Control method and device for vehicle glass cleanliness, and vehicle

Abstract

An embodiment of the present application discloses a control method, a control device and a vehicle for the cleanliness of vehicle glass. The control method includes: obtaining the cleanliness information of the glass of the current vehicle and the cleaning conditions of the vehicle, where the cleaning conditions are the conditions related to the cleanliness of the glass of the vehicle when the driver makes a cleaning decision; predicting the execution decision of the driver based on the cleanliness information of the glass of the current vehicle and the cleaning conditions, where the execution decision includes a decision to perform cleaning; and outputting a prompt message to the driver when the execution decision is the decision to perform cleaning, where the prompt message is used to prompt the driver to clean the glass of the vehicle.

Description

Technical Field

[0001] This application relates to, but is not limited to, the field of intelligent driving technology, and particularly relates to a control method, a control device, and a vehicle for the cleanliness of vehicle glass. Background Art

[0002] The glass of a vehicle, such as the front windshield, is the only medium for the driver to look outside the vehicle. It not only needs to have good enough quality but also needs to ensure that it does not affect the driver's line of sight during driving. Due to the diverse environmental impacts during parking or driving, the front windshield will be contaminated to varying degrees and in different types, making the front windshield in a non-clean state, thus affecting the driver's line of sight. Common reasons for contaminating the front windshield include: 1) not washing the car for a long time, with a lot of accumulated dust; 2) leaves, sundries, etc. sticking to the glass; 3) muddy water adhering during rainy days; 4) water vapor adhering when the temperature inside the car is high in winter. When the front windshield is in a non-clean state, it is necessary to intelligently feedback to the driver or take necessary measures to ensure driving safety.

[0003] However, each driver takes different measures (clean or not clean) under different cleanliness levels. How to provide intelligent measures or reminders personalized according to the driver's habits has become a need. Summary of the Invention

[0004] In view of this, at least one embodiment of this application provides a control method, a control device, and a vehicle for the cleanliness of vehicle glass.

[0005] The technical solution of the embodiment of this application is implemented as follows:

[0006] In a first aspect, an embodiment of this application provides a control method for the cleanliness of vehicle glass. The method includes: obtaining the cleanliness information of the glass of the current vehicle and the cleaning conditions of the vehicle, where the cleaning conditions are the conditions related to the cleanliness of the glass of the vehicle when the driver makes a cleaning decision; predicting the execution decision of the driver based on the cleanliness information of the glass of the current vehicle and the cleaning conditions, where the execution decision includes a decision to perform cleaning; and outputting a prompt message to the driver when the execution decision is the decision to perform cleaning, where the prompt message is used to prompt the driver to clean the glass of the vehicle.

[0007] In some embodiments, it further includes: obtaining a set of historical images of the glass of the vehicle; for each image in the set of historical images, determining the cleanliness information of the glass corresponding to each image; based on the cleanliness information of the glass corresponding to each image, obtaining the execution decision of the driver, wherein the execution decision includes a decision to perform cleaning; based on the cleanliness information of the glass corresponding to each image and the execution decision of the driver, determining the cleaning condition of the vehicle, wherein the cleaning condition is the condition related to the cleanliness of the glass of the vehicle when the driver makes a cleaning decision.

[0008] In some embodiments, the cleanliness information includes: cleanliness and the amount of change in cleanliness. Correspondingly, the obtaining of the decision of whether the driver cleans based on the cleanliness information of the glass corresponding to each image includes: obtaining the execution decision of the driver when the cleanliness of the glass corresponding to each image is greater than a first threshold; obtaining the execution decision of the driver when the amount of change in cleanliness of the glass corresponding to each image is greater than a second threshold.

[0009] In some embodiments, the cleanliness information includes cleanliness. Correspondingly, for a target image which is any image in the set of historical image frames, determining the cleanliness information of the glass corresponding to the target image includes: determining the clarity of the glass in different regions of the target image; based on the clarity of the glass in different regions of the target image and the positions of the different regions in the target image, determining the cleanliness of the glass in different regions of the target image; based on the cleanliness of the glass in different regions of the target image, determining the cleanliness of the glass corresponding to the target image.

[0010] In some embodiments, the different regions include the upper region, the middle region, and the lower region in the target image, where: the lower region is the region formed after imaging in the target image of the space within a first preset distance from the glass outside the vehicle; the middle region is the region formed after imaging in the target image of the space between the first preset distance and the second preset distance from the glass outside the vehicle; the lower region is the region formed after imaging in the target image of the space outside the second preset distance from the glass outside the vehicle.

