Methods, equipment and storage media for determining polarization angle

Abstract

This invention discloses a method, device, and storage medium for determining the polarization angle. The method includes: acquiring a target vehicle image captured by a camera, wherein a polarizing mirror is provided before the image sensor of the camera; extracting reference information from the window area of ​​the target vehicle image, wherein the reference information includes at least one of the following: texture information of the window area and skin color information of the target object within the window area; and determining the target polarization angle of the polarizing mirror based on the reference information of the target vehicle image. This method can reduce the impact of reflections on the image of the window area.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation, and in particular to a method, device and storage medium for determining polarization angle. Background Technology

[0002] In the field of intelligent transportation, cameras are typically installed on traffic routes to capture images of moving vehicles. By acquiring vehicle images captured by these cameras, target objects can be identified from the images to verify their identity, thereby enabling the imposition of relevant penalties or issuing alerts.

[0003] However, natural light shining on the surface of car windows can easily cause reflections, resulting in rainbow-like patterns in the image of the corresponding window area, which reduces the image clarity of the window area and makes it difficult to accurately identify the target. Summary of the Invention

[0004] The main technical problem solved by this invention is to provide a method, device and storage medium for determining polarization angle, which can reduce the impact of reflection on the image of the vehicle window area.

[0005] To address the aforementioned technical problems, this application provides a method for determining polarization angle. The method includes: acquiring a target vehicle image captured by a camera, wherein a polarizing mirror is provided before the image sensor of the camera; extracting reference information from the window area of ​​the target vehicle image, wherein the reference information includes at least one of the following: texture information of the window area, skin color information of the target object within the window area; and determining the target polarization angle of the polarizing mirror based on the reference information of the target vehicle image.

[0006] To solve the above-mentioned technical problems, one technical solution adopted in this application is: providing a polarization angle determination device, the device comprising: an acquisition module for acquiring a target vehicle image captured by a camera, wherein a polarizing mirror is provided in front of the image sensor of the camera; an extraction module for extracting reference information from the window area of ​​the target vehicle image, wherein the reference information includes at least one of the following: texture information of the window area, skin color information of the target object within the window area; and a first determination module for determining the target polarization angle of the polarizing mirror based on the reference information of the target vehicle image.

[0007] To solve the above-mentioned technical problems, another technical solution adopted in this application is: to provide a processing device, including a memory and a processor coupled to each other, wherein the memory stores program instructions; and the processor is used to execute the program instructions stored in the memory to implement the above-mentioned polarization angle determination method.

[0008] To solve the above-mentioned technical problems, another technical solution adopted in this application is to provide a computer-readable storage medium for storing program instructions that can be executed to implement the above-mentioned polarization angle determination method.

[0009] The above scheme extracts reference information from the window area of ​​the target vehicle image and determines the target polarization angle of the polarizing filter based on this reference information. The reference information includes at least one of the texture information of the window area and the skin color information of the target object within the window area. When the reflection in the window area changes, both the texture information and the skin color information of the target object within the window area change accordingly. Therefore, during the adjustment of the polarizing filter, a suitable target polarization angle can be determined based on the texture information of the window area and the skin color information of the target object within the window area in the target vehicle image. This reduces the impact of reflection on the image of the window area and thus accurately identifies the target object. Attached Figure Description

[0010] Figure 1 This is a flowchart illustrating an embodiment of the polarization angle determination method provided in this application;

[0011] Figure 2 This is a flowchart illustrating another embodiment of the polarization angle determination method provided in this application;

[0012] Figure 3 This is a flowchart illustrating another embodiment of the polarization angle determination method provided in this application;

[0013] Figure 4 This is a schematic diagram of the frame of an embodiment of the polarization angle determining device provided in this application;

[0014] Figure 5 This is a schematic diagram of the framework of an embodiment of the processing device provided in this application;

[0015] Figure 6 This is a schematic diagram of a framework of an embodiment of the computer-readable storage medium provided in this application. Detailed Implementation

[0016] To make the purpose, technical solution and effects of this application clearer and more explicit, the following describes this application in further detail with reference to the accompanying drawings and embodiments.

[0017] It should be noted that if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0018] Please see Figure 1 , Figure 1 This is a schematic flowchart of an embodiment of the polarization angle determination method provided in this application. It should be noted that if substantially the same result is obtained, the method of this invention is not necessarily identical. Figure 1 The illustrated process sequence is limited. For example... Figure 1 As shown, the method includes the following steps:

[0019] S101: Acquire the image of the target vehicle captured by the camera device.

