the target area is obtained.

[0182] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0183] For each of the target objects, according to the snow amount level and the clarity level corresponding to the target object, searching for a visibility coefficient corresponding to the target object, wherein the visibility coefficient is negatively correlated with the snowfall intensity of the target area represented by the snow amount level, and the visibility coefficient is positively correlated with the clarity level corresponding to the target object;

[0184] Detecting the target distance between the target object and the high-sensitivity imaging component;

[0185] According to the target distance corresponding to each of the target objects and the visibility coefficient corresponding to each of the target objects, the snowfall visibility value corresponding to the target area is obtained.

[0186] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0187] For each target object, multiply the target distance corresponding to the target object and the visibility coefficient corresponding to the target object to obtain a multiplication result;

[0188] The average value of the multiplication results corresponding to each of the target objects is calculated to obtain the snowfall visibility value corresponding to the target area.

[0189] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0190] Acquire snowfall data corresponding to the target area through a snow depth sensor, wherein the snowfall data includes at least one of snowfall depth and precipitation corresponding to the target area;

[0191] According to a preset snow level classification standard, detecting whether the snow level matches the snowfall data, and detecting whether the snow level matches the snowfall visibility value, the snow level classification standard including a matching relationship between a standard snow level and a standard snowfall visibility value, and the snow level classification standard also including a matching relationship between a standard snow level and a standard snowfall data;

[0192] If the snow level matches the snowfall data, and the snow level matches the snowfall visibility value, then the snowfall visibility value is output.

[0193] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0194] Acquiring environmental data corresponding to the target area through an environmental sensor;

[0195] Detecting whether the environmental data meets a preset condition, wherein the preset condition is related to a meteorological factor causing snowfall;

[0196] Correspondingly, the step of acquiring a target image of a target area by using a high-sensitivity imaging component includes:

[0197] If the environmental data meets the preset conditions, a target image of the target area is acquired through a high-sensitivity imaging component.

[0198] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0199] Measuring the target brightness value corresponding to the target area by using a light meter brightness meter;

[0200] Searching a preset parameter adjustment table according to the target brightness value to obtain a target imaging parameter corresponding to the target brightness value, wherein the parameter adjustment table includes a mapping relationship between each brightness value and each imaging parameter;

[0201] The target imaging parameters are set as working parameters of the high-sensitivity imaging component.

[0202] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0203] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are 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.

[0204] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof 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 a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A snowfall detection method, It is characterized in that The method comprises: Acquiring a target image of a target area through a high-sensitivity imaging component, and detecting whether the target image includes snowfall, wherein the target area includes at least one target object; If the target image includes snowfall, the target image is classified using a snow amount classification model to obtain a snow amount level corresponding to the target area, where the snow amount level is used to characterize the snowfall intensity of the target area; Based on the snow level, obtaining a snowfall visibility value corresponding to the target area; The obtaining, based on the snow level, a snowfall visibility value corresponding to the target area includes: Intercepting imaging images corresponding to each of the targets from the target image, and acquiring a clarity level corresponding to each of the targets according to each of the imaging images and a clarity classification model, wherein the clarity level is used to characterize the clarity of the imaging of the corresponding target in the target image; Based on the snow level and the clarity level corresponding to each of the target objects, obtaining a snowfall visibility value corresponding to the target area; The obtaining, based on the snow amount level and the clarity level corresponding to each of the target objects, a snowfall visibility value corresponding to the target area includes: For each of the target objects, according to the snow amount level and the clarity level corresponding to the target object, searching for a visibility coefficient corresponding to the target object, wherein the visibility coefficient is negatively correlated with the snowfall intensity of the target area represented by the snow amount level, and the visibility coefficient is positively correlated with the clarity level corresponding to the target object; Detecting the target distance between the target object and the high-sensitivity imaging component; According to the target distance corresponding to each of the target objects and the visibility coefficient corresponding to each of the target objects, the snowfall visibility value corresponding to the target area is obtained.

