Vehicle surface bird droppings cleaning method and device, electronic equipment, medium and vehicle

Abstract

The embodiment of the invention relates to the technical field of vehicle cleaning, and discloses a vehicle surface bird droppings cleaning method and device, electronic equipment, a medium and a vehicle. According to the method, the light reflectivity of at least one wave band is collected as the background reference value, the second spectrum is determined based on the background reference value, the subsequent bird droppings detection efficiency can be effectively improved, the light absorptivity corresponding to the first preset wave band and the adjacent wave band is calculated on the basis, and the detection accuracy is improved. And when the light absorptivity of the first preset wave band is greater than the preset absorptivity and the light absorptivity of the adjacent wave band satisfies the preset condition, determining that uric acid exists, identifying the bird droppings in the to-be-detected area based on the light absorptivity, and performing secondary determination by using the bird droppings verification model, thereby further improving the accuracy of bird droppings detection. The problem that bird droppings attached to the vehicle body cannot be cleaned in time at least is solved, the vehicle body is guaranteed to be clean, and the vehicle body using experience of a user is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle cleaning, in particular to a vehicle surface bird droppings cleaning method, device, electronic equipment, medium and vehicle. BACKGROUND

[0002] Bird droppings contain high concentrations of uric acid and salt, which can corrode the paint if left for a long time. Traditional cleaning methods rely on manual observation and manual cleaning, which is inefficient and prone to omissions. In the prior art, vehicle-mounted cleaning systems (such as wipers and water sprayers) are designed only for windshields and cannot cover other parts of the vehicle body. Therefore, there is an urgent need for an automated cleaning solution that can detect in real time and respond quickly. SUMMARY

[0003] The present application aims to provide a vehicle surface bird droppings cleaning method, device, electronic equipment, medium and vehicle to at least solve the problem of not being able to clean bird droppings attached to the vehicle body in time, which is beneficial to ensuring the cleanliness of the vehicle body and improving the user's driving experience.

[0004] To solve the above technical problems, in a first aspect, the present application provides a vehicle surface bird droppings cleaning method, comprising at least:

[0005] Scanning the unpolluted area of the vehicle body and recording at least the light reflectance of at least one wave band in the unpolluted area of the vehicle body as a background reference value;

[0006] Collecting image information of at least one wave band of the area to be detected and determining an ambient light intensity coefficient;

[0007] Determining a second spectrum corresponding to each wave band of image information based on the background reference value, the first spectrum of each wave band of image information and the ambient light intensity coefficient;

[0008] Calculating the light absorption rate corresponding to the first preset wave band and its adjacent wave bands based on at least the second spectrum, and if the light absorption rate of the first preset wave band is greater than a preset absorption rate and the light absorption rate of the adjacent wave bands meets a preset condition, confirming the presence of uric acid;

[0009] Determining the light reflectance ratio of the second preset wave band and the third preset wave band based on at least the second spectrum;

[0010] If the uric acid exists and the light reflectance ratio is greater than a preset reflectance ratio, it is determined that bird droppings exist in the area to be detected;

[0011] Starting a bird droppings verification model to make a second determination of whether bird droppings exist in the area to be detected, and if the confidence level output by the bird droppings verification model is not less than a preset confidence level, the second determination is successful, and a bird droppings cleaning module is controlled to perform bird droppings cleaning work to remove the bird droppings.

[0012] Optionally, the light reflectivity of at least one wave band in the non-pollution area of the vehicle body is recorded as the background reference value at least once every preset time length or when the vehicle travels a preset distance.

[0013] Optionally, after determining that the uric acid exists and the reflectivity ratio is greater than a preset reflectivity ratio, the method further comprises:

[0014] determining a light ratio of a third preset wave band and a fourth preset wave band based on at least the second spectrum;

[0015] if the light ratio is greater than a first threshold value, determining that the bird droppings in the to-be-detected area are fresh bird droppings;

[0016] if the light ratio is less than a second threshold value, determining that the bird droppings in the to-be-detected area are dry bird droppings;

[0017] wherein the first threshold value is greater than the second threshold value.

[0018] Optionally, after determining the second spectrum corresponding to each wave band image information based on the background reference value, the first spectrum of each wave band image information, and the ambient light intensity coefficient, the method further comprises:

[0019] aligning the image information of each wave band to the same coordinate system by using a feature matching algorithm, and locally correcting the aligned image information by using a preset interpolation method.

[0020] Optionally, the bird droppings verification model is started to determine whether bird droppings exist in the to-be-detected area, and if the confidence output by the bird droppings verification model is not less than a preset confidence, the secondary determination is successful, and the bird droppings cleaning module is controlled to perform bird droppings cleaning work to remove the bird droppings, specifically comprising:

[0021] starting the bird droppings verification model to perform standardization processing on the image information of each wave band to obtain standard image information corresponding to each wave band;

[0022] extracting feature information corresponding to the standard image information under each wave band;

[0023] outputting a confidence based on the feature information to determine whether bird droppings exist in the to-be-detected area, and if the confidence is not less than a preset confidence, the secondary determination is successful, and the bird droppings cleaning module is controlled to perform bird droppings cleaning work to remove the bird droppings.

