Exposure control methods, devices, cameras, equipment, media and products

Abstract

This application provides an exposure control method, apparatus, camera, device, medium, and product. The method includes: extracting scene features of the current scene based on real-time image data acquired by a camera sensor; determining multi-factor triggering conditions corresponding to the current scene based on the scene features; and then determining a parameter set corresponding to the current scene to achieve camera exposure control based on the parameter set. The solution in this example, by fusing multi-dimensional scene features such as ambient light intensity, image overexposure, image content information, and motion state to establish a dynamic parameter set, can enhance adaptability to complex lighting conditions. Adjusting parameter sets such as metering weight position, exposure gain, exposure time, exposure convergence speed, and target brightness can improve the targeting and accuracy of adjustments, thereby improving the reliability of exposure control.

Description

Technical Field

[0001] This application relates to the field of image processing, and more particularly to an exposure control method, apparatus, camera, device, medium, and product. Background Technology

[0002] Image acquisition devices, such as mobile phone cameras, surveillance cameras, and professional cameras, are widely used in diverse scenarios including daily shooting, security monitoring, medical imaging, and machine vision. In order to automatically acquire images with appropriate brightness and clear details under complex and changing lighting conditions, image acquisition devices usually integrate automatic exposure algorithms to achieve intelligent control of image exposure.

[0003] Currently, many automatic exposure solutions rely on preset brightness thresholds or basic classifications (such as indoor / outdoor modes) for control logic, and switch corresponding exposure parameters by looking up tables. This approach lacks the ability to dynamically adapt to changes in scene lighting. For example, if the scene is roughly divided based solely on ambient light intensity, it can easily lead to inaccurate exposure judgments in situations with complex or rapidly changing lighting conditions, thereby affecting overall image quality and reducing the reliability of exposure control. Summary of the Invention

[0004] This application provides an exposure control method, apparatus, camera, device, medium, and product to improve the reliability of exposure control.

[0005] In a first aspect, embodiments of this application provide an exposure control method, comprising: extracting scene features of the current scene based on real-time image data acquired by a camera sensor; wherein the scene features include ambient light intensity, image overexposure degree, image content information, and motion state; determining multi-factor triggering conditions corresponding to the current scene based on the scene features, wherein the multi-factor triggering conditions are a combination of the states of multiple scene features; determining a parameter group corresponding to the current scene based on the multi-factor triggering conditions, and performing camera exposure control based on the parameter group to make the image brightness of the camera image match the lighting conditions of the current scene; wherein the parameter group includes at least one of the following: metering weight position, exposure gain, exposure time, exposure convergence speed, and target brightness.

[0006] In one possible implementation, based on scene features, determining multi-factor triggering conditions corresponding to the current scene includes: determining a first factor triggering condition based on ambient light intensity in the scene features; wherein the first factor triggering condition includes any one of low light triggering, indoor triggering, and outdoor triggering; determining a second factor triggering condition based on image overexposure in the scene features; wherein the second factor triggering condition includes any one of highlight triggering and non-highlight triggering; determining a third factor triggering condition based on image content information in the scene features; wherein the third factor triggering condition includes any one of non-face triggering, face front lighting triggering, and face backlighting triggering; determining a fourth factor triggering condition based on motion state in the scene features; wherein the fourth factor triggering condition includes any one of motion triggering and non-motion triggering; and determining multi-factor triggering conditions based on the first factor triggering condition, the second factor triggering condition, the third factor triggering condition, and the fourth factor triggering condition.

[0007] In one possible implementation, a parameter set corresponding to the current scene is determined based on multi-factor triggering conditions, including: when the first factor triggering condition includes outdoor triggering and the third factor triggering condition includes face backlighting triggering, the metering weight position in the parameter set is set to the face region, and the exposure convergence speed is reduced from the first speed to the second speed; when the first factor triggering condition includes outdoor triggering, the second factor triggering condition includes highlight triggering, and the third factor triggering condition includes non-face triggering, the target brightness in the parameter set is reduced; when the first factor triggering condition includes low light triggering or outdoor triggering, and the fourth factor triggering condition includes motion triggering, the upper limit of exposure time in the parameter set is set to the first threshold, and the upper limit threshold of exposure gain in the parameter set is increased.

[0008] In one possible implementation, when the first factor triggering condition includes outdoor triggering, the third factor triggering condition includes face backlighting triggering, and the determined parameter set is used for camera exposure control, the method further includes: performing gamma correction on the camera image based on a first gamma curve; increasing the brightness of the face area and decreasing the brightness of the background area of ​​the camera image based on a local tone mapping algorithm; when the first factor triggering condition includes outdoor triggering, the second factor triggering condition includes highlight triggering, and the third factor triggering condition includes non-face triggering, and the determined parameter set is used for camera exposure control, the method further includes: performing gamma correction on the camera image based on a second gamma curve; wherein the contrast of the second gamma curve is higher than that of the first gamma curve; and increasing the brightness of the central and dark areas of the camera image based on a local tone mapping algorithm.

[0009] In one possible implementation, the first speed corresponds to a first convergence speed adjustment strategy, and the second speed corresponds to a second convergence speed adjustment strategy; the method further includes: determining the current exposure index based on the current exposure gain and the current exposure time, and determining the target exposure index based on the target brightness; adjusting the current exposure index according to the first convergence speed adjustment strategy or the second convergence speed adjustment strategy until the current exposure index is the target exposure index.

[0010] In one possible implementation, adjusting the current exposure index according to a first convergence speed adjustment strategy includes: calculating a first difference between the exposure index of the previous frame and the target exposure index, and a second difference between the average exposure index of the previous n frames and the target exposure index; when the first difference and the second difference are equal, the product of the first difference and a first coefficient is used as the adjustment step size for the current frame; wherein the first coefficient is used to adjust the convergence speed; when the first difference and the second difference are not equal, and the first difference and the second difference have the same sign, the product of the difference with the smaller absolute value and the first coefficient is used as the adjustment step size for the current frame; when the first difference and the second difference have the same sign, the product of the difference with the smaller absolute value and the first coefficient is used as the adjustment step size for the current frame; when the first difference and the second difference have the same sign, the product of the difference with the smaller absolute value and the first coefficient is used as the adjustment step size for the current frame; when the first difference and the second difference have the same absolute value, the product of the difference with the smaller absolute value and the first coefficient is used as the adjustment step size for the current frame; when the first difference and the second difference have the same absolute value, the product of the difference with the smaller absolute value and the first coefficient is used as the adjustment step size for the current frame; when the first difference and the second difference have the same absolute value, the product of the difference with the smaller absolute value and the first coefficient is used as the adjustment step size for the current frame; when the first difference and the second difference have the same absolute value, the product of the difference with the smaller absolute value and the second ... If the second difference is not equal, and the first difference and the second difference have different signs, then the product of the first difference and the first coefficient is used as the adjustment step size in the current frame. For the adjustment step size in the current frame, when the adjustment step size meets the first condition, the adjustment step size is updated to the basic adjustment step size. The first condition is that the adjustment step size is less than the basic adjustment step size, and the first difference and the second difference have the same sign. When the adjustment step size does not meet the first condition, the adjustment step size is optimized: when the difference between the sum of the adjustment step size and the exposure index in the current frame and the target exposure index is less than the corresponding threshold, the exposure index in the current frame is directly adjusted to the target exposure index.