[0020] A polarizing filter is provided before the image sensor of the camera device. For example, the camera device is mounted on a pole in a traffic area. When a target vehicle enters the camera device's field of view, the camera device can capture an image of the target vehicle that includes it. When the target vehicle does not enter the camera device's field of view, the image captured by the camera device will not include the target vehicle.

[0021] S102: Extract reference information from the window area of ​​the target vehicle image, wherein the reference information includes at least one of the following: texture information of the window area and skin color information of the target object within the window area.

[0022] In this embodiment, the reference information includes texture information of the window area; or, the reference information includes skin color information of the target object within the window area; or, the reference information includes both texture information of the window area and skin color information of the target object within the window area. For example, the window area is the windshield area of ​​the target vehicle. The target object can be the driver, or it can be a passenger other than the driver.

[0023] In one embodiment, the texture information of the window area includes the image texture intensity of the window area, which characterizes the amount of image information in the window area. The image texture intensity of the window area can be obtained by calculating any one of the image entropy, image energy, and image uniformity of the window area. The image entropy of the window area reflects the complexity of the image in the window area. The lower the image entropy, the simpler the image texture, and the window area tends to be a solid color with high brightness and reflection; the higher the image entropy, the more complex the image texture, and the window area tends to be a reflection of the sky or surrounding environment, or a rainbow effect. That is, both excessively high and low image entropy in the window area will result in low image clarity. The image energy of the window area reflects the uniformity of the grayscale distribution and the coarseness of the texture. The image uniformity of the window area reflects the smoothness of the image distribution in the window area.

[0024] In one embodiment, the skin color information of the target object within the window area includes first probability values ​​for different preset skin colors of the target object in the target vehicle image. By combining the first probability values ​​of different preset skin colors of the target object in each target vehicle image, the target skin color of the target object can be determined. The first probability value of the target skin color of the target object in the target vehicle image can reflect the transparency of the window area, that is, the degree to which the target object can be seen clearly through the window. When the first probability value of the target skin color of the target object is higher, the transparency of the window area is higher; when the first probability value of the target skin color of the target object is lower, the transparency of the window area is lower.

[0025] S103: Determine the target polarization angle of the polarizing mirror based on reference information from the target vehicle image.

[0026] In this embodiment, the target polarization angle of the polarizing mirror can be determined based on the texture information of the window area in the target vehicle image. Alternatively, the target polarization angle can be determined based on the skin color information of the target object within the window area in the target vehicle image. Or, the target polarization angle can be determined based on both the texture information of the window area and the skin color information of the target object within the window area. For example, the final target polarization angle of the polarizing mirror can be determined by combining the target polarization angle determined based on texture information and the target polarization angle determined based on skin color information. For instance, the final target polarization angle of the polarizing mirror can be obtained by directly weighting the target polarization angle determined based on texture information and the target polarization angle determined based on skin color information; or, when the absolute value of the angle difference between the target polarization angle determined based on texture information and the target polarization angle determined based on skin color information is less than a preset angle threshold, the final target polarization angle of the polarizing mirror can be obtained by weighting the target polarization angle determined based on texture information and the target polarization angle determined based on skin color information.

[0027] In this embodiment, reference information is extracted from the window area of ​​the target vehicle image, and the target polarization angle of the polarizing filter is determined based on this reference information. The reference information includes at least one of the texture information of the window area and the skin color information of the target object within the window area. When the reflection in the window area changes, the texture information of the window area and the skin color information of the target object within the window area also change accordingly. Therefore, during the adjustment of the polarizing filter, a suitable target polarization angle can be determined based on the texture information of the window area and the skin color information of the target object within the window area in the target vehicle image, thereby reducing the impact of reflection on the image of the window area and accurately identifying the target object.

[0028] Please see Figure 2 , Figure 2 This is a flowchart illustrating another embodiment of the polarization angle determination method provided in this application. Figure 2 In the method shown, the target polarization angle of the polarizing mirror is determined based on the texture information of the window area in the target vehicle image. For example... Figure 2 As shown, the method includes the following steps:

[0029] S201: Acquire the image of the target vehicle captured by the camera device.

[0030] S202: Extract texture information from the window area of ​​the target vehicle image. The texture information includes the image texture intensity of the window area.

[0031] The image texture intensity of the window area can characterize the amount of image information in the window area. The image texture intensity of the window area can be obtained by calculating any one of the image entropy, image energy, and image uniformity of the window area. See step S102 above for related details, which will not be repeated here.

[0032] In one example, the image texture intensity of the window region is the image entropy of the window region. The image entropy of the window region is calculated using the following formula:

[0033]

[0034] In another example, the image texture intensity of the window region is equal to the image energy of the window region. The image texture intensity of the window region is calculated using the following formula:

[0035]

[0036] In another example, the image texture intensity of the window area is equal to the image uniformity of the window area. The image texture intensity of the window area is calculated using the following formula:

[0037]

[0038] In formulas (1), (2) and (3), (i, j) represents the coordinates of a pixel, P(i, j) represents the frequency of a pixel pair under a specific positional relationship, and M and N represent the length and width of the image corresponding to the window area, respectively.

