Control Method, Device, Vehicle and Storage Medium of Intelligent Windshield Wiper

Abstract

The present invention belongs to the technical field of intelligent vehicles, and discloses a control method, device, vehicle and storage medium for an intelligent windshield wiper. The control method includes: when it is detected that the real-time information of the vehicle meets a preset condition, turning on a camera to obtain a real-time image of the vehicle window; comparing the similarity between the real-time image of the vehicle window and a preset image set, where the preset image set includes at least one preset image, and the preset image includes the degree of blurriness of the image and the reason for the blurriness; taking the degree of blurriness of the preset image with the highest similarity to the real-time image of the vehicle window as the target degree of blurriness of the real-time image of the vehicle window; and if the target degree of blurriness is greater than a first preset blurriness threshold, executing a corresponding vehicle window cleaning strategy according to the reason for the blurriness corresponding to the target degree of blurriness. The control method of the present invention can be more accurately applied to various scenarios such as light rain, window fogging, frosting, and icing caused by changes in temperature and humidity, improving driving safety.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent vehicles, and particularly to a control method, device, vehicle and storage medium for intelligent windshield wipers. Background Art

[0002] In the current design of intelligent windshield wipers, most of them obtain rainfall data through a rainfall sensor and automatically start the vehicle windshield wipers according to the rainfall data to achieve intelligent control of the windshield wipers and improve the driving experience. However, this control method is not suitable for other scenarios where the windshield wipers need to be started, such as when the rainfall is small, there is fog, frost, or ice. Summary of the Invention

[0003] The present application provides a control method, device, vehicle and storage medium for intelligent windshield wipers, so as to solve the problem in the related prior art that it is not suitable for scenarios where the windshield wipers are started by rainfall, with a wider range of applicable scenarios and higher driving safety.

[0004] The first aspect embodiment of the present invention provides a control method for intelligent windshield wipers, including:

[0005] The control method for intelligent windshield wipers includes:

[0006] When it is detected that the real-time information of the vehicle meets a preset condition, turn on the camera to obtain a real-time image of the vehicle window;

[0007] Compare the similarity between the real-time image of the vehicle window and a preset image set, where the preset image set includes at least one preset image, and the preset image includes the degree of blurriness of the image and the reason for the blurriness;

[0008] Use the degree of blurriness of the preset image with the highest similarity to the real-time image of the vehicle window as the target degree of blurriness of the real-time image of the vehicle window; and

[0009] If the target degree of blurriness is greater than a first preset blurriness threshold, execute a corresponding vehicle window cleaning strategy according to the reason for the blurriness corresponding to the target degree of blurriness;

[0010] Wherein, the real-time information of the vehicle includes the location of the vehicle, the weather at the location of the vehicle, and the operation instructions received by the vehicle, and the weather at the location of the vehicle includes the temperature and / or humidity at the location of the vehicle.

[0011] According to the above technical means, the embodiments of the present application avoid using a rain sensor to control the activation of the windshield wiper, but instead implement it based on a vehicle camera. By obtaining real-time vehicle information, it is dynamically determined whether to activate the camera to obtain real-time images. After activation, by comparing the real-time window image with the images in the database, the preset image in the database that is closest to the real-time image is found, and the blurriness of this preset image is used as the target blurriness of the corresponding real-time image. The blurriness information of the preset image can improve the accuracy of judging the blurriness of the real-time image.

[0012] Optionally, in an embodiment of the present application, when the real-time information of the vehicle meets any of the following preset conditions, the camera is activated to obtain a real-time window image:

[0013] The location where the vehicle is located enters a preset area;

[0014] The difference between the temperature at the location where the vehicle is located and the internal temperature of the vehicle exceeds a preset temperature threshold;

[0015] The difference between the humidity at the location where the vehicle is located and the internal humidity of the vehicle exceeds a preset humidity threshold;

[0016] The operation instruction received by the vehicle is an instruction for the user to manually activate the windshield wiper.

[0017] According to the above technical means, the embodiments of the present application can determine whether to activate the camera to obtain a real-time window image based on whether the real-time position of the vehicle is a specified area, whether the temperature difference or humidity difference inside and outside the vehicle reaches critical values that are likely to cause atomization, water droplet formation, icing, frosting, etc., or any of the situations when the user manually activates the windshield wiper.

[0018] Optionally, in an embodiment of the present application, the camera is activated to obtain real-time window images at different time intervals, and the method for adjusting the different time intervals includes any of the following:

[0019] When the target blurriness is less than a second preset blurriness threshold, a real-time window image is obtained at a first time interval, and the second preset blurriness threshold is less than the first preset blurriness threshold;

[0020] When the target blurriness is greater than the second preset blurriness threshold and less than the first preset blurriness threshold, a real-time window image is obtained at a second time interval, and the second time interval is less than the first time interval;

[0021] If the time for the real-time window image to reach the first preset blurriness threshold gradually decreases, a real-time window image is obtained at a third time interval, and the third time interval is less than the second time interval;

[0022] If the target blurriness is less than the first preset blurriness threshold after exceeding the first preset time, obtain a real-time image of the window within the first time interval.