[0011] In one possible implementation, adjusting the current exposure index according to a second convergence speed adjustment strategy includes: detecting whether a user-triggered focus area exists in the camera frame; calculating a dynamic hold time based on the motion state and the difference between the current exposure index and the target exposure index, and performing exposure adjustment only when the dynamic hold time has not been exceeded and there is no user-triggered focus area; when performing exposure adjustment, performing the following steps: determining the maximum adjustment step size based on the proportion of the dark area of ​​the camera frame when brightening, or determining the maximum adjustment step size based on the proportion of the bright area of ​​the camera frame when darkening; wherein, the closer the current exposure index is to the target exposure index, the smaller the maximum adjustment step size; performing exposure adjustment based on the determined maximum adjustment step size and a first convergence speed adjustment strategy after updating the first coefficient to the second coefficient; wherein, the second coefficient is smaller than the first coefficient.

[0012] In one possible implementation, the method further includes: adjusting the exposure gain and exposure time based on a smooth transition algorithm; wherein the smooth transition algorithm includes a linear interpolation algorithm or an inertial filtering algorithm.

[0013] In one possible implementation, the method further includes: detecting the camera image after camera exposure control; if the detection fails, updating the parameter group corresponding to the current scene until the detection passes; wherein the detection includes at least one of the following: brightness detection, dynamic range detection, color saturation detection, white balance detection, flicker frequency and amplitude detection, expert detection, convergence speed detection, convergence smoothness detection, and anti-flicker capability detection.

[0014] Secondly, embodiments of this application provide an exposure control device, comprising: an extraction module, configured to extract scene features of the current scene based on real-time image data acquired by a camera sensor; wherein the scene features include ambient light intensity, image overexposure degree, image content information, and motion state; a determination module, configured to determine multi-factor triggering conditions corresponding to the current scene based on the scene features, wherein the multi-factor triggering conditions are a combination of the states of multiple scene features; and a control module, configured to determine a parameter set corresponding to the current scene based on the multi-factor triggering conditions, and perform camera exposure control based on the parameter set to match the image brightness of the camera image with the lighting conditions of the current scene; wherein the parameter set includes at least one of the following: metering weight position, exposure gain, exposure time, exposure convergence speed, and target brightness.

[0015] Thirdly, embodiments of this application provide a camera, which includes the exposure control device described above.

[0016] Fourthly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0017] The memory stores instructions that the computer executes;

[0018] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0019] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0020] In a sixth aspect, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0021] The exposure control method, apparatus, camera, device, medium, and product provided in this application include: extracting scene features of the current scene based on real-time image data collected by a camera sensor; determining multi-factor triggering conditions corresponding to the current scene based on the scene features, and then determining a parameter set corresponding to the current scene to achieve camera exposure control based on the parameter set. The solution in this example, by fusing multi-dimensional scene features such as ambient light intensity, image overexposure, image content information, and motion state to establish a dynamic parameter set, can enhance adaptability to complex lighting conditions. Adjusting parameter sets such as metering weight position, exposure gain, exposure time, exposure convergence speed, and target brightness can improve the targeting and accuracy of adjustments, thereby improving the reliability of exposure control. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0023] Figure 1 A schematic flowchart illustrating the exposure control method provided in an embodiment of this application;

[0024] Figure 2 A schematic flowchart illustrating the exposure control method provided in an embodiment of this application;

[0025] Figure 3 A schematic flowchart illustrating the exposure control method provided in an embodiment of this application;

[0026] Figure 4 A schematic flowchart illustrating the exposure control method provided in an embodiment of this application;

[0027] Figure 5 A schematic flowchart illustrating the exposure control method provided in an embodiment of this application;

[0028] Figure 6 A schematic flowchart illustrating the exposure control method provided in an embodiment of this application;

[0029] Figure 7 A schematic flowchart illustrating the exposure control method provided in an embodiment of this application;

[0030] Figure 8 A schematic flowchart illustrating the exposure control method provided in an embodiment of this application;

[0031] Figure 9 This is a schematic diagram of the exposure control device provided in the embodiments of this application;

[0032] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0033] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0034] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0035] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning. In addition, the terms "comprising" and "having," and any variations thereof, are intended to be omnipresent but not exclusive. For example, a product or device that comprises a series of components is not necessarily limited to those components that are explicitly listed, but may include other components that are not explicitly listed or that are inherent to such product or device.

[0036] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0037] The following disclosure provides many different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the invention. Furthermore, reference numerals and / or letters may be repeated in different examples; such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. In addition, examples of various specific processes and materials are provided in this invention, but those skilled in the art will recognize the application of other processes and / or the use of other materials.

[0038] Image acquisition devices, such as mobile phone cameras, surveillance cameras, and professional cameras, are widely used in diverse scenarios including everyday photography, security monitoring, medical imaging, and machine vision. During photo taking and video recording, the camera needs to dynamically adjust exposure parameters based on ambient lighting conditions and the content being captured (e.g., to ensure moderate image brightness, clear details, and no significant noise or overexposure). For example, in photo shooting scenarios, users need to quickly and accurately adjust exposure parameters to ensure image quality when capturing still images under different lighting conditions; in video shooting scenarios, exposure parameters need to be continuously adjusted in the real-time video stream, while simultaneously ensuring frame rate stability and continuous image brightness to avoid visual jumps or flickering caused by sudden parameter changes.

[0039] In related technologies, automatic exposure (AE) adjustment in cameras mainly relies on static parameter adjustments based on ambient light sensors. For example, an ambient light sensor (Lux sensor) measures the ambient light intensity (Lux value) and selects parameters according to a preset exposure table to increase gain or extend exposure time in low-light environments to improve image brightness. However, this approach relies on a single ambient light sensor and cannot detect dynamic changes in the scene content, leading to exposure imbalances in backlit or high-contrast scenes.

[0040] The technical content provided in this application aims to solve the aforementioned technical problems in related technologies. The exposure control method, apparatus, camera, device, medium, and product provided in the embodiments of this application include: extracting scene features of the current scene based on real-time image data collected by a camera sensor; determining multi-factor triggering conditions corresponding to the current scene based on the scene features, and then determining a parameter set corresponding to the current scene to achieve camera exposure control based on the parameter set. The solution in this example, by fusing multi-dimensional scene features such as ambient light intensity, image overexposure degree, image content information, and motion state to establish a dynamic parameter set, can enhance adaptability to complex lighting conditions. Adjusting parameter sets such as metering weight position, exposure gain, exposure time, exposure convergence speed, and target brightness can improve the targeting and accuracy of adjustments, thereby improving the reliability of exposure control.

[0041] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0042] Figure 1 This is a flowchart illustrating the exposure control method provided in an embodiment of this application, as shown below. Figure 1 As shown, the method includes:

[0043] S101. Extract scene features of the current scene based on real-time image data collected by the camera sensor; the scene features include ambient light intensity, image overexposure, image content information, and motion state.

[0044] S102. Based on scene features, determine the multi-factor triggering conditions corresponding to the current scene. The multi-factor triggering conditions are a combination of the states of multiple scene features.

[0045] S103. Determine the parameter group corresponding to the current scene based on the multi-factor triggering conditions, and perform camera exposure control based on the parameter group so that the image brightness of the camera screen matches the lighting conditions of the current scene; wherein, the parameter group includes at least one of the following: metering weight position, exposure gain, exposure time, exposure convergence speed, and target brightness.

[0046] In practical applications, the subject executing this method can be an exposure control device, which can be implemented in various ways. For example, it can be implemented through a computer program, such as application software; or it can be implemented as a medium storing the relevant computer program, such as a cloud disk; or it can be implemented through a physical device that integrates or installs the relevant computer program, such as a chip.

[0047] In some alternative embodiments, the execution entity of the method can be an image signal processor within the camera or a dedicated exposure control module. These hardware components are responsible for processing real-time image data and executing exposure adjustment algorithms. In mobile devices or professional cameras, the execution entity may be integrated into the camera application or firmware, working in conjunction with the sensor hardware through software algorithms to achieve exposure control.