[0024] Optionally, the bird droppings cleaning module is at least retractably integrated on a vehicle door or an engine cover, and is used to spray bird droppings cleaning agent to remove bird droppings when it is confirmed that bird droppings exist in the to-be-detected area.

[0025] In a second aspect, the present application further provides a vehicle surface bird droppings cleaning device, comprising at least:

[0026] A first recording module is configured to scan a non-polluted area of the vehicle body and record a light reflectivity of at least one wave band in the non-polluted area of the vehicle body as a background reference value;

[0027] A collection determining module is configured to collect image information of at least one wave band in the to-be-detected area and determine an ambient light intensity coefficient;

[0028] A spectrum determining module is configured to determine a second spectrum corresponding to each wave band image information based on the background reference value, a first spectrum of each wave band image information and the ambient light intensity coefficient;

[0029] An uric acid determining module is configured to calculate a light absorption rate corresponding to a first preset wave band and an adjacent wave band based on the second spectrum, and confirm the presence of uric acid when the light absorption rate of the first preset wave band is greater than a preset absorption rate and the light absorption rate of the adjacent wave band meets a preset condition;

[0030] A reflectivity determining module is configured to determine a light reflectivity ratio of a second preset wave band and a third preset wave band based on the second spectrum;

[0031] A bird droppings determining module is configured to determine the presence of bird droppings in the to-be-detected area when the uric acid is present and the light reflectivity ratio is greater than a preset reflectivity ratio;

[0032] A verification and cleaning module is configured to start a bird droppings verification model to secondarily determine whether bird droppings exist in the to-be-detected area, and when a confidence level output by the bird droppings verification model is not less than a preset confidence level, the secondary determination is successful, and a bird droppings cleaning module is controlled to perform bird droppings cleaning work to remove the bird droppings.

[0033] In a third aspect, the present application further provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor implements the steps in the vehicle surface bird droppings cleaning method of any one of the first aspect when executing the program.

[0034] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps in the vehicle surface bird droppings cleaning method of any one of the first aspect when executed by a processor.

[0035] In a fifth aspect, the present application further provides a vehicle, which integrates at least the vehicle surface bird droppings cleaning device and the bird droppings cleaning module of the second aspect.

[0036] The technical scheme provided by the embodiment of the present application firstly scans the non-polluted area of the vehicle body, and records the light reflectivity of at least one wave band in the non-polluted area of the vehicle body as a background reference value; secondly, image information of at least one wave band of the to-be-detected area is collected, and an ambient light intensity coefficient is determined; thirdly, the second spectrum corresponding to each wave band image information is determined based on the background reference value, the first spectrum of each wave band image information and the ambient light intensity coefficient; fourthly, the light absorption rate corresponding to the first preset wave band and its adjacent wave bands is calculated based on at least the second spectrum, and if the light absorption rate of the first preset wave band is greater than a preset absorption rate and the light absorption rates of the adjacent wave bands meet a preset condition, it is confirmed that uric acid exists; fifthly, the light reflectivity ratio of the second preset wave band and the third preset wave band is determined based on at least the second spectrum; then, if uric acid exists and the light reflectivity ratio is greater than a preset reflectivity ratio, it is determined that bird droppings exist in the to-be-detected area. Finally, a bird droppings verification model is started to secondarily determine whether bird droppings exist in the to-be-detected area, and if the confidence degree output by the bird droppings verification model is not less than a preset confidence degree, the secondary determination is successful, and a bird droppings cleaning module is controlled to perform bird droppings cleaning work to remove the bird droppings.

[0037] It can be seen that, by collecting the light reflectivity of at least one wave band as a background reference value and determining the second spectrum based on the background reference value, the detection efficiency of the bird droppings can be effectively improved, and on this basis, the light absorption rate corresponding to the first preset wave band and its adjacent wave bands is calculated, and when the light absorption rate of the first preset wave band is greater than a preset absorption rate and the light absorption rates of the adjacent wave bands meet a preset condition, it is confirmed that uric acid exists, the bird droppings in the to-be-detected area are identified based on the light reflectivity, and the secondary determination is performed by using the bird droppings verification model, so as to further improve the accuracy of the bird droppings detection. The embodiment of the present application at least solves the problem that the bird droppings attached to the vehicle body cannot be cleaned in time, and is beneficial to protecting the cleanliness of the vehicle body and improving the user experience of using the vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 is a flowchart of a vehicle surface bird droppings cleaning method provided by the embodiment of the present application;

[0039] Figure 2 is a cleaning schematic diagram provided by the embodiment of the present application;

[0040] Figure 3 is a flowchart of another vehicle surface bird droppings cleaning method provided by the embodiment of the present application;

[0041] Figure 4 is a structural schematic diagram of a vehicle surface bird droppings cleaning device provided by the embodiment of the present application;

[0042] Figure 5 is a structural schematic diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to make the purposes, technical solutions and advantages of the present application clearer, the following further describes the present application with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0044] The terms used in the embodiments of the present application are only for the purpose of describing particular embodiments and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. "Plural" generally includes at least two.