2. The method according to claim 1, It is characterized in that The obtaining, according to the target distance corresponding to each of the target objects and the visibility coefficient corresponding to each of the target objects, the snowfall visibility value corresponding to the target area includes: For each target object, multiply the target distance corresponding to the target object and the visibility coefficient corresponding to the target object to obtain a multiplication result; The average value of the multiplication results corresponding to each of the target objects is calculated to obtain the snowfall visibility value corresponding to the target area.

3. The method according to any one of claims 1 to 2, It is characterized in that After obtaining the snowfall visibility value corresponding to the target area based on the snow level, the method further includes: Acquire snowfall data corresponding to the target area through a snow depth sensor, wherein the snowfall data includes at least one of snowfall depth and precipitation corresponding to the target area; According to a preset snow level classification standard, detecting whether the snow level matches the snowfall data, and detecting whether the snow level matches the snowfall visibility value, the snow level classification standard including a matching relationship between a standard snow level and a standard snowfall visibility value, and the snow level classification standard also including a matching relationship between a standard snow level and a standard snowfall data; If the snow level matches the snowfall data, and the snow level matches the snowfall visibility value, then the snowfall visibility value is output.

4. The method according to claim 1, It is characterized in that The method further comprises: Acquiring environmental data corresponding to the target area through an environmental sensor; Detecting whether the environmental data meets a preset condition, wherein the preset condition is related to a meteorological factor causing snowfall; Correspondingly, the step of acquiring a target image of a target area by using a high-sensitivity imaging component includes: If the environmental data meets the preset conditions, a target image of the target area is acquired through a high-sensitivity imaging component.

5. The method according to claim 1, It is characterized in that The method further comprises: Measuring the target brightness value corresponding to the target area by using a light meter brightness meter; Searching a preset parameter adjustment table according to the target brightness value to obtain a target imaging parameter corresponding to the target brightness value, wherein the parameter adjustment table includes a mapping relationship between each brightness value and each imaging parameter; The target imaging parameters are set as working parameters of the high-sensitivity imaging component.

6. A snowfall detection device, It is characterized in that The device comprises: A first acquisition module, configured to acquire a target image of a target area through a high-sensitivity imaging component, and detect whether the target image includes snowfall, wherein the target area includes at least one target object; A classification module, for classifying the target image using a snow amount classification model if the target image includes snowfall, to obtain a snow amount level corresponding to the target area, wherein the snow amount level is used to characterize the snowfall intensity of the target area; A second acquisition module, configured to acquire a snowfall visibility value corresponding to the target area based on the snow level; The second acquisition module is specifically used to intercept the imaging images corresponding to each of the targets from the target image, and obtain the clarity level corresponding to each of the targets based on the imaging images and the clarity classification model, the clarity level is used to characterize the clarity of the imaging of the corresponding target in the target image; for each of the targets, according to the snow amount level and the clarity level corresponding to the target, find the visibility coefficient corresponding to the target, the visibility coefficient is negatively correlated with the snowfall intensity of the target area represented by the snow amount level, and the visibility coefficient is positively correlated with the clarity level corresponding to the target; detect the target distance between the target and the high-sensitivity imaging component; according to the target distance corresponding to each of the targets and the visibility coefficient corresponding to each of the targets, obtain the snowfall visibility value corresponding to the target area.

7. The device according to claim 6, It is characterized in that The device also includes: A fourth acquisition module, used to acquire environmental data corresponding to the target area through an environmental sensor; A second detection module is used to detect whether the environmental data meets a preset condition, wherein the preset condition is related to a meteorological factor causing snowfall; Correspondingly, the first acquisition module is specifically configured to acquire a target image of the target area through a high-sensitivity imaging component if the environmental data meets the preset condition.

8. The device according to claim 6, It is characterized in that The device also includes: A measuring module, used for measuring a target brightness value corresponding to the target area by using a photometer brightness meter; A search module, used to search a preset parameter adjustment table according to the target brightness value to obtain a target imaging parameter corresponding to the target brightness value, wherein the parameter adjustment table includes a mapping relationship between each brightness value and each imaging parameter; A setting module is used to set the target imaging parameters as working parameters of the high-sensitivity imaging component.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images