[0048] For example, ambient light intensity can be assessed by calculating the overall brightness histogram of the image, such as by taking the average or weighted average of pixel values. Specifically, the state of ambient light intensity can include low light, normal light, and high light, and the state judgment criteria are usually based on the average brightness value of the image, such as below 50 for low light, 50-200 for normal light, and above 200 for high light (assuming 8-bit image data).

[0049] For example, the degree of overexposure can be determined by detecting the proportion of pixel values ​​in the highlight area that are close to saturation, such as using a threshold to determine the number of overexposed pixels. For example, the degree of overexposure in an image can be categorized as no overexposure, slight overexposure, and severe overexposure. The criteria for determining the degree are based on the proportion of overexposed pixels to the total number of pixels. For example, less than 5% is no overexposure, 5%-20% is slight overexposure, and more than 20% is severe overexposure.

[0050] For example, computer vision techniques, such as object detection or scene classification algorithms, can be used to identify the presence of faces, buildings, or natural elements. For example, the state of the image content information may include face dominance, landscape dominance, or text dominance. The state determination criterion is based on object detection confidence; for example, if the face detection score is higher than a threshold, it is considered face dominance.

[0051] For example, motion states are typically calculated by analyzing differences between consecutive frames, such as by estimating motion vectors using optical flow or block matching methods. For example, motion states can be categorized as static, low-speed motion, and high-speed motion, and the criteria for determining the state can be based on the magnitude of the motion vector; for example, an average motion vector less than 5 pixels indicates static motion, 5-20 pixels indicates low-speed motion, and greater than 20 pixels indicates high-speed motion.

[0052] In some embodiments, motion state may include camera motion state and the motion state of the subject being photographed. The former can be determined by the camera's motion sensor, while the latter can be determined by analyzing the content of the image.

[0053] In some optional embodiments, scene features may also include image contrast, which may be low or high contrast; and color saturation, which may be low or high saturation.

[0054] In some embodiments, the multi-factor triggering condition is composed of a combination of the states of multiple scene features. For example, one multi-factor triggering condition may be that the ambient light intensity is high and the image overexposure is severe, indicating that the scene brightness is excessive and needs to be adjusted quickly; another factor triggering condition may be that the image content information is dominated by a face and the motion state is high-speed motion, indicating that it is necessary to prioritize ensuring the stability of the face exposure.

[0055] It's important to note that some multi-factor triggering conditions may only involve the state of one or two scene features. For example, when the motion is high-speed, even if other features such as ambient light intensity are normal, the motion state may be prioritized to avoid blurring. In other words, motion state has higher priority under certain conditions. High-priority scene features have higher priority in exposure control. For instance, in low-light environments, the ambient light intensity may take precedence over image content information to ensure correct basic exposure. In practical applications, this priority can be achieved through weighting or hierarchical rules.

[0056] In some embodiments, the parameter set corresponding to the current scene is determined based on multi-factor triggering conditions, typically using a predefined mapping table or machine learning model. Specifically, the extracted scene feature state combinations can be matched with a stored condition library to find the most suitable multi-factor triggering conditions, and then the corresponding parameter set can be invoked.

[0057] For example, the parameter set includes metering weight position, exposure gain, exposure time, exposure convergence speed, and target brightness, etc. These parameters are preset through experiments or optimization algorithms to ensure that the image brightness matches the current scene. For example, if the conditions are successfully matched, the parameter values ​​are loaded from the database and applied to the camera control loop.

[0058] In some optional embodiments, the parameter set may also include the camera frame rate. In video recording or photo preview mode, exposure control can be achieved by adjusting the frame rate to limit exposure time. For example, at a frame rate of 30 frames per second, the maximum exposure time per frame theoretically cannot exceed approximately 33 milliseconds. When the scene light is extremely low, even with the exposure time set to the maximum value, the image may still be underexposed. In this case, the frame rate can be actively reduced, for example, to 24 frames per second, thus extending the maximum exposure time per frame to approximately 41 milliseconds. A longer exposure time means the sensor can capture more light, effectively increasing image brightness and improving imaging performance in low light conditions.

[0059] In this example, the correspondence between multi-factor triggering conditions and parameter groups can be varied. For instance, one multi-factor triggering condition is low ambient light intensity and the dominant image content is a face. The corresponding parameter group might set the metering weights to favor the face area, increase the exposure gain, moderately extend the exposure time, slow down the exposure convergence speed, and slightly increase the target brightness to ensure the face is sharp. Another multi-factor triggering condition is high-speed motion and slight overexposure. The corresponding parameter group might prioritize shortening the exposure time to reduce motion blur, while slightly reducing the exposure gain and accelerating the exposure convergence speed to adapt to rapid changes.

[0060] The exposure control method provided in this application includes: extracting scene features of the current scene based on real-time image data acquired by a camera sensor; determining multi-factor triggering conditions corresponding to the current scene based on the scene features, and then determining a parameter set corresponding to the current scene to achieve camera exposure control based on the parameter set. The solution in this example, by fusing multi-dimensional scene features such as ambient light intensity, image overexposure, image content information, and motion state to establish a dynamic parameter set, can enhance adaptability to complex lighting conditions. Adjusting parameter sets such as metering weight position, exposure gain, exposure time, exposure convergence speed, and target brightness can improve the targeting and accuracy of adjustments, thereby improving the reliability of exposure control.

[0061] Figure 2 This is a flowchart illustrating the exposure control method provided in an embodiment of this application, as shown below. Figure 2 As shown, in S102, based on scene features, the multi-factor triggering conditions corresponding to the current scene are determined, including:

[0062] S201. Determine the first factor triggering condition based on the ambient light intensity in the scene features; wherein, the first factor triggering condition includes any one of: dark light triggering, indoor triggering, and outdoor triggering;

[0063] S202. Determine the triggering condition for the second factor based on the degree of overexposure in the scene features; wherein, the triggering condition for the second factor includes either highlight triggering or non-highlight triggering;

[0064] S203. Determine the third factor triggering condition based on the image content information in the scene features; wherein, the third factor triggering condition includes any one of: non-face triggering, face front lighting triggering, and face backlighting triggering;

[0065] S204. Determine the triggering condition for the fourth factor based on the motion state in the scene features; wherein, the triggering condition for the fourth factor includes either motion triggering or non-motion triggering.

[0066] S205. Determine the multi-factor triggering conditions based on the first factor triggering condition, the second factor triggering condition, the third factor triggering condition, and the fourth factor triggering condition.

[0067] In some embodiments, the distinction between low-light triggering, indoor triggering, and outdoor triggering is primarily based on the specific numerical range of ambient light intensity (e.g., via an ambient light sensor) and color temperature information. Specifically, low-light triggering typically sets a low brightness threshold; when the overall average brightness of the image is below this threshold, it is determined to be a low-light environment. Outdoor scenes are generally brighter, have a cooler color temperature (more blue tones), and the brightness distribution may be more uneven due to elements such as the sky, while indoor scenes may have moderate brightness, a warmer color temperature (more yellow tones), and a relatively uniform light distribution.

[0068] In some embodiments, highlight triggering and non-highlight triggering correspond to the degree of overexposure in the camera image. Specifically, the proportion of pixels in the camera image whose brightness value reaches or approaches the sensor's saturation limit (e.g., in an 8-bit image, the brightness value is higher than a specific threshold such as 240) can be calculated. When this proportion of overexposed pixels exceeds a preset threshold (e.g., 15%), it is determined to be a highlight triggering condition; conversely, if the proportion is lower than the threshold, it is a non-highlight triggering condition.