[0045] It should be understood that the term "and / or" used herein is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects.

[0046] It should be understood that although the terms first, second, third, etc. can be used in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the description. For example, without departing from the scope of the embodiments of the present application, the first can also be called the second, and similarly, the second can also be called the first.

[0047] Depending on the context, the word "if" as used herein can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if it is determined" or "if (a stated condition or event) is detected" can be interpreted as "when it is determined" or "in response to determining" or "when (a stated condition or event) is detected" or "in response to detecting (a stated condition or event)".

[0048] It should also be noted that the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusion, so that a product or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such product or device. Without more limitations, the element defined by the sentence "including a" does not exclude the presence of another identical element in the product or device including the element.

[0049] It is particularly noted that the symbols and / or numbers existing in the specification, if not marked in the description of the drawings, are not the drawing marks.

[0050] Figure 1 is a flowchart of a vehicle surface bird droppings cleaning method provided by an embodiment of the present application. The vehicle surface bird droppings cleaning method can be executed by the vehicle surface bird droppings cleaning device as an execution subject, but is not limited thereto. The execution subject can be realized in the form of software and / or hardware. As shown in the figure, the vehicle surface bird droppings cleaning method at least includes the following steps: Figure 1

[0051] S1, scanning a vehicle body non-pollution area and recording at least the light reflectivity of at least one wave band in the vehicle body non-pollution area as a background reference value.

[0052] The scanning time can be when the vehicle is started or after the vehicle is cleaned. The vehicle body non-pollution area generally refers to the middle of the vehicle door or the smooth part of the roof. It can be understood that the background reference value needs to be updated regularly to avoid the influence of long-term environmental changes (such as vehicle paint aging) on subsequent bird droppings identification, and to ensure the accuracy of subsequent bird droppings identification.

[0053] In a specific embodiment, the light reflectivity of at least one wave band in the vehicle body non-pollution area is recorded as a background reference value at least once every preset time interval or when the vehicle driving distance reaches a preset distance.

[0054] The preset time interval can be 24 hours. The preset distance can be 100 kilometers.

[0055] S2, collecting image information of at least one wave band of the to-be-detected area and determining an ambient light intensity coefficient.

[0056] The ambient light intensity coefficient is obtained in real time by an ambient light sensor.

[0057] S3, determining a second spectrum corresponding to each wave band image information based on the background reference value, the first spectrum of each wave band image information, and the ambient light intensity coefficient.

[0058] The first spectrum is the original spectrum of the wave band image information. The second spectrum can be determined at least by the following method:

[0059] ;

[0060] ​In the formula, R2 represents the second spectrum, R1 represents the first spectrum, K represents the ambient light intensity coefficient, and R represents the background reference value. The above formula can also be understood as point-by-point subtraction of the background reference value according to the wave band to determine the second spectrum.

[0061] S4, at least based on the second spectrum, the light absorption rate corresponding to the first preset wave band and its adjacent wave band is calculated, if the light absorption rate of the first preset wave band is greater than the preset absorption rate and the light absorption rate of the adjacent wave band meets the preset condition, it is confirmed that uric acid exists.

[0062] Wherein, the first preset wave band can be 280nm. The absorption rate can be confirmed at least by the following way:

[0063] ;

[0064] In the formula, A represents the light absorption rate. A i represents the light reflectance corresponding to the second spectrum of the first preset wave band. A o represents the light reflectance corresponding to the first spectrum of the first preset wave band. The adjacent wave band of 280nm can be 260nm and 300nm, and the adjacent wave band can also correspond to a range interval such as [260, 300]. The preset absorption rate can be obtained by calibration. Exemplarily, the preset absorption rate is 0.7. The preset condition can be that the light absorption rate program "uric acid peak" shape, that is, after performing Gaussian fitting operation, the Gaussian fitting value is greater than 0.9 (that is, it meets the spectral characteristics of uric acid).

[0065] S5, at least based on the second spectrum, the light reflectance ratio of the second preset wave band and the third preset wave band is determined.

[0066] Wherein, the second preset wave band can be 350nm. The third preset wave band can be 550nm. The light reflectance ratio can be confirmed at least by the following way:

[0067] ;

[0068] In the formula, Ratio represents the light reflectance ratio. X i represents the light reflectance corresponding to the second spectrum of the second preset wave band. X o represents the light reflectance corresponding to the second spectrum of the third preset wave band. It is known that the reflectance ratio of different objects is different, and Table 1 is a reflectance ratio and substance corresponding table provided by the embodiment, as shown in Table 1.

[0069] Table 1

[0070] Substance Ratio Bird droppings Greater than 1.5 Dust / water stains [0.6,1.5] Tree leaves Less than 0.6

[0071] S6, if uric acid exists and the light reflectance ratio is greater than the preset reflectance ratio, it is determined that bird droppings exist in the to-be-detected region.

[0072] S7, start the bird droppings verification model to determine whether bird droppings exist in the to-be-detected area, if the confidence output by the bird droppings verification model is not less than the preset confidence, the secondary determination is successful, and the bird droppings cleaning module is controlled to perform bird droppings cleaning work to remove the bird droppings.

