Exposure parameter adjustment method and device, electronic equipment and computer readable storage medium

Abstract

The invention discloses an exposure parameter adjustment method and device, electronic equipment and a computer readable storage medium, which can enable an exposure effect to be more prominent on a shooting main body and improve the consistency of the exposure effects of multiple cameras, thereby improving the exposure effect. The method comprises the steps of performing region identification on first original image data acquired by a first image sensor, and determining a first main body region and a first non-main body region in the first original image data; respectively carrying out brightness weighting processing on the first main body region and the first non-main body region, and determining first total image brightness corresponding to the first original image data; adjusting at least one exposure parameter corresponding to at least one image sensor based on the first total image brightness; the at least one image sensor includes a first image sensor.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to an exposure parameter adjustment method, device, electronic device and computer-readable storage medium. Background Art

[0002] At present, when a terminal equipped with at least one camera performs image acquisition, due to the limitations of the metering mode in terms of metering range and adaptation scenes, as well as the differences in exposure effects between different image sensors, it is easy to cause poor exposure of the subject and visual brightness jumps caused by the difference in exposure effects, thereby reducing the exposure effect. Summary of the invention

[0003] The present application hopes to provide an exposure parameter adjustment method, device, electronic device and computer-readable storage medium, which can make the exposure effect more prominent on the photographed subject and improve the consistency of exposure effects of multiple cameras, thereby improving the exposure effect.

[0004] The technical solution of this application is implemented as follows:

[0005] In a first aspect, the present application provides an exposure parameter adjustment method, the method comprising:

[0006] Performing region recognition on first original image data acquired by a first image sensor to determine a first subject region and a first non-subject region in the first original image data;

[0007] Performing brightness weighted processing on the first main area and the first non-main area respectively to determine a first full-image brightness corresponding to the first original image data;

[0008] Based on the first full image brightness, at least one exposure parameter corresponding to at least one image sensor is adjusted; the at least one image sensor includes the first image sensor.

[0009] In a second aspect, the present application provides an exposure parameter adjustment device, the device comprising:

[0010] A region recognition module, configured to perform region recognition on the first original image data acquired by the first image sensor, and determine a first subject region and a first non-subject region in the first original image data;

[0011] a brightness processing module, configured to perform brightness weighted processing on the first main body area and the first non-main body area respectively, and determine a first full image brightness corresponding to the first original image data;

[0012] An adjustment module is used to adjust at least one exposure parameter corresponding to at least one image sensor based on the first full image brightness; the at least one image sensor includes the first image sensor.

[0013] Optionally, the brightness processing module is also used to determine the main area weight corresponding to the first main area and the non-main area weight corresponding to the first non-main area; the first main area weight is higher than the first non-main area weight; the brightness corresponding to the first main area is weighted using the first main area weight, and the brightness corresponding to the first non-main area is weighted using the first non-main area weight to determine the weighted first main area brightness and the weighted first non-main area brightness; the weighted first main area brightness and the weighted first non-main area brightness are merged to determine the first full image brightness.

[0014] Optionally, the first non-main area includes: a first background area and a first transition area; the first non-main area weight includes: a first background area weight and a first transition area weight; the first transition area weight is higher than the first background area weight.

[0015] Optionally, the at least one image sensor also includes: at least one second image sensor; the adjustment module is further used to adjust the first exposure parameter corresponding to the first image sensor based on the first full image brightness when the first image sensor is enabled; determine the second full image brightness corresponding to each second image sensor in the at least one second image sensor when the first image sensor and the at least one second image sensor are enabled; and adjust the second exposure parameter corresponding to each second image sensor based on the first full image brightness and the second full image brightness.

[0016] Optionally, the first exposure parameter includes: a first exposure time and / or a first exposure gain; the adjustment module is further used to update the first exposure time and / or first exposure gain corresponding to the first image sensor based on the first full image brightness and the target full image brightness.

[0017] Optionally, the adjustment module is also used to determine a first exposure corresponding to the first full-image brightness; determine a first updated exposure based on the first exposure, the first full-image brightness and the target full-image brightness; determine a first updated exposure time and / or a first updated exposure gain based on the first updated exposure, and use the first updated exposure time and / or the first updated exposure gain to update the first exposure time and / or the first exposure gain.

[0018] Optionally, the adjustment module is further used to perform region recognition on the second original image data collected by each second image sensor to determine a second main area and a second non-main area in the second original image data; and perform brightness weighted processing on the second main area and the second non-main area respectively to determine the second full image brightness corresponding to each second image sensor.

[0019] Optionally, the second exposure parameter includes: a second exposure time and / or a second exposure gain; the adjustment module is also used to determine the first exposure amount corresponding to the first full image brightness; determine the second updated exposure amount corresponding to each second image sensor according to the second full image brightness, the first full image brightness, the first exposure amount and a preset mapping factor corresponding to each second image sensor; determine the second updated exposure time and / or the second updated exposure gain according to the second updated exposure amount, and use the second updated exposure time and / or the second updated exposure gain to update the second exposure time and / or the second exposure gain; the preset mapping factor represents the exposure parameter mapping relationship between the second image sensor and the first image sensor when the exposure effect of the second image sensor and the exposure effect of the first image sensor meet a preset consistency condition.

[0020] Optionally, the exposure parameter adjustment device also includes a calibration module; the calibration module is used to obtain a reference first exposure time and a reference first exposure gain corresponding to the first image sensor, and a reference second exposure time and a reference second exposure gain corresponding to the second image sensor when the image brightness difference captured by the second image sensor and the first image sensor in the same field of view angle area is less than or equal to a preset difference threshold before determining the second updated exposure corresponding to each second image sensor based on the second full image brightness, the first full image brightness, the first exposure and the preset mapping factor corresponding to each second image sensor; determine a first product of the reference first exposure time and the reference first exposure gain; determine a second product of the reference second exposure time and the reference second exposure gain; and determine the preset mapping factor according to the ratio of the second product to the first product.

[0021] Optionally, the exposure parameter adjustment device also includes a scene recognition module; the scene recognition module is used to identify the lighting environment of the current shooting scene and determine the lighting scene corresponding to the current shooting scene; according to the lighting scene, adjust at least one metering mode corresponding to the at least one image sensor, and / or adjust the area weight corresponding to the at least one image sensor; the area weight includes a subject area weight and / or a non-subject area weight.

[0022] Optionally, region recognition includes at least one of target detection, semantic segmentation and instance segmentation.

[0023] In a third aspect, the present application provides an electronic device, including a memory and a processor; wherein:

[0024] The memory is used to store executable instructions;

[0025] The processor is used to implement the exposure parameter adjustment method provided in the embodiment of the present application when executing the executable instructions stored in the memory.

