Method and device for improving image quality and storage medium

Abstract

The invention discloses a method and device for improving image quality and a storage medium. The method for improving the image quality comprises the steps of obtaining image data corresponding to each exposure mode in the same image collection scene based on at least two preset exposure modes; performing target detection processing on the image data corresponding to the at least one exposure mode to obtain object information of a target object in the image data; determining a target exposure mode from the exposure modes based on the object information and the exposure demand corresponding to the object information; and outputting the image data corresponding to the target exposure mode as target image data to obtain a high-quality image. According to the scheme, the high-quality image can be obtained from the image data of multiple exposure modes.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device and storage medium for improving image quality. Background Art

[0002] In image acquisition scenarios, time-sharing exposure technology is often used to improve image quality. It mainly uses time-sharing fill light from external light sources (such as visible light and infrared light) to obtain scene images with different exposure brightness, and then performs processing such as image fusion based on wide dynamic technology to obtain high-quality images.

[0003] However, the image fusion method is not applicable to all image acquisition scenarios. If the target object in the image moves too fast, obvious ghosting and afterimages will appear after image fusion, which will reduce the image quality.

[0004] Moreover, the fused images output by wide dynamic range technology may not necessarily meet various image acquisition requirements. Therefore, a more optimized method is urgently needed to improve image quality. Summary of the invention

[0005] The present application at least provides a method, apparatus, device and computer-readable storage medium for improving image quality.

[0006] In a first aspect, the present application provides a method for improving image quality, comprising: acquiring image data corresponding to each exposure mode in the same image acquisition scenario based on at least two preset exposure modes; performing target detection processing on the image data corresponding to at least one exposure mode to obtain object information of the target object in the image data; determining a target exposure mode from each exposure mode based on the object information and the exposure requirement corresponding to the object information; and outputting the image data corresponding to the target exposure mode as target image data to obtain a high-quality image.

[0007] In one embodiment, the object information includes a moving speed, the exposure mode includes a long exposure mode and a short exposure mode, and determining a target exposure mode from each exposure mode based on the object information and an exposure requirement corresponding to the object information includes: distinguishing each target object into a high-speed moving object and a low-speed moving object based on the moving speed of each target object; if the exposure requirement is to obtain image data of the high-speed moving object, determining the short exposure mode as the target exposure mode; if the exposure requirement is to obtain image data of the low-speed moving object, determining the long exposure mode as the target exposure mode.

[0008] In one embodiment, the object information includes an object type, each object type is preset with a corresponding exposure mode, and determining a target exposure mode from each exposure mode based on the object information and an exposure requirement corresponding to the object information includes: determining a target object type to be detected from each object type based on the exposure requirement; and determining the exposure mode corresponding to the target object type as the target exposure mode.

[0009] In one embodiment, the image data corresponding to the target exposure mode is output as the target image data to obtain a high-quality image, including: obtaining a brightness value of the target image data; if the brightness value is less than the left boundary of a preset brightness range, extending the exposure frame length of the target exposure mode to obtain an adjusted target exposure mode; if the brightness value is greater than the right boundary of the preset brightness range, shortening the exposure frame length of the target exposure mode to obtain an adjusted target exposure mode; and outputting an image based on the adjusted target exposure mode to obtain the high-quality image.

[0010] In one embodiment, determining a target exposure mode from each exposure mode based on the object information and the exposure requirement corresponding to the object information includes: determining a first candidate exposure mode from multiple exposure modes based on the object information and the exposure requirement corresponding to the object information, and acquiring first image data corresponding to the first candidate exposure mode; determining a second candidate exposure mode from multiple exposure modes based on image quality of the image data corresponding to each exposure mode, and acquiring second image data corresponding to the second candidate exposure mode; determining the target exposure mode from the first candidate exposure mode and the second candidate exposure mode based on an image quality difference between the first image data and the second image data.

[0011] In one embodiment, the image quality includes a quality score, and the determining of a second candidate exposure mode from multiple exposure modes based on the image quality of the image data corresponding to each exposure mode, and obtaining the second image data corresponding to the second candidate exposure mode, include: performing quality score processing based on the image data corresponding to each exposure mode, respectively, to obtain the quality score corresponding to the image data of each exposure mode; comparing each exposure mode based on the quality score, and selecting the exposure mode with the highest quality score from each exposure mode as the second candidate exposure mode.

[0012] In one embodiment, the image quality includes a quality score, and the determining the target exposure mode from the first candidate exposure mode and the second candidate exposure mode based on the image quality difference between the first image data and the second image data includes: if the quality score difference between the first image data and the second image data is within a preset difference threshold interval, adjusting the first quality score of the first image data and the second quality score of the second image data respectively based on a preset score adjustment strategy to obtain an adjusted first quality score and an adjusted second quality score; determining the target exposure mode from the first candidate exposure mode and the second candidate exposure mode based on a comparison result between the adjusted first quality score and the adjusted second quality score; if the quality score difference between the first image data and the second image data is greater than the right boundary of the difference threshold interval, and the second quality score is greater than the first quality score, determining the second candidate exposure mode as the target exposure mode.

[0013] In one embodiment, the object information includes a moving speed, and the first quality score of the first image data and the second quality score of the second image data are adjusted based on a preset score adjustment strategy to obtain an adjusted first quality score and an adjusted second quality score, including: performing weighted sum processing on the moving speed of the target object in the first image data and the first quality score to obtain the adjusted first quality score; performing weighted sum processing on the moving speed of the target object in the second image data and the second quality score to obtain the adjusted second quality score.

[0014] In a second aspect of the present application, there is provided a device for improving image quality, comprising: an acquisition module, for acquiring image data corresponding to each exposure mode in the same image acquisition scenario based on at least two preset exposure modes; a detection module, for performing target detection processing on image data corresponding to at least one exposure mode to obtain object information of a target object in the image data; an exposure determination module, for determining a target exposure mode from each exposure mode based on the object information and the exposure requirement corresponding to the object information; and an output module, for outputting the image data corresponding to the target exposure mode as target image data to obtain a high-quality image.