[0039] S203: Detect whether the image texture intensity of the target vehicle image meets the first preset condition.

[0040] In this embodiment, the first preset condition includes the image texture intensity being within a set intensity range. The first preset condition is set according to actual conditions. When the image texture intensity of the target vehicle image is within the set intensity range, the image texture intensity of the target vehicle image meets the first preset condition; at this time, the impact of reflection on the target vehicle image is relatively small. When the image texture intensity of the target vehicle image is outside the set intensity range, the image texture intensity of the target vehicle image does not meet the first preset condition; at this time, the impact of reflection on the target vehicle image is relatively large.

[0041] S204: In response to the fact that the image texture intensity of the target vehicle image does not meet the first preset condition, the polarizing mirror is adjusted to the first polarization angle, and the step of acquiring the target vehicle image captured by the camera device is re-executed at the first polarization angle until the image texture intensity of the latest target vehicle image meets the first preset condition.

[0042] When the texture information of the target vehicle image does not meet the first preset condition, the reflection has a significant impact on the target vehicle image. In this case, it is necessary to adjust the polarization angle of the polarizing mirror to reduce the impact of the reflection on the target vehicle image. Therefore, step S201 is repeated until the image texture intensity of the latest target vehicle image meets the first preset condition.

[0043] In this embodiment, adjusting the polarizer to a first polarization angle includes: determining the adjustment angle of the polarizer; and using the sum of the current polarization angle and the adjustment angle of the polarizer as the first polarization angle. For example, the polarizer can be adjusted at intervals of a set time threshold; for instance, the set threshold can be 0.5 seconds or 1 second.

[0044] In one embodiment, the adjustment angle is a set angle. That is, each time the polarization angle of the polarizer is adjusted, the set angle is added to the current polarization angle of the polarizer. The set angle can be set according to actual needs. For example, the set angle is 5°, 10°, etc.

[0045] In another embodiment, to further improve the efficiency of adjusting the polarizer, the adjustment angle of the polarizer can be determined by a dichotomy method. Specifically, the sum of the current polarization angle and the preset angle is obtained as the second polarization angle; half of the second polarization angle is obtained as the adjustment angle. The preset angle is 180°.

[0046] S205: Determine the latest first polarization angle as the target polarization angle.

[0047] The latest first polarization angle is the polarization angle of the polarizing mirror when the image texture intensity of the target vehicle image meets the first preset condition.

[0048] In this embodiment, when the image texture intensity of the target vehicle image meets the first preset condition, the impact of reflection on the target vehicle image is relatively small. Therefore, by using the polarization angle of the polarizing mirror when the image texture intensity of the target vehicle image meets the first preset condition as the target polarization angle of the polarizing mirror, the impact of reflection on the image of the window area can be reduced.

[0049] Please see Figure 3 , Figure 3 This is a flowchart illustrating another embodiment of the polarization angle determination method provided in this application. Figure 3 In the method shown, the target polarization angle of the polarizing mirror is determined based on the skin color information of the target object within the window area of ​​the target vehicle image. For example... Figure 3 As shown, the method includes the following steps:

[0050] S301: Acquire target vehicle images captured at different third polarization angles by adjusting the polarizing filter.

[0051] In one example, n different third polarization angles can be preset, the polarizing filter can be adjusted to each third polarization angle, and the target vehicle image can be captured at each third polarization angle to obtain n target vehicle images at n different third polarization angles. Here, n is an integer greater than 2.

[0052] S302: Extract skin color information of the target object from the window area of ​​each target vehicle image. The skin color information of the target object includes the first probability value of the target object for each of the different preset skin colors.

[0053] The preset skin tone can be determined based on the skin tone of people in a designated area. In this embodiment, the preset skin tone can include at least two of the following: yellow skin, white skin, and black skin. For example, the preset skin tone may include yellow skin and white skin, or it may include yellow skin, white skin, and black skin.

[0054] For example, the defined area can be divided into units such as country, province, city, district, county, town, or street. For instance, the defined area could be the district where the camera device is installed. This embodiment does not specifically limit the division of the defined area; in other embodiments, other methods can be used to divide the defined area.