[0026] In a fourth aspect, the present application provides a computer-readable storage medium storing executable instructions for causing a processor to execute and implement the exposure parameter adjustment method provided in an embodiment of the present application.

[0027] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements the exposure parameter adjustment method provided in the embodiment of the present application.

[0028] The present application provides an exposure parameter adjustment method, device, electronic device and computer-readable storage medium, which performs region recognition on the first original image data collected by the first image sensor, determines the first main area and the first non-main area in the first original image data; performs brightness weighting processing on the first main area and the first non-main area respectively, determines the first full image brightness corresponding to the first original image data; based on the first full image brightness, adjusts at least one exposure parameter corresponding to at least one image sensor; at least one image sensor includes the first image sensor. In this way, by performing brightness weighting processing on the first main area and the first non-main area respectively, the main area and the non-main area of ​​the picture in the first original image data collected by the first image sensor are weighted to different degrees to obtain the first full image brightness, so that the adjustment of the exposure parameters based on the first full image brightness can better highlight the main area in the picture. In addition, adjusting at least one exposure parameter corresponding to at least one image sensor on the electronic device based on the first full image brightness can make the exposure effect of at least one image sensor close to the first image sensor, improve the consistency of the exposure effect, and thus improve the exposure effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A schematic diagram of a flow chart of an exposure parameter adjustment method provided in an embodiment of the present application;

[0030] Figure 2 A schematic diagram of a weight mask provided in an embodiment of the present application;

[0031] Figure 3A schematic diagram of the process of the exposure parameter adjustment method applied to an actual scene provided in an embodiment of the present application;

[0032] Figure 4 A schematic diagram of the processing process of the automatic exposure control algorithm applied to an actual scene provided in an embodiment of the present application;

[0033] Figure 5 A schematic diagram of the structure of an exposure parameter adjustment device provided in an embodiment of the present application;

[0034] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0036] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0037] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0038] Before further describing the embodiments of the present invention in detail, the nouns and terms involved in the embodiments of the present invention are described. The nouns and terms involved in the embodiments of the present invention are subject to the following interpretations.

[0039] 1) Metering: Metering refers to the process by which electronic equipment measures light intensity through photosensitive elements before shooting to determine appropriate exposure parameters. The current mainstream metering modes include:

[0040] Spot metering: The metering element only measures a very small area in the center of the picture, usually 1% to 3%. For example, when taking a photo, the camera is pointed at different parts of the subject several times to measure their brightness one by one, and the photographer finally determines the exposure parameters based on the measured data.

[0041] Center metering: Meters the light in the center of the picture, which accounts for about 3% to 12% of the picture. It is suitable for some scenes with complex lighting. It can better ensure that the camera processor calculates the exposure required for the main object in the center of the picture.

[0042] Average metering: Measures the average brightness of the entire screen.

[0043] 2) Exposure: Exposure refers to the process by which the photosensitive element receives light and records the image during shooting. Exposure parameters include exposure time (shutter speed), aperture size, exposure gain, etc. These parameters or a combination of parameters determine the amount of light entering the camera, thereby affecting the brightness, contrast and color of the image.

[0044] At present, several common metering modes have the following disadvantages:

[0045] Spot metering has a small metering range and high operational requirements. The photographer needs to accurately align the metering point with the area that he wants to accurately expose. Otherwise, the metering result will be biased, resulting in overexposure or underexposure of other areas. This requires high operational skills and experience of the photographer. In addition, because the metering range is too narrow, it can only ensure accurate exposure of the area where the metering point is located, and cannot take into account the exposure of other parts of the picture, such as the main body of the picture.

[0046] Center metering focuses on the center of the image. When the subject is not in the center of the image, the subject is prone to inaccurate exposure or exposure deviation. In addition, although center metering uses the center area as the main basis for metering, the ambient brightness still has a certain impact on the metering result. When the ambient light is significantly different from the subject light, the exposure may be biased.

[0047] Average metering cannot provide accurate exposure guarantee for the subject that needs to be highlighted in the picture, which may make the brightness contrast between the subject and the background less than ideal. In addition, average metering cannot cope with complex lighting scenes. When there are large areas of overly bright or dark objects, it is difficult to determine the appropriate exposure based on the metering value, which can easily lead to inaccurate exposure of the subject.

[0048] In other words, the current common metering modes have certain limitations in metering range and adaptation scenes, which may result in poor exposure of the main area of ​​the picture when applied.

[0049] Furthermore, current user terminals are usually equipped with multiple cameras or multiple image sensors. During the light metering process, the multiple image sensors may have different exposure effects due to differences in hardware or software parameters. The differences in exposure effects of different image sensors may cause the following problems:

[0050] Reduced image quality: Photos taken by an overexposed camera will be too bright, resulting in loss of details in the highlights and inability to clearly show the outline and texture of the object; photos taken by an underexposed camera will be too dark, making it difficult to discern details in the dark areas, affecting the overall layering and three-dimensionality of the image. In addition, different exposure effects will result in inaccurate color reproduction of images taken by the camera. Overexposure will cause colors to be biased toward the highlights and reduce color saturation; underexposure will cause colors to be biased toward the dark areas, making the colors darker and possibly bluer or greener.

[0051] Reduced shooting experience: When users switch between different cameras during shooting, if the exposure effects are different, the brightness and color of the picture will change suddenly, causing visual differences when switching cameras, which will bring visual discontinuity and discomfort to users and affect the smoothness and continuity of shooting. In video shooting, if the exposure effects of multiple cameras are different, when the lens switches between different cameras, the brightness and color of the picture will jump significantly, affecting the continuity and viewing experience of the video, and making the audience feel uncomfortable.

[0052] Post-processing becomes more difficult: For scenes that require image stitching, fusion or synthesis after multiple cameras are shot, such as panoramic shooting and background blur, different exposure effects will make post-processing more complicated. It takes more time and effort to perform operations such as exposure correction and color matching to make the final synthesized image look natural and coordinated.

[0053] Impact on the realization of specific functions: For example, when shooting in portrait mode, multiple cameras are usually required to work together to achieve background blur and highlight the main subject through different exposure parameters. If the exposure effects are different, the background blur effect may not be ideal, and the transition between the main subject and the background may not be natural, affecting the overall beauty of the portrait photo.

[0054] Impact on the collaborative work of multi-camera systems: Different cameras have different exposure effects, which will lead to inconsistent white balance calculation results. In a multi-camera system, this will cause differences in color balance in images taken by different cameras, affecting the overall imaging effect when multiple cameras work together.

[0055] Image fusion is difficult: For some applications that require multi-camera image fusion, such as high-dynamic range (HDR) shooting, different exposure effects will make it difficult for the image fusion algorithm to accurately process the details and colors of different exposure areas, resulting in artifacts and unnatural colors in the fused image.