[0015] A third aspect of the present application provides an electronic device, including a memory and a processor, wherein the processor is used to execute program instructions stored in the memory to implement the above-mentioned method for improving image quality.

[0016] A fourth aspect of the present application provides a computer-readable storage medium having program instructions stored thereon, which implement the above-mentioned method for improving image quality when the program instructions are executed by a processor.

[0017] The above scheme obtains the image data corresponding to each exposure mode in the same image acquisition scene through at least two preset exposure modes, thereby obtaining multiple image data corresponding to multiple exposure data; performs target detection processing on the image data corresponding to at least one of the exposure modes to obtain the object information of the target object in the image data; determines the target exposure mode suitable for displaying the target object from each exposure mode by analyzing the object information of the target object (such as object type and / or moving speed, etc.) and the exposure requirements corresponding to the object information; outputs the image data corresponding to the target exposure mode as the target image data, and obtains high-quality images with good display effects for the target object under multiple exposure modes. In this way, the target image data suitable for displaying the target object can be selected from the image data corresponding to the multiple exposure modes, which can meet various exposure requirements in the same image acquisition scene and improve the image quality.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0020] Figure 1 is a flowchart of an exemplary embodiment of a method for improving image quality of the present application;

[0021] Figure 2 is an exemplary image processing flow chart of the method for improving image quality of the present application;

[0022] Figure 3 is a schematic diagram of an exemplary image data structure in the method for improving image quality of the present application;

[0023] Figure 4 is a block diagram of a device for improving image quality shown in an exemplary embodiment of the present application;

[0024] Figure 5 It is a structural schematic diagram of an embodiment of the electronic device of the present application;

[0025] Figure 6 It is a structural diagram of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0026] The scheme of the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.

[0027] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0028] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the objects associated before and after are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of, for example, including at least one of A, B, and C, can mean including any one or more elements selected from the set consisting of A, B, and C.

[0029] See also Figure 1 , Figure 1 : is a flowchart of an exemplary embodiment of the method for improving image quality of the present application. Specifically, it may include the following steps:

[0030] Step S110, based on at least two preset exposure modes, image data corresponding to each exposure mode in the same image acquisition scene are respectively acquired.

[0031] The at least two preset exposure modes may include at least a long exposure mode and a short exposure mode, wherein the exposure frame length of the long exposure mode is greater than the exposure frame length of the short exposure mode, and the specific exposure value is not limited here. In addition, the exposure mode may also include a medium exposure mode, wherein the exposure frame length of the medium exposure mode is less than the exposure frame length of the long exposure mode, and greater than the exposure frame length of the short exposure mode. In addition, more other exposure modes may be obtained according to the adjustment and setting of the exposure frame length, which are not limited here.

[0032] For easier understanding, please refer to Figure 2 , Figure 2 This is an exemplary image processing flow chart in the method for improving image quality of the present application. Among them, the sensor of the image acquisition device can perform image acquisition on the current image acquisition scene according to the preset N exposure modes (N≥2, and N is a positive integer), and respectively output F1-FN, a total of N frames of image data (or exposure data), and the image acquisition device is not configured for wide dynamic fusion, so that the image data corresponding to each exposure mode can be obtained through a separate acquisition configuration, a total of N channels of image data. Subsequent to this step, image signal processing (Image Signal Processing, ISP) is performed based on each channel of image data, and then encoding and decoding processing, image algorithm processing, image selection processing, etc. are performed to obtain the required image data. The specific steps are not repeated here.

[0033] Step S120: performing target detection processing on the image data corresponding to at least one exposure mode to obtain object information of the target object in the image data.

[0034] There may be one or more objects to be detected in the image data, and some or all of these objects to be detected may be target objects that need to be focused on. Therefore, the target objects obtained after target detection processing on the image data can be one or more (each can be one or more).

[0035] The object information of the target object refers to the relevant information that can be obtained through target detection processing of image data, such as the movement speed of the target object, the object type of the target object, etc. The specific detection method can refer to the existing detection technology (such as image processing, deep learning, etc.), which will not be elaborated here.

[0036] It should be noted that since the time difference between multiple exposures of the sensor is small and the corresponding timestamp is added through interruption during the acquisition process of each frame of the image, it is usually possible to find image data corresponding to the timestamp in different exposure modes, which is equivalent to image data of different exposures acquired simultaneously for the same image acquisition scene.

[0037] Therefore, in order to improve the target detection efficiency in this application, the image data corresponding to one of the multiple exposure modes can be selected for target detection processing to obtain its target detection result. The target detection result is then used to find the image data corresponding to the same timestamp in other exposure modes through the timestamp of the image data, and the target detection result is reused in the image data corresponding to the other exposure modes, instead of performing one or more target detection processing on the image data corresponding to each exposure mode, which greatly improves the target detection efficiency and saves the computing power consumption of target detection.

[0038] However, it is understandable that, in this embodiment, selecting image data corresponding to one of the multiple exposure modes for target detection processing is one possible implementation, and selecting image data corresponding to multiple exposure modes such as two or three of the multiple exposure modes for target detection processing is another possible implementation, and this application does not limit this. The more types of target detection processing are, the more accurate the target detection result is. Therefore, the image data corresponding to the exposure mode that needs to be processed for target detection can also be selected according to the exposure requirements in the actual application scenario.

[0039] Exemplarily, when selecting image data for target detection processing, it can be randomly selected, or it can be specifically selected according to a preset selection rule (including selecting the longest exposure frame length, and / or selecting the shortest exposure frame length, and / or selecting the one corresponding to the current exposure requirement, etc., which are not limited here). For example, if it is necessary to specifically select image data corresponding to an exposure mode, the average value can be calculated according to the exposure frame lengths of the currently preset multiple exposure modes to obtain the average exposure frame length, and the image data corresponding to the average exposure frame length can be selected for target detection processing (corresponding to the average exposure frame length can mean being equal to the average exposure frame length, or having the smallest difference with the average exposure frame length). Similarly, it is also possible to perform a median calculation on the exposure frame lengths of each exposure mode to obtain the median exposure frame length, and select the image data corresponding to the median exposure frame length for target detection processing, etc. In this way, image data with relatively even exposure can be obtained, which can take into account both the bright and dark areas in the image.