[0023] According to the above means, after the camera is turned on, it is necessary to automatically adjust the time interval for obtaining the real-time image of the window according to the actual situation, so that the camera can more accurately capture the first preset blurriness threshold when the windshield wiper is started, and improve the accuracy of timely starting the windshield wiper.

[0024] Optionally, in an embodiment of the present application, the first preset blurriness threshold is determined according to the blurriness of the real-time image of the window corresponding to the operation instruction received by the vehicle when the instruction for the user to manually activate the windshield wiper is received.

[0025] According to the above means, the embodiment of the present application can record the blurriness corresponding to the real-time image of the window when the user manually activates the windshield wiper, and automatically adjust the first preset range by recording multiple times and statistically learning the threshold for the user's habitual activation of the windshield wiper.

[0026] Optionally, in an embodiment of the present application, before comparing the similarity between the real-time image of the window and the preset image set, preprocess the real-time image of the window;

[0027] Wherein, the preprocessing method is: divide the real-time image of the window into N regions, and determine the first pixel average value of each region; determine the pixel range according to the first pixel average value; delete the regions in the N regions that exceed the pixel range; and perform interpolation processing on the deleted regions;

[0028] The similarity comparison method is: determine the second pixel average value of each region in the image after interpolation processing; divide each preset image into N regions, and determine the third pixel average value of each region in each preset image; compare the similarity between the second pixel average value and the third pixel average value of the corresponding regions in the image after interpolation processing and the preset image; and average the similarities of the N regions to obtain the similarity between the preprocessed image and the preset image.

[0029] According to the above means, the embodiment of the present application can improve the accuracy of judging the blurry situation through preprocessing when the obtained real-time image is greatly affected by the environment.

[0030] Optionally, in an embodiment of the present application, the window cleaning strategy includes starting the windshield wiper and window heating. The reasons for the blurring include atomization, water droplet formation, icing, and frosting. When the target blurring degree is greater than the first preset blurring threshold and the vehicle does not receive a user's manual instruction to start the windshield wiper, the windshield wiper is automatically started once, and this step is repeated. When the time for the real-time window image to reach the first preset blurring threshold is less than the first preset time, the windshield wiper is continuously started. When the real-time window image reaches the first preset blurring threshold and the reason for the blurring is icing or frosting, window heating is started.

[0031] According to the above means, in each embodiment of the present application, when the blurring degree of the real-time window image exceeds the threshold, the windshield wiper is turned on once. If the blurring becomes faster and reaches a certain level, the windshield wiper is continuously started. If it is found that the blurring is caused by icing or frosting, window heating can be used to better solve the problem of window blurring.

[0032] Optionally, in an embodiment of the present application, the intelligent windshield wiper start or the camera is turned off when any of the following conditions is met:

[0033] If the vehicle does not receive a user's manual instruction to start the windshield wiper and the blurring degree of the real-time window image is less than the first preset blurring threshold, the intelligent windshield wiper start is turned off;

[0034] If the operation instruction received by the vehicle is a user's manual instruction to start the windshield wiper, the intelligent windshield wiper start is turned off;

[0035] If the blurring degree of the real-time window image is less than the first preset blurring threshold within the second preset time and the real-time information of the vehicle does not meet the preset conditions, the camera is turned off.

[0036] According to the above technical means, the embodiments of the present application can automatically determine the moments to turn off the windshield wiper and the camera, realizing comprehensive and intelligent control of the windshield wiper.

[0037] The second aspect of the present application provides a control device for an intelligent windshield wiper, including: an image acquisition module, configured to turn on a camera to obtain a real-time image of the vehicle window when it is detected that the real-time information of the vehicle meets a preset condition; a comparison module, configured to compare the real-time image of the vehicle window with a preset image set, where the preset image set includes at least one preset image, and the preset image includes the blur information of the image, and the blur information includes the degree of blur and the reason for the blur; a determination module, configured to use the degree of blur of the preset image with the highest similarity to the real-time image of the vehicle window as the target degree of blur of the real-time image of the vehicle window; and an action module, configured to, if the target degree of blur is greater than a first preset blur threshold, execute a corresponding vehicle window cleaning strategy according to the blur information corresponding to the degree of blur; where the real-time information of the vehicle includes the location of the vehicle, the weather at the location of the vehicle, and the operation instructions received by the vehicle, and the weather at the location of the vehicle includes the temperature and / or humidity at the location of the vehicle.

[0038] Optionally, in an embodiment of the present application, it further includes an image preprocessing module, configured to preprocess the real-time image of the vehicle window before comparing the similarity between the real-time image of the vehicle window and the preset image set.

[0039] The third aspect of the present application provides a vehicle, including the control device for the intelligent windshield wiper as described above.

[0040] The fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, characterized in that the program is executed by a processor to implement the control method for the intelligent windshield wiper as described above.