[0056] At present, some related technologies improve the consistency of exposure effects of multiple cameras by configuring sensors with the same or similar hardware parameters on the terminal; for example, selecting sensors with similar sensitivity range, pixel size, aperture size and other parameters, and lenses with similar optical performance. However, using the same or similar sensor and lens parameters will significantly increase hardware costs; and the reasonable layout of three cameras with similar parameters and related circuits in a limited space puts higher requirements on the internal structure design of mobile phones and other devices; further, even if the hardware parameters are similar, different cameras may still have performance differences in actual use, so the improvement method from the hardware aspect is too costly, difficult to implement, and the improvement effect is limited.

[0057] Alternatively, some other related technologies collect and analyze a large amount of shooting data to obtain exposure statistics of each camera in different scenes, and establish an exposure adjustment model based on these statistics. During actual shooting, the exposure of the three cameras is adjusted in real time according to the model to achieve a better consistent exposure effect. This statistical information-based exposure adjustment method may not be able to accurately judge and adjust the exposure parameters in some extreme or special scenes, such as extremely dark or bright environments, complex light reflection conditions, etc., so the exposure consistency of multiple cameras is still poor.

[0058] In summary, at least one camera on the electronic device reduces the overall exposure effect due to defects in the current metering mode and differences in exposure effects between image sensors.

[0059] The embodiments of the present application provide an exposure parameter adjustment method, device, electronic device and computer-readable storage medium, which can make the exposure effect more prominent on the subject of the shooting, and improve the consistency of the exposure effect of multiple cameras, thereby improving the exposure effect. The exposure parameter adjustment method provided in the embodiments of the present application is applied to an electronic device equipped with at least one image sensor and having a shooting function. In some embodiments, the electronic device may include various types of user terminals such as smart phones, tablet computers, laptop computers, smart watches, vehicle-mounted devices, etc., which are not specifically limited in this application. The exposure parameter adjustment method provided in the embodiments of the present application can be combined with the current metering mode, and the exposure parameters can be adjusted using the exposure parameter adjustment method provided in the embodiments of the present application according to the brightness of the image measured by any metering mode.

[0060] The exposure parameter adjustment method provided in the embodiment of the present application can be as follows: Figure 1 As shown, including S101-S103, as follows:

[0061] S101 . Performing region recognition on first original image data acquired by a first image sensor to determine a first subject region and a first non-subject region in the first original image data.

[0062] The embodiment of the present application is applied to the image acquisition process of an electronic device. Exemplarily, when the image acquisition function of the electronic device is started and the image acquisition preview screen is entered, the first image sensor is enabled and the first original image data is acquired by the first image sensor.

[0063] The first image sensor may include a main camera on the electronic device. Exemplarily, the first image sensor may include a camera with 1x zoom on a multi-camera electronic device.

[0064] Here, the first original image data may include original data (raw data) directly captured by the first image sensor when performing image acquisition according to historical exposure parameters, such as historical exposure time and historical exposure gain.

[0065] It should be noted that, since exposure has a lag, the first original image data currently collected by the first image sensor is obtained by triggering exposure according to historical exposure parameters determined at a historical moment, and applying the exposure effect of the historical exposure parameters to the image collection at the current moment.

[0066] By using a region recognition algorithm, the first original image data is subjected to region recognition, and a region occupied by a subject part in the first original image data can be identified as a first subject region, and a region occupied by a non-subject part can be identified as a first non-subject region. Here, the subject region represents the subject object to be captured by the picture, and the non-subject region includes other regions except the subject region.

[0067] In some embodiments, region recognition may include at least one of target detection, semantic segmentation, and instance segmentation. Exemplarily, through the target detection algorithm, the target can be predicted on the feature map of different scales, so as to detect the target objects of different sizes in the first original image data, and then determine the main area and the non-main area. Through the semantic segmentation algorithm, at least one semantic area corresponding to at least one semantic in the first original image data can be output, and then the main area and the non-main area can be determined from at least one semantic area. Through the instance segmentation algorithm, the target object in the first original image data can be detected, and an accurate mask can be generated for each object, so as to accurately separate the target object from the background and determine the main area and the non-main area. Alternatively, any two or all of target detection, semantic segmentation, and instance segmentation can be combined by algorithm to perform region recognition to determine the main area and the non-main area. The specific selection is made according to the actual situation, and the embodiments of the present application are not limited.

[0068] S102: Perform brightness weighted processing on the first main area and the first non-main area respectively to determine a first full image brightness corresponding to the first original image data.

[0069] In an embodiment of the present application, in order to highlight the exposure effect of the main area, different weights can be used to perform brightness weighted processing on the first main area and the first non-main area, respectively, to obtain a weighted brightness of the first main area and a weighted brightness of the first non-main area, and then the whole image is fused based on the weighted brightness of the first main area and the weighted brightness of the first non-main area to determine the first whole image brightness corresponding to the first original image data.

[0070] In some embodiments, the weight corresponding to the main area and the weight corresponding to the non-main area can be preset, wherein the weight corresponding to the main area is higher than the weight corresponding to the non-main area. In this way, according to the image parts occupied by the main area and the non-main area in the image data collected in real time, different image parts are weighted with different brightness weights to achieve enhanced exposure effect processing of the main area.

[0071] In some embodiments, the pixel brightness of the first main area and the pixels of the first non-main area may be statistically processed to obtain the brightness corresponding to the first main area and the brightness corresponding to the first non-main area.

[0072] In some embodiments, a main area weight corresponding to the first main area and a non-main area weight corresponding to the first non-main area are determined; the first main area weight is higher than the first non-main area weight; the brightness corresponding to the first main area is weighted using the first main area weight, and the brightness corresponding to the first non-main area is weighted using the first non-main area weight to determine the weighted first main area brightness and the weighted first non-main area brightness; the weighted first main area brightness and the weighted first non-main area brightness are fused to determine the first full image brightness.

[0073] In some embodiments, the non-main area includes a background area and a transition area; the non-main area weight includes: a background area weight and a transition area weight; the transition area weight is higher than the background area weight.

[0074] That is to say, the weight of the main area is higher than that of the transition area, and the weight of the transition area is higher than that of the background area.

[0075] For the first original image data, the first main area weight is higher than the first transition area weight, and the first transition area weight is higher than the first background area weight.

[0076] Exemplarily, a weight mask corresponding to the first original image data can be generated based on the first main area and the first non-main area, under the constraint that the weight of the main area is higher than the weight of the non-main area. Through the weight mask, the first main area and the first non-main area in the first original image data are brightness-weighted to obtain the weighted brightness of the first main area and the weighted brightness of the first non-main area.