[0011] In some embodiments, the cleanliness information includes the amount of change in cleanliness. The images in the historical image set have a chronological relationship. The target image is any image in the historical image set. Correspondingly, determining the cleanliness information of the glass corresponding to the target image includes: determining the first cleanliness of the glass corresponding to the target image; determining the second cleanliness of the glass corresponding to the previous image of the target image in the historical image set; and determining the amount of change in cleanliness of the glass corresponding to the target image based on the first cleanliness and the second cleanliness.

[0012] In some embodiments, the cleanliness information includes cleanliness. After obtaining the cleanliness information of the glass of the current vehicle, it further includes: when the cleanliness of the glass of the current vehicle is greater than a third threshold, controlling the cleaning device of the vehicle to clean the glass.

[0013] In a second aspect, an embodiment of the present application further provides a control device for the cleanliness of a vehicle glass. The control device includes: a processor of the vehicle, configured to obtain the cleanliness information of the glass of the current vehicle and the cleaning conditions of the vehicle, where the cleaning conditions are the conditions related to the cleanliness of the glass of the vehicle when the driver makes a cleaning decision; predicting the execution decision of the driver based on the cleanliness information of the glass of the current vehicle and the cleaning conditions, where the execution decision includes a decision to perform cleaning; and when the execution decision is the decision to perform cleaning, outputting a prompt message to the driver, where the prompt message is used to prompt the driver to clean the glass of the vehicle; and an output device of the vehicle, configured to output a prompt message to the driver.

[0014] In some embodiments, the control device further includes:

[0015] An image acquisition device, configured to obtain a historical image set of the glass of the vehicle; the processor of the vehicle is further configured to, for each image in the historical image set, determine the cleanliness information of the glass corresponding to each image; obtain the execution decision of the driver based on the cleanliness information of the glass corresponding to each image, where the execution decision includes a decision to perform cleaning; and determine the cleaning conditions of the vehicle based on the cleanliness information of the glass corresponding to each image and the execution decision of the driver, where the cleaning conditions are the conditions related to the cleanliness of the glass of the vehicle when the driver makes a cleaning decision.

[0016] In a third aspect, an embodiment of the present application further provides a vehicle, including the above control device for the cleanliness of a vehicle glass.

[0017] In the embodiments of the present application, first, the cleanliness information of the glass of the current vehicle and the cleaning conditions of the vehicle are obtained, where the cleaning conditions are the conditions related to the cleanliness of the vehicle's glass when the driver makes a cleaning decision; then, based on the cleanliness information of the glass of the current vehicle and the cleaning conditions, the driver's execution decision is predicted; finally, when the execution decision is a decision to execute cleaning, a prompt message is output to the driver. It can be seen that since the cleaning conditions of the vehicle glass are the cleaning conditions that match the driver's own habits, it is possible to remind the driver to clean the vehicle glass when the cleanliness information meets the cleaning conditions that match the driver's own habits, thereby providing intelligent reminders personalized according to the driver's habits, and further improving the user experience.

[0018] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the technical solutions of the present disclosure. Brief Description of the Drawings

[0019] The accompanying drawings herein are incorporated into the specification and form a part of this specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to explain the technical solutions of the present application.

[0020] Figure 1 It is a schematic flowchart of the implementation of a control method for the cleanliness of vehicle glass provided by an embodiment of the present application;

[0021] Figure 2 It is a schematic flowchart of the implementation of a method for determining the cleaning conditions of a vehicle provided by an embodiment of the present application;

[0022] Figure 3A It is a schematic flowchart of the implementation of a method for determining the glass cleanliness information corresponding to a target image provided by an embodiment of the present application;

[0023] Figure 3B It is a schematic diagram of a defined glass clarity provided by an embodiment of the present application;

[0024] Figure 3C It is a schematic diagram showing the positions of the first preset distance and the second preset distance taking the front windshield as an example provided by an embodiment of the present application;

[0025] Figure 4 It is a schematic flowchart of the implementation of another control method for the cleanliness of vehicle glass provided by an embodiment of the present application. Detailed Description of the Embodiments

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be further elaborated in detail below with reference to the accompanying drawings and embodiments. The described embodiments should not be construed as limitations on this application. All other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of this application.

[0027] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict.

[0028] The terms "first / second / third" involved are only used to distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first / second / third" can be interchanged with a specific order or sequence when permitted, so that the embodiments of this application described here can be implemented in an order other than that illustrated or described here.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing this application and are not intended to limit this application.

[0030] An embodiment of this application provides a method for controlling the cleanliness of vehicle glass. As Figure 1 shown, this method includes the following steps S101 to step S103:

[0031] Step S101: Obtain the cleanliness information of the glass of the current vehicle and the cleaning conditions of the vehicle, where the cleaning conditions are the conditions related to the cleanliness of the glass of the vehicle when the driver makes a cleaning decision.