[0040] In addition, if it is necessary to pay attention to target objects in brighter and darker areas at the same time, the image data with the longest exposure frame length and the image data with the shortest exposure frame length can be selected from each exposure mode for target detection processing respectively, to obtain two target detection results. The two target detection results can then be combined for analysis and processing.

[0041] Step S130 : determining a target exposure mode from various exposure modes based on the object information and the exposure requirement corresponding to the object information.

[0042] Since there may be multiple objects to be detected in the image, and the moving speeds and brightness of different objects to be detected may be different, for the target objects that need to be focused on among the objects to be detected, a suitable exposure mode is required to show a good display effect. For example, for a target object moving at high speed, in the image captured using a longer exposure frame length, there may be obvious ghosting and other phenomena that affect the image quality, so its exposure requirement is to use a shorter exposure frame length; while for a target object moving at low speed, it is usually not easy to have a ghosting phenomenon, but in the image captured using a shorter exposure frame length, its displayed brightness is lower, so its exposure requirement is to use a longer exposure frame length. Therefore, for different target objects, corresponding exposure requirements can be set based on the object information, and the exposure requirements can be preset or acquired in real time, which is not limited here.

[0043] Step S140: outputting the image data corresponding to the target exposure mode as target image data to obtain a high-quality image.

[0044] In conjunction with the above steps, the target exposure mode is an exposure mode that is determined to be more suitable for displaying the target object after detection and analysis of each exposure mode, which is equivalent to the image data corresponding to the target exposure mode being image data that can have a good display effect for the target object. Therefore, the image data corresponding to the target exposure mode is output as the target image data, and an image that meets the requirements and has a high quality can be screened out from the image data of each exposure mode.

[0045] It should be noted that, in addition to outputting the image data corresponding to the target exposure mode as target image data to obtain a high-quality image, this step can also output the image data corresponding to the target exposure mode as target image data to obtain a high-quality video, etc., which is not limited here.

[0046] It can be seen that the present application obtains the image data corresponding to each exposure mode in the same image acquisition scene through at least two preset exposure modes, thereby obtaining multiple image data corresponding to multiple exposure data; performing target detection processing on the image data corresponding to at least one of the exposure modes to obtain the object information of the target object in the image data; determining the target exposure mode suitable for displaying the target object from each exposure mode by analyzing the object information of the target object (such as object type and / or moving speed, etc.) and the exposure requirements corresponding to the object information; outputting the image data corresponding to the target exposure mode as the target image data, and obtaining high-quality images with good display effects on the target object under multiple exposure modes. In this way, the target image data suitable for displaying the target object can be selected from the image data corresponding to the multiple exposure modes, which can meet various exposure requirements in the same image acquisition scene and improve the image quality.

[0047] Based on the above embodiments, the embodiment of the present application describes the steps of determining a target exposure mode from various exposure modes based on object information and exposure requirements corresponding to the object information. The object information includes a moving speed, and the exposure mode includes a long exposure mode and a short exposure mode. Specifically, the method of this embodiment includes the following steps:

[0048] Based on the moving speed of each target object, each target object is divided into a high-speed moving object and a low-speed moving object; if the exposure requirement is to obtain image data of a high-speed moving object, the short exposure mode is determined as the target exposure mode; if the exposure requirement is to obtain image data of a low-speed moving object, the long exposure mode is determined as the target exposure mode.

[0049] With reference to the above-mentioned embodiments, in the present application, the method of determining the target exposure mode from various exposure modes may be to select according to the moving speed of the target object.

[0050] Exemplarily, two preset exposure modes are used as an example for explanation, which may include a long exposure mode and a short exposure mode, wherein the exposure frame length of the long exposure mode is longer, and is mainly used in scenes where the target object moves at a lower speed; the exposure frame length of the short exposure mode is shorter, and is mainly used in scenes where the target object moves at a higher speed. Based on the moving speed of the target object and a preset speed threshold, the target object can be distinguished as a high-speed moving object and / or a low-speed moving object, wherein there may be one or more speed thresholds. Specifically, it may be to judge a target object as a high-speed moving object or a low-speed moving object, or it may be to classify multiple target objects as high-speed moving objects and / or low-speed moving objects respectively. For the method of obtaining the moving speed of the target object, reference may be made to existing related methods, such as an optical flow method based on feature matching, a pixel displacement method through pixel analysis, or a method for collecting speed based on timestamp correspondence in combination with external devices such as a speedometer in the current scene, which is not limited here.

[0051] It is understandable that if the target object that needs to be focused on is a high-speed moving object, the exposure requirement corresponding to the object information of the target object should be short exposure. Therefore, if it is necessary to obtain image data of a high-speed moving object, the short exposure mode is determined as the target exposure mode. Subsequently, the image data corresponding to the short exposure mode can be output as target image data, and the target object in the image obtained in the short exposure mode will usually not have problems such as smear and afterimage. Similarly, if the target object that needs to be focused on is a low-speed moving object, the exposure requirement corresponding to the object information of the target object should be long exposure. Therefore, if it is necessary to obtain image data of a low-speed moving object, the long exposure mode is determined as the target exposure mode. Subsequently, the image data corresponding to the long exposure mode can be output as target image data, and the target object in the image obtained in the long exposure mode will be displayed with sufficient brightness.

[0052] In another exemplary embodiment, a plurality of exposure modes are preset as an example for explanation. When collecting images in a common urban road scene, a series of objects to be detected, such as animals (including but not limited to humans), non-motor vehicles, and motor vehicles, may appear in the image. By analyzing the distribution of the moving speeds of various objects in actual application scenarios, it can be seen that the animal speed is mainly in [0,6] km / h, corresponding to the long exposure mode, the non-motor vehicle speed is mainly in (6,42] km / h, corresponding to the medium exposure mode, and the motor vehicle speed is mainly in (42,60] km / h, corresponding to the short exposure mode. Therefore, multiple speed threshold intervals in units of km / h can be preset. Furthermore, the speed threshold intervals can be divided more finely to improve accuracy. For example, if the speed of the target object is [0,6], it corresponds to the long frame exposure mode, (6,15] corresponds to the medium frame longer exposure mode, (15,24] corresponds to the medium frame moderate exposure mode, (24,33] corresponds to the medium frame shorter exposure mode, (33,42] corresponds to the short frame longer exposure mode, (42,51] corresponds to the short frame moderate exposure mode, and (51,60] corresponds to the short frame short exposure mode.