[0041] The embodiments of the present application have the following beneficial effects:

[0042] (1) The embodiments of the present application can determine that when the vehicle enters a specific area, a specific weather environment or the user manually turns on the windshield wiper, start obtaining real-time data of the vehicle window, and control the windshield wiper to turn on according to the degree of blur of the vehicle window. This control method avoids controlling the windshield wiper to turn on according to the rainfall, and can be more accurately applied to various scenarios such as light rainfall, window fogging, frosting, and icing caused by changes in temperature and humidity, realizing the intelligent control of the windshield wiper and improving driving safety.

[0043] (2) The embodiments of the present application compare the real-time collected vehicle window image with the blurred pictures stored in the database. The blurred pictures stored in the database include information such as the corresponding degree of blur and the reason for the blur, making the determined degree of blur of the real-time image of the vehicle window more accurate and improving the accuracy of windshield wiper control.

[0044] (3) The embodiments of the present application can adjust the time interval for collecting real-time images according to the blur situation of the real-time image of the vehicle window, realizing dynamic adjustment of the collection frequency.

[0045] (4) Embodiments of the present application can record the threshold value of the window obscurity corresponding to when the user manually turns on the windshield wiper, and adjust the window obscurity situation corresponding to when the windshield wiper is automatically turned on according to this threshold value.

[0046] (5) Embodiments of the present application can determine whether it is necessary to continuously start the windshield wiper according to the time required for the window to reach the same obscurity situation.

[0047] (6) Embodiments of the present application can automatically determine whether it is necessary to stop the windshield wiper from starting and stop acquiring real-time images of the window.

[0048] (7) When the window image is greatly affected by the environment resulting in large image differences, embodiments of the present application can preprocess the acquired window image to improve the accuracy of determining the obscurity situation.

[0049] Additional aspects and advantages of the present application will be given in part in the following description, will become apparent in part from the following description, or will be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic flowchart of a control method for an intelligent windshield wiper provided by an embodiment of the present application;

[0051] Figure 2 It is a schematic structural block diagram of a control device for an intelligent windshield wiper provided by an embodiment of the present application;

[0052] Figure 3 It is a schematic structural block diagram of a vehicle provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as a limitation of the present application.

[0054] In this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0055] The control method, device, vehicle, and storage medium of the intelligent windshield wiper according to the embodiments of the present application will be described below with reference to the accompanying drawings. As mentioned in the above background art, currently, the windshield wiper is mostly started by rainfall, but there are far more scenarios where the windshield wiper needs to be started, especially when the external front windshield fogs up due to temperature and humidity changes, and in special climates, the front windshield may also frost / ice up. In such cases, if the driver cannot timely judge and activate the windshield wiper, traffic accidents may occur. For example, when the vehicle passes through a tunnel, due to the large difference in temperature and humidity between the inside and outside of the tunnel, the water droplets suspended in the air can fog up / condense into water droplets on the vehicle's front windshield within a few seconds. The limited vision and special environment inside the tunnel make it impossible for the driver to distinguish whether it is fogging up inside or outside the vehicle, and thus unable to operate correctly and safely. Another example is when the rainfall is very small and the rainfall sensor fails to detect enough rainfall, the front windshield will also be blocked and the windshield wiper will not be automatically activated. To solve these technical problems, the present application provides a control method for an intelligent windshield wiper. Since window fogging, water droplet formation, icing, frosting, etc. will all affect the blurring of the window, this method starts to obtain the real-time image of the window when the vehicle may become blurred, and controls the activation of the windshield wiper according to the blurring condition of the real-time image of the window. Thus, it solves the situation in the prior art where it is not applicable to control the windshield wiper by rainfall, has a wider application range, and more accurate control.

[0056] The control scheme of the intelligent windshield wiper proposed in the present application is applicable to all vehicles equipped with windshield wipers, including vehicles that do not travel on land and vehicles that travel on land. Vehicles that do not travel on land include airplanes, spacecraft, and ships. Land vehicles include motorcycles, electric vehicles, cars, sedans, trucks, lorries, trains, buses, subways, light rails, snowmobiles, etc.

[0057] In the first aspect of the embodiments of the present application, a control method for an intelligent windshield wiper is provided. Figure 1 It is a flowchart of the control method for the intelligent windshield wiper provided by the embodiments of the present application.

[0058] As Figure 1 shown, the control method of the intelligent windshield wiper includes the following steps:

[0059] In step S101, when it is detected that the real-time information of the vehicle meets the preset conditions, the camera is turned on to obtain the real-time image of the window; wherein, the real-time information of the vehicle includes the location of the vehicle, the weather at the location of the vehicle, and the operation instructions received by the vehicle, and the weather at the location of the vehicle includes the temperature and / or humidity at the location of the vehicle.

[0060] It is understandable that this step is to determine the timing of turning on the camera to obtain real-time images of the vehicle window. Turning on the camera means that the vehicle may be in a situation where the window starts to become blurred, and it is necessary to enter the monitoring state to monitor the window situation in real time so as to take subsequent measures in a timely manner. The real-time image of the vehicle window can be an image of the front window, or a real-time image of the window at other positions, such as the side window or the rear window.