[0073] The bird droppings verification model can be a convolutional neural network (CNN) model. The CNN model is fed with labeled sample data (bird droppings, dust, leaves and water stains) under different light conditions and weather, and the CNN model is repeatedly fed with the same labeled sample data after adjusting the rotation angle, brightness fluctuation and noise interference (such as blurring) of the labeled sample data, so as to improve the accuracy of subsequent CNN model in identifying bird droppings. The confidence can be the confidence level of confirming bird droppings, and the value range can be [0, 1]. The preset confidence can be 0.9. Figure 2 is a cleaning schematic diagram provided by an embodiment of the present application, referring to Figure 2 In another specific embodiment, the bird droppings cleaning module can be at least telescopic integrated on the vehicle door or the engine cover, for spraying bird droppings cleaning agent to remove bird droppings when it is confirmed that bird droppings exist in the to-be-detected area. After starting the bird droppings cleaning work, the bird droppings cleaning module can spray the environment-friendly cleaning agent / biodegradable cleaning agent with a pH value between 7 and 8 at a pressure of 0.2 Mpa through the telescopic micro rotary nozzle integrated on the edge of the vehicle door or the engine cover, to remove the bird droppings. When the bird droppings cleaning work is started, the engine cover, roof and other high-risk areas can be preferentially processed in this embodiment.

[0074] The technical solution provided by the embodiment first scans the pollution-free area of the vehicle body, and records at least the light reflectance of at least one wave band in the pollution-free area of the vehicle body as a background reference value; secondly, image information of at least one wave band in the to-be-detected area is collected, and an ambient light intensity coefficient is determined; thirdly, a second spectrum corresponding to each wave band image information is determined based on the background reference value, the first spectrum of each wave band image information and the ambient light intensity coefficient; fourthly, at least based on the second spectrum, the light absorption rate corresponding to the first preset wave band and its adjacent wave bands is calculated, if the light absorption rate of the first preset wave band is greater than a preset absorption rate and the light absorption rate of the adjacent wave bands meets a preset condition, it is confirmed that uric acid exists; fifthly, at least based on the second spectrum, the light reflectance ratio of the second preset wave band and the third preset wave band is determined; then, if the uric acid exists and the light reflectance ratio is greater than a preset reflectance ratio, it is determined that bird droppings exist in the to-be-detected area; finally, the bird droppings verification model is started to determine whether bird droppings exist in the to-be-detected area, if the confidence output by the bird droppings verification model is not less than the preset confidence, the secondary determination is successful, and the bird droppings cleaning module is controlled to perform bird droppings cleaning work to remove the bird droppings.

[0075] Therefore, by collecting reflectivity of at least one wave band as a background reference value, and determining the second spectrum based on the background reference value, the detection efficiency of the subsequent bird droppings can be effectively improved. On this basis, the light absorption rate corresponding to the first preset wave band and its adjacent wave bands is calculated, and when the light absorption rate of the first preset wave band is greater than the preset absorption rate and the light absorption rate of the adjacent wave bands meets the preset condition, it is confirmed that uric acid exists. The bird droppings in the detection area are identified based on light reflectivity, and the bird droppings verification model is used for secondary determination, further improving the accuracy of bird droppings detection. The present embodiment at least solves the problem that the bird droppings attached to the vehicle body cannot be cleaned in time, which is beneficial to protect the vehicle body clean and improve the user's vehicle experience.

[0076] On the basis of the above embodiments or implementations, Figure 2 is a flowchart of another vehicle surface bird droppings cleaning method provided by the embodiments of the present application. The vehicle surface bird droppings cleaning of the present embodiment is based on the above-mentioned embodiments. As shown in Figure 2 , the vehicle surface bird droppings cleaning method at least includes the following steps:

[0077] S1, scanning the vehicle body pollution-free area, and recording at least the light reflectivity of at least one wave band in the vehicle body pollution-free area as a background reference value.

[0078] S2, collecting image information of at least one wave band of the detection area and determining the ambient light intensity coefficient.

[0079] S3, determining the second spectrum corresponding to each wave band image information based on the background reference value, the first spectrum of each wave band image information and the ambient light intensity coefficient.

[0080] S8, aligning each wave band image information to the same coordinate system by using a feature matching algorithm, and locally correcting the aligned image information by using a preset interpolation method.

[0081] Wherein, the feature matching algorithm can be SIFT feature matching or phase correlation method. The preset interpolation method can be thin plate spline interpolation. The same coordinate system can be pixel coordinate system.

[0082] S4, calculating the light absorption rate corresponding to the first preset wave band and its adjacent wave bands based on at least the second spectrum, and if the light absorption rate of the first preset wave band is greater than the preset absorption rate and the light absorption rate of the adjacent wave bands meets the preset condition, it is confirmed that uric acid exists.

[0083] Wherein, the second spectrum in step S4 is aligned and corrected after step S8. The processing of step S8 makes the feature information in the image information more obvious, and the subsequent bird droppings identification is more accurate.

[0084] S5, determining the light reflectivity ratio of the second preset wave band and the third preset wave band based on at least the second spectrum.