[0069] In some embodiments, non-face triggering, face-lighting triggering, and face-backlighting triggering are primarily determined by face detection results and the light ratio of the face area. Specifically, a face detection algorithm is first used to determine whether a face exists in the image. If no face is detected, it is directly classified as non-face triggering. If a face is detected, the brightness difference between the face area and the background or different parts of the face itself (such as the front and the edges) is further analyzed. When the brightness of the main face area is significantly higher than the background or the average brightness of the overall image, it is determined to be face-lighting triggering; conversely, when the brightness of the face area is significantly lower than the brightness of the background (especially bright backgrounds such as the sky), it is determined to be backlighting triggering.

[0070] In some embodiments, the distinction between motion-triggered and non-motion-triggered states can be based on the analysis of consecutive frame sequences. Specifically, the amplitude and velocity of objects in the scene are calculated by calculating optical flow vectors or analyzing inter-frame differences. When the detected average motion vector amplitude or the number of moving pixels exceeds a motion threshold, it is determined to be a motion-triggered condition, indicating that there is significant motion in the scene; if the motion amplitude is weak or negligible, it is determined to be a non-motion-triggered condition. Optionally, this motion can also be combined with camera shake or dynamic changes in noise from sequence analysis to improve the accuracy of the analysis.

[0071] Furthermore, the four triggering factors mentioned above (such as "low light," "non-highlight," "backlit face," and "non-motion") can be combined into a unique scene identifier. This identifier is used to look up a predefined, large-scale strategy mapping table. In practical applications, this table is developed by engineers through extensive scene experiments and experience, mapping each possible combination of triggering factors to an optimal set of exposure parameters. For example, for the combination of "low light + non-highlight + backlit face + non-motion," it directly corresponds to a set of specific parameters aimed at improving face brightness while maintaining image clarity and stability.

[0072] The solution in this example decomposes and then merges complex scene features, enabling the exposure control strategy to be more refined and intelligently adapted to specific and varied shooting scenarios such as backlighting of people and motion blur suppression, thereby improving the final image quality.

[0073] Figure 3 This is a flowchart illustrating the exposure control method provided in an embodiment of this application, as shown below. Figure 3 As shown, in S103, the parameter set corresponding to the current scene is determined based on the multi-factor triggering conditions, including:

[0074] S301. When the first factor triggering condition includes outdoor triggering and the third factor triggering condition includes face backlighting triggering, the metering weight position in the parameter group is set to the face area and the exposure convergence speed is reduced from the first speed to the second speed.

[0075] S302. When the first factor triggering condition includes outdoor triggering, the second factor triggering condition includes highlight triggering, and the third factor triggering condition includes non-face triggering, reduce the target brightness in the parameter group.

[0076] S303. When the first factor triggering condition includes low light triggering or outdoor triggering, and the fourth factor triggering condition includes motion triggering, the upper limit of exposure time in the parameter group is set to the first threshold, and the upper limit threshold of exposure gain in the parameter group is increased.

[0077] For example, when executing S301, setting the metering weight position in the parameter group to the face area changes the camera's priority in evaluating image brightness. In backlit environments, the background is usually very bright, while the face is in shadow and dark. If global average metering is used, the camera will be misled by the bright background, thus reducing the overall exposure and causing the face to be too dark. By focusing the metering weight on the detected face area, the background brightness can be ignored, ensuring that the subject, the face, receives correct exposure.

[0078] Meanwhile, reducing the exposure convergence speed from the first speed to the second speed allows for a smoother exposure transition. It should be understood that the "first speed" typically represents a faster convergence speed, while the "second speed" represents a slower one. In complex lighting scenarios like backlit faces, slowing down the convergence speed prevents drastic fluctuations or flickering in the exposure value as it searches for optimal brightness, and avoids abrupt changes in background brightness caused by increasing face brightness.

[0079] For example, when executing S302, the target brightness in the parameter group is reduced, i.e., the exposure compensation strategy is adjusted. The target brightness is the baseline value that the exposure algorithm attempts to achieve for the overall brightness of the image. In outdoor, non-face-centric highlight scenes (such as shooting the sky, snow, or bright buildings), there is a risk of large areas of overexposure in the image. If the standard target brightness is still used as the benchmark, the sensor will tend to increase the exposure to make the image brighter, which will exacerbate the loss of detail in overexposure in highlight areas. Therefore, reducing the target brightness can sacrifice some brightness in midtones or shadow areas to retain more detail in highlight areas, preventing "whitewashed" areas in the image, thus better handling high dynamic range scenes. It should be noted that the metering weight position in S302 is the highlight position; this example fine-tunes the target brightness based on this.

[0080] For example, by setting the upper limit of exposure time in S303 to a first threshold and increasing the upper limit of exposure gain, a balance can be achieved between motion blur and image noise. In practical applications, while a longer exposure time increases the amount of light entering the image in low light, it can cause moving objects to appear as blur on the image sensor. By setting a short upper limit, this motion blur can be significantly reduced. However, shortening the exposure time reduces the amount of light entering the image, resulting in a darker image. To compensate for the brightness, the exposure gain needs to be increased (essentially signal amplification). However, increasing the gain amplifies sensor noise, resulting in graininess in the image. Therefore, increasing the upper limit of exposure gain allows for the use of a higher gain value when necessary to maintain image brightness.

[0081] In some alternative embodiments, signal noise during the process of increasing exposure gain can be reduced by prioritizing increasing the camera's analog exposure gain until the analog exposure gain reaches a hardware upper limit threshold.

[0082] The solution presented in this example improves image quality in complex shooting scenarios such as motion blur, image noise, and highlight overexposure by precisely matching multi-factor triggering conditions and parameter group adjustments, thereby enhancing the stability of exposure control.

[0083] Figure 4 This is a flowchart illustrating the exposure control method provided in an embodiment of this application, as shown below. Figure 4 As shown, after satisfying the conditions in S301 where the first factor triggering condition includes outdoor triggering, the third factor triggering condition includes face backlighting triggering, and the determined parameter set is used for camera exposure control, the method further includes:

[0084] S401. Perform gamma correction on the camera image based on the first gamma curve;

[0085] S402. Based on the local tone mapping algorithm, increase the brightness of the face area in the camera image and reduce the brightness of the background area;

[0086] Figure 5 This is a flowchart illustrating the exposure control method provided in an embodiment of this application, as shown below. Figure 5 As shown, after satisfying the conditions in S302 where the first factor triggering condition includes outdoor triggering, the second factor triggering condition includes highlight triggering, and the third factor triggering condition includes non-face triggering, and after using the determined parameter set for camera exposure control, the method further includes:

[0087] S501. Perform gamma correction on the camera image based on the second gamma curve; wherein the contrast of the second gamma curve is higher than that of the first gamma curve;

[0088] S502: Based on a local tone mapping algorithm, improve the brightness of the central and dark areas of the camera image.

[0089] It's important to note that in the image processing workflow, after automatic exposure control is completed and the image is output, gamma curve correction and local tone mapping are typically performed. Gamma curve correction is a global non-linear transformation used to reshape the image's brightness response curve, making the image's tonal distribution more consistent with human visual perception. Local tone mapping, on the other hand, is a pixel-level adjustment technique that analyzes the local features of different regions of the image to independently adjust their brightness and contrast, thereby enhancing the representation of local details.

[0090] In some embodiments, the first gamma curve may have a relatively gentle slope in the dark region to map the dark input grayscale value to a wider output grayscale range, thereby lifting facial details hidden in shadows, while the first gamma curve avoids overstretching in the highlight region to prevent new overexposure.

[0091] Furthermore, a local tone mapping algorithm is used to enhance the brightness of the face area and reduce the brightness of the background area. Specifically, the local tone mapping algorithm first identifies the face area as the region of interest, then locally brightens the pixels in that area to highlight the subject. At the same time, for the background area, especially the already bright sky, brightness suppression is applied, thus making the face clearer and brighter under backlight while preserving background details.