[0032] Here, the cleaning decision refers to the decision made by the driver to perform a cleaning operation. The cleaning conditions refer to the conditions related to cleanliness, such as: the threshold of cleanliness, the threshold of the change in cleanliness, etc. That is, when the cleaning conditions are met, the driver will make a cleaning decision. For example, when the cleanliness of the vehicle glass is greater than the cleanliness threshold, the driver makes a cleaning decision. The glass can be the front windshield, rear windshield, side glass, top glass, etc. of the vehicle.

[0033] In some embodiments, the method for obtaining cleaning conditions may include: presetting the cleaning conditions related to the cleanliness of the vehicle's glass when the driver makes a cleaning decision, for example: the threshold of cleanliness is level 5, and the threshold of the change in cleanliness is level 4. Among them, the level of cleanliness can be a manually defined level. For example: the level of cleanliness can be defined according to the clarity of the glass, where each clarity corresponds to a cleanliness level; or for another example: the level of cleanliness can also be defined according to the clarity of the glass when looking at different distances outside the glass, that is, considering both the distance and clarity dimensions. Since different distances will affect the timeliness of the driver's cleaning, areas farther away can be cleaned later, and areas closer will be cleaned first. Therefore, the cleanliness level obtained by combining distance and clarity can better reflect the factors affecting the driver's cleaning decision-making.

[0034] In some embodiments, the method for obtaining cleaning conditions may further include: obtaining the cleanliness information of the vehicle's glass in the past and the driver's execution decisions, so as to obtain the cleaning conditions related to the cleanliness of the vehicle's glass when the driver makes a cleaning decision. Among them, the cleanliness information of the vehicle's glass in the past can be obtained by an image acquisition device to collect an image of the vehicle's glass, and then a classification neural network (such as VGG, Googlenet, ResNet50, MobileNetV2, etc.) is used to determine the cleanliness of the glass. For example: first, different cleanliness levels of the glass are defined, and then the classification neural network is trained to identify the cleanliness of the image, so as to obtain the cleanliness information of the vehicle's glass.

[0035] The cleanliness information may include the cleanliness and the change in cleanliness. The cleanliness information can correspond to the cleaning conditions. For example, when the cleaning conditions include the threshold of cleanliness, the cleanliness information may include the cleanliness; or for another example, when the cleaning conditions include the threshold of the change in cleanliness, the cleanliness information may include the change in cleanliness.

[0036] Step S102: Predict the driver's execution decision based on the current cleanliness information of the vehicle's glass and the cleaning conditions, where the execution decision includes the decision to perform cleaning;

[0037] Here, the execution decision may further include the decision not to perform cleaning. The implementation of step S102 may include: predicting that the driver makes a decision to perform cleaning when the cleanliness information of the current vehicle's glass meets the cleaning conditions. Predicting that the driver makes a decision not to perform cleaning when the cleanliness information of the current vehicle's glass does not meet the cleaning conditions. For example, when the cleanliness of the vehicle's glass is greater than the cleanliness threshold, the driver makes a decision to perform cleaning. Or for another example, when the change in cleanliness of the vehicle's glass is less than the threshold of the change in cleanliness, the driver makes a decision not to perform cleaning.

[0038] Step S103: When the execution decision is the decision to perform cleaning, output a prompt message to the driver, where the prompt message is used to prompt the driver to clean the glass of the vehicle.

[0039] Here, the form of outputting the prompt message can be in voice form; it can also be in text form; it can also include both voice form and text form.

[0040] During implementation, the above steps S101 to S102 can be executed by the vehicle's processor, and the above step S103 can be executed by the vehicle's output device such as a multimedia device or a display device, so as to output a prompt message to prompt the driver to clean the glass of the vehicle, thereby realizing reminding the driver to clean the glass of the vehicle according to the driver's own habit when the cleanliness information meets the cleaning conditions.

[0041] In the embodiment of the present application, first, obtain the cleanliness information of the glass of the current vehicle and the cleaning conditions of the vehicle, where the cleaning conditions are the conditions related to the cleanliness of the vehicle's glass when the driver makes a cleaning decision; then, based on the cleanliness information of the glass of the current vehicle and the cleaning conditions, predict the driver's execution decision; finally, when the execution decision is the decision to perform cleaning, output a prompt message to the driver. It can be seen that since the cleaning conditions of the vehicle glass are the cleaning conditions matching the driver's own habits, it is possible to realize reminding the driver to clean the glass of the vehicle when the cleanliness information meets the cleaning conditions matching the driver's own habits, thereby providing intelligent reminders personalized according to the driver's habits, and further improving the user experience.