[0077] Taking the subject area in the center of the picture as an example, the weight mask can be as follows Figure 2 shown. Figure 2 The distribution of the main area weight, transition area weight and background area weight is shown in . It should be noted that when the main area in the original image data collected in real time is at other positions of the picture, the corresponding weight distribution will also change with the change of the area, but it meets the constraint that the weight of the main area is higher than the weight of the non-main area, and the weight of the transition area in the non-main area is higher than the weight of the background area.

[0078] In some examples, the brightness of each color channel in the full image can be fused according to the weighted brightness of the first main area and the weighted brightness of the first non-main area to obtain the first full image brightness. Here, the first full image brightness represents the brightness level of the entire image after the brightness of the main area and the non-main area in the first original image data are weighted.

[0079] S103: Adjust at least one exposure parameter corresponding to at least one image sensor based on the first full image brightness.

[0080] Wherein, the at least one image sensor includes a first image sensor.

[0081] In the embodiment of the present application, since the first full image brightness is obtained by weighting the brightness of different regions of the first original image data acquired by the first image sensor based on the historical exposure parameters at the historical moment, a new exposure parameter can be calculated based on the first full image brightness, and the exposure parameter of the first image sensor can be adjusted using the new exposure parameter, so that the exposure effect corresponding to the first full image brightness is converted into an exposure parameter applied to the first image sensor, thereby improving the exposure effect of the main body of the picture. Alternatively, based on the first full image brightness, the exposure parameters of the first image sensor and at least one second image sensor are adjusted so that the exposure effects of the first image sensor and at least one second image sensor are consistent, thereby reducing various problems caused by differences in exposure effects of different image sensors.

[0082] Among them, at least one second image sensor may include a secondary camera on an electronic device. Exemplarily, at least one second image sensor may include a 2x, 3x, 6x, etc. camera on an electronic device with multiple cameras.

[0083] In some embodiments, after S103, a preview image can be generated based on at least one exposure parameter adjusted by at least one image sensor to achieve a better exposure effect for the main body of the image in the preview image. In this way, when the user performs a camera switching operation on the preview image, such as zooming, the exposure effect of the image when switching between different focal lengths can remain consistent, reducing the brightness jump during the zooming process and reducing the workload of fusing images collected by multiple cameras in subsequent image processing.

[0084] It can be understood that the first original image data collected by the first image sensor is subjected to region recognition to determine the first main body region and the first non-main body region in the first original image data; the first main body region and the first non-main body region are subjected to brightness weighting processing respectively to determine the first full image brightness corresponding to the first original image data; based on the first full image brightness, at least one exposure parameter corresponding to at least one image sensor is adjusted; at least one image sensor includes the first image sensor. In this way, by performing brightness weighting processing on the first main body region and the first non-main body region respectively, the main body region and the non-main body region of the first original image data collected by the first image sensor are weighted to different degrees to obtain the first full image brightness, so that the adjustment of the exposure parameter based on the first full image brightness can better highlight the main body region in the picture. In addition, by adjusting at least one exposure parameter corresponding to at least one image sensor on the electronic device based on the first full image brightness, the exposure effect of at least one image sensor can be brought close to the first image sensor, thereby improving the consistency of the exposure effect and thus improving the exposure effect.

[0085] In some embodiments, adjusting at least one exposure parameter corresponding to at least one image sensor based on the first full image brightness in S103 includes:

[0086] When the first image sensor is enabled, adjusting a first exposure parameter corresponding to the first image sensor based on the first full image brightness;

[0087] When the first image sensor and at least one second image sensor are enabled, a second full image brightness corresponding to each second image sensor in the at least one second image sensor is determined; and based on the first full image brightness and the second full image brightness, a second exposure parameter corresponding to each second image sensor is adjusted.

[0088] That is, when only the first image sensor is enabled, the first exposure parameter of the first sensor can be adjusted according to the first full image brightness, so that the first image sensor can generate an image with an exposure effect that more prominently highlights the main body of the picture according to the adjusted first exposure parameter. When the first image sensor and at least one second image sensor are enabled at the same time, the first exposure parameter corresponding to the first image sensor is still adjusted based on the first full image brightness; and for each second image sensor, the second exposure parameter corresponding to the second image sensor can be adjusted in combination with the first full image brightness corresponding to the first image sensor and the second full image brightness corresponding to the image sensor, so that the second image sensor can generate an image with an exposure effect that more prominently highlights the main body of the picture and is closer to the exposure effect of the first image sensor according to the adjusted second exposure parameter.

[0089] Here, the second full image brightness represents the overall brightness level of the image obtained after weighting the brightness of the main area and the non-main area of ​​the second original image data collected by the second image sensor. The method process for determining the second full image brightness is similar to the method process for determining the first full image brightness.

[0090] In some embodiments, determining the second full image brightness corresponding to each second image sensor in at least one second image sensor includes:

[0091] Performing region recognition on the second original image data collected by each second image sensor to determine a second main region and a second non-main region in the second original image data; performing brightness weighted processing on the second main region and the second non-main region respectively to determine the second full image brightness corresponding to each second image sensor.

[0092] In some embodiments, the pixel brightness of the second main area and the pixels of the second non-main area may be statistically processed to obtain the brightness corresponding to the second main area and the brightness corresponding to the second non-main area.

[0093] In some embodiments, by performing brightness weighting processing on the brightness corresponding to the second main area and the brightness corresponding to the second non-main area respectively, a weighted second main area brightness and a weighted second non-main area brightness can be obtained; the weighted second main area brightness and the weighted second non-main area brightness are fused to determine the second full image brightness.

[0094] It should be noted that, since the second image sensor has a different focal length and a different field of view (FOV) from the first image sensor, the second main area is different from the first main area, and the second non-main area is different from the first non-main area. Exemplarily, the main camera FOV is larger, and the first original image data includes the first main area, the first transition area and the first background area, while the secondary camera FOV is smaller, and the second original image data may only include the second main area and the second transition area, and the occupied area of ​​the main area may be different. Therefore, the weight mask corresponding to the first original image data may be different from the weight mask corresponding to the second original image data. In practical applications, the weight mask corresponding to the second original image data can be generated under the constraint that the weight of the main area is higher than the weight of the non-main area according to the actual distribution of the second main area and the second non-main area in the second original image data collected in real time. Alternatively, the weight mask corresponding to the first original image data can be cropped and / or scaled according to the FOV difference between the first image sensor and the second image sensor to obtain the weight mask corresponding to the second original image data. Furthermore, the brightness of the second main area and the second non-main area can be weighted according to the weight mask corresponding to the second original image data to obtain the weighted second main area brightness and the weighted second non-main area brightness.