[0055] In this embodiment, step S302 includes: for each target vehicle image, first determining the proportion of pixels in the window area of ​​the target vehicle image that fall within different preset pixel ranges. Then, multiplying the proportion of pixels within each preset pixel range by the corresponding preset skin tone proportion to obtain the first probability value of the target object in the target vehicle image being each preset skin tone. Different preset skin tones correspond to different preset pixel ranges. The preset pixel range corresponding to each preset skin tone can be set according to actual needs. Different preset skin tones correspond to different preset skin tone proportions, and the preset skin tone proportions corresponding to each preset skin tone can be set according to the skin tone of people in the aforementioned set area. For example, the preset skin tone proportions corresponding to yellow skin, white skin, and black skin are represented by x, y, and z, respectively, and the values ​​of x, y, and z can be 80%, 15%, and 5%, respectively.

[0056] In one embodiment, for each target vehicle image, determining the proportion of pixels within each preset pixel range in the window region of the target vehicle image includes: first determining the number of pixels within each preset pixel range in the window region; then dividing the number of pixels within each preset pixel range in the window region by the total number of pixels in the window region to obtain the proportion of pixels within each preset pixel range in the window region. For example, in n target vehicle images, the proportions of pixels within each preset pixel range in the window region of the first target vehicle image are Ly1, Lw1, and Lb1, respectively; the proportions of pixels within each preset pixel range in the window region of the nth target vehicle image are Ly1, Lw1, and Lb1, respectively. n Lw n and Lb n .

[0057] In one embodiment, the proportion of pixels corresponding to yellow skin tone in the window area is multiplied by a preset skin tone proportion corresponding to yellow skin tone to obtain a first probability value that the target object in the target vehicle image has yellow skin tone. For example, the first probability value that the target object in the target vehicle image has yellow skin tone is x*Ly. n The proportion of pixels corresponding to white skin in the car window area is multiplied by a preset proportion corresponding to white skin to obtain a first probability value that the target object in the target vehicle image has white skin. For example, the first probability value that the target object in the target vehicle image has white skin is y*Lw. n The proportion of pixels corresponding to dark skin in the window area is multiplied by a preset skin tone proportion to obtain a first probability value that the target object in the target vehicle image has dark skin. For example, the first probability value that the target object in the target vehicle image has dark skin is z*Lb. n .

[0058] Because the colors of other objects within the window area can interfere with the statistical proportion of pixels within each preset pixel range, the skin color of the final determined target object may be inaccurate. Multiplying the proportion of pixels within each preset pixel range by the corresponding preset skin color proportion yields the first probability value of the target object in the target vehicle image for each preset skin color, thus providing a more accurate assessment of the target object's skin color.

[0059] S303: Determine the target skin color of the target object by combining the first probability values ​​of the target objects in each target vehicle image as different preset skin colors.

[0060] In one embodiment, firstly, the first probability values ​​of each preset skin tone for the target object are summed to obtain a second probability value for each preset skin tone. For example, the n first probability values ​​of the target object having a yellow skin tone in n images of the target vehicle are summed to obtain a second probability value for yellow skin tone; the n first probability values ​​of the target object having a white skin tone in n images of the target vehicle are summed to obtain a second probability value for white skin tone; and the n first probability values ​​of the target object having a black skin tone in n images of the target vehicle are summed to obtain a second probability value for black skin tone. Optionally, in this embodiment, the first probability values ​​of each preset skin tone for the target object can also be summed and averaged to obtain a second probability value for each preset skin tone.

[0061] After obtaining the second probability value for each preset skin color, the preset skin color with the highest second probability value is taken as the target skin color. For example, if the second probability values ​​for yellow skin, white skin, and black skin obtained from n images of the target vehicle are A, B, and C respectively, and A>B>C, then yellow skin is taken as the target skin color of the target object.

[0062] S304: Based on the first probability value of the target skin color in each target vehicle image, select one target vehicle image from the target vehicle images captured at different third polarization angles.

[0063] In one embodiment, the target vehicle image with the highest first probability value for the target skin tone is selected from target vehicle images captured at different third polarization angles. For example, if the target skin tone of the determined target object is yellow, the target vehicle image with the highest first probability value for yellow skin tone is selected from the aforementioned n target vehicle images.

[0064] S305: Determine the third polarization angle corresponding to the selected target vehicle image as the target polarization angle.

[0065] In this embodiment, the first probability value of the target skin color of the target object in the target vehicle image reflects the transparency of the window area, i.e., the degree to which the target object can be clearly seen through the window. The smaller the first probability value of the target skin color, the lower the transparency of the window area, and the greater the impact of reflection on the window area. Conversely, the larger the first probability value of the target skin color, the higher the transparency of the window area, and the smaller the impact of reflection on the window area. Therefore, determining the third polarization angle corresponding to the target vehicle image with the highest first probability value of the target skin color as the target polarization angle can reduce the impact of reflection on the image of the window area.