[0085] S6, if the uric acid exists and the light reflectance ratio is greater than the preset reflectance ratio, it is determined that the bird droppings exist in the to-be-detected region.

[0086] S9, determining a light ratio of a third preset wave band and a fourth preset wave band based on at least the second spectrum.

[0087] The light ratio can be a light reflectance ratio of red light and green light. The fourth preset wave band can be 550 nm. The fifth preset wave band can be 650 nm. The light ratio can be determined at least by the following manner:

[0088] ;

[0089] In the formula, T represents the light ratio. T i represents the reflectance corresponding to the second spectrum of the fourth preset wave band, T o represents the reflectance corresponding to the second spectrum of the third preset wave band.

[0090] S10, if the light ratio is greater than a first threshold value, it is determined that the bird droppings in the to-be-detected region are fresh bird droppings.

[0091] The first threshold value can be 1.2.

[0092] S11, if the light ratio is less than a second threshold value, it is determined that the bird droppings in the to-be-detected region are dry bird droppings.

[0093] The first threshold value is greater than the second threshold value, and the second threshold value can be 0.8.

[0094] S71, starting a bird droppings verification model to perform standardization processing on image information of each wave band to obtain standard image information corresponding to each wave band.

[0095] The standardization can correspond to normalization. A corresponding wavelength channel can be established for the image information of each wave band, and normalization processing is performed on the image information of each wave band respectively to eliminate differences between different wave bands. The specific normalization manner can be:

[0096] Image information = (pixel value of image information - pixel mean value in image information) / pixel variance in image information.

[0097] Table 2 is a possible wave band, mean value and variance table provided by an embodiment of the present application, as shown in Table 2.

[0098] Table 2

[0099] Waveband (nm) Pixel mean Pixel variance 280 0.12 0.05 350 0.23 0.08 550 0.45 0.12 650 0.38 0.10

[0100] S72, extracting feature information corresponding to the standard image information under each wave band.

[0101] The extraction can be performed by using a two-dimensional convolution layer. During feature extraction, the standard image information can also be cut into 64*64 overlapping blocks, and edge padding can be performed between adjacent overlapping blocks to include the continuity between the overlapping blocks. The feature information can be feature information of the bird droppings.

[0102] S73, output a confidence level based on the feature information to make a secondary determination of whether bird droppings exist in the to-be-detected region. If the confidence level is not less than a preset confidence level, the secondary determination is successful, and the bird droppings cleaning module is controlled to perform bird droppings cleaning work to remove the bird droppings.

[0103] The confidence level can be determined by extracting feature information of each overlapping block and identifying the feature information to determine whether bird droppings exist in the current detection area. The embodiment also provides an abnormal processing mechanism. If the image information obtained by the CNN has invalid pixel values, the image information of the to-be-detected region is automatically reacquired.

[0104] The technical scheme provided in the embodiment first scans the pollution-free area of the vehicle body and records the light reflectivity of at least one wave band in the pollution-free area of the vehicle body as a background reference value. Further, image information of at least one wave band in the to-be-detected region is collected, and an ambient light intensity coefficient is determined. Further, the second spectrum corresponding to each wave band of image information is determined based on the background reference value, the first spectrum of each wave band of image information, and the ambient light intensity coefficient. Further, the image information of each wave band is aligned to the same coordinate system by using a feature matching algorithm, and the aligned image information is locally corrected by using a preset interpolation method. Further, the absorption rate corresponding to the first preset wave band and its adjacent wave bands is calculated based on at least the second spectrum, and if the absorption rate of the first preset wave band is greater than a preset absorption rate and the absorption rates of the adjacent wave bands satisfy a preset condition, it is determined that uric acid exists. Further, the light reflectivity ratio of the second preset wave band and the third preset wave band is determined based on at least the second spectrum. Further, if the uric acid exists and the light reflectivity ratio is greater than a preset reflectivity ratio, it is determined that bird droppings exist in the to-be-detected region. Further, the light ratio of the third preset wave band and the fourth preset wave band is determined based on at least the second spectrum. Further, if the light ratio is greater than a first threshold value, it is determined that the bird droppings in the to-be-detected region are fresh bird droppings. Further, if the light ratio is less than a second threshold value, it is determined that the bird droppings in the to-be-detected region are dry bird droppings. Further, a bird droppings verification model is started to perform standardized processing on the image information of each wave band to obtain standard image information corresponding to each wave band. Further, feature information corresponding to the standard image information under each wave band is extracted. Finally, a confidence level is output based on the feature information to make a secondary determination of whether bird droppings exist in the to-be-detected region. If the confidence level is not less than a preset confidence level, the secondary determination is successful, and the bird droppings cleaning module is controlled to perform bird droppings cleaning work to remove the bird droppings.