[0095] In some embodiments, the first exposure parameter includes: a first exposure time and / or a first exposure gain; and adjusting the first exposure parameter corresponding to the first image sensor based on the first full image brightness includes:

[0096] Based on the first full image brightness and the target full image brightness, the first exposure time and / or the first exposure gain corresponding to the first image sensor are updated.

[0097] Here, based on the first full-image brightness and the target full-image brightness, a corresponding exposure amount, such as a first updated exposure amount, can be calculated, and the first updated exposure amount can be converted into exposure time and exposure gain as the first updated exposure time and / or the first updated exposure gain; the first updated exposure time and / or the first updated exposure gain are used to update the first exposure time and / or the first exposure gain, thereby achieving adjustment of the first exposure parameter among at least one exposure parameter.

[0098] Alternatively, the corresponding exposure time and exposure gain, such as the first updated exposure time and / or the first updated exposure gain, can be directly calculated based on the first full-image brightness and the target full-image brightness; and the first updated exposure time and / or the first updated exposure gain can be used to update the first exposure time and / or the first exposure gain, thereby adjusting the first exposure parameter among at least one exposure parameter.

[0099] Exemplarily, updating the first exposure time and / or the first exposure gain corresponding to the first image sensor based on the first full image brightness includes:

[0100] Determine a first exposure corresponding to a first full-image brightness; determine a first updated exposure based on the first exposure, the first full-image brightness and the target full-image brightness; determine a first updated exposure time and / or a first updated exposure gain based on the first updated exposure, and use the first updated exposure time and / or the first updated exposure gain to update the first exposure time and / or the first exposure gain.

[0101] Here, the first exposure represents the exposure required to achieve the first full image brightness. The target full image brightness is obtained, and the first exposure is adjusted according to the target full image brightness and the first full image brightness to obtain a first updated exposure. The target full image brightness represents the overall image brightness level expected to be achieved by the current image acquisition. The target full image brightness can be a preset fixed value or can be automatically generated according to the acquisition environment or shooting requirements of the current image acquisition, which is not limited here.

[0102] Exemplarily, the first updated exposure amount can be calculated by formula (1), as follows:

[0103] CurExpindex=MatchExpindexLuma1*TuningLuma / Luma1 Formula (1)

[0104] Among them, CurExpindex is the first updated exposure, Luma1 is the first full-image brightness, MatchExpindexLuma1 is the first exposure corresponding to the first full-image brightness, and TuningLuma is the target full-image brightness.

[0105] In some embodiments, the second exposure parameter includes: a second exposure time and / or a second exposure gain; based on the first full image brightness and the second full image brightness, adjusting the second exposure parameter corresponding to each second image sensor includes:

[0106] Based on the first full image brightness and the second full image brightness, the second updated exposure time and / or the second updated exposure gain corresponding to each second image sensor are directly calculated; the second updated exposure time and / or the second updated exposure gain are used to update the second exposure time and / or the second exposure gain, thereby adjusting the second exposure parameter corresponding to each second image sensor in at least one exposure parameter.

[0107] Alternatively, determine the first exposure corresponding to the first full image brightness; determine the second updated exposure corresponding to each second image sensor according to the second full image brightness, the first full image brightness, the first exposure and the preset mapping factor corresponding to each second image sensor; determine the second updated exposure time and / or the second updated exposure gain according to the second updated exposure, and use the second updated exposure time / or the second updated exposure gain to update the second exposure time / or the second exposure gain, thereby adjusting the second exposure parameter corresponding to each second image sensor in at least one exposure parameter. The preset mapping factor represents the exposure parameter mapping relationship between the second image sensor and the first image sensor when the exposure effect of the second image sensor and the exposure effect of the first image sensor meet the preset consistency condition.

[0108] Among them, since the exposure effects of different image sensors are different, for each second image sensor, the exposure parameter mapping relationship between the second image sensor and the first image sensor can be determined by a pre-calibration method when the exposure effects of the second image sensor and the first image sensor meet the preset consistency conditions, thereby obtaining a preset mapping factor. In this way, the exposure effect of the second image sensor can be adjusted to be close to the exposure effect of the first image sensor according to the preset mapping factor, which is helpful to improve the consistent exposure effect of multiple shots.

[0109] Exemplarily, the preset consistency condition may include: the brightness difference of the images collected in the same field of view angle area is less than or equal to the preset difference threshold. Before updating the second updated exposure corresponding to each second image sensor according to the second full image brightness, the first full image brightness, the first exposure and the preset mapping factor corresponding to each second image sensor, the exposure time and exposure gain corresponding to the first image sensor can be obtained as the reference first exposure time and the reference first exposure gain, and the exposure time and exposure gain corresponding to the second image sensor can be obtained as the reference second exposure time and the reference second exposure gain; determine the first product of the reference first exposure time and the reference first exposure gain; determine the second product of the reference second exposure time and the reference second exposure gain; and determine the preset mapping factor according to the ratio of the second product to the first product.

[0110] For example, as shown in formula (2), it is as follows:

[0111] Factor=exptime(other)*expgain(other) / (exptime(main)*expgain(main)) (2)

[0112] Among them, exptime(other) is the reference to the second exposure time; expgain(other) is the reference to the second exposure gain; exptime(main) is the reference to the first exposure time; expgain(main) is the reference to the first exposure gain; and Factor is the preset mapping factor.

[0113] For example, the second updated exposure corresponding to each second image sensor can be determined by formula (3) according to the second full image brightness, the first full image brightness, the first exposure and the preset mapping factor corresponding to each second image sensor, as follows:

[0114] MatchExpindex=Luma2 / Luma1*MatchExpindexLuma1*Factor (3)

[0115] Among them, Luma2 is the second full-image brightness; MatchExpindex is the second updated exposure.

[0116] For example, Figure 3 As shown, only when the main camera (equivalent to the first image sensor) is enabled, the main camera runs the process steps S301-S304.

[0117] S301. The main camera generates an image according to historical exposure parameters determined at historical moments, such as historical exposure time and historical exposure gain, to obtain first raw data (equivalent to first original image data).

[0118] S302, subject recognition (ie, region recognition) is performed on the first raw data, and the first raw data is divided into regions to obtain a first subject region and a first non-substance region in the first raw data, illustratively including: a first subject region, a first transition region, and a first background region.

[0119] S303 , performing regional brightness statistical processing on the first raw data to obtain first statistical data (statistics) corresponding to the first raw data, and sending the first statistical data (statistics) to an AEC algorithm module.

[0120] Among them, the first statistical data includes: the brightness corresponding to the first main area and the brightness corresponding to the first non-main area; further, the first statistical data can also include: a brightness histogram of the first raw data, an average brightness value, and at least one of color statistical data, to provide to the AEC algorithm module as a reference for generating exposure parameters, which is not specifically limited here.