[0042] In some embodiments, as Figure 2 shown, the method includes the following steps S201 to S204:

[0043] Step S201: Obtain a set of historical images of the glass of the vehicle;

[0044] Here, the set of historical images can be a set of images of the vehicle glass collected by the image acquisition device when the driver previously drove the vehicle. It can also be a set of images other than the current image collected in real time by the image acquisition device when the driver is driving the vehicle this time. It should be noted that after the above steps S101 to S103 have been executed for the current image, it can also become a frame of the set of historical images.

[0045] When the cleanliness information includes cleanliness, the images in the image set may or may not have a chronological order. When the cleanliness information includes the amount of change in cleanliness, in order to determine the amount of change in cleanliness, the images in the image set may have a chronological order.

[0046] Step S202: For each image in the historical image set, determine the cleanliness information of the glass corresponding to each image;

[0047] Here, when the cleanliness information includes cleanliness, the target image is any image in the historical image set. As Figure 3A shown, the implementation of determining the cleanliness information of the glass corresponding to the target image may include the following steps S301 to S303:

[0048] Step S301: Determine the clarity of the glass in different regions of the target image;

[0049] Here, the clarity can be the clarity degree of the glass. During implementation, the clarity of the glass in different images can be defined manually. As Figure 3B shown, the definition of the clarity of the glass includes 5 types. The first type is clear, the state after just washing the car; the second type is the state with fewer foreign objects; the third type is the state with medium foreign objects; the fourth type is the state with more foreign objects; the fifth type is the state with a very large number of foreign objects, seriously affecting driving. Among them, the black dots represent foreign objects on the front windshield, which are shown as blocking the vehicle ahead by some unknown pixels in the image. The present application embodiment does not limit the definition method and quantity of the clarity.

[0050] The different regions may refer to the regions divided in the up-down dimension of the target image, such as the upper region, the lower region, etc. The present application embodiment does not limit the number of different regions.

[0051] Step S302: Based on the clarity of the glass in different regions of the target image and the positions of the different regions in the target image, determine the cleanliness of the glass in different regions of the target image;

[0052] Here, during the driving process, the driver actually checks whether the space in front is clear. Since the scene seen by the driver is similar to the scene formed in the image, and different regions in the image correspond to different spaces in the real environment. For example, the lower region of the image corresponds to the space closer to the glass in the real environment, while the upper region of the image corresponds to the space farther from the glass in the real environment. Also, since the space closer to the glass will immediately affect the driver's driving, while the space farther from the glass will not affect the driver's driving temporarily, therefore, in step S302, according to the clarity of the glass in different regions of the target image and the positions of different regions in the target image, the cleanliness of the glass in different regions of the target image is obtained. In this way, not only the clarity of the actual glass is considered, but also the severity of the impact of different positions on the driver's driving is considered. The cleanliness is defined from two dimensions, which can more accurately reflect the necessity and timeliness of whether the driver needs to clean, and more accurately simulate the influencing factors that affect the driver's cleaning decision-making.

[0053] In some embodiments, different regions may include the upper region, the middle region, and the lower region in the target image, where: the lower region is the region formed after the space within a first preset distance from the glass outside the vehicle is imaged in the target image;

[0054] the middle region is the region formed after the space between the first preset distance and the second preset distance from the glass outside the vehicle is imaged in the target image;

[0055] the upper region is the region formed after the space outside the second preset distance from the glass outside the vehicle is imaged in the target image.

[0056] Here, the first preset distance may be less than the second preset distance. For example, the first preset distance may be 10 meters, and the second preset distance may be 50 meters. Then the lower region is the region formed after the space within 10 meters from the glass outside the vehicle is imaged in the target image; the middle region is the region formed after the space between 10 meters and 50 meters from the glass outside the vehicle is imaged in the target image; the upper region is the region formed after the space outside 50 meters from the glass outside the vehicle is imaged in the target image. In some embodiments, the space outside 50 meters is the space greater than 50 meters and less than 100 meters. Figure 3C Taking the front windshield as an example, the positions of the first preset distance and the second preset distance are shown. Among them, the first preset distance and the second preset distance are the distances from the outside of the vehicle to the front windshield. The first preset distance is 10 meters, the second preset distance is 50 meters, and 100 meters is the distance boundary after the space outside 50 meters is imaged in the image. The embodiments of the present application do not limit the first preset distance and the second preset distance.

[0057] In some embodiments, the upper region, the middle region, and the lower region can be determined according to the position of the image acquisition device for acquiring the target image. The positions of the upper region, the middle region, and the lower region corresponding to image acquisition devices at different positions are different. During implementation, markers can be placed at the boundaries of 10 meters and 50 meters outside the vehicle, and then the image acquisition device is used to acquire an image. After finding the markers at 10 meters and 50 meters in the image, draw a line through the markers, and the image can be divided into three regions, namely the upper region, the middle region, and the lower region. The embodiments of the present application do not limit the method for determining the upper region, the middle region, and the lower region.