[0066] Optionally, in this embodiment, considering that different target vehicle models may have different target polarization angles due to variations in the angle between the windshield and the ground, this embodiment allows for the determination of target polarization angles for different vehicle models.

[0067] Before executing steps S102, S202, or S302, the process may further include: determining the target vehicle model corresponding to the target vehicle based on the target vehicle image; determining the initial polarization angle of the polarizing mirror corresponding to the target vehicle model from a preset correspondence, wherein the preset correspondence includes several preset vehicle models corresponding to the initial polarization angles of the polarizing mirrors. By performing image recognition on the target vehicle image, the target vehicle model in the target vehicle image can be determined. For example, the target vehicle model can be one of a sedan, SUV, MPV (multi-Purpose Vehicle), truck, and bus. The initial polarization angles corresponding to different preset vehicle models are set according to the actual situation. For example, when the polarizing mirror is adjusted to the initial polarization angle corresponding to the preset vehicle model, the reflection has a smaller impact on the image of the window area of ​​the preset vehicle model.

[0068] In this embodiment, considering that changes in the installation position or orientation of the camera device, or changes in ambient brightness or time, adjusting the polarizing mirror to the initial polarization angle corresponding to the preset vehicle model does not improve the impact of reflections on the image of the preset vehicle model's window area. Therefore, when a target vehicle of the preset model is detected, the polarizing mirror can be first adjusted to the initial polarization angle corresponding to that preset model, and then the target polarization angle corresponding to the preset vehicle model can be determined based on the texture information of the window area and the skin color information of the target object within the window area, in order to further reduce the impact of reflections on the image of the preset vehicle model's window area.

[0069] Furthermore, the determined target polarization angle corresponding to the preset vehicle model can be updated to the preset correspondence, that is, the initial polarization angle corresponding to the preset vehicle model in the preset correspondence can be updated to the target polarization angle. When the target vehicle corresponding to the preset vehicle model is detected again, the polarizing filter can be adjusted to the updated initial polarization angle corresponding to the preset vehicle model.

[0070] Optionally, in this embodiment, in order to further reduce the impact of reflection on the image of the window area, the final target polarization angle of the polarizing mirror can be determined by combining the target polarization angle determined based on texture information and the target polarization angle determined based on skin color information.

[0071] In one embodiment, the target polarization angle of the polarizing mirror determined based on texture information and the target polarization angle of the polarizing mirror determined based on skin color information can be directly weighted to obtain the final target polarization angle of the polarizing mirror.

[0072] In another embodiment, to further improve the reliability of the final target polarization angle of the polarizing mirror, when the absolute value of the angle difference between the target polarization angle determined based on texture information and the target polarization angle determined based on skin color information is less than a preset angle threshold, the reliability of the target polarization angles determined based on texture information and skin color information is considered high. In this case, the target polarization angles determined based on texture information and skin color information are weighted to obtain the final target polarization angle of the polarizing mirror. When the absolute value of the angle difference between the target polarization angles determined based on texture information and the target polarization angle determined based on skin color information is greater than or equal to the preset angle threshold, the reliability of the target polarization angles determined based on texture information and skin color information is considered low. In this case, the initial polarization angle of the polarizing mirror is used as the final target polarization angle of the polarizing mirror. The preset angle threshold can be set according to actual needs.

[0073] Specifically, in this embodiment, the target polarization angle of the polarizing mirror determined based on texture information and the target polarization angle of the polarizing mirror determined based on skin color information are weighted to obtain the final target polarization angle of the polarizing mirror. This includes: multiplying the target polarization angle determined based on the texture information of the window area by a first weighting coefficient to obtain a first target polarization angle; and multiplying the target polarization angle determined based on the skin color information of the target object within the window area by a second weighting coefficient to obtain a second target polarization angle; and using the sum of the first and second target polarization angles as the final target polarization angle. For example, the first and second weighting coefficients can be determined according to actual conditions.

[0074] In this embodiment, the relevant content on determining the target polarization angle of the polarizing mirror based on texture information can be found in [reference needed]. Figure 2 The embodiment shown illustrates how to determine the target polarization angle of a polarizing filter based on skin color information. For more information, please refer to [link / reference needed]. Figure 3 The illustrated embodiment will not be described again here. It should be noted that when the target polarization angle of the polarizing mirror is determined based on both the texture information of the window area and the skin color information of the target object within the window area, the multiple third polarization angles adjusted in step S301 are the same as the multiple first polarization angles adjusted in step S202.