[0105] Therefore, by collecting the reflectivity of at least one wave band as a background reference value and determining the second spectrum based on the background reference value, the detection efficiency of the subsequent bird droppings can be effectively improved. On this basis, the light absorption rate corresponding to the first preset wave band and its adjacent wave bands is calculated, and when the light absorption rate of the first preset wave band is greater than the preset absorption rate and the light absorption rates of the adjacent wave bands meet the preset condition, it is confirmed that uric acid exists. The bird droppings in the detection area are identified based on the light reflectivity, and the bird dropping verification model is used for secondary determination, further improving the accuracy of bird dropping detection. The present embodiment at least solves the problem that the bird droppings attached to the vehicle body cannot be cleaned in time, which is beneficial to protect the vehicle body and improve the user's vehicle experience.

[0106] Figure 4 is a structural schematic diagram of a vehicle surface bird dropping cleaning device provided by an embodiment of the present application. The present embodiment is at least applicable to bird dropping cleaning scenes on surfaces of various vehicles, and the vehicle surface bird dropping cleaning device can be realized in a software and / or hardware manner. As shown in the figure, the vehicle surface bird dropping cleaning device 100 at least includes: Figure 4

[0107] The first recording module 110 is configured to scan a pollution-free area of the vehicle body and record at least the light reflectivity of at least one wave band in the pollution-free area of the vehicle body as a background reference value.

[0108] The acquisition and determination module 120 is configured to acquire image information of at least one wave band of a detection area and determine an ambient light intensity coefficient.

[0109] The spectrum determination module 130 is configured to determine a second spectrum corresponding to each wave band image information based on the background reference value, the first spectrum of each wave band image information and the ambient light intensity coefficient.

[0110] The uric acid determination module 140 is configured to calculate the light absorption rate corresponding to the first preset wave band and its adjacent wave bands based on at least the second spectrum, and if the light absorption rate of the first preset wave band is greater than the preset absorption rate and the light absorption rates of the adjacent wave bands meet the preset condition, it is confirmed that uric acid exists.

[0111] The reflectivity determination module 150 is configured to determine the light reflectivity ratio of the second preset wave band and the third preset wave band based on at least the second spectrum.

[0112] The bird dropping determination module 160 is configured to determine that bird droppings exist in the detection area when uric acid exists and the light reflectivity ratio is greater than the preset reflectivity ratio.

[0113] The inspection and cleaning module 170 is configured to start the bird dropping verification model to make a secondary determination on whether bird droppings exist in the detection area. If the confidence degree output by the bird dropping verification model is not less than the preset confidence degree, the secondary determination is successful, and the bird dropping cleaning module is controlled to perform bird dropping cleaning work to remove the bird droppings. ​

[0114] Optionally, at least once every preset time length or vehicle driving distance reaches a preset distance, the light reflectivity of at least one wave band in the pollution-free area of the vehicle body is recorded again as a background reference value.

[0115] Optionally, the method further comprises:

[0116] The red-green light determination module 180 determines the light ratio of the third preset wave band and the fourth preset wave band based on at least the second spectrum; and when the light ratio is greater than a first threshold value, determines that the bird droppings in the to-be-detected area are fresh bird droppings; and when the light ratio is less than a second threshold value, determines that the bird droppings in the to-be-detected area are dry bird droppings.

[0117] The first threshold value is greater than the second threshold value.

[0118] Optionally, the method further comprises:

[0119] The marking correction module 190 is configured to align the image information of each wave band to the same coordinate system by using a feature matching algorithm, and locally correct the aligned image information by using a preset interpolation method.

[0120] Optionally, the inspection and cleaning module 170 is specifically configured to:

[0121] The bird droppings verification model is started to perform standardization processing on the image information of each wave band to obtain corresponding standard image information of each wave band; feature information corresponding to the standard image information under each wave band is extracted; and the confidence is output based on the feature information to make a second determination on whether there are bird droppings in the to-be-detected area. When the confidence is not less than a preset confidence, the second determination is successful, and the bird droppings cleaning module is controlled to perform bird droppings cleaning work to remove the bird droppings.

[0122] The technical scheme provided in the embodiment first records the light reflectivity of at least one wave band in the pollution-free area of the vehicle body as a background reference value through the first recording module. Further, the image information of at least one wave band of the to-be-detected area is collected and the ambient light intensity coefficient is determined through the collection determining module. Further, the second spectrum corresponding to each wave band image information is determined based on the background reference value, the first spectrum of each wave band image information and the ambient light intensity coefficient through the spectrum determining module. Further, the light absorption rate corresponding to the first preset wave band and the adjacent wave band is calculated based on the second spectrum through the uric acid determining module. Further, when the light absorption rate of the first preset wave band is greater than the preset absorption rate and the light absorption rate of the adjacent wave band meets the preset condition, the presence of uric acid is confirmed through the uric acid determining module. Further, the light reflectivity ratio of the second preset wave band and the third preset wave band is determined based on the second spectrum through the reflectivity determining module. Further, when the uric acid exists and the light reflectivity ratio is greater than the preset reflectivity ratio, the presence of bird droppings in the to-be-detected area is determined through the bird dropping determining module. Further, the bird dropping verification model is started to secondarily determine whether the bird droppings exist in the to-be-detected area through the inspection and cleaning module. Finally, when the confidence degree output by the bird dropping verification model is not less than the preset confidence degree, the secondary determination is successful, and the bird dropping cleaning module is controlled to perform the bird dropping cleaning work to remove the bird droppings through the inspection and cleaning module.