[0061] In a preferred embodiment, when the real-time information of the vehicle meets any of the following preset conditions, the camera is turned on to obtain real-time images of the vehicle window: the position where the vehicle is located enters a preset area; the difference between the temperature at the position where the vehicle is located and the internal temperature of the vehicle exceeds a preset temperature threshold; the difference between the humidity at the position where the vehicle is located and the internal humidity of the vehicle exceeds a preset humidity threshold; the operation instruction received by the vehicle is an instruction for the user to manually enable the windshield wiper.

[0062] It is understandable that as long as any of the above preset conditions is met, the camera can be turned on to enter the monitoring state. Of course, in actual situations, multiple or all of these conditions may be met simultaneously, and this still does not affect entering the monitoring state. Specifically, it can be determined that the real-time position of the vehicle is in a special area where window fogging, water droplet formation, icing, frosting, etc. are likely to occur. For example, when it can include areas such as tunnels, mountain roads, and forests, the camera is turned on to obtain real-time images of the vehicle window. In order to make the judgment and control more timely, it is best to make the judgment at the entrance and vicinity of the area where window fogging, water droplet formation, icing, frosting, etc. are likely to occur. For example, it is determined that the real-time position of the vehicle is at or near the entrance of a tunnel, at or near the entrance of a mountain road, or at or near the entrance of a forest.

[0063] It can also be determined that when the temperature difference or humidity difference inside and outside the vehicle reaches the preset temperature threshold or preset humidity threshold, the camera is turned on to obtain real-time images of the vehicle window. The preset temperature threshold or preset humidity threshold can be adjusted according to the actual situation. For example, under standard atmospheric pressure, when the temperature difference between the inside and outside of the vehicle exceeds 3°C, the window is likely to fog up, affecting driving safety; when the temperature difference is large enough, even water droplet formation, frosting, icing, etc. that affect the line of sight may occur. When the atmospheric pressure changes, the temperature difference threshold is adjusted in the same proportion. When the humidity difference between the inside and outside of the vehicle exceeds 57.4%RH, the window is also likely to fog up.

[0064] It can also be determined that when the operation instruction received by the vehicle is an instruction for the user to manually enable the windshield wiper, the camera is turned on to obtain real-time images of the vehicle window. Generally, when the user manually starts the windshield wiper, it means that the user believes that the current window view may affect safe driving. At this time, even if the vehicle has not entered a special area, or the temperature difference or humidity difference has not been detected, the camera needs to be turned on to enter the monitoring state.

[0065] In step S102, the real-time image of the vehicle window is compared with a preset image set. The preset image set contains at least one preset image, and the preset image includes the degree of blurriness of the image and the reason for the blurriness.

[0066] The preset image set contains at least one preset image. To make the similarity comparison more accurate, more preset images are needed. These preset images are pictures of atomization, water droplet formation, icing, frosting, etc. Each preset image is marked with the corresponding degree of blurriness of the vehicle window and the reason for the blurriness. Therefore, the degree of blurriness of the target image in the database is also the degree of blurriness of the corresponding real-time image of the vehicle window.

[0067] Exemplarily, the degrees of blurriness are 0%, 5%, 10%, 20%, 30%, 40%, etc.; the reasons for the blurriness are such as atomization, water droplet formation, icing, frosting, etc. The same degree of blurriness can correspond to multiple images under different light intensities, such as a 10% atomization image at night, a 10% atomization image in the evening, a 10% atomization image in the sun, a 10% atomization image on a cloudy day, etc. The combination of the reason for the blurriness and multiple images with the same blurriness in different scenarios can further improve the accuracy of the similarity comparison.

[0068] In some preferred embodiments, the preset image set is stored in a database, which can be a local database or a cloud database. When comparing with the pictures in the local database, it does not depend on the network and can complete the recognition comparison more quickly and obtain the judgment result quickly. When comparing with the pictures in the cloud database, the cloud database will update the pictures of atomization, water droplet formation, icing, frosting, etc. regularly or irregularly, making the comparison result more accurate. In addition, when comparing with the pictures in the local database, the cloud database can also push the newly added atomization / water droplet formation / icing / frosting pictures to the local database regularly or irregularly to achieve the dynamic update of the abnormal database and further improve the accuracy of the comparison result.

[0069] In step S103, the degree of blurriness of the preset image with the highest similarity to the real-time image of the vehicle window is used as the target degree of blurriness of the real-time image of the vehicle window.

[0070] It can be understood that by comparison, the preset image in the database that is most similar to the real-time image of the vehicle window is obtained. The corresponding degree of blurriness and the reason for the blurriness of this preset image are the degree of blurriness and the reason for the blurriness of the real-time image of the vehicle window, such as atomization / water droplet formation 10%, icing / frosting 20%, etc.