[0053] Based on the above embodiment, the embodiment of the present application describes another possible implementation method of the step of determining the target exposure mode from various exposure modes based on the object information and the exposure requirements corresponding to the object information. The object information includes the object type, and each object type is preset with a corresponding exposure mode. Specifically, the method of this embodiment includes the following steps:

[0054] A target object type to be detected is determined from each object type based on the exposure requirement; and an exposure mode corresponding to the target object type is determined as the target exposure mode.

[0055] In combination with the above-mentioned embodiment, the above-mentioned embodiment provides an implementation method for determining the target exposure mode from various exposure modes according to the speed of the target object, while this embodiment provides an implementation method for determining the target exposure mode from various exposure modes according to the type of the target object.

[0056] Similarly, taking the application scenario of the aforementioned embodiment as an example, when performing image acquisition in an urban road scene, various objects to be detected, such as animals, non-motor vehicles, and motor vehicles, may appear in the image, and the speeds of different types of objects to be detected are usually different, which leads to different exposure modes required for each type of object. Therefore, the corresponding exposure mode can be set in advance based on the object type of each object to be detected, and the corresponding exposure mode can be used as the target exposure mode after the exposure requirement is determined (for example, the object type of the target object to be detected is determined).

[0057] For example, it is possible to pre-set that the animal type corresponds to the long exposure mode, the non-motor vehicle type corresponds to the medium exposure mode, and the motor vehicle type corresponds to the short exposure mode. If the current exposure requirement characterization requires focusing on the animals in the image data, the target object type is the animal type, and the long exposure mode is selected as the target exposure mode; if the current exposure requirement characterization requires focusing on the non-motor vehicle in the image data, the target object type is the non-motor vehicle type, and the medium exposure mode is selected as the target exposure mode; if the current exposure requirement characterization requires focusing on the motor vehicle in the image data, the target object type is the motor vehicle type, and the short exposure mode is selected as the target exposure mode.

[0058] It should be noted that the exposure requirements in the present application can be preset or acquired in real time. For example, after the image data is subjected to target detection processing, the object information of the target object in the image data can be obtained, and the image data, the target object, and the object information can be previewed and displayed through a set display device. After reading the displayed content, the user can issue an exposure requirement instruction through a display device or other terminal device; the system of the method for running the image quality improvement method of the present application can parse the instruction after receiving the exposure requirement instruction, and generate a corresponding exposure requirement, thereby determining the user's exposure requirement, and selecting the image collected by the exposure mode corresponding to the exposure requirement for output display. Exemplarily, if the user issues an exposure requirement instruction representing the type of animal that needs to be detected, after the instruction is parsed, it can be known that the target object type is an animal type, then the image data corresponding to the long exposure mode corresponding to the animal type is selected for output.

[0059] Based on the above embodiments, the present embodiment of the application describes the steps of outputting the image data corresponding to the target exposure mode as the target image data to obtain a high-quality image. Specifically, the method of this embodiment includes the following steps:

[0060] The brightness value of the target image data is obtained; if the brightness value is less than the left boundary of the preset brightness range, the exposure frame length of the target exposure mode is extended to obtain an adjusted target exposure mode; if the brightness value is greater than the right boundary of the preset brightness range, the exposure frame length of the target exposure mode is shortened to obtain an adjusted target exposure mode; an image is output based on the adjusted target exposure mode to obtain a high-quality image.

[0061] In conjunction with the above-mentioned embodiment, the above-mentioned embodiment provides a method for outputting image data corresponding to a suitable exposure mode according to the object information of the target object. However, it should be noted that the image data corresponding to the exposure mode selected based on the object information such as speed or type may still not be able to provide a good display effect in some special scenes. For example, in some scenes, the ambient light is very sufficient so that the long exposure mode will be overexposed; or in some scenes, the ambient light is very insufficient so that the short exposure mode will be underexposed; or some target objects have a high degree of reflectivity so that the brightness displayed in the image is too high. Therefore, in this embodiment, after determining the target image data corresponding to the target exposure mode, the brightness of the target object in the target image data can also be analyzed based on the brightness value of the target image data, and then it can be determined whether the brightness of the target image data needs to be further adjusted.

[0062] Specifically, the brightness value of the target image data is obtained and compared with the preset brightness threshold interval, for example, the Y value (brightness) of the image is obtained according to the YUV channel of the image as the brightness value. Among them, one or more brightness threshold intervals can be provided. In this embodiment, one brightness threshold interval is first used as an example for explanation. For example, if the brightness value of the target image data is within the brightness threshold interval, it can be considered that the target image data is of normal brightness and does not need to be adjusted; if the brightness value of the target image data is less than the left boundary of the brightness threshold interval, it can be considered that the brightness of the target image data is low, and its brightness needs to be enhanced; if the brightness value of the target image data is greater than the right boundary of the brightness threshold interval, it can be considered that the brightness of the target image data is high, and its brightness needs to be reduced.

[0063] Exemplarily, the method of adjusting the brightness may include, but is not limited to, adjusting the corresponding exposure data (e.g., extending or shortening the exposure frame length corresponding to the target image data; or adjusting the exposure value of the target image data), etc., to affect the brightness of the data output by the sensor. In addition, in the process of outputting the image based on the adjusted target exposure mode, it is possible to immediately adjust the currently acquired target image data in real time before outputting it, or, when it is determined that the current target image data is not within the brightness threshold range, adjust the subsequently acquired target image data before outputting it. The specific method can be selected and set according to the actual application scenario, and is not limited here.