[0058] In some embodiments, the cleanliness can be divided into 11 grades, and Table 1 shows the definition methods for different grades.

[0059] Table 1: Cleanliness grades and definition methods

[0060]

[0061] According to the definition of cleanliness in Table 1, the cleanliness of the glass in different regions of the target image can be obtained.

[0062] Step S303: Based on the cleanliness of the glass in different regions of the target image, determine the cleanliness of the glass corresponding to the target image.

[0063] Here, the method for determining the cleanliness of the glass corresponding to the target image can include: determining the maximum value of the cleanliness of the glass in different regions of the target image as the cleanliness of the glass corresponding to the target image. Since the maximum value of the cleanliness can better reflect whether the glass needs to be cleaned, therefore, the maximum value of the cleanliness can be used to represent the overall cleanliness of the glass. In some embodiments, the average value, median, etc. of the cleanliness of the glass in different regions of the target image can also be determined as the cleanliness of the glass corresponding to the target image. The embodiments of the present application do not limit the method for determining the cleanliness of the glass corresponding to the target image.

[0064] In the embodiments of the present application, when the cleanliness information includes cleanliness, by obtaining the cleanliness of the glass in different regions of the target image, the cleanliness of the entire glass can be obtained. Since the final cleanliness of the entire glass is determined according to the cleanliness of the glass in different regions of the target image, taking into account the influence of the cleanliness of the glass at different positions on the driver's cleaning decision, therefore, the final obtained cleanliness of the entire glass can better reflect the cleanliness when the driver actually makes a cleaning decision, thereby providing a cleaning reminder that is more in line with the driver's habits for the driver.

[0065] In some embodiments, the cleanliness information includes the amount of change in cleanliness, the target image is any image in the set of historical images. Correspondingly, the implementation of determining the cleanliness information of the glass corresponding to the target image may include the following steps S401 to S403:

[0066] Step S401: Determine the first cleanliness of the glass corresponding to the target image;

[0067] Here, the images in the set of historical images may have a chronological relationship, so as to obtain the amount of change in cleanliness through the images with chronological order. In some embodiments, the method for determining the first cleanliness may refer to the above steps S301 to S303.

[0068] Step S402: Determine the second cleanliness of the glass corresponding to the previous image of the target image in the set of historical images;

[0069] Here, the previous image of the target image is the image that is one frame before the target image in terms of time sequence. For example, if the target image is the 10th frame, the previous image of the target image may be the 9th frame image. In some embodiments, the previous image of the target image may also be determined according to the acquisition frequency of the images. For example, if one frame is acquired every 2 seconds, the previous image of the target image is the image acquired 2 seconds before the target image. The method for determining the second cleanliness may also refer to the above steps S301 to S303.

[0070] Step S403: Based on the first cleanliness and the second cleanliness, determine the amount of change in cleanliness of the glass corresponding to the target image.

[0071] Here, the implementation of step S403 may include: subtracting the second cleanliness from the first cleanliness to obtain the amount of change in cleanliness of the glass corresponding to the target image.

[0072] In the embodiments of the present application, when the images in the set of historical images have a chronological relationship, the amount of change in cleanliness of the glass corresponding to the target image can be obtained by acquiring the cleanliness of the target image and the previous image of the target image.

[0073] Step S203: Based on the cleanliness information of the glass corresponding to each image, obtain the execution decision of the driver, where the execution decision includes the decision to perform cleaning;

[0074] Here, the implementation of step S203 may include: obtaining the driver's execution decision for the cleanliness information of the glass corresponding to each image; or it may include: setting a certain empirical threshold, and after the cleanliness information of the glass corresponding to each image exceeds the empirical threshold, then obtaining the driver's execution decision, thereby reducing the calculation amount. At the same time, when quickly obtaining the driver's decision to execute cleaning, the conditions related to the cleanliness of the vehicle's glass can be obtained.

[0075] In some embodiments, the cleanliness information includes: cleanliness and the amount of change in cleanliness. Correspondingly, the implementation of step S203 may include the following steps S2031 and S2032:

[0076] Step S2031: When the cleanliness of the glass corresponding to each image is greater than a first threshold, obtain the driver's execution decision;

[0077] Here, the first threshold may be the above-mentioned empirical threshold, that is, usually, after the cleanliness is greater than this empirical threshold, a cleaning decision will be executed.

[0078] Step S2032: When the amount of change in the cleanliness of the glass corresponding to each image is greater than a second threshold, obtain the driver's execution decision.