[0071] In some preferred embodiments, during vehicle driving, sometimes the acquired real-time window image may be greatly different from the actual image due to the driving environment, resulting in inaccurate judgment of the actual blur situation of the window when comparing the real-time window image with the preset image set in the database. For example, when there is another vehicle in front of the host vehicle, the acquired real-time vehicle image will include the image of the preceding vehicle. Usually, the area of the image region occupied by the preceding vehicle is not too large. At this time, in order to make the judgment result more accurate, it is necessary to preprocess the acquired real-time window image before comparing it with the preset image set.

[0072] At this time, the preprocessing method is as follows: divide the real-time window image into N regions, and determine the first pixel average value of each region; determine the pixel range according to the first pixel average value; delete the regions in the N regions that exceed the pixel range; and perform interpolation processing on the deleted regions.

[0073] Among them, the interpolation processing method is a common image interpolation processing method, such as the nearest neighbor interpolation method, the bilinear interpolation method, the cubic interpolation method, etc.

[0074] Exemplarily, the captured real-time window image is divided into 9 regions according to a preset rule, and the pixel average values are 55, 56, 55, 55, 57, 92, 124, 167, 55 respectively. Then, the average mode is determined to be 55, the threshold is 5, the range is determined to be 50 - 60, the regions with pixel average values of 55, 56, 55, 55, 57, 55 are retained, and the regions with pixel average values of 92, 124, 167 are filled. The filling priority can be defined as up, down, left, right, and the upper adjacent image is preferentially used for filling, followed by the lower, left, and right; the similarity between the filled image and the preset image in the database is compared.

[0075] The similarity comparison method is as follows: determine the second pixel average value of each region in the image after interpolation processing; divide each preset image into N regions, and determine the third pixel average value of each region in each preset image; compare the similarity between the second pixel average value and the third pixel average value of the corresponding regions in the image after interpolation processing and the preset image; and average the similarities of the N regions to obtain the similarity between the preprocessed image and the preset image.

[0076] Exemplarily, the average pixel value of each of the N regions of the filled image and the average pixel value of each of the N regions in the database are obtained, and the similarity between each region is obtained by means of corresponding comparison. Finally, the similarities of each region are averaged to obtain the similarity between the images. The similarity between each region is determined by the difference between the pixel values. For example, if the pixels are the same, the similarity is 100%. For each increase of 1 in the pixel difference, the similarity is correspondingly reduced by 1%, with a minimum of 0. The blurring information of the preset image with the highest similarity to the preprocessed real-time window image is the blurring information of the real-time window image.

[0077] In step S104, if the target blurring degree is greater than the first preset blurring degree threshold, the corresponding window cleaning strategy is executed according to the cause of blurring corresponding to the target blurring degree.

[0078] Specifically, when the blurring condition of the real-time window image obtained exceeds the preset blurring degree, it means that the current window blurring condition will already affect the user's driving safety and the windshield wiper needs to be started. For example, if it is determined that the blurring degree of the real-time window image is 40% and has exceeded the preset blurring degree of 35%, the windshield wiper is started at this time. If it is determined that the blurring degree of the real-time window image is 10% and has not exceeded the preset blurring degree of 35%, the windshield wiper does not need to be started at this time, but the real-time window image is continuously obtained and the blurring degree is judged.

[0079] In some preferred embodiments, the window cleaning strategy includes starting the windshield wiper. When the target blurring degree is greater than the first preset blurring degree threshold and the vehicle has not received an instruction from the user to manually activate the windshield wiper, the windshield wiper is automatically activated once, and this step is repeated, that is, every time it is monitored that the target blurring degree is greater than the first preset blurring degree threshold, the windshield wiper is automatically activated once. When the time for the real-time window image to reach the first preset blurring degree threshold is less than the first preset time, the windshield wiper is continuously activated. For example, when the time for the atomization degree to reach the first preset blurring degree threshold is less than 3 s, the windshield wiper changes to continuous activation.

[0080] In some preferred embodiments, in addition to starting the windshield wiper, the window cleaning strategy may also include window heating. Since the causes of blurring may include atomization, water droplet formation, icing, and frosting; when the real-time window image reaches the first preset blurring degree threshold and it is found by comparison that the cause of blurring is icing or frosting, window heating is also started.

[0081] In a preferred embodiment, the first preset blur threshold is determined according to the blur degree of the real-time image of the window when the vehicle receives an operation instruction for the user to manually activate the windshield wiper. Specifically, the initial first preset blur threshold is determined by the vehicle R & D personnel based on the atomization degree of the vehicle when different users activate the windshield wiper. For example, if most users activate the windshield wiper at 50% atomization degree, the initial windshield wiper threshold can be 50%. As the user uses this method multiple times, the blur degree of the real-time image of the window corresponding to each time the user manually triggers the activation of the windshield wiper is automatically recorded, and the threshold at which the driving user is accustomed to activating the windshield wiper is learned through statistics, and the first preset range is adjusted according to this threshold. For example, if it is learned that the driving user usually manually activates the windshield wiper when the blur degree of the real-time image of the window is 40%, the first preset range is defined as 40%; in order to be able to activate the windshield wiper in advance before the user manually activates it, it can also be appropriately reduced on the basis of 40%, for example, the first preset range is defined as 38%, etc.