[0075] Optionally, in this embodiment, before executing steps S102, S202, or S302, the method further includes: determining environmental data; and, in response to the environmental data satisfying a second preset condition, extracting reference information from the window area of ​​the target vehicle image and subsequent steps. The environmental data includes at least one of ambient brightness and time. For example, the ambient brightness can be calculated based on the image brightness value of the target vehicle image, the exposure of the camera device, and the automatic exposure enhancement factor of the camera device. The second preset condition includes at least one of the change in ambient brightness being greater than a first threshold and the change in time being greater than a second threshold. The first and second thresholds can be set according to actual needs.

[0076] When the environmental data meets the second preset condition, it is considered that the degree of change in the environmental data is relatively large. At this time, the reflection of natural light on the window area may change, and the polarization angle of the polarizing mirror needs to be adjusted to reduce the impact of reflection on the image of the window area. When the environmental data does not meet the second preset condition, it is considered that the degree of change in the environmental data is relatively small, and the change in the reflection of natural light on the window area is small. Therefore, it is not necessary to adjust the polarization angle of the polarizing mirror, that is, the current polarization angle of the polarizing mirror remains unchanged. When the environmental data meets the second preset condition, the extraction of reference information from the window area of ​​the target vehicle image and subsequent steps are then performed. This reduces the number of times the polarizing mirror needs to be adjusted, thereby reducing the mechanical and energy losses associated with adjusting the polarizing mirror.

[0077] Please see Figure 4 , Figure 4 This is a schematic diagram of a framework of an embodiment of the polarization angle determination device provided in this application. In this embodiment, the polarization angle determination device 40 includes: an acquisition module 41, an extraction module 42, and a first determination module 43.

[0078] The acquisition module 41 is used to acquire an image of the target vehicle captured by a camera device, wherein a polarizing filter is provided before the image sensor of the camera device. The extraction module 42 is used to extract reference information from the window area of ​​the target vehicle image, wherein the reference information includes at least one of the following: texture information of the window area and skin color information of the target object within the window area. The first determination module 43 is used to determine the target polarization angle of the polarizing filter based on the reference information of the target vehicle image.

[0079] Optionally, when the reference information includes texture information, the texture information includes the image texture intensity of the window area, and the image texture intensity represents the amount of image information in the window area. The first determining module 43 is used to detect whether the image texture intensity of the target vehicle image meets a first preset condition, wherein the first preset condition includes that the image texture intensity is within a set intensity range; in response to the image texture intensity of the target vehicle image not meeting the first preset condition, the polarizing mirror is adjusted to a first polarization angle until the image texture intensity of the latest target vehicle image meets the first preset condition; the latest first polarization angle is determined as the target polarization angle.

[0080] Optionally, the first determining module 43 is used to determine the adjustment angle of the polarizer; the sum of the current polarization angle and the adjustment angle is used as the first polarization angle.

[0081] Optionally, the first determining module 43 is used to obtain the sum of the current polarization angle and the preset angle as the second polarization angle; and to obtain half of the second polarization angle as the adjustment angle.

[0082] Optionally, when the reference information includes skin color information, the skin color information includes a first probability value for the target object being a different preset skin color. The acquisition module 41 is used to acquire target vehicle images captured at different third polarization angles by adjusting the polarizing filter; the first determination module 43 is used to combine the first probability values ​​of the target object being a different preset skin color in each target vehicle image to determine the target skin color of the target object, wherein the target skin color is one of the preset skin colors; based on the first probability value of the target skin color in each target vehicle image, select one target vehicle image from the target vehicle images captured at different third polarization angles; and determine the third polarization angle corresponding to the selected target vehicle image as the target polarization angle.

[0083] Optionally, the first determining module 43 is used to select the target vehicle image with the highest first probability value of the target skin color from the target vehicle images captured from different third polarization angles.

[0084] Optionally, the first determining module 43 is used to add the first probability values ​​of each preset skin color of the target object to obtain the second probability value of each preset skin color; and to take the preset skin color with the highest second probability value as the target skin color.

[0085] Optionally, the extraction module 42 is used to determine the proportion of pixels in the window area of ​​the target vehicle image that are located within different preset pixel ranges, wherein different preset skin tones correspond to different preset pixel ranges; and multiply the proportion of pixels located within each preset pixel range by the corresponding preset skin tone proportion to obtain the first probability value of the target object in the target vehicle image being each preset skin tone.

[0086] Optionally, when the reference information includes texture information and skin color information, the first determining module 43 is further used to combine the target polarization angle determined based on the texture information and the target polarization angle determined based on the skin color information to determine the final target polarization angle of the polarizing mirror.