[0064] In another exemplary embodiment, in the present embodiment, multiple brightness threshold intervals may be set to determine whether the brightness of the target object in the target image data meets the standard, and then the corresponding brightness adjustment is performed. The specific brightness adjustment method can refer to the description of the above example, which will not be described here. There is a certain difference from the above example in that setting multiple brightness threshold intervals for brightness judgment and adjustment can make a more detailed division of the interval values, so that the brightness adjustment step size can also be adjusted accordingly, that is, the brightness adjustment effect can be smoother.

[0065] Based on the above embodiments, the embodiment of the present application describes the steps of determining a target exposure mode from various exposure modes based on object information and exposure requirements corresponding to the object information. Specifically, the method of this embodiment includes the following steps:

[0066] A first candidate exposure mode is determined from multiple exposure modes based on object information and exposure requirements corresponding to the object information, and first image data corresponding to the first candidate exposure mode is obtained; a second candidate exposure mode is determined from multiple exposure modes based on image quality of image data corresponding to each exposure mode, and second image data corresponding to the second candidate exposure mode is obtained; a target exposure mode is determined from the first candidate exposure mode and the second candidate exposure mode based on an image quality difference between the first image data and the second image data.

[0067] In conjunction with the above-mentioned embodiment, the above-mentioned embodiment mainly selects the target image data corresponding to the corresponding target exposure mode through the object information of the target object. Taking the object category of the target object as an example, in a simple application scenario, if the target objects of the same category move in the same or similar state (moving speed, moving direction, etc.), this type of implementation has a good effect. However, in a more complex application scenario (for example, the target objects of the same category move in different states), the effect of the method of selecting the target exposure mode based on the object category will be affected to a certain extent.

[0068] Still taking the urban road scene as an example, an example is given. There may be a target object A walking normally, a target object B driving a non-motor vehicle, and a target object C driving a motor vehicle on the urban road. It can be understood that the target objects A, B, and C are the same type of target objects, but the moving speeds of A, B, and C are all different. Therefore, if it is necessary to focus on this type of target object in the image data, and display the image data obtained by the exposure mode (long exposure mode) corresponding to the object category, the target object C driving the motor vehicle may have a smear problem in the image because the moving speed is faster than that of the target object A walking normally. Therefore, in this embodiment, a hybrid optimization method can also be set to select image data with better overall quality as target image data.

[0069] Specifically, the exposure mode determined according to the object information in the aforementioned embodiment is used as the first candidate exposure mode, and the first image data corresponding to the first candidate exposure mode is obtained. In addition, the image qualities of the image data corresponding to each exposure mode are compared to obtain a comparison result, and the second candidate exposure mode is determined from each exposure mode according to the comparison result, and the second image data corresponding to the second candidate exposure mode is obtained. In this way, the first image data obtained by intelligent optimization based on the object information and the second image data obtained by comparison based on the image quality can be obtained respectively. Among them, the first image data and the second image data obtained by the two methods can be the same image data corresponding to the same exposure mode, or can be different image data corresponding to different exposure modes, which is not limited here.

[0070] Furthermore, a difference calculation is performed based on the image quality of the first image data and the image quality of the second image data to obtain the image quality difference between the first image data and the second image data. The image quality can be obtained by performing quality scoring processing based on various data indicator values ​​of the image data (which may include but is not limited to the resolution size, image noise, clarity, angle, etc. of the image data) and according to preset quality scoring rules. The specific quality scoring rules can be specifically set according to the actual application scenario and will not be described in detail here. In the quality scoring process, the scoring processing can be based on the overall image data of each frame, or based on the image area where the target object is located in each frame of image data. According to the image quality difference between the two image data, the target image data that is more suitable for display and the corresponding target exposure mode can be selected from the two image data.

[0071] Exemplarily, if the image quality difference is less than a certain threshold, the first candidate exposure mode corresponding to the first image data may still be used as the target exposure mode; if the image quality difference is greater than a certain threshold and the image quality of the second image data is better than that of the first image data, the second candidate exposure mode corresponding to the second image data may be used as the target exposure mode.

[0072] As can be seen from the above, this embodiment selects the corresponding exposure mode and obtains the image data corresponding to the two exposure modes through two standards respectively, and determines which image data has higher image quality and better display effect by comparing the image quality of the two image data, and then determines the target image data and its corresponding target exposure mode. Compared with the simple application scenario of using object information to select the corresponding exposure mode, this embodiment further improves the rigor and image display effect of the method of this application, and can obtain image data with higher overall quality, without interfering with the exposure mode screening process and the image screening process due to the presence of target objects of the same type but different states in the same image data.

[0073] Based on the above embodiments, the embodiment of the present application describes the steps of determining a second candidate exposure mode from multiple exposure modes based on the image quality of the image data corresponding to each exposure mode, and obtaining the second image data corresponding to the second candidate exposure mode. The image quality includes a quality score. Specifically, the method of this embodiment includes the following steps:

[0074] Quality scoring is performed based on the image data corresponding to each exposure mode to obtain the quality score corresponding to the image data of each exposure mode; each exposure mode is compared based on the quality score, and the exposure mode with the highest quality score is selected from each exposure mode as the second candidate exposure mode.

[0075] In conjunction with the above-mentioned embodiment, in the process of determining the second candidate exposure mode from each exposure mode, the image data corresponding to each exposure mode can be firstly subjected to quality scoring processing. On the one hand, a quality score can be assigned to each image data according to a data indicator of each image data (such as resolution or clarity or noise, etc.) (resolution and clarity are positively correlated with the quality score; noise and quality score are negatively correlated), that is, the higher the resolution or clarity, the higher the quality score of the image data, and the higher the noise value, the lower the quality score of the image data. On the other hand, the image data can be scored in combination with multiple data indicators. For example, each data indicator of the image data can be regarded as an influencing factor in the process of calculating the image quality score, and each data indicator has a corresponding preset weight value. By performing a weighted sum operation on the scores corresponding to various influencing factors of the same image data, the quality score of the image data can be obtained. Among them, the specific quality scoring formula can be obtained by referring to the existing image quality scoring method and combining it with the actual application scenario of the present application, and will not be repeated here.