[0082] In some preferred embodiments, after the camera is turned on, real-time images of the window are acquired at different time intervals, and the different time interval adjustment methods include any of the following situations:

[0083] Situation 1: In the initial stage of entering the monitoring state, real-time images of the window are acquired according to the initial time interval, that is, the first time interval. For example, to avoid excessive computing power consumption, the picture capture frequency can be dynamically adjusted, and the real-time image of the window is acquired every 10 s initially.

[0084] Situation 2: When the target blur degree is greater than the second preset blur threshold and less than the first preset blur threshold, real-time images of the window are acquired at the second time interval, and the second time interval is less than the first time interval. The second preset blur threshold can be set by oneself. For example, when the first preset blur threshold is 30%, the second preset blur threshold can be 10%. The time for setting the second preset blur threshold is to illustrate that when the target blur degree reaches this threshold, the window starts to enter the atomization stage. Since atomization, water droplet formation, etc. are continuous processes, when the window shows an atomization situation, the subsequent image acquisition frequency needs to be increased to accurately capture the moment exceeding the windshield wiper threshold. At this time, the time interval can be appropriately shortened to the second time interval. For example, the real-time image of the window is acquired every 3 s, so that the camera can more accurately capture the first preset blur threshold exceeding the activation of the windshield wiper and improve the accuracy of timely activation of the windshield wiper.

[0085] Case 3: If the time for the real-time window image to reach the first preset blur threshold gradually decreases, obtain the real-time window image at the third time interval, where the third time interval is less than the second time interval. That is, after exceeding the blur threshold for wiper activation, if the duration from the window fogging degree being greater than 0 to exceeding the blur threshold for wiper activation is T and T is gradually decreasing, it indicates that the fogging is getting faster. Dynamically adjust the monitoring interval time. For example, it can be shortened to 1 / 2, 1 / 3, or 1 / 4 of the previous interval time, etc.

[0086] Case 4: If the target blur degree is less than the first preset blur threshold after exceeding the first preset time, obtain the real-time window image at the first time interval. That is, if the wiper has not been intelligently activated for a period of time, it means that the current fogging degree is not serious and there is no tendency to intensify. At this time, readjust the cycle for obtaining the real-time window image to the initial time interval. For example, if the vehicle has not activated the wiper for 10 minutes, it means that it has passed the corresponding section where the wiper is needed. At this time, adjust it to the initial time interval to save computing power.

[0087] Exemplarily, initially obtain the real-time window image every 10s. After determining that the vehicle has currently entered the fogging stage, adjust the cycle for image acquisition to make the cycle shorter. For example, adjust it to 3s, that is, obtain the real-time window image every 3s. During this process, the duration from the fogging degree being greater than 0 to a fixed fogging degree can be recorded, and the time for the next acquisition of the real-time window image can be determined based on the duration. For example, if the duration from the fogging degree being greater than 0 to exceeding 30% fogging degree is 2min, then the cycle for the next acquisition of the real-time window image can be adjusted to half of the duration of 2min.

[0088] In a specific embodiment, if the currently acquired real-time window image is most similar to the preset image with a blur degree of 0%, it means that the current blur degree of the window is 0%. At this time, it means that the window is clear and there is no need to activate the wiper, and then judge again after obtaining the window image in the next image acquisition cycle. If the real-time window image acquired in the next cycle is most similar to the preset image with a blur degree of 10%, judge whether 10% is higher than the wiper threshold. If not, do not activate the wiper and determine that the vehicle has currently entered the fogging stage. Adjust the cycle for obtaining the real-time window image to make the cycle shorter. For example, adjust it to 2s, that is, obtain an image every 2 seconds. If the real-time window image acquired in the next cycle is most similar to the preset image with a fogging degree of 60%, judge whether 60% is higher than the wiper threshold. If so, trigger the wiper and determine the duration from the fogging degree being greater than 0 to exceeding the wiper threshold, and determine the time for the next acquisition of the window image based on the duration. For example, if the duration from the fogging degree being greater than 0 to exceeding the wiper threshold is 1min, then the cycle for the next image acquisition can be adjusted to 1 / 4 of the duration.

[0089] In some preferred embodiments, when the intelligent windshield wiper is turned on, if the degree of blurriness of the real-time window image is less than the first preset blurriness threshold and the vehicle does not receive a user's manual instruction to activate the windshield wiper, then the intelligent windshield wiper startup is turned off. After stopping the windshield wiper, the monitoring startup state is still maintained. If the degree of atomization gradually decreases, the monitoring interval gradually increases. For every 10% decrease in the degree of atomization, the monitoring interval increases by 5s.