[0092] In some embodiments, the second gamma curve typically has a more pronounced "S" shape, which enhances the sense of depth and texture details of objects in the image by stretching the contrast of the midtones and compressing the brightness values ​​of the highlight areas.

[0093] The mid-tone and dark-tone brightness regions are often defined based on the image's brightness histogram. The brightness range of a digital image (e.g., 0-255 for an 8-bit image) can be divided into three parts: Dark-tone brightness region: This refers to the pixel area with lower brightness values, typically corresponding to the left side of the histogram. For example, pixels with brightness values ​​between 0 and 85 (or 0-1 / 3 of the total range) are considered dark pixels. Increasing the brightness of the dark area means brightening these low-brightness pixels to enhance shadow details. Mid-tone brightness region: This refers to the pixel area with brightness values ​​in the middle range, typically corresponding to the middle part of the histogram. For example, pixels with brightness values ​​between 86 and 170 (or 1 / 3-2 / 3 of the total range). Adjusting the mid-tone brightness aims to optimize the main body of the image, improving its contrast and depth.

[0094] Furthermore, by using local tone mapping algorithms to enhance the brightness of midtone and shadow areas, the potential side effects of globally reducing target brightness and applying high-contrast gamma curves can be balanced. By detecting areas in the midtones and shadows of the image and selectively boosting their brightness, details in these areas can be preserved, resulting in a more balanced high dynamic range image effect overall.

[0095] This example solution combines exposure control with gamma correction and local tone mapping to further optimize specific complex lighting scenarios such as backlit faces and highlighted landscapes, thereby obtaining more natural-looking images while preserving details in both highlights and shadows.

[0096] Figure 6 This is a flowchart illustrating the exposure control method provided in an embodiment of this application, as shown below. Figure 6 As shown, the first velocity corresponds to the first convergence velocity adjustment strategy, and the second velocity corresponds to the second convergence velocity adjustment strategy; the method also includes:

[0097] S601. Determine the current exposure index based on the current exposure gain and the current exposure time, and determine the target exposure index based on the target brightness;

[0098] S602. Adjust the current exposure index according to the first convergence speed adjustment strategy or the second convergence speed adjustment strategy until the current exposure index is the target exposure index.

[0099] It's important to note that when performing exposure control, a reference baseline must first be established. This baseline is the minimum exposure that the sensor hardware can support (usually the exposure corresponding to the shortest exposure time at the minimum exposure gain) as the starting point for calculations. Then, based on the currently used exposure gain and exposure time, the current exposure index is calculated. This index represents the ratio of the current actual exposure to the minimum exposure, and is typically expressed in logarithmic or exponential form for linear control.

[0100] Simultaneously, based on the target brightness value, the target exposure required to achieve that brightness is calculated, and then the target exposure / minimum exposure = target exposure index is calculated. Therefore, the entire exposure control process is essentially a process of adjusting the gain and exposure time parameters with reference to a pre-calibrated exposure table, thereby smoothly and efficiently driving the current exposure index to the target exposure index.

[0101] In some embodiments, the first convergence speed adjustment strategy is a strategy that responds quickly to changes in brightness, such as adjusting the exposure index change step size as large as possible within each control cycle. Specifically, when suddenly transitioning from a dark environment to a bright environment, this strategy may control the exposure index to complete most or even all of the convergence path in a single adjustment to achieve a rapid response.

[0102] In some embodiments, the second convergence speed adjustment strategy typically limits the range of change in the exposure index within each control cycle, causing it to slowly approach the target value in a small and fixed step size, in order to achieve smooth and gentle changes in image brightness and avoid visible brightness flickering or abrupt jumps.

[0103] It's important to note that determining the target brightness is not a fixed value, but a dynamic process based on image content analysis, scene feature recognition, and pre-defined imaging preferences. The system typically sets a baseline target brightness value, such as ensuring the overall average brightness of the image reaches a certain grayscale level. However, this baseline value is adjusted in real-time and adaptively based on extracted scene features. For example, when the system identifies a backlit face, the target brightness might be appropriately increased from the baseline value to prioritize brightening the face area in shadow, ensuring the subject remains sharp. Furthermore, the user's mode selection also affects the target brightness; for instance, in "night mode," the target brightness might be set lower to maintain a nighttime atmosphere. Therefore, the target brightness is the final ideal brightness value determined by the algorithm based on the baseline value, combined with real-time scene semantic understanding and image quality considerations.

[0104] The solution presented in this example, based on a differentiated convergence speed adjustment strategy that adapts to the needs of different scenarios, can improve the balance between rapid response and smooth transition in the exposure control process, thereby improving the timeliness of control and the stability of the image.

[0105] Figure 7 This is a flowchart illustrating the exposure control method provided in an embodiment of this application, as shown below. Figure 7 As shown, in S602, the current exposure index is adjusted according to the first convergence speed adjustment strategy, including:

[0106] S701. Calculate the first difference between the exposure index of the previous frame and the target exposure index, and the second difference between the average exposure index of the previous n frames and the target exposure index.

[0107] S702. When the first difference is equal to the second difference, the product of the first difference and the first coefficient is used as the adjustment step size in the current frame; wherein, the first coefficient is used to adjust the convergence speed.

[0108] S703. When the first difference and the second difference are not equal, and the first difference and the second difference have the same sign, the product of the difference with the smaller absolute value and the first coefficient is used as the adjustment step size in the current frame; when the first difference and the second difference are not equal, and the first difference and the second difference have different signs, the product of the first difference and the first coefficient is used as the adjustment step size in the current frame.

[0109] S704. For the adjustment step size in the current frame, when the adjustment step size meets the first condition, the adjustment step size is updated to the basic adjustment step size; wherein, the first condition is that the adjustment step size is less than the basic adjustment step size, and the first difference and the second difference have the same sign.

[0110] S705. When the adjustment step size does not meet the first condition, optimize the adjustment step size: when the difference between the sum of the adjustment step size and the exposure index of the current frame and the target exposure index is less than the corresponding threshold, directly adjust the exposure index of the current frame to the target exposure index.

[0111] In this example, the exposure index parameters of the previous frame and the previous n frames are used to more comprehensively capture the changing trend of the exposure state. Specifically, by analyzing the data sequence within a short time window, it can be determined whether the exposure is continuously deviating from the target, converging towards the target, or in an unstable fluctuating state. This can filter out noise interference or instantaneous brightness fluctuations that may exist in a single frame image, making the calculation of the adjustment step size more robust and accurate.

[0112] For example, n is a configurable window size parameter used to define the number of historical frames the algorithm references. Its specific value can be set according to system performance (such as processing power, memory) and stability requirements, for example, n=3, 5, 10, etc.

[0113] It should be noted that the average exposure index of the first n frames should be interpreted as the average of the exposure indexes of the first n frames.

[0114] In this example, when the first difference equals the second difference, it means that the difference between the exposure index and the target has remained constant in recent frames, showing no signs of natural convergence. The first coefficient acts as a configurable gain amplifier; a larger first coefficient amplifies the adjustment step size, while a smaller first coefficient reduces the step size, making the convergence process more cautious and smooth. The first coefficient is typically a value between 0.1 and 1.0. For example, in initial calibration, it can be set to 0.2 or 0.5, representing adjusting 20% ​​or 50% of the target difference each time. The specific value needs to be determined experimentally: when testing exposure convergence behavior, if convergence is too fast causing oscillations, decrease the coefficient; if convergence is too slow, increase the coefficient.

[0115] In this example, when the first and second differences are unequal but have the same sign, it indicates that the gap between the exposure index and the target is narrowing, and the convergence process is underway, but the rate of narrowing may not be constant. If a larger error value is still used to calculate the step size at this point, it is easy to over-adjust due to inertia, causing the exposure index to oscillate around the target value. Therefore, using a smaller error value to generate the step size allows the convergence process to stop smoothly and stably at the target point, avoiding flickering in the image brightness.