[0123] Therefore, the reflectivity of at least one wave band is collected as the background reference value, and the second spectrum is determined based on the background reference value, which can effectively improve the detection efficiency of the subsequent bird droppings. The light absorption rate corresponding to the first preset wave band and the adjacent wave band is calculated, and when the light absorption rate of the first preset wave band is greater than the preset absorption rate and the light absorption rate of the adjacent wave band meets the preset condition, the presence of uric acid is confirmed. The bird droppings in the to-be-detected area are identified based on the light reflectivity, and the secondary determination is performed by using the bird dropping verification model, which further improves the accuracy of the bird dropping detection. The embodiment at least solves the problem that the bird droppings attached to the vehicle body cannot be cleaned in time, which is beneficial to protecting the cleanliness of the vehicle body and improving the user experience of using the vehicle.

[0124] The embodiment provides an electronic device, Figure 5 is a structural schematic diagram of an electronic device provided by the embodiment of the present application, referring to Figure 5The electronic device 1000 comprises a processor 1001 and a memory 1002, and the memory 1002 stores computer readable instructions, when the computer readable instructions are executed by the processor 1001, the steps in any one of the vehicle surface bird droplet cleaning methods described above are executed. Through the above technical solution, the processor 1001 and the memory 1002 are interconnected and communicate with each other through a communication bus and / or other forms of connection mechanism (not marked), the memory 1002 stores a computer program executable by the processor, when the electronic device 1000 is running, the processor 1001 executes the computer program to execute the vehicle surface bird droplet cleaning method in any one of the optional implementation manners of the above embodiments, to at least achieve the following functions: scanning a pollution-free area of the vehicle body, and recording at least the light reflectivity of at least one wave band in the pollution-free area of the vehicle body as a background reference value; collecting image information of at least one wave band of the to-be-detected area, and determining an ambient light intensity coefficient; determining a second spectrum corresponding to each wave band image information based on the background reference value, the first spectrum of each wave band image information and the ambient light intensity coefficient; calculating the light absorption rate corresponding to the first preset wave band and its adjacent wave band based on at least the second spectrum, if the light absorption rate of the first preset wave band is greater than a preset absorption rate and the light absorption rate of the adjacent wave band meets a preset condition, it is confirmed that uric acid exists; determining the light reflectivity ratio of the second preset wave band and the third preset wave band based on at least the second spectrum; if uric acid exists and the light reflectivity ratio is greater than a preset reflectivity ratio, it is determined that bird droplets exist in the to-be-detected area; starting a bird droplet verification model to secondarily determine whether bird droplets exist in the to-be-detected area, if the confidence output by the bird droplet verification model is not less than a preset confidence, the secondary determination is successful, and the bird droplet cleaning module is controlled to execute bird droplet cleaning work to remove the bird droplets.

[0125] The embodiment provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement a vehicle surface bird dropping cleaning method provided by all the embodiments of the present application: scanning a non-pollution area of a vehicle body, and recording reflectivity of at least one wave band in the non-pollution area of the vehicle body as a background reference value; collecting image information of the to-be-detected area at least one wave band, and determining an ambient light intensity coefficient; collecting image information of the to-be-detected area at least one wave band, and determining an ambient light intensity coefficient; determining a second spectrum corresponding to each wave band image information based on the background reference value, the first spectrum of each wave band image information and the ambient light intensity coefficient; calculating light absorption rates corresponding to a first preset wave band and adjacent wave bands based on at least the second spectrum, and if the light absorption rate of the first preset wave band is greater than a preset absorption rate and the light absorption rates of the adjacent wave bands satisfy preset conditions, it is confirmed that uric acid exists; determining a light reflectivity ratio of a second preset wave band and a third preset wave band based on at least the second spectrum; if the uric acid exists and the light reflectivity ratio is greater than a preset reflectivity ratio, it is determined that bird dropping exists in the to-be-detected area; starting a bird dropping verification model to secondarily determine whether bird dropping exists in the to-be-detected area, if a confidence degree output by the bird dropping verification model is not less than a preset confidence degree, the secondary determination is successful, and a bird dropping cleaning module is controlled to perform bird dropping cleaning work to remove the bird dropping.

[0126] Any combination of one or more computer readable medium can be employed. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present document, a computer readable storage medium can be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0127] A computer readable signal medium can include a computer readable medium that stores a program in a modulated data signal such as a carrier wave or other transport mechanism, and includes any computer readable medium that is not a computer readable storage medium. A computer readable signal medium can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0128] The program code embodied on the computer readable media can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0129] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0130] The embodiment provides a vehicle, and the vehicle integrates the bird dropping cleaning device and the bird dropping cleaning module provided by the application.