[0090] In some preferred embodiments, if the operation instruction received by the vehicle is a user's manual instruction to activate the windshield wiper, then the intelligent windshield wiper startup is turned off, and at the same time, the camera is turned off to stop the monitoring state; if the vehicle receives another user's manual instruction to activate the windshield wiper, then the camera is turned on again to enter the monitoring state, and the real-time window image is obtained at the initial time interval.

[0091] In some preferred embodiments, if within the second preset time, the degree of blurriness of the real-time window image is less than the first preset blurriness threshold and the real-time information of the vehicle does not meet any of the preset conditions, the camera is turned off to stop the monitoring state.

[0092] In the second aspect of the embodiments of the present application, a control device for an intelligent windshield wiper is provided. Figure 2 This is a control device for an intelligent windshield wiper provided by the embodiments of the present application. As Figure 2 shown, the control device 20 for an intelligent windshield wiper provided by the embodiments of the present application includes: an image acquisition module 201, a comparison module 202, a determination module 203, and an action module 204.

[0093] Among them, the image acquisition module 201 is used to turn on the camera to obtain the real-time window image when it is detected that the real-time information of the vehicle meets the preset conditions; the real-time information of the vehicle includes the location of the vehicle, the weather at the location of the vehicle, and the operation instructions received by the vehicle, and the weather at the location of the vehicle includes the temperature and / or humidity at the location of the vehicle.

[0094] The comparison module 202 is used to compare the real-time window image with a preset image set. The preset image set includes at least one preset image, and the preset image includes the blurriness information of the image. The blurriness information includes the degree of blurriness and the reason for the blurriness.

[0095] The determination module 203 is used to use the degree of blurriness of the preset image with the highest similarity to the real-time window image as the target degree of blurriness of the real-time window image; and

[0096] The action module 204 is used to, if the target degree of blurriness is greater than the first preset blurriness threshold, execute the corresponding window cleaning strategy according to the blurriness information corresponding to the degree of blurriness.

[0097] In some preferred embodiments, the control device of the intelligent windshield wiper further includes an image processing module, which is used to preprocess the real-time image of the vehicle window and then determine whether the blur situation of the real-time image of the vehicle window exceeds a first preset range.

[0098] The third aspect of the embodiments of the present application provides a vehicle. Figure 3 It is a schematic structural block diagram of a vehicle provided by the embodiments of the present application. As Figure 3 shown, the vehicle provided by the embodiments of the present application includes the control device 20 of the intelligent windshield wiper as described in the second aspect.

[0099] The vehicle provided by the embodiments of the present application automatically turns on the camera to collect the real-time image of the vehicle window in the case of easy atomization, water droplet blooming, frosting, and icing, analyzes and judges the blur degree of the vehicle window image, controls the opening of the windshield wiper according to the judgment result, and can also realize functions such as continuous opening and closing of the windshield wiper according to the change of the blur degree of the vehicle window image, realizing more intelligent control of the windshield wiper and ensuring the driving safety of the vehicle.

[0100] It should be noted that in the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0101] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0102] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in one Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0103] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more of the procedures Figure 1 one or more procedures and / or blocks Figure 1 one or more blocks.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the procedures Figure 1 one or more procedures and / or blocks Figure 1 one or more blocks.

[0105] A fourth aspect of the embodiments of the present application provides a computer-readable storage medium, on which a computer program is stored, characterized in that the program is executed by a processor to implement the control method of the intelligent windshield wiper as described above.

[0106] If the module / unit integrated in the control device / terminal device of the intelligent windshield wiper is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-described embodiment methods of the present invention can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented.

[0107] Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0108] In several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed with each other can be indirect couplings or communication connections through some interfaces, devices, or units, and can be in electrical, mechanical, or other forms.

[0109] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or can be 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.

[0110] In addition, in each embodiment of the present application, the functional units can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0111] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present application.

[0112] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. Control method of intelligent windshield wiper, characterized in that, It includes: When the real-time information of the vehicle is detected to meet the preset conditions, turn on the camera to obtain the real-time image of the window; Compare the real-time image of the window with a preset image set. The preset image set contains at least one preset image, and the preset image includes the blur degree of the image and the reason for the blur; Take the blur degree of the preset image with the highest similarity to the real-time image of the window as the target blur degree of the real-time image of the window; And If the target blur degree is greater than the first preset blur degree threshold, execute the corresponding window cleaning strategy according to the reason for the blur corresponding to the target blur degree; Wherein, the real-time information of the vehicle includes the location of the vehicle, the weather at the location of the vehicle, and the operation instructions received by the vehicle. The weather at the location of the vehicle includes the temperature and / or humidity at the location of the vehicle; Before comparing the real-time image of the window with the preset image set, preprocess the real-time image of the window; Wherein, the preprocessing method is: Divide the real-time image of the window into N regions, and determine the first pixel average value of each region; Determine the pixel range according to the first pixel average value; Delete the regions in the N regions that exceed the pixel range; and Perform interpolation processing on the deleted regions; The similarity comparison method is: Determine the second pixel average value of each region in the image after interpolation processing; Divide each preset image into N regions, and determine the third pixel average value of each region in each preset image; Compare the similarity of the second pixel average value and the third pixel average value of the corresponding regions in the image after interpolation processing and the preset image; and Average the similarities of the N regions to obtain the similarity between the preprocessed image and the preset image.