[0087] Optionally, the first determining module 43 is used to weight the target polarization angle determined based on texture information and the target polarization angle determined based on skin color information to obtain the final target polarization angle of the polarizing mirror in response to the absolute value of the angle difference between the target polarization angle determined based on texture information and the target polarization angle determined based on skin color information being less than a preset angle threshold; and to take the initial polarization angle of the polarizing mirror as the final target polarization angle of the polarizing mirror in response to the absolute value of the angle difference between the target polarization angle determined based on texture information and the target polarization angle determined based on skin color information being greater than or equal to the preset angle threshold.

[0088] Optionally, the polarization angle determining device 40 further includes a second determining module 44. Before determining the target polarization angle of the polarizer based on the reference information of the target vehicle image, the second determining module 44 is used to determine the target vehicle model corresponding to the target vehicle based on the target vehicle image; and to determine the initial polarization angle of the polarizer corresponding to the target vehicle model from a preset correspondence relationship, wherein the preset correspondence relationship includes a number of preset vehicle models corresponding to the initial polarization angles of the polarizers respectively.

[0089] Optionally, the polarization angle determining device 40 further includes a third determining module 45. Before extracting reference information from the window area of ​​the target vehicle image, the third determining module 45 determines environmental data, including at least one of ambient brightness and time; and determines whether the environmental data meets a second preset condition, wherein the second preset condition includes at least one of the change in ambient brightness being greater than a first threshold and the change in time being greater than a second threshold. When the environmental data meets the second preset condition, the extraction of reference information from the window area of ​​the target vehicle image and subsequent steps are performed. When the environmental data does not meet the second preset condition, the extraction of reference information from the window area of ​​the target vehicle image and subsequent steps are not performed.

[0090] It should be noted that the apparatus of this embodiment can perform the steps in the above method. For detailed descriptions of the relevant content, please refer to the method section above, which will not be repeated here.

[0091] Please see Figure 5 , Figure 5 This is a schematic diagram of a framework of an embodiment of the processing device provided in this application. In this embodiment, the processing device 50 includes a memory 51 and a processor 52.

[0092] Processor 52 can also be referred to as CPU (Central Processing Unit). Processor 52 may be an integrated circuit chip with signal processing capabilities. Processor 52 can also be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. A general-purpose processor can be a microprocessor, or processor 52 can be any conventional processor 52, etc.

[0093] The memory 51 in the processing device 50 is used to store the program instructions required for the processor 52 to run.

[0094] The processor 52 is used to execute program instructions to implement the polarization angle determination method in this application.

[0095] Please see Figure 6 , Figure 6 This is a schematic diagram of a framework of an embodiment of the computer-readable storage medium provided in this application. The computer-readable storage medium 60 of this embodiment stores program instructions 61, which, when executed, implement the polarization angle determination method provided in this application. The program instructions 61 can be formed into a program file and stored in the aforementioned computer-readable storage medium 60 in the form of a software product, so that a computer device (which may be a personal computer, server, or network device, etc.) can execute all or part of the steps of the methods of various embodiments of this application. The aforementioned computer-readable storage medium 60 includes various media capable of storing program code, such as a USB flash drive, mobile hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or terminal devices such as computers, servers, mobile phones, and tablets.

[0096] The above scheme extracts reference information from the window area of ​​the target vehicle image and determines the target polarization angle of the polarizing filter based on this reference information. The reference information includes at least one of the texture information of the window area and the skin color information of the target object within the window area. When the reflection in the window area changes, both the texture information and the skin color information of the target object within the window area change accordingly. Therefore, during the adjustment of the polarizing filter, a suitable target polarization angle can be determined based on the texture information of the window area and the skin color information of the target object within the window area in the target vehicle image. This reduces the impact of reflection on the image of the window area and thus accurately identifies the target object.

[0097] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0098] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0099] In the several embodiments provided in this application, it should be understood that the disclosed methods, apparatuses, and systems can be implemented in other ways. For example, the apparatus implementations described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or units may be electrical, mechanical, or other forms.

[0100] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0101] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0102] If the integrated unit is implemented as 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, the technical solution of this 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0103] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for determining polarization angle, characterized in that, The method includes: Acquire an image of a target vehicle captured by a camera device, wherein a polarizing mirror is provided in front of the image sensor of the camera device; Reference information is extracted from the window area of ​​the target vehicle image; Based on the reference information of the target vehicle image, the target polarization angle of the polarizing mirror is determined; When the reference information includes skin color information of the target object within the window area, the skin color information includes a first probability value for the target object being a different preset skin color; acquiring the target vehicle image includes: acquiring target vehicle images captured at different third polarization angles by adjusting the polarizing filter; determining the target polarization angle of the polarizing filter based on the reference information of the target vehicle image includes: determining the target skin color of the target object by combining the first probability values ​​of the target object being a different preset skin color in each of the target vehicle images, wherein the target skin color is one of the preset skin colors; selecting one target vehicle image from the target vehicle images captured at different third polarization angles based on the first probability value of the target skin color in each of the target vehicle images; and determining the third polarization angle corresponding to the selected target vehicle image as the target polarization angle.