[0076] Furthermore, based on the quality scores of the image data, the image data with the highest quality score is selected as the second image data and the exposure mode corresponding to the image data is selected as the second candidate exposure mode, that is, the optimal image data and the optimal exposure mode selected based on the image quality score are obtained. It should be noted that the process of quality scoring the first image data can also refer to the above-mentioned scoring process, so that the quality score of the first image data and the quality score of the second image data can be compared later, which will not be described in detail here.

[0077] Based on the above embodiment, the embodiment of the present application describes the steps of determining the target exposure mode from the first candidate exposure mode and the second candidate exposure mode based on the image quality difference between the first image data and the second image data. The image quality includes a quality score. Specifically, the method of this embodiment includes the following steps:

[0078] If the quality score difference between the first image data and the second image data is within a preset difference threshold interval, the first quality score of the first image data and the second quality score of the second image data are adjusted respectively based on a preset score adjustment strategy to obtain an adjusted first quality score and an adjusted second quality score; based on a comparison result between the adjusted first quality score and the adjusted second quality score, a target exposure mode is determined from the first candidate exposure mode and the second candidate exposure mode; if the quality score difference between the first image data and the second image data is greater than the right boundary of the difference threshold interval, and the second quality score is greater than the first quality score, the second candidate exposure mode is determined as the target exposure mode.

[0079] The image quality scoring process of the present application is specifically described in conjunction with the aforementioned embodiments. Among them, the preset difference threshold interval is used to characterize that there is a certain gap between the image qualities of the two image data, but the gap is not large. Therefore, for the first image data and the second image data whose quality score difference is within the difference threshold interval (for example, [5,16]), it is necessary to readjust the quality scores of the two according to the preset score adjustment strategy, respectively obtain the adjusted quality scores of the two, and then calculate the quality score difference between the two image data based on the adjusted quality scores of the two, and make subsequent judgments.

[0080] If the quality score difference between the first image data and the second image data is greater than the right boundary of the difference threshold interval (i.e., greater than 16), it indicates that there is an obvious difference between the image qualities of the two image data. If the second quality score is greater than the first quality score, it means that the image quality of the second image data is significantly better than that of the first image data, so the second candidate exposure mode is determined as the target exposure mode, and the second image data is determined as the target image data. On the contrary, if the second quality score is less than the first quality score, it means that the image quality of the first image data is significantly better than that of the second image data, so the first candidate exposure mode is determined as the target exposure mode, and the first image data is determined as the target image data.

[0081] If the quality score difference between the first image data and the second image data is less than the left boundary of the difference threshold interval (i.e., less than 5), it indicates that there is no obvious difference between the image qualities of the two image data. Therefore, the first image data can still be selected as the target image data, and the first candidate exposure mode can be selected as the target exposure mode.

[0082] It should also be noted that the above examples are mainly used to illustrate the application scenario of setting a difference threshold interval, and multiple difference threshold intervals can also be set in the specific implementation process of the present application. In the implementation scenario of multiple difference threshold intervals, the method for selecting the right boundary and the left boundary of the difference threshold interval for comparison is different from the implementation scenario of one difference threshold interval. Exemplarily, the difference threshold interval [5,16] is further subdivided to obtain multiple difference threshold intervals such as [5,10] and (10,16]. Then, the value (5) with the smallest left boundary value in each interval and the value (16) with the largest right boundary value in each interval are selected to judge whether the quality difference between the two image data is obvious. If the quality score difference between the two image data is in [5,10] or (10,16], the first quality score of the first image data and the second quality score of the second image data can be adjusted based on the preset score adjustment strategy; but the score adjustment strategy corresponding to [5,10] and the score adjustment strategy corresponding to (10,16] can be different.

[0083] Exemplarily, if the quality score difference is in [5,10], the corresponding score adjustment strategy is speed impact factor * 0.5 + image quality score * 0.5, that is, the speed of the target object is used as one of the factors affecting image quality. For example, for the first image data, the moving speeds of the target objects A, B, and C in the first image data are multiplied by 0.5 and then summed to obtain the first speed score; the first quality score * 0.5 of the first image data is summed with the first speed score to obtain the first quality score after adjustment of the first image data. Similarly, the moving speeds of the target objects A, B, and C in the second image data are multiplied by 0.5 and then summed to obtain the second speed score; the second quality score * 0.5 of the second image data is summed with the second speed score to obtain the second quality score after adjustment of the second image data. Then, the first quality score and the second quality score are compared and the image data with the larger quality score is selected as the target image data. Therefore, the quality problem that is easy to occur when capturing images of target objects of the same type and different states can be solved by a mixed optimization method. In addition to using the moving speed of the target object as one of the influencing factors, other data may also be used for reference, which is not limited here.

[0084] In another exemplary embodiment, if the quality score difference is in (10, 16], since the quality score difference is larger than the previous interval, the weight ratio of the speed impact factor should be reduced and the weight ratio of the image quality score should be increased. The corresponding score adjustment strategy may be speed impact factor * 0.4 + image quality score * 0.6. If the quality score difference obtained by subtracting the first quality score from the second quality score is greater than 16, the second candidate exposure mode corresponding to the second image data is selected as the target exposure mode; if the quality score difference obtained by subtracting the second quality score from the first quality score is greater than 16, the first candidate exposure mode corresponding to the first image data is selected as the target exposure mode; if the quality score difference obtained by subtracting the first quality score from the second quality score (or the first quality score from the second quality score) is less than 5, the first candidate exposure mode corresponding to the first image data is selected as the target exposure mode.

[0085] On the basis of the above-mentioned embodiment, the embodiment of the present application describes the steps of adjusting the first quality score of the first image data and the second quality score of the second image data respectively based on the preset score adjustment strategy to obtain the adjusted first quality score and the adjusted second quality score. The object information includes the moving speed. Specifically, the method of this embodiment includes the following steps:

[0086] The moving speed of the target object in the first image data and the first quality score are weighted and summed to obtain an adjusted first quality score; the moving speed of the target object in the second image data and the second quality score are weighted and summed to obtain an adjusted second quality score.