[0121] S304: The AEC algorithm module performs AEC algorithm processing based on the first statistical data, and outputs a first exposure parameter corresponding to the main camera, such as a first exposure time and a first exposure gain. The first exposure time and the first exposure gain output by the AEC algorithm are then applied to the main camera, which is equivalent to adjusting the first exposure parameter of the main camera.

[0122] When at least one secondary camera (equivalent to at least one second image sensor) is enabled, the main camera is also enabled at the same time and executes the above S301-S304. It should be noted that when the main camera and at least one secondary camera are enabled at the same time, the main camera will send the first statistical data to the secondary camera, and the secondary camera will run Figure 3 Process steps S305-S309 in .

[0123] S305. The secondary camera (each secondary camera) generates a picture according to historical exposure parameters determined at historical moments, such as historical exposure time and historical exposure gain, to obtain second raw data (equivalent to second original image data).

[0124] S306 , subject recognition (ie, region recognition) is performed on the second raw data, and the second raw data is region-divided into a second subject region and a second non-substance region. Exemplarily, a second subject region, a second transition region, and a second background region are obtained.

[0125] S307 , performing regional brightness statistical processing on the second raw data to obtain second statistical data corresponding to the second raw data, and sending the second statistical data to the AEC algorithm module.

[0126] Among them, the second statistical data include: the brightness corresponding to the second main area and the brightness corresponding to the second non-main area; further, the second statistical data can also include: a brightness histogram of the second raw data, an average brightness value, and at least one of color statistical data, to provide to the AEC algorithm module as a reference for generating exposure parameters, which is not specifically limited here.

[0127] S308: Receive first statistical data sent by the main camera, and send second statistical data to the AEC algorithm module.

[0128] It should be noted that Figure 3 The AEC algorithm module corresponding to the main camera and the AEC algorithm module corresponding to the auxiliary camera can be the same module, that is, the main camera and at least one auxiliary camera share the same AEC algorithm module. Figure 3It reflects the respective processes of the same AEC algorithm module when calculating the first exposure parameter of the main camera and the second exposure parameter of the secondary camera. The AEC algorithm module corresponding to the main camera and the AEC algorithm module corresponding to the secondary camera can also be different modules, that is, the main camera and the secondary camera correspond to independent AEC algorithm modules respectively, and each calculates the exposure parameters independently. In this case, there is a data connection between the AEC algorithm module of the main camera and the AEC algorithm module of the secondary camera (not shown in the figure) to send the first full-image brightness corresponding to the main camera to the AEC algorithm module of the secondary camera.

[0129] S309: The AEC algorithm module calculates the second exposure parameters corresponding to each secondary camera based on the first statistical data and the second statistical data of each secondary camera, such as the second exposure time and the second exposure gain corresponding to each secondary camera. The obtained exposure parameters corresponding to each secondary camera are then applied to the corresponding secondary camera.

[0130] It can be understood that the embodiment of the present application enhances the exposure effect by focusing on the shooting subject, and when calculating the exposure parameters, other cameras can also enhance the exposure of the subject area in their own pictures, and can combine the brightness information after the main camera exposure effect is enhanced to bring the exposure effect closer to the exposure effect of the main camera, thereby achieving full-link conduction of multi-camera exposure consistency and improving the exposure effect.

[0131] For example, based on Figure 3 , the processing flow of the AEC algorithm module can be as follows Figure 4 As shown. In which, only when the main camera (equivalent to the first image sensor) is enabled, the main camera runs Figure 4 The process steps S401->S402->S403->S409 in the embodiment include:

[0132] S401. Generate a weight mask corresponding to the first original image data; obtain the brightness corresponding to the first main area and the brightness corresponding to the first non-main area according to the first statistical data; and weight the brightness corresponding to the first main area and the brightness corresponding to the first non-main area according to the weight mask corresponding to the first original image data to obtain the weighted brightness of the first main area and the weighted brightness of the first non-main area.

[0133] S402: Obtain a first full-image brightness according to the weighted brightness of the first main area and the weighted brightness of the first non-main area.

[0134] S403, calculating the target exposure corresponding to the first full image brightness, where the target exposure is equivalent to the first updated exposure.

[0135] S409: Calculate and output corresponding exposure parameters according to the target exposure.

[0136] Here, the exposure parameters may include exposure time and / or exposure gain. For example, they may include a first exposure time and / or a first exposure gain.

[0137] When at least one secondary camera (equivalent to at least one second image sensor) is enabled, the main camera is also enabled and executes the above S401->S402->S403->S409. It should be noted that when the main camera and at least one secondary camera are enabled at the same time, the main camera will send the first full image brightness to the secondary camera, and the secondary camera will run Figure 3 Process steps S404-S409 in .

[0138] S404, generate a weight mask corresponding to the second original image data; obtain the brightness corresponding to the first main area and the brightness corresponding to the first non-main area according to the second statistical data; according to the weight mask corresponding to the second original image data, weight the brightness corresponding to the second main area and the brightness corresponding to the second non-main area respectively to obtain the weighted second main area brightness and the weighted second non-main area brightness.

[0139] S405: Obtain the second full image brightness according to the weighted second main area brightness and the weighted second non-main area brightness.

[0140] S406: Send the second full image brightness to an exposure calculation module.

[0141] S407: The exposure calculation module obtains the first full image brightness.

[0142] S408. Calculate the target exposure corresponding to each secondary camera based on the first full image brightness and the second full image brightness through the exposure calculation module. Here, the target exposure refers to the second updated exposure.

[0143] S409: Calculate and output corresponding exposure parameters according to the target exposure.

[0144] Here, the exposure parameters may include exposure time and / or exposure gain. For example, they may include a second exposure time and / or a second exposure gain.

[0145] It can be understood that the exposure parameter adjustment method of the embodiment of the present application can significantly improve the image quality. When shooting at different focal lengths, it can ensure that the picture exposure is accurate and natural, avoid overexposure or underexposure, and make the photos taken at each focal length present rich details and delicate colors. For example, when shooting scenery under strong light, the bright parts of the pictures taken by the main camera, ultra-wide-angle and telephoto lenses are not overexposed, and the dark parts retain enough details to improve the overall image quality. In addition, when the user switches the camera to shoot in different scenes, there is no need to frequently adjust the exposure parameters, which improves the shooting efficiency and convenience. When capturing, continuously shooting and shooting videos, the exposure stability and consistency can be ensured, thereby enhancing the shooting experience. In addition, through the three-camera exposure consistency technology, the ideal exposure effect can be obtained at different focal lengths, providing more possibilities for creation. For example, when shooting portraits, using an ultra-wide-angle lens to shoot environmental portraits, or using a telephoto lens to shoot close-ups, the consistency of exposure and color can be guaranteed, so that the style of the whole group of photos is unified.