2. The method according to claim 1, characterized in that, The step of selecting one target vehicle image from target vehicle images captured at different third polarization angles based on the first probability value of the target skin color in each of the target vehicle images includes: From the target vehicle images captured at different third polarization angles, select the target vehicle image with the highest first probability value for the target skin color.

3. The method according to claim 1, characterized in that, The step of determining the target skin color of the target object by combining the first probability values ​​of different preset skin colors of the target objects in each of the target vehicle images includes: The first probability values ​​of each preset skin color for the target object are added together to obtain the second probability value of each preset skin color; The preset skin color with the highest second probability value is taken as the target skin color.

4. The method according to claim 1, characterized in that, For each of the target vehicle images, the skin color information is extracted from the window area of ​​the target vehicle image, including: Determine the proportion of pixels in the window area of ​​the target vehicle image that fall within different preset pixel ranges, wherein different preset skin tones correspond to different preset pixel ranges; The proportion of pixels within each preset pixel range is multiplied by the corresponding preset skin tone proportion to obtain the first probability value of the target object in the target vehicle image being each of the preset skin tones.

5. The method according to any one of claims 1 to 4, characterized in that, If the reference information also includes texture information of the window area, the method further includes: The final target polarization angle of the polarizing mirror is determined by combining the target polarization angle determined based on the texture information and the target polarization angle determined based on the skin color information.

6. The method according to claim 5, characterized in that, The texture information includes the image texture intensity of the window area, and the image texture intensity represents the amount of image information in the window area; Based on the texture information of the target vehicle image, the target polarization angle of the polarizing mirror is determined, including: Detect whether the image texture intensity of the target vehicle image meets a first preset condition, wherein the first preset condition includes that the image texture intensity is within a set intensity range; In response to the fact that the image texture intensity of the target vehicle image does not meet the first preset condition, the polarizing mirror is adjusted to the first polarization angle, and the step of acquiring the target vehicle image captured by the camera device is re-executed at the first polarization angle until the image texture intensity of the latest target vehicle image meets the first preset condition. The latest first polarization angle is determined as the target polarization angle based on the texture information.

7. The method according to claim 6, characterized in that, Adjusting the polarizing mirror to the first polarization angle includes: Determine the adjustment angle of the polarizing mirror; The sum of the current polarization angle and the adjustment angle is taken as the first polarization angle.

8. The method according to claim 7, characterized in that, Determining the adjustment angle of the polarizing mirror includes: The sum of the current polarization angle and the preset angle is obtained as the second polarization angle; Half of the second polarization angle is obtained as the adjustment angle.

9. The method according to claim 5, characterized in that, The step of determining the final target polarization angle of the polarizing filter by combining the target polarization angle determined based on the texture information and the target polarization angle determined based on the skin color information includes: In response to the absolute value of the angle difference between the target polarization angle determined based on the texture information and the target polarization angle determined based on the skin color information being less than a preset angle threshold, the target polarization angle determined based on the texture information and the target polarization angle determined based on the skin color information are weighted to obtain the final target polarization angle of the polarizing mirror. In response to the absolute value of the angle difference between the target polarization angle determined based on the texture information and the target polarization angle determined based on the skin color information being greater than or equal to a preset angle threshold, the initial polarization angle of the polarizing mirror is taken as the final target polarization angle of the polarizing mirror.

10. The method according to claim 1, characterized in that, Before determining the target polarization angle of the polarizing mirror based on reference information from the target vehicle image, the method further includes: Based on the target vehicle image, determine the target vehicle model corresponding to the target vehicle; The initial polarization angle of the polarizing mirror corresponding to the target vehicle model is determined from a preset correspondence, wherein the preset correspondence includes a number of preset vehicle models corresponding to the initial polarization angles of the polarizing mirrors.

11. The method according to claim 1, characterized in that, Before extracting reference information from the window area of ​​the target vehicle image, the method further includes: Determine environmental data, which includes at least one of ambient brightness and time; In response to the environmental data meeting the second preset condition, the steps of extracting reference information from the window area of ​​the target vehicle image and subsequent steps are executed. The second preset condition includes at least one of the following: the change in ambient brightness is greater than a first threshold, and the change in time is greater than a second threshold.

12. A processing apparatus, characterized in that, Including interconnected memory and processor, The memory stores program instructions; The processor is used to execute program instructions stored in the memory to implement the method according to any one of claims 1-11.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program instructions that can be executed to implement the method of any one of claims 1-11.

Images