[0087] Based on the above embodiments, the present application embodiment describes the steps of selecting at least one exposure mode to perform target detection processing on the image data to obtain the object information of the target object in the image data. Specifically, in this embodiment, the image acquisition frame rate of the sensor can be set to M frames / second, which can be referred to Figure 2 As shown, Figure 2 Each exposure mode can output M frames of data (e.g., F1-1 to F1-M) per second. However, when selecting image data for target detection processing, selection can be made based on the currently preset exposure requirement or the received exposure requirement instruction (including image preview requirement or target detection requirement, etc.), for example, a total of M frames of data from F1-1 to F1-M of one of the selected exposure modes are transmitted to the encoded output bitstream, thereby obtaining a more accurate detection effect than randomly selecting image data for target detection.

[0088] For example, if the image needs to be clear and bright, long frame data (image data corresponding to the long exposure mode) can be selected to send the encoded output stream to ensure that it is clear and bright enough for target detection in the currently displayed image. If the license plate of the motor vehicle in the image needs to be clear and not overexposed, short frame data (image data corresponding to the short exposure mode) can be selected to send the encoded output stream to ensure that the license plate of the motor vehicle in the image can be clearly identified and not overexposed.

[0089] In summary, according to specific needs, the image data corresponding to one exposure mode in each exposure mode is selected and sent to the algorithm module for target detection to obtain the target detection result. Because the time difference between the sensor's multi-channel exposures is small and each frame acquisition is interrupted and marked with a corresponding timestamp, the target detection result can be reused for the sensor's other N-1 exposure data, thereby saving the computing power consumption of the target detection process.

[0090] In addition, combined Figure 2 To continue the explanation, the image acquisition process of the present application can be implemented based on multi-frame time-sharing exposure technology. During the image exposure process, for the target object in the current acquisition scene that has different exposure requirements, each of F1-FN can be controlled to acquire at a frame rate of M frames / second based on the exposure requirements, and time-sharing exposure (time-sharing stroboscopic exposure) is performed according to the preset P frames as a group to obtain M / P group exposure data, thereby obtaining images with a variety of light source effects, improving image compatibility and obtaining excellent imaging effects. The specific time-sharing exposure process can refer to the existing time-sharing exposure technology, which will not be described here. Then, the M / P group exposure data is output through ISP image processing and transmitted to the algorithm module for intelligent optimization and attribute analysis, thereby determining the target exposure mode, and outputting the target image data corresponding to the target exposure mode.

[0091] For example, the matching process for P frame data may include but is not limited to: the matching of each group of P frame data may be implemented through the Embedded Data register of the sensor. Figure 3 As shown, Figure 3 This is an exemplary image data structure diagram in the method for improving image quality of the present application. By configuring the sensor exposure and Embedded Data registers to take effect at the same time, the sensor will output the valid image data Active Data together with the Embedded Data. The exposure value, serial number and other data of the frame image data can be determined by subsequently parsing the Embedded Data. In this way, continuous P frame data of the same exposure value can be uniformly divided into a group of exposure data. Subsequently, analysis can be performed based on each group of image data to select the appropriate exposure mode and image data.

[0092] It should be further explained that the execution subject of the method for improving image quality may be a device for improving image quality, for example, the method for improving image quality may be executed by a terminal device or a server or other processing device, wherein the terminal device may be a user equipment (UE), a computer, a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the method for improving image quality may be implemented by a processor calling a computer-readable instruction stored in a memory.

[0093] Figure 4 FIG. 1 is a block diagram of an apparatus for improving image quality according to an exemplary embodiment of the present application. Figure 4 As shown, the exemplary apparatus 400 for improving image quality includes: an acquisition module 410, a detection module 420, an exposure determination module 430 and an output module 440. Specifically:

[0094] The acquisition module 410 is used to acquire image data corresponding to each exposure mode in the same image acquisition scene based on at least two preset exposure modes.

[0095] The detection module 420 is used to perform target detection processing on the image data corresponding to at least one exposure mode to obtain object information of the target object in the image data.

[0096] The exposure determination module 430 is used to determine a target exposure mode from various exposure modes based on the object information and the exposure requirement corresponding to the object information.

[0097] The output module 440 is used to output the image data corresponding to the target exposure mode as target image data to obtain a high-quality image.

[0098] In this exemplary device for improving image quality, image data corresponding to each exposure mode in the same image acquisition scene is obtained by using at least two preset exposure modes, thereby obtaining multiple image data corresponding to multiple exposure data; performing target detection processing on the image data corresponding to at least one of the exposure modes to obtain object information of the target object in the image data; determining a target exposure mode suitable for displaying the target object from each exposure mode by analyzing the object information of the target object (such as object type and / or moving speed, etc.) and the exposure requirements corresponding to the object information; outputting the image data corresponding to the target exposure mode as target image data, thereby obtaining high-quality images with good display effects on the target object under multiple exposure modes. In this way, target image data suitable for displaying the target object can be selected from the image data corresponding to the multiple exposure modes, which can meet various exposure requirements in the same image acquisition scene and improve image quality.

[0099] It should be noted that the device provided in the above embodiment and the method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment, and will not be repeated here. In practical applications, the device provided in the above embodiment can distribute the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0100] The functions of each module can be found in the method embodiment for improving image quality, which will not be described in detail here.

[0101] See also Figure 5 , Figure 5 1 is a schematic diagram of the structure of an embodiment of an electronic device of the present application. The electronic device 500 includes a memory 501 and a processor 502, and the processor 502 is used to execute program instructions stored in the memory 501 to implement the steps in any of the above-mentioned methods for improving image quality. In a specific implementation scenario, the electronic device 500 may include but is not limited to: a microcomputer, a server, and in addition, the electronic device 500 may also include a mobile device such as a laptop computer and a tablet computer, which is not limited here.

[0102] Specifically, the processor 502 is used to control itself and the memory 501 to implement the steps in any of the above-mentioned methods for improving image quality. The processor 502 can also be called a CPU (Central Processing Unit). The processor 502 may be an integrated circuit chip with signal processing capabilities. The processor 502 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 502 can be implemented by an integrated circuit chip.