[0146] In some embodiments, the lighting environment of the current shooting scene is identified to determine the lighting scene corresponding to the current shooting scene; according to the lighting scene, at least one metering mode corresponding to at least one image sensor is adjusted, and / or the area weight corresponding to at least one image sensor is adjusted; the area weight includes the subject area weight and / or the non-subject area weight.

[0147] Among them, the lighting environment of the current shooting scene is identified to determine the lighting scene corresponding to the current shooting scene, such as night scene, backlight, indoor, outdoor, etc. According to the lighting scene, it can be determined whether the current metering mode of the image sensor is suitable for the lighting scene. If it is not suitable, the metering mode corresponding to the image sensor is adjusted, such as when shooting a night scene portrait, the average metering mode is changed to a spot metering mode to improve the exposure effect of the face of the character. In addition, based on the metering mode, in combination with the exposure parameter adjustment method provided in the embodiment of the present application, the exposure effect of the main area can be improved and the exposure effect of the multi-shot consistency can be synchronized to further improve the exposure effect. And / or, based on the lighting scene, the above-mentioned main area weight and / or non-main area weight can be updated. For example, in the lighting scene of the night scene, the weight of the light part in the generated weight mask of the first image sensor and / or the weight mask of the second image sensor is updated to suppress the brightness of the light part in the image to prevent overexposure. In this way, more accurate exposure parameters can be generated by updating the regional weights to improve the exposure effect.

[0148] It can be understood that by adjusting the exposure parameters in combination with the lighting scene, the exposure effect is adapted to the shooting environment, thereby further improving the exposure effect.

[0149] The present application embodiment provides an exposure parameter adjustment device 1, such as Figure 5As shown, including:

[0150] The region recognition module 11 is used to perform region recognition on the first original image data collected by the first image sensor, and determine a first subject region and a first non-subject region in the first original image data;

[0151] A brightness processing module 12, configured to perform brightness weighted processing on the first main area and the first non-main area respectively, to determine a first full image brightness corresponding to the first original image data;

[0152] The adjustment module 13 is used to adjust at least one exposure parameter corresponding to at least one image sensor based on the first full image brightness; the at least one image sensor includes the first image sensor.

[0153] Optionally, the brightness processing module is also used to determine the main area weight corresponding to the first main area and the non-main area weight corresponding to the first non-main area; the first main area weight is higher than the first non-main area weight; the brightness corresponding to the first main area is weighted using the first main area weight, and the brightness corresponding to the first non-main area is weighted using the first non-main area weight to determine the weighted first main area brightness and the weighted first non-main area brightness; the weighted first main area brightness and the weighted first non-main area brightness are merged to determine the first full image brightness.

[0154] Optionally, the first non-main area includes: a first background area and a first transition area; the first non-main area weight includes: a first background area weight and a first transition area weight; the first transition area weight is higher than the first background area weight.

[0155] Optionally, the at least one image sensor also includes: at least one second image sensor; the adjustment module is further used to adjust the first exposure parameter corresponding to the first image sensor based on the first full image brightness when the first image sensor is enabled; determine the second full image brightness corresponding to each second image sensor in the at least one second image sensor when the first image sensor and the at least one second image sensor are enabled; and adjust the second exposure parameter corresponding to each second image sensor based on the first full image brightness and the second full image brightness.

[0156] Optionally, the first exposure parameter includes: a first exposure time and / or a first exposure gain; the adjustment module is further used to update the first exposure time and / or first exposure gain corresponding to the first image sensor based on the first full image brightness and the target full image brightness.

[0157] Optionally, the adjustment module is also used to determine a first exposure corresponding to the first full-image brightness; determine a first updated exposure based on the first exposure, the first full-image brightness and the target full-image brightness; determine a first updated exposure time and / or a first updated exposure gain based on the first updated exposure, and use the first updated exposure time and / or the first updated exposure gain to update the first exposure time and / or the first exposure gain.

[0158] Optionally, the adjustment module is further used to perform region recognition on the second original image data collected by each second image sensor to determine a second main area and a second non-main area in the second original image data; and perform brightness weighted processing on the second main area and the second non-main area respectively to determine the second full image brightness corresponding to each second image sensor.

[0159] Optionally, the second exposure parameter includes: a second exposure time and / or a second exposure gain; the adjustment module is also used to determine the first exposure amount corresponding to the first full image brightness; determine the second updated exposure amount corresponding to each second image sensor according to the second full image brightness, the first full image brightness, the first exposure amount and a preset mapping factor corresponding to each second image sensor; determine the second updated exposure time and / or the second updated exposure gain according to the second updated exposure amount, and use the second updated exposure time and / or the second updated exposure gain to update the second exposure time and / or the second exposure gain; the preset mapping factor represents the exposure parameter mapping relationship between the second image sensor and the first image sensor when the exposure effect of the second image sensor and the exposure effect of the first image sensor meet a preset consistency condition.

[0160] Optionally, the exposure parameter adjustment device also includes a calibration module; the calibration module is used to obtain a reference first exposure time and a reference first exposure gain corresponding to the first image sensor, and a reference second exposure time and a reference second exposure gain corresponding to the second image sensor when the image brightness difference captured by the second image sensor and the first image sensor in the same field of view angle area is less than or equal to a preset difference threshold before determining the second updated exposure corresponding to each second image sensor based on the second full image brightness, the first full image brightness, the first exposure and the preset mapping factor corresponding to each second image sensor; determine a first product of the reference first exposure time and the reference first exposure gain; determine a second product of the reference second exposure time and the reference second exposure gain; and determine the preset mapping factor according to the ratio of the second product to the first product.

[0161] Optionally, the exposure parameter adjustment device also includes a scene recognition module; the scene recognition module is used to identify the lighting environment of the current shooting scene and determine the lighting scene corresponding to the current shooting scene; according to the lighting scene, adjust at least one metering mode corresponding to the at least one image sensor, and / or adjust the area weight corresponding to the at least one image sensor; the area weight includes a subject area weight and / or a non-subject area weight.

[0162] Optionally, region recognition includes at least one of target detection, semantic segmentation and instance segmentation.

[0163] It should be noted that the description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.

[0164] The present application also provides an electronic device, Figure 6 This is an optional structural diagram of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 3 includes: a memory 32 and a processor 33. The memory 32 and the processor 33 are connected via a communication bus 34; the memory 32 is used to store executable instructions; the processor 33 is used to implement the exposure parameter adjustment method provided in the embodiment of the present application when executing the executable instructions stored in the memory 32.

[0165] An embodiment of the present application provides a computer-readable storage medium storing executable instructions, wherein executable instructions are stored. When the executable instructions are executed by the above-mentioned processor, the above-mentioned processor will execute the exposure parameter adjustment method provided in the embodiment of the present application.