[0079] Here, the second threshold may be the above-mentioned empirical threshold, that is, usually, after the amount of change in cleanliness is greater than this empirical threshold, a cleaning decision will be executed. This is for the situation where when the driver suddenly encounters rainy, snowy or other weather during driving, the driver may execute a cleaning decision.

[0080] In the embodiments of the present application, by setting a first threshold for cleanliness and a second threshold for the amount of change in cleanliness, the calculation amount can be reduced, and when quickly obtaining the driver's decision to execute cleaning, the conditions related to the cleanliness of the vehicle's glass can be obtained.

[0081] Step S204: Based on the cleanliness information of the glass corresponding to each image and the driver's execution decision, determine the cleaning conditions of the vehicle, where the cleaning conditions are the conditions related to the cleanliness of the vehicle's glass when the driver executes a cleaning decision.

[0082] Here, when the cleanliness information includes cleanliness, the cleaning conditions related to the cleanliness of the vehicle's glass may be a cleanliness threshold, that is, according to the cleanliness of the glass corresponding to each image and the driver's execution decision, determine the cleanliness threshold of the vehicle's glass when the driver executes a cleaning decision.

[0083] When the cleanliness information includes the amount of change in cleanliness, the cleaning condition related to the cleanliness of the vehicle's glass can be the threshold value of the amount of change in cleanliness. That is, according to the amount of change in the cleanliness of the glass corresponding to each image and the driver's execution decision, when determining the driver's cleaning decision, the threshold value of the amount of change in the cleanliness of the vehicle's glass is obtained, so as to obtain the condition related to the cleanliness of the vehicle's glass when the driver executes the cleaning decision.

[0084] In the embodiments of the present application, first, a set of historical images of the vehicle's glass is obtained; then, the cleanliness information of the glass corresponding to each image in the image set is determined; after that, the execution decision of the driver under the above cleanliness information condition is obtained. Finally, according to the cleanliness information of the glass corresponding to each image and the driver's execution decision, the condition related to the cleanliness of the vehicle's glass when the driver executes the cleaning decision is obtained.

[0085] In some embodiments, the cleanliness information includes cleanliness. After step S101, "obtain the cleanliness information of the current vehicle's glass", the following step S501 is further included:

[0086] Step S501: When the cleanliness of the current vehicle's glass is greater than the third threshold, control the cleaning device of the vehicle to clean the glass.

[0087] Here, the third threshold can be the threshold that completely affects the driver's driving, or the threshold at which most drivers will execute the cleaning decision after exceeding this threshold. For example, in Table 1, the cleanliness includes 11 levels, and the third threshold can be the 9th level. The cleaning device can be a windshield wiper.

[0088] In the embodiments of the present application, by controlling the cleaning device of the vehicle to clean the glass when the cleanliness of the current vehicle's glass is greater than the third threshold, manual cleaning operations can be reduced, making the driving of the vehicle more intelligent.

[0089] The embodiments of the present application also provide a control method for the cleanliness of a vehicle's glass, which can monitor the cleanliness of the front windshield in real time and make timely feedback according to the driver's habits, and quickly perform cleaning actions in case of emergency. The method includes the following steps:

[0090] Step 1: Detect the cleanliness of the front windshield in real time;

[0091] Here, the cleanliness is defined according to the clarity of the front windshield when the driver looks at different distances outside the glass, with a total of 11 levels, as shown in Table 1 above. 1 means the clearest, and 11 means the least clear. The different distances are 10 meters (i.e., the above first preset distance), 50 meters (i.e., the above second preset distance), and 100 meters (i.e., the distance boundary of the above image).

[0092] Step 2: Generate a real-time relationship between the driver and the windshield cleanliness (i.e., the above-mentioned cleaning condition) according to the driver's interaction habits with the windshield during driving;

[0093] Step 3: When the cleanliness reaches the level that affects the driver's line of sight (i.e., in the case where the driver executes the cleaning decision predicted above), make a timely feedback to remind the driver;

[0094] Step 4: When the cleanliness suddenly and seriously affects the driver's line of sight due to various emergencies (i.e., in the case where the cleanliness of the current vehicle's glass is greater than the third threshold), enforce the cleaning or ventilation operation in a timely manner.

[0095] The embodiment of the present application also provides a method for controlling the cleanliness of vehicle glass, as Figure 4 shown, this method includes the following steps S601 to step S611:

[0096] Step S601: Perform real-time cleanliness detection during vehicle driving;

[0097] Step S602: Determine whether the current cleanliness seriously affects the driver's line of sight (i.e., the case where the cleanliness of the current vehicle's glass is greater than the third threshold); if so, enter step S603; if not, enter step S204.

[0098] Here, seriously affecting the driver's line of sight refers to the situation where the detected current cleanliness value is too large (exceeding the third threshold).