[0103] In this exemplary electronic device, image data corresponding to each exposure mode in the same image acquisition scene is obtained respectively through at least two preset exposure modes, thereby obtaining multiple image data corresponding to multiple exposure data respectively; target detection processing is performed on the image data corresponding to at least one of the exposure modes to obtain object information of the target object in the image data; by analyzing the object information of the target object (such as object type and / or moving speed, etc.) and the exposure requirements corresponding to the object information, a target exposure mode suitable for displaying the target object is determined from each exposure mode; the image data corresponding to the target exposure mode is output as target image data, and high-quality images with good display effects on the target object under multiple exposure modes can be obtained. In this way, target image data suitable for displaying the target object can be selected from the image data corresponding to the multiple exposure modes, which can meet various exposure requirements in the same image acquisition scene and improve image quality.

[0104] See also Figure 6 , Figure 6 The computer-readable storage medium 610 stores program instructions 611 that can be executed by a processor, and the program instructions 611 are used to implement the steps in any of the above-mentioned methods for improving image quality.

[0105] In this exemplary storage medium, by running the program instructions in the storage medium, image data corresponding to each exposure mode in the same image acquisition scene is obtained based on at least two preset exposure modes, thereby obtaining multiple image data corresponding to multiple exposure data; performing target detection processing on the image data corresponding to at least one exposure mode to obtain object information of the target object in the image data; determining a target exposure mode suitable for displaying the target object from each exposure mode by analyzing the object information of the target object (such as object type and / or moving speed, etc.) and the exposure requirements corresponding to the object information; outputting the image data corresponding to the target exposure mode as target image data, and obtaining high-quality images with good display effects on the target object under multiple exposure modes. In this way, target image data suitable for displaying the target object can be selected from the image data corresponding to the multiple exposure modes, which can meet various exposure requirements in the same image acquisition scene and improve image quality.

[0106] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0107] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0108] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0109] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially 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, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

Claims

1. A method for improving image quality, characterized in that: The method comprises: Based on at least two preset exposure modes, respectively acquiring image data corresponding to each exposure mode in the same image acquisition scene; Performing target detection processing on image data corresponding to at least one exposure mode to obtain object information of a target object in the image data; determining a target exposure mode from among the exposure modes based on the object information and an exposure requirement corresponding to the object information; The image data corresponding to the target exposure mode is output as target image data to obtain a high-quality image.

2. The method according to claim 1, characterized in that The object information includes a moving speed, the exposure mode includes a long exposure mode and a short exposure mode, and determining a target exposure mode from each exposure mode based on the object information and an exposure requirement corresponding to the object information includes: Differentiate each target object into a high-speed moving object and a low-speed moving object based on the moving speed of each target object; If the exposure requirement is to obtain image data of the high-speed moving object, determining the short exposure mode as the target exposure mode; If the exposure requirement is to obtain image data of the slow-moving object, the long exposure mode is determined as the target exposure mode.

3. The method according to claim 1, characterized in that The object information includes an object type, each object type is preset with a corresponding exposure mode, and determining a target exposure mode from each exposure mode based on the object information and an exposure requirement corresponding to the object information includes: Determining a target object type to be detected from each object type based on the exposure requirement; An exposure mode corresponding to the target object type is determined as the target exposure mode.

4. The method according to claim 1, characterized in that: The step of outputting the image data corresponding to the target exposure mode as target image data to obtain a high-quality image includes: Acquire the brightness value of the target image data; If the brightness value is less than the left boundary of the preset brightness range, the exposure frame length of the target exposure mode is extended to obtain an adjusted target exposure mode; If the brightness value is greater than the right boundary of the preset brightness range, shortening the exposure frame length of the target exposure mode to obtain an adjusted target exposure mode; The image is output based on the adjusted target exposure mode to obtain the high-quality image.

5. The method according to claim 1, characterized in that The determining a target exposure mode from various exposure modes based on the object information and the exposure requirement corresponding to the object information includes: determining a first candidate exposure mode from a plurality of exposure modes based on the object information and an exposure requirement corresponding to the object information, and acquiring first image data corresponding to the first candidate exposure mode; determining a second candidate exposure mode from a plurality of exposure modes based on image quality of image data corresponding to each exposure mode, and acquiring second image data corresponding to the second candidate exposure mode; The target exposure mode is determined from among the first candidate exposure mode and the second candidate exposure mode based on an image quality difference between the first image data and the second image data.

6. The method according to claim 5, characterized in that The image quality includes a quality score, and determining a second candidate exposure mode from a plurality of exposure modes based on the image quality of the image data corresponding to each exposure mode, and acquiring second image data corresponding to the second candidate exposure mode, include: Performing quality scoring processing based on the image data corresponding to each exposure mode to obtain a quality score corresponding to the image data of each exposure mode; The exposure modes are compared based on the quality scores, and the exposure mode with the highest quality score is selected from the exposure modes as the second candidate exposure mode.

7. The method according to claim 5, characterized in that The image quality includes a quality score, and determining the target exposure mode from the first candidate exposure mode and the second candidate exposure mode based on an image quality difference between the first image data and the second image data includes: If the quality score difference between the first image data and the second image data is within a preset difference threshold range, adjusting the first quality score of the first image data and the second quality score of the second image data respectively based on a preset score adjustment strategy to obtain an adjusted first quality score and an adjusted second quality score; determining the target exposure mode from the first candidate exposure mode and the second candidate exposure mode based on a comparison result between the adjusted first quality score and the adjusted second quality score; If the quality score difference between the first image data and the second image data is greater than the right boundary of the difference threshold interval, and the second quality score is greater than the first quality score, the second candidate exposure mode is determined as the target exposure mode.

8. The method according to claim 7, characterized in that The object information includes a moving speed, and the first quality score of the first image data and the second quality score of the second image data are adjusted based on a preset score adjustment strategy to obtain an adjusted first quality score and an adjusted second quality score, including: Performing weighted sum processing on the moving speed of the target object in the first image data and the first quality score to obtain the adjusted first quality score; The moving speed of the target object in the second image data and the second quality score are weightedly summed to obtain the adjusted second quality score.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the processor is used to execute program instructions stored in the memory to implement the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images