2. The control method of the intelligent windshield wiper according to claim 1, wherein When the real-time information of the vehicle meets any of the following preset conditions, turn on the camera to obtain the real-time image of the window: The vehicle enters a preset area; The difference between the temperature at the location of the vehicle and the temperature inside the vehicle exceeds the preset temperature threshold; The difference between the humidity at the location of the vehicle and the humidity inside the vehicle exceeds the preset humidity threshold; The operation instruction received by the vehicle is an instruction for the user to manually enable the windshield wiper.

3. The control method of the intelligent windshield wiper according to claim 1, wherein, Turn on the camera to obtain the real-time image of the window at different time intervals. The different time interval adjustment methods include any of the following: When the target blur degree is less than the second preset blur degree threshold, obtain the real-time image of the window at the first time interval, and the second preset blur degree threshold is less than the first preset blur degree threshold; When the target blur degree is greater than the second preset blur degree threshold and less than the first preset blur degree threshold, obtain the real-time image of the window at the second time interval, and the second time interval is less than the first time interval; If the time for the real-time image of the window to reach the first preset blur degree threshold gradually decreases, obtain the real-time image of the window at the third time interval, and the third time interval is less than the second time interval; If the target blur degree is less than the first preset blur degree threshold for more than the first preset time, obtain the real-time image of the window at the first time interval.

4. The control method of the intelligent windshield wiper according to claim 1, characterized in that, The first preset blur threshold is determined according to the blur degree of the real-time image of the window when the vehicle receives an operation instruction for the user to manually activate the windshield wiper.

5. The control method of the intelligent windshield wiper according to claim 1, characterized in that, The window cleaning strategy includes activating the windshield wiper and window heating, and the reasons for the blur include atomization, water droplet formation, icing, and frosting; When the target blur degree is greater than the first preset blur threshold and the vehicle does not receive an operation instruction for the user to manually activate the windshield wiper, the windshield wiper is automatically activated once, and this step is repeated; When the time for the real-time image of the window to reach the first preset blur threshold is less than the first preset time, the windshield wiper is continuously activated; When the real-time image of the window reaches the first preset blur threshold and the reason for the blur is icing or frosting, window heating is activated.

6. The control method of the intelligent windshield wiper according to claim 1, wherein, The intelligent windshield wiper is turned off or the camera is turned off when any of the following conditions is met: If the vehicle does not receive an operation instruction for the user to manually activate the windshield wiper and the blur degree of the real-time image of the window is less than the first preset blur threshold, the activation of the intelligent windshield wiper is turned off; If the operation instruction received by the vehicle is an operation instruction for the user to manually activate the windshield wiper, the activation of the intelligent windshield wiper is turned off; If the blur degree of the real-time image of the window is less than the first preset blur threshold within the second preset time and the real-time information of the vehicle does not meet the preset conditions, the camera is turned off.

7. The control device of the intelligent windshield wiper, characterized in that, It includes: An image acquisition module for turning on the camera to obtain the real-time image of the window when it detects that the real-time information of the vehicle meets the preset conditions; A comparison module for comparing the real-time image of the window with a preset image set, where the preset image set includes at least one preset image, and the preset image includes the blur information of the image, and the blur information includes the blur degree and the reason for the blur; A determination module for using the blur degree of the preset image with the highest similarity to the real-time image of the window as the target blur degree of the real-time image of the window; And An action module for, if the target blur degree is greater than the first preset blur threshold, executing the corresponding window cleaning strategy according to the blur information corresponding to the blur degree; Wherein, the real-time information of the vehicle includes the location of the vehicle, the weather at the location of the vehicle, and the operation instruction received by the vehicle, and the weather at the location of the vehicle includes the temperature and / or humidity at the location of the vehicle; Before comparing the similarity between the real-time image of the window and the preset image set, preprocess the real-time image of the window; Wherein, the method of the preprocessing is: Dividing the real-time image of the window into N regions and determining the first pixel average value of each region; Determining the pixel range according to the first pixel average value; Deleting the regions in the N regions that exceed the pixel range; and Performing interpolation processing on the deleted regions; The method of the similarity comparison is: Determining the second pixel average value of each region in the image after interpolation processing; Dividing each preset image into N regions and determining the third pixel average value of each region in each preset image; Comparing the similarity of the second pixel average value and the third pixel average value of the corresponding regions in the image after interpolation processing and the preset image; and Averaging the similarities of the N regions to obtain the similarity between the preprocessed image and the preset image.

8. A vehicle, characterized in that, Comprising: the control device of the intelligent windshield wiper as described in claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by a processor to implement the control method of the intelligent windshield wiper as described in any one of claims 1-6.

Images