[0116] In this example, if the calculated adjustment step size is too small, less than a preset minimum effective step size (i.e., the base adjustment step size), it indicates that the convergence speed is slow. Therefore, directly updating the adjustment step size to the base adjustment step size can avoid spending too many unnecessary frames on minor adjustments in the final stage, thereby accelerating the entire convergence process.

[0117] In this example, when the difference between the sum of the current adjustment step size and the current exposure index and the target exposure index is less than the corresponding threshold, the step-by-step calculation method is abandoned, and the exposure index is directly set to the target value. In practical applications, this corresponding threshold can be adjusted according to needs.

[0118] The solution in this example dynamically optimizes the step size based on the convergence trend, which can reduce overshoot oscillations and accelerate the convergence process while improving exposure stability, thereby achieving fast and smooth automatic exposure adjustment.

[0119] Figure 8 This is a flowchart illustrating the exposure control method provided in an embodiment of this application, as shown below. Figure 8 As shown, in S602, the current exposure index is adjusted according to the second convergence speed adjustment strategy, including:

[0120] S801: Obtain the motion state of the camera image and detect whether there is a focus area triggered by the user;

[0121] S802. Based on the motion state and the difference between the current exposure index and the target exposure index, calculate the dynamic hold time, and only adjust the exposure if the dynamic hold time has not been exceeded and there is no user-triggered focus area.

[0122] S803. When adjusting exposure, perform the following steps: when brightening, determine the maximum adjustment step size based on the proportion of the dark area of ​​the camera image, or when darkening, determine the maximum adjustment step size based on the proportion of the bright area of ​​the camera image; wherein, the closer the current exposure index is to the target exposure index, the smaller the adjustment amount;

[0123] S804. Based on the determined maximum adjustment step size and the first convergence speed adjustment strategy after updating the first coefficient to the second coefficient, perform exposure adjustment; wherein the second coefficient is smaller than the first coefficient.

[0124] In practical applications, detecting whether a user-triggered focus area exists in the camera frame is usually achieved by listening to the user's interactive behavior on the device's touchscreen.

[0125] In some embodiments, when calculating the dynamic hold time, if the motion state is determined to be high-speed motion, the calculated dynamic hold time is lower so that the exposure can quickly follow the changes to prevent blurring. Conversely, if the motion state is determined to be static, the calculated dynamic hold time is higher.

[0126] Example formula for calculating dynamic hold time:

[0127]

[0128] This is the base hold time (e.g., the time corresponding to several frames, such as 5 frames, based on the frame rate setting); It is the difference between the current exposure index and the target exposure index; These are motion state quantities (such as the magnitude of motion vectors or the amplitude of optical flow calculated based on inter-frame difference); and These are weighting coefficients used to adjust the degree of influence of the difference and motion (usually set experimentally, such as...). =0.1, =0.05).

[0129] At the same time, calculate the absolute value of the difference between the current exposure index and the target exposure index. If the difference is large, it indicates an exposure error, and shorten the dynamic hold time. If the difference is small, extend the hold time to avoid unnecessary responses to brightness fluctuations that may be caused by noise.

[0130] In some embodiments, when brightening the image, the proportion of dark areas is analyzed, that is, the percentage of pixels with brightness below a certain threshold is calculated. If the proportion of dark areas is large, it indicates that the overall image is too dark, allowing a relatively large maximum adjustment step size to quickly brighten it; conversely, if the dark areas are small, a smaller step size is used for fine adjustment to avoid overexposure of areas that were originally bright. The logic for darkening is the opposite, limiting the step size based on the proportion of bright areas.

[0131] In some alternative implementations, the closer the current exposure index is to the target exposure index, the smaller the maximum adjustment step size will be. This is usually achieved through a function that is proportional to the difference, thereby ensuring that the exposure can converge smoothly and avoid oscillations around the target value.

[0132] For example, the formula for calculating the maximum adjustment step size when brightening is:

[0133]

[0134] in, This represents the proportion of dark areas (e.g., the percentage of all pixels with a pixel value below 50). It is the maximum allowable base step size (such as 10% of the exposure index). It is the dynamic range of the exposure index (such as the difference between the minimum and maximum exposure index). It is the difference between the current exposure index and the target exposure index.

[0135] For example, the formula for calculating the maximum adjustment step size when brightening is:

[0136]

[0137] in, This represents the proportion of the bright area (e.g., the percentage of pixels with a pixel value below 200); the meanings of other parameters are the same as in the previous formula.

[0138] For example, the first coefficient can be a weight value greater than 1, and the second coefficient can be a weight value less than 1. Optionally, both the first and second coefficients can be values ​​less than 1. Step S804 can refer to the first convergence speed adjustment strategy described above, which will not be elaborated further here.

[0139] The solution in this example optimizes the accuracy of exposure adjustment by introducing user interaction awareness and dynamic hold time mechanism, combined with adaptive step size control of the screen area ratio. This makes the exposure convergence process smoother and more controllable, and the brightness transition more natural and coherent.

[0140] As yet another example, the method also includes:

[0141] The exposure gain and exposure time are adjusted based on a smooth transition algorithm; the smooth transition algorithm includes a linear interpolation algorithm or an inertial filtering algorithm.

[0142] In this example, adjusting the exposure gain and exposure time based on a smooth transition algorithm can reduce flickering or sudden changes in image brightness caused by parameter jumps. In practice, after calculating the new target exposure gain and target exposure time, they are not immediately applied to the sensor. Instead, the smooth transition algorithm gradually transitions the values ​​from the current values ​​to the target values ​​over multiple frame periods.

[0143] For example, using a linear interpolation algorithm, the current exposure gain and exposure time are increased or decreased linearly and uniformly in fixed steps until the target value is reached. For instance, when adjusting from gain value A to B, the gain is changed by (BA) / 10 every frame over 10 frames, achieving a smooth change. Alternatively, using an inertial filtering algorithm, such as a first-order low-pass filter, simulates physical inertia. The adjustment step size depends not only on the difference between the target value and the current value but may also be influenced by historical adjustment speeds. This causes the parameters to accelerate in the initial stages of change and decelerate as they approach the target, resulting in a smoother transition curve and better suppression of high-frequency jitter.

[0144] In some alternative embodiments, in addition to exposure gain and exposure time, several other parameters in this scheme can also be adjusted based on a smooth transition algorithm. These include parameters such as target brightness value, metering weight position, exposure convergence speed, and frame rate.

[0145] The solution in this example introduces a smooth transition algorithm to gradually control key exposure parameters, achieving continuity and predictability of parameter changes. This reduces instantaneous disturbances during exposure switching and avoids abrupt flickering in the image.

[0146] As yet another example, the method also includes:

[0147] The camera image after exposure control is inspected. If the inspection fails, the parameter group corresponding to the current scene is updated until the inspection passes. The inspection includes at least one of the following: brightness inspection, dynamic range inspection, color saturation inspection, white balance inspection, flicker frequency and amplitude inspection, expert inspection, convergence speed inspection, convergence smoothness inspection, and anti-flicker capability inspection.

[0148] It should be noted that the scheme in this example is applied to the preparation or training phase of the exposure control method. A closed-loop testing and optimization process is used to pre-calibrate and determine the optimal parameter sets corresponding to different multi-factor triggering conditions. Specifically, candidate parameter sets are run on a controlled environment or a dataset covering a large number of typical scenes, and a series of automated image quality assessments are performed on the generated camera footage.

[0149] For example, brightness detection analyzes the overall average brightness or weighted average brightness of an image. The standard is that the brightness detection value must be within a preset ideal range to avoid underexposure or overexposure.