[0099] Step S603: Feed back to the driver and automatically start the cleaning operation;

[0100] Step S604: Determine whether the current cleanliness exceeds the general threshold (i.e., the above-mentioned first preset threshold); if so, enter step S605; if not, directly enter step S606;

[0101] Step S605: Feed back to the driver, and the driver makes a decision on whether to clean;

[0102] Step S606: Record the current cleanliness and the driver's decision (i.e., the driver's decision on whether to clean);

[0103] Step S607: Determine whether the difference between the current cleanliness and the previous cleanliness (i.e., the above-mentioned cleanliness change amount) exceeds a certain threshold (i.e., the above-mentioned second preset threshold); if so, enter step S608; if not, directly enter step S609;

[0104] Step S608: Feed back to the driver, and the driver makes a decision on whether to clean;

[0105] Step S609: Record the current cleanliness difference and the driver's decision;

[0106] Step S610: Create a real-time "cleanliness - driver behavior" relationship (i.e., the cleaning conditions related to the cleanliness of the vehicle's glass when the driver makes a cleaning decision as described above);

[0107] Step S611: According to the established real-time relationship, detect the cleanliness in real time and adaptively feedback it to the driver.

[0108] In the embodiment of the present application, first, a real-time dynamic relationship between the "driver - front windshield cleanliness" is created, and then, according to the driving situation, it is intelligently feedback to the driver or a forced cleaning action is taken, thus proposing a solution to monitor the front windshield cleanliness through the real-time dynamic relationship to ensure driving safety.

[0109] The embodiment of the present application also provides a control device for the cleanliness of the vehicle glass. The device includes:

[0110] A processor of the vehicle, configured to obtain the cleanliness information of the glass of the current vehicle and the cleaning conditions of the vehicle, where the cleaning conditions are the conditions related to the cleanliness of the glass of the vehicle when the driver makes a cleaning decision; based on the cleanliness information of the glass of the current vehicle and the cleaning conditions, predict the execution decision of the driver, where the execution decision includes a decision to perform cleaning; in the case where the execution decision is the decision to perform cleaning, output a prompt message to the driver, where the prompt message is used to prompt the driver to clean the glass of the vehicle;

[0111] An output device of the vehicle, configured to output a prompt message to the driver.

[0112] In some embodiments, the device further includes:

[0113] An image acquisition device, configured to obtain a set of historical images of the glass of the vehicle;

[0114] Correspondingly, the processor of the vehicle is further configured to, for each image in the set of historical images, determine the cleanliness information of the glass corresponding to each image; based on the cleanliness information of the glass corresponding to each image, obtain the execution decision of the driver, where the execution decision includes a decision to perform cleaning; based on the cleanliness information of the glass corresponding to each image and the execution decision of the driver, determine the cleaning conditions of the vehicle, where the cleaning conditions are the conditions related to the cleanliness of the glass of the vehicle when the driver makes a cleaning decision.

[0115] The description of the above device embodiments is similar to that of the above method embodiments and has similar beneficial effects to those of the method embodiments. In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments. For the technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0116] The embodiments of the present application further provide a vehicle, including the above control device for the cleanliness of vehicle glass.

[0117] It should be noted here that the descriptions of the above embodiments tend to emphasize the differences between the embodiments, and their similarities or likenesses can be referred to each other. The descriptions of the above device, storage medium, computer program, and computer program product embodiments are similar to those of the above method embodiments and have similar beneficial effects to those of the method embodiments. For the technical details not disclosed in the device, storage medium, computer program, and computer program product embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0118] It should be understood that the term "one embodiment" or "an embodiment" mentioned throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of the present application. Therefore, the appearances of "in one embodiment" or "in an embodiment" throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above steps / processes do not mean the order of execution is prior or subsequent. The order of execution of each step / process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The sequence numbers of the embodiments of the present application above are only for description and do not represent the advantages or disadvantages of the embodiments.

[0119] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0120] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0121] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0122] In addition, each functional unit in the embodiments of this application can be all integrated in a processing unit, or each unit can be separately a unit alone, or two or more units can be integrated in a unit; the above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.

[0123] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM), magnetic disks, or optical disks and other various media that can store program codes.

[0124] Alternatively, if the above-mentioned integrated units of this application are implemented in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the related technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of this application. And the foregoing storage medium includes: removable storage devices, ROM, magnetic disks, or optical disks and other various media that can store program codes.

[0125] As described above, this is only the implementation mode of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. A control method for the cleanliness of vehicle glass, characterized in that, Including: Obtain a set of historical images of the glass of the vehicle; for each image in the set of historical images, determine the cleanliness information of the glass corresponding to each image; Based on the cleanliness information of the glass corresponding to each image, obtain the execution decision of the driver, wherein the execution decision includes a decision to perform cleaning; based on the cleanliness information of the glass corresponding to each image and the execution decision of the driver, determine the cleaning condition of the vehicle; obtain the cleanliness information of the glass of the current vehicle and the cleaning condition of the vehicle, wherein the cleaning condition is the condition related to the cleanliness of the glass of the vehicle when the driver makes a cleaning decision; Based on the cleanliness information of the glass of the current vehicle and the cleaning condition, predict the execution decision of the driver, wherein the execution decision includes a decision to perform cleaning; In the case where the execution decision is the decision to perform cleaning, output a prompt message to the driver, wherein the prompt message is used to prompt the driver to clean the glass of the vehicle; Wherein the cleanliness information includes cleanliness, the target image is any image in the set of historical images, and determining the cleanliness information of the glass corresponding to the target image includes: determining the clarity of the glass in different regions of the target image; based on the clarity of the glass in different regions of the target image and the positions of the different regions in the target image, determine the cleanliness of the glass in different regions of the target image; based on the cleanliness of the glass in different regions of the target image, determine the cleanliness of the glass corresponding to the target image; The different regions include the upper region, the middle region, and the lower region in the target image, wherein: the lower region is the region formed after imaging in the target image of the space within a first preset distance from the glass outside the vehicle; the middle region is the region formed after imaging in the target image of the space between the first preset distance and the second preset distance from the glass outside the vehicle; the lower region is the region formed after imaging in the target image of the space outside the second preset distance from the glass outside the vehicle.

2. The control method according to claim 1, characterized in that, The cleanliness information includes: cleanliness and cleanliness change amount. Correspondingly, obtaining the execution decision of the driver based on the cleanliness information of the glass corresponding to each image includes: In the case where the cleanliness of the glass corresponding to each image is greater than a first threshold, obtain the execution decision of the driver; In the case where the cleanliness change amount of the glass corresponding to each image is greater than a second threshold, obtain the execution decision of the driver.

3. The control method according to claim 1 or 2, characterized in that, The cleanliness information includes the cleanliness change amount, the images in the set of historical images have a chronological relationship, and the target image is any image in the set of historical images, Correspondingly, determining the cleanliness information of the glass corresponding to the target image includes: Determine the first cleanliness of the glass corresponding to the target image; Determine the second cleanliness of the glass corresponding to the previous image of the target image in the historical image set; Based on the first cleanliness and the second cleanliness, determine the change amount of the cleanliness of the glass corresponding to the target image.

4. The control method according to any one of claims 1 or 2, characterized in that, The cleanliness information includes cleanliness. After obtaining the cleanliness information of the glass of the current vehicle, it further includes: When the cleanliness of the glass of the current vehicle is greater than a third threshold, control the cleaning device of the vehicle to clean the glass.

5. A control device for the cleanliness of vehicle glass, characterized in that, It includes: An image acquisition device for acquiring a historical image set of the glass of the vehicle; The processor of the vehicle is used to: for each image in the historical image set, determine the cleanliness information of the glass corresponding to each image; based on the cleanliness information of the glass corresponding to each image, obtain the execution decision of the driver, where the execution decision includes a decision to perform cleaning; based on the cleanliness information of the glass corresponding to each image and the execution decision of the driver, determine the cleaning conditions of the vehicle; Obtain the cleanliness information of the glass of the current vehicle and the cleaning conditions of the vehicle, where the cleaning conditions are the conditions related to the cleanliness of the glass of the vehicle when the driver makes a cleaning decision; Based on the cleanliness information of the glass of the current vehicle and the cleaning conditions, predict the execution decision of the driver, where the execution decision includes a decision to perform cleaning; When the execution decision is the decision to perform cleaning, output a prompt message to the driver, where the prompt message is used to prompt the driver to clean the glass of the vehicle; Wherein, the cleanliness information includes cleanliness, the target image is any image in the historical image set, and determining the cleanliness information of the glass corresponding to the target image includes: determining the clarity of the glass in different regions of the target image; based on the clarity of the glass in different regions of the target image and the positions of the different regions in the target image, determine the cleanliness of the glass in different regions of the target image; based on the cleanliness of the glass in different regions of the target image, determine the cleanliness of the glass corresponding to the target image; The different regions include the upper region, the middle region and the lower region in the target image, where: the lower region is the region formed after imaging in the target image of the space within a first preset distance from the glass outside the vehicle; the middle region is the region formed after imaging in the target image of the space between the first preset distance and the second preset distance from the glass outside the vehicle; the lower region is the region formed after imaging in the target image of the space outside the second preset distance from the glass outside the vehicle.

6. A vehicle, characterized in that, It includes the control device for the cleanliness of the vehicle glass described in claim 5.

Images