[0131] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of cleaning bird droppings from a surface of a vehicle, characterized by, At least comprising: Scanning the pollution-free area of the vehicle body and recording at least the light reflectivity of at least one wave band in the pollution-free area of the vehicle body as a background reference value; Collecting image information of at least one wave band in the to-be-detected area and determining an ambient light intensity coefficient; Determining a second spectrum corresponding to each wave band image information based on the background reference value, the first spectrum of each wave band image information and the ambient light intensity coefficient; At least based on the second spectrum, calculating the light absorption rate corresponding to the first preset wave band and its adjacent wave bands, if the light absorption rate of the first preset wave band is greater than a preset absorption rate and the light absorption rate of the adjacent wave bands meets a preset condition, it is confirmed that uric acid exists; At least based on the second spectrum, determining the light reflectivity ratio of the second preset wave band and the third preset wave band; If the uric acid exists and the light reflectivity ratio is greater than a preset reflectivity, it is determined that bird droppings exist in the to-be-detected area; Starting a bird droppings verification model to secondarily determine whether bird droppings exist in the to-be-detected area, if the confidence output by the bird droppings verification model is not less than a preset confidence, the secondary determination is successful, and a bird droppings cleaning module is controlled to perform bird droppings cleaning work to remove the bird droppings.

2. The vehicle surface bird droppings cleaning method according to claim 1, characterized by, At least once every preset time length or when the vehicle driving distance reaches a preset distance, the light reflectivity of at least one wave band in the pollution-free area of the vehicle body is recorded again as the background reference value.

3. The vehicle surface bird droppings cleaning method according to claim 1, characterized by, After the if the uric acid exists and the reflectivity ratio is greater than a preset reflectivity, it is determined that bird droppings exist in the to-be-detected area, further comprising: At least based on the second spectrum, determining the light ratio of the third preset wave band and the fourth preset wave band; If the light ratio is greater than a first threshold value, it is determined that the bird droppings in the to-be-detected area are fresh bird droppings; If the light ratio is less than a second threshold value, it is determined that the bird droppings in the to-be-detected area are dry bird droppings; Wherein, the first threshold value is greater than the second threshold value.

4. The vehicle surface bird droppings cleaning method according to claim 1, characterized by, After the based on the background reference value, the first spectrum of each wave band image information and the ambient light intensity coefficient to determine the second spectrum corresponding to each wave band image information, further comprising: Aligning each wave band image information to the same coordinate system by using a feature matching algorithm, and locally correcting the aligned image information by using a preset interpolation method.

5. The method of claim 1, wherein, The starting bird droppings verification model to secondarily determine whether bird droppings exist in the to-be-detected area, if the confidence output by the bird droppings verification model is not less than a preset confidence, the secondary determination is successful, and a bird droppings cleaning module is controlled to perform bird droppings cleaning work to remove the bird droppings, specifically comprising: Starting the bird droppings verification model to perform standardization processing on each wave band image information to obtain standard image information corresponding to each wave band; Extracting feature information corresponding to the standard image information under each wave band; Based on the feature information, outputting a confidence to secondarily determine whether bird droppings exist in the to-be-detected area, if the confidence is not less than a preset confidence, the secondary determination is successful, and a bird droppings cleaning module is controlled to perform bird droppings cleaning work to remove the bird droppings.

6. The method of claim 1-5, wherein, The bird droppings cleaning module is at least telescopic integrated on the vehicle door or the engine cover, for spraying bird droppings cleaning agent to remove the bird droppings when it is confirmed that the bird droppings exist in the to-be-detected area.

7. A vehicle surface bird dropping cleaning device, characterised in that, At least comprising: The first recording module is configured to scan a pollution-free area of the vehicle body and record light reflectivity of at least one wave band in the pollution-free area of the vehicle body as a background reference value; The acquisition determining module is configured to acquire image information of at least one wave band of the to-be-detected area and determine an ambient light intensity coefficient; The spectrum determining module is configured to determine a second spectrum corresponding to each wave band of image information based on the background reference value, the first spectrum of each wave band of image information and the ambient light intensity coefficient; The uric acid determining module is configured to calculate light absorption rates corresponding to a first preset wave band and adjacent wave bands based on the second spectrum, and confirm the presence of uric acid when the light absorption rate of the first preset wave band is greater than a preset absorption rate and the light absorption rates of the adjacent wave bands satisfy a preset condition; The reflectivity determining module is configured to determine a light reflectivity ratio of a second preset wave band and a third preset wave band based on the second spectrum; The bird dropping determining module is configured to determine that bird droppings exist in the to-be-detected area when the uric acid exists and the light reflectivity ratio is greater than a preset reflectivity ratio; The inspection and cleaning module is configured to start a bird dropping verification model to secondarily determine whether bird droppings exist in the to-be-detected area, and when a confidence level output by the bird dropping verification model is not less than a preset confidence level, the secondary determination is successful, and a bird dropping cleaning module is controlled to perform bird dropping cleaning work to remove bird droppings.

8. An electronic device comprising a memory and a processor, said memory storing a computer program operable on said processor, characterized in that, The processor executes the program to implement the steps in the vehicle surface bird dropping cleaning method of any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps in the vehicle surface bird dropping cleaning method of any one of claims 1 to 6.

10. A vehicle characterized by comprising: The vehicle at least integrates the vehicle surface bird dropping cleaning device of claim 7 and the bird dropping cleaning module.

Images