[0166] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface storage, optical disk, or CD-ROM; or it may be various devices including one or any combination of the above memories.

[0167] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0168] As examples, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file storing other programs or data, such as one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions). As examples, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one location, or on multiple computing devices distributed at multiple locations and interconnected by a communication network.

[0169] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of hardware embodiments, software embodiments, or embodiments in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0170] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0171] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0172] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0173] The above is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application. Any modifications, equivalent substitutions and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. A method for adjusting exposure parameters, characterized in that: include: Performing region recognition on first original image data acquired by a first image sensor to determine a first subject region and a first non-subject region in the first original image data; Performing brightness weighted processing on the first main area and the first non-main area respectively to determine a first full-image brightness corresponding to the first original image data; Based on the brightness of the first full image, adjusting at least one exposure parameter corresponding to at least one image sensor; The at least one image sensor includes the first image sensor.

2. The method according to claim 1, characterized in that The performing brightness weighted processing on the first main area and the first non-main area respectively to determine the first full image brightness corresponding to the first original image data includes: Determine a main area weight corresponding to the first main area and a non-main area weight corresponding to the first non-main area; the first main area weight is higher than the first non-main area weight; Using the first main area weight, weighting the brightness corresponding to the first main area, and using the first non-main area weight, weighting the brightness corresponding to the first non-main area, to determine the weighted first main area brightness and the weighted first non-main area brightness; The weighted brightness of the first main area and the weighted brightness of the first non-main area are fused to determine the brightness of the first full image.

3. The method according to claim 2, characterized in that The first non-main area includes: a first background area and a first transition area; the first non-main area weight includes: a first background area weight and a first transition area weight; the first transition area weight is higher than the first background area weight.

4. The method according to any one of claims 1 to 3, characterized in that: The at least one image sensor further includes: at least one second image sensor; and adjusting at least one exposure parameter corresponding to the at least one image sensor based on the first full image brightness includes: When the first image sensor is enabled, adjusting a first exposure parameter corresponding to the first image sensor based on the first full image brightness; When the first image sensor and the at least one second image sensor are enabled, determining a second full image brightness corresponding to each second image sensor in the at least one second image sensor; Based on the first full image brightness and the second full image brightness, the second exposure parameter corresponding to each second image sensor is adjusted.

5. The method according to claim 4, characterized in that The first exposure parameter includes: a first exposure time and / or a first exposure gain; and adjusting the first exposure parameter corresponding to the first image sensor based on the first full image brightness includes: Based on the first full image brightness and the target full image brightness, a first exposure time and / or a first exposure gain corresponding to the first image sensor is updated.

6. The method according to claim 5, characterized in that The updating of the first exposure time and / or the first exposure gain corresponding to the first image sensor based on the first full image brightness and the target full image brightness includes: Determine a first exposure value corresponding to the brightness of the first full image; Determining a first updated exposure amount according to the first exposure amount, the first full image brightness, and a target full image brightness; A first updated exposure time and / or a first updated exposure gain is determined according to the first updated exposure amount, and the first updated exposure time and / or the first updated exposure gain are used to update the first exposure time and / or the first exposure gain.

7. The method according to claim 4, characterized in that The determining of the second full image brightness corresponding to each second image sensor in the at least one second image sensor comprises: Performing region recognition on the second original image data collected by each second image sensor to determine a second subject region and a second non-subject region in the second original image data; Perform brightness weighted processing on the second main area and the second non-main area respectively to determine the second full image brightness corresponding to each second image sensor.

8. The method according to claim 4, characterized in that The second exposure parameter includes: a second exposure time and / or a second exposure gain; and adjusting the second exposure parameter corresponding to each second image sensor based on the first full image brightness and the second full image brightness includes: Determine a first exposure value corresponding to the brightness of the first full image; Determine a second updated exposure corresponding to each second image sensor according to the second full image brightness, the first full image brightness, the first exposure, and a preset mapping factor corresponding to each second image sensor; A second updated exposure time and / or a second updated exposure gain is determined according to the second updated exposure amount, and the second updated exposure time and / or the second updated exposure gain are used to update the second exposure time and / or the second exposure gain; the preset mapping factor represents the exposure parameter mapping relationship between the second image sensor and the first image sensor when the exposure effect of the second image sensor and the exposure effect of the first image sensor meet a preset consistency condition.

9. The method according to claim 8, characterized in that Before determining the second updated exposure corresponding to each second image sensor according to the second full image brightness, the first full image brightness, the first exposure, and the preset mapping factor corresponding to each second image sensor, the method further includes: When a brightness difference between images captured by the second image sensor and the first image sensor in the same field of view angle area is less than or equal to a preset difference threshold, obtaining a reference first exposure time and a reference first exposure gain corresponding to the first image sensor, and a reference second exposure time and a reference second exposure gain corresponding to the second image sensor; determining a first product of the reference first exposure time and the reference first exposure gain; determining a second product of the reference second exposure time and the reference second exposure gain; The preset mapping factor is determined according to a ratio of the second product to the first product.

10. The method according to any one of claims 1 to 3, or any one of claims 5 to 8, or claim 9, characterized in that: The method further comprises: Identify the lighting environment of the current shooting scene to determine the lighting scene corresponding to the current shooting scene; According to the lighting scene, at least one metering mode corresponding to the at least one image sensor is adjusted, and / or the area weight corresponding to the at least one image sensor is adjusted; the area weight includes a main area weight and / or a non-main area weight.

11. The method according to any one of claims 1 to 3, or any one of claims 5 to 8, or claim 9, characterized in that: Region recognition includes at least one of target detection, semantic segmentation and instance segmentation.

12. An exposure parameter adjustment device, characterized in that: The device comprises: A region recognition module, configured to perform region recognition on the first original image data acquired by the first image sensor, and determine a first subject region and a first non-subject region in the first original image data; a brightness processing module, configured to perform brightness weighted processing on the first main area and the first non-main area respectively, and determine a first full-image brightness corresponding to the first original image data; An adjustment module is used to adjust at least one exposure parameter corresponding to at least one image sensor based on the first full image brightness; the at least one image sensor includes the first image sensor.

13. An electronic device, characterized in that: comprising a memory and a processor; wherein, The memory is used to store executable instructions; The processor is used to implement the method according to any one of claims 1-11 when executing the executable instructions stored in the memory.

14. A computer-readable storage medium, characterized in that: Executable instructions are stored, which are used to cause a processor to execute and implement the method according to any one of claims 1 to 11.

15. A computer program product, characterized in that The method comprises a computer program or an instruction, which, when executed by a processor, implements the method according to any one of claims 1 to 11.

Images