[0150] For example, dynamic range detection evaluates whether the two ends of the image brightness histogram, namely the darkest and brightest areas, still retain discernible details rather than being completely black or white. The passing standard is that the ratio of high and low light pixels does not exceed a threshold.

[0151] For example, color saturation detection calculates the average saturation of an image in a specific color space, with the standard being moderate saturation, avoiding pale or overly saturated colors.

[0152] For example, white balance detection analyzes the color difference in areas that should be gray in an image, and ensures that white objects are displayed correctly by setting the standard that the color difference is less than a perceptible threshold.

[0153] For example, flicker frequency and amplitude detection analyzes the periodic fluctuations in brightness in a video sequence caused by the asynchrony between the light source and the exposure time, with the standard being that the flicker amplitude is below the sensitivity threshold of the human eye.

[0154] For example, expert detection may introduce image quality assessment algorithms based on pre-trained models to score the overall aesthetics and noise levels of the image, with the standard being a score higher than a set threshold.

[0155] For example, convergence speed detection measures the number of frames it takes for the exposure index to stabilize from its initial value to the target value, with the convergence time meeting real-time requirements as a standard.

[0156] For example, the convergence smoothness test analyzes the derivative of brightness changes during the convergence process, and the standard is that the change curve is smooth without drastic jumps.

[0157] For example, flicker resistance testing is specifically conducted in a flickering light source environment to assess the stability of the output screen brightness. The passing standard is that the brightness variance is controlled at a low level.

[0158] The solution in this example is based on a closed-loop detection and iterative optimization mechanism that includes multi-dimensional image quality assessment. The parameter set is screened and fine-tuned during the technical preparation stage, which helps to improve the robustness and scene adaptability of the parameter set in practical applications.

[0159] The exposure control method provided in this application includes: extracting scene features of the current scene based on real-time image data acquired by a camera sensor; determining multi-factor triggering conditions corresponding to the current scene based on the scene features, and then determining a parameter set corresponding to the current scene to achieve camera exposure control based on the parameter set. The solution in this example, by fusing multi-dimensional scene features such as ambient light intensity, image overexposure, image content information, and motion state to establish a dynamic parameter set, can enhance adaptability to complex lighting conditions. Adjusting parameter sets such as metering weight position, exposure gain, exposure time, exposure convergence speed, and target brightness can improve the targeting and accuracy of adjustments, thereby improving the reliability of exposure control.

[0160] Figure 9 This is a schematic diagram of the exposure control device provided in the embodiments of this application, as shown below. Figure 9 As shown, the device includes:

[0161] The extraction module 91 is used to extract scene features of the current scene based on real-time image data collected by the camera sensor; the scene features include ambient light intensity, image overexposure, image content information, and motion state.

[0162] Module 92 determines the multi-factor triggering conditions corresponding to the current scene based on scene features. The multi-factor triggering conditions are a combination of the states of multiple scene features.

[0163] The control module 93 is used to determine the parameter group corresponding to the current scene according to the multi-factor triggering conditions, and to perform camera exposure control based on the parameter group so that the image brightness of the camera screen matches the lighting conditions of the current scene; wherein, the parameter group includes at least one of the following: metering weight position, exposure gain, exposure time, exposure convergence speed, and target brightness.

[0164] In one possible implementation, module 92 is specifically used for:

[0165] The first factor triggering condition is determined based on the ambient light intensity in the scene characteristics; wherein, the first factor triggering condition includes any one of: low light triggering, indoor triggering, and outdoor triggering;

[0166] The triggering condition for the second factor is determined based on the degree of overexposure in the scene features; the triggering condition for the second factor includes either highlight triggering or non-highlight triggering.

[0167] The triggering conditions for the third factor are determined based on the image content information in the scene features; among them, the triggering conditions for the third factor include any one of the following: non-face triggering, face with front lighting triggering, and face with backlighting triggering.

[0168] The triggering condition for the fourth factor is determined based on the motion state in the scene features; the triggering condition for the fourth factor includes either motion triggering or non-motion triggering.

[0169] The multi-factor triggering conditions are determined based on the first factor triggering condition, the second factor triggering condition, the third factor triggering condition, and the fourth factor triggering condition.

[0170] In one possible implementation, the control module 93 is specifically used for:

[0171] When the first factor triggering condition includes outdoor triggering and the third factor triggering condition includes face backlighting triggering, the metering weight position in the parameter group is set to the face region, and the exposure convergence speed is reduced from the first speed to the second speed.

[0172] When the first factor triggering condition includes outdoor triggering, the second factor triggering condition includes highlight triggering, and the third factor triggering condition includes non-face triggering, reduce the target brightness in the parameter group;

[0173] When the first factor triggering condition includes low light triggering or outdoor triggering, and the fourth factor triggering condition includes motion triggering, the upper limit of exposure time in the parameter group is set to the first threshold, and the upper limit of exposure gain in the parameter group is increased.

[0174] In one possible implementation, the control module 93 is further used for:

[0175] Gamma correction is performed on the camera image based on the first gamma curve;

[0176] Based on a local tone mapping algorithm, the brightness of the face area in the camera image is increased while the brightness of the background area is reduced.

[0177] Control module 93 is also used for:

[0178] Gamma correction is performed on the camera image based on the second gamma curve; the contrast of the second gamma curve is higher than that of the first gamma curve.

[0179] Based on a local tone mapping algorithm, the brightness of the central and dark areas of the camera image is increased.

[0180] In one possible implementation, the control module 93 is further used for:

[0181] The current exposure index is determined based on the current exposure gain and current exposure time, and the target exposure index is determined based on the target brightness;

[0182] Adjust the current exposure index according to either the first or second convergence speed adjustment strategy until the current exposure index is the target exposure index.

[0183] In one possible implementation, the control module 93 is specifically used for:

[0184] Calculate the first difference between the exposure index of the previous frame and the target exposure index, and the second difference between the exposure index of the previous n frames and the target exposure index;

[0185] When the first difference is equal to the second difference, the product of the first difference and the first coefficient is used as the adjustment step size in the current frame; where the first coefficient is used to adjust the convergence speed.

[0186] When the first difference and the second difference are not equal, and the first difference and the second difference have the same sign, the product of the difference with the smaller absolute value and the first coefficient is used as the adjustment step size in the current frame.

[0187] For the adjustment step size in the current frame, when the adjustment step size meets the first condition, the adjustment step size is updated to the basic adjustment step size; wherein, the first condition is that the adjustment step size is less than the basic adjustment step size, and the first difference and the second difference have the same sign;

[0188] When the adjustment step size does not meet the first condition, the adjustment step size is optimized: when the difference between the sum of the adjustment step size and the exposure index of the current frame and the target exposure index is less than the corresponding threshold, the exposure index of the current frame is directly adjusted to the target exposure index.

[0189] In one possible implementation, the control module 93 is specifically used for:

[0190] Acquire the motion state of the camera image and detect whether there is a focus area triggered by the user;

[0191] Based on the motion state and the difference between the current exposure index and the target exposure index, the dynamic hold time is calculated, and exposure adjustment is only performed when the dynamic hold time has not been exceeded and there is no user-triggered focus area.

[0192] When adjusting exposure, perform the following steps: when brightening, determine the maximum adjustment step size based on the proportion of the dark areas in the camera image, or when darkening, determine the maximum adjustment step size based on the proportion of the bright areas in the camera image; wherein, the closer the current exposure index is to the target exposure index, the smaller the adjustment amount;

[0193] Exposure adjustment is performed based on the determined maximum adjustment step size and the first convergence speed adjustment strategy after updating the first coefficient to the second coefficient; wherein the second coefficient is smaller than the first coefficient.

[0194] In one possible implementation, the control module 93 is further used for:

[0195] The exposure gain and exposure time are adjusted based on a smooth transition algorithm; the smooth transition algorithm includes a linear interpolation algorithm or an inertial filtering algorithm.

[0196] In one possible implementation, the determining module 92 is also used for:

[0197] The camera image after exposure control is inspected. If the inspection fails, the parameter group corresponding to the current scene is updated until the inspection passes. The inspection includes at least one of the following: brightness inspection, dynamic range inspection, color saturation inspection, white balance inspection, flicker frequency and amplitude inspection, expert inspection, convergence speed inspection, convergence smoothness inspection, and anti-flicker capability inspection.

[0198] The exposure control device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0199] This application also provides a camera that includes the exposure control device as described in any of the above embodiments.

[0200] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 10 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus.

[0201] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0202] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0203] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0204] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0205] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0206] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0207] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0208] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0209] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0210] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0211] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0212] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0213] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0214] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0215] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. An exposure control method characterized by comprising: The method comprises the following steps: extracting scene features of a current scene according to real-time image data collected by a camera sensor; wherein the scene features include ambient light intensity, picture overexposure degree, picture content information, and motion state; determining a first factor trigger condition according to the ambient light intensity in the scene features, a second factor trigger condition according to the picture overexposure degree in the scene features, a third factor trigger condition according to the picture content information in the scene features, and a fourth factor trigger condition according to the motion state in the scene features, and determining a multi-factor trigger condition according to the first factor trigger condition, the second factor trigger condition, the third factor trigger condition, and the fourth factor trigger condition; wherein the first factor trigger condition includes any one of dark light triggering, indoor triggering, and outdoor triggering; the second factor trigger condition includes any one of high light triggering and non-high light triggering; the third factor trigger condition includes any one of non-face triggering, face front light triggering, and face back light triggering; and the fourth factor trigger condition includes any one of motion triggering and non-motion triggering; determining a parameter group corresponding to the current scene according to the multi-factor trigger condition, and performing camera exposure control based on the parameter group to match the image brightness of a camera picture with the lighting condition of the current scene; wherein the parameter group includes at least one of the following: a light meter weight position, an exposure gain, an exposure time, an exposure convergence speed, and a target brightness; wherein when the first factor trigger condition includes outdoor triggering and the third factor trigger condition includes face back light triggering, the light meter weight position in the parameter group is set to a face area, and the exposure convergence speed is reduced from a first speed to a second speed; when the first factor trigger condition includes outdoor triggering, the second factor trigger condition includes high light triggering, and the third factor trigger condition includes non-face triggering, the target brightness in the parameter group is reduced; when the first factor trigger condition includes dark light triggering or outdoor triggering, and the fourth factor trigger condition includes motion triggering, the upper limit of the exposure time in the parameter group is set to a first threshold, and the upper limit threshold of the exposure gain in the parameter group is increased; and the first speed corresponds to a first convergence speed adjustment strategy; adjusting a current exposure index according to the first convergence speed adjustment strategy until the current exposure index is a target exposure index, including: calculating a first difference between the exposure index of a previous frame and the target exposure index, and a second difference between the average exposure index of the previous n frames and the target exposure index; when the first difference is equal to the second difference, the product of the first difference and a first coefficient is taken as the adjustment step length of the current frame; wherein the first coefficient is used to adjust the convergence speed. When the first difference value and the second difference value are not equal, and the first difference value and the second difference value have the same sign, a product of a difference value with a smaller absolute value and the first coefficient is taken as the adjustment step length under the current frame; when the first difference value and the second difference value are not equal, and the first difference value and the second difference value have different signs, a product of the first difference value and the first coefficient is taken as the adjustment step length under the current frame; For the adjustment step length under the current frame, when the adjustment step length satisfies a first condition, the adjustment step length is updated as a basic adjustment step length; wherein the first condition is that the adjustment step length is smaller than the basic adjustment step length, and the first difference value and the second difference value have the same sign; When the adjustment step length does not satisfy the first condition, the adjustment step length is optimized: when a sum of the adjustment step length and an exposure index under the current frame is smaller than a difference between the target exposure index and a corresponding threshold value, the exposure index of the current frame is directly adjusted to the target exposure index.

2. The method of claim 1, wherein, When the first factor trigger condition includes an outdoor trigger, the third factor trigger condition includes a face backlight trigger, and the determined parameter group is used for camera exposure control, the method further comprises: Gamma correcting the camera picture based on a first gamma curve; Improving the face region brightness and reducing the background region brightness of the camera picture based on a local tone mapping algorithm; When the first factor trigger condition includes an outdoor trigger, and the second factor trigger condition includes a highlight trigger, and the third factor trigger condition includes a non-face trigger, and the determined parameter group is used for camera exposure control, the method further comprises: Gamma correcting the camera picture based on a second gamma curve; wherein a contrast of the second gamma curve is higher than that of the first gamma curve; Improving the brightness of the middle part brightness region and the dark part brightness region of the camera picture based on a local tone mapping algorithm.

3. The method of claim 1, wherein, The second speed corresponds to a second convergence speed adjustment strategy; the method further comprises: Determining a current exposure index based on a current exposure gain and a current exposure time, and determining a target exposure index based on the target brightness; Adjusting the current exposure index according to the second convergence speed adjustment strategy until the current exposure index is the target exposure index.

4. The method of claim 3, wherein, Adjusting the current exposure index according to the second convergence speed adjustment strategy comprises: Detecting whether there is a user triggered focusing region in the camera picture; Calculating a dynamic holding time based on the motion state, a difference between the current exposure index and the target exposure index, and only when the dynamic holding time is not exceeded and there is no user triggered focusing region, exposure adjustment is performed; When exposure adjustment is performed, the following steps are executed: when brightening, a maximum adjustment step length is determined based on a proportion of a dark part region of the camera picture, or when dimming, a maximum adjustment step length is determined based on a proportion of a bright part region of the camera picture; wherein the closer the current exposure index is to the target exposure index, the smaller the maximum adjustment step length is. adjust exposure based on the determined maximum adjustment step and a first convergence speed adjustment strategy after updating the first coefficient to a second coefficient; wherein the second coefficient is smaller than the first coefficient.

5. The method of claim 1, wherein, The method further comprises: adjusting the exposure gain and the exposure time based on a smooth transition algorithm; wherein the smooth transition algorithm comprises a linear interpolation algorithm or an inertial filtering algorithm.

6. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: detecting a camera picture after camera exposure control, and if the detection fails, updating a parameter group corresponding to the current scene until the detection passes; wherein the detection comprises at least one of the following: brightness detection, dynamic range detection, color saturation detection, white balance detection, flicker frequency and amplitude detection, expert detection, convergence speed detection, convergence smoothness detection, and anti-flicker capability detection.

7. An exposure control device characterized by comprising: comprises: an extraction module configured to extract scene features of a current scene according to real-time image data collected by a camera sensor; wherein the scene features comprise ambient light intensity, picture overexposure degree, picture content information, and motion state; a determination module configured to determine a first factor trigger condition according to the ambient light intensity in the scene features, a second factor trigger condition according to the picture overexposure degree in the scene features, a third factor trigger condition according to the picture content information in the scene features, a fourth factor trigger condition according to the motion state in the scene features, and a multi-factor trigger condition according to the first factor trigger condition, the second factor trigger condition, the third factor trigger condition, and the fourth factor trigger condition; wherein the first factor trigger condition comprises any one of the following: dark light trigger, indoor trigger, and outdoor trigger; the second factor trigger condition comprises any one of the following: highlight trigger and non-highlight trigger; the third factor trigger condition comprises any one of the following: non-face trigger, face front light trigger, and face back light trigger; and the fourth factor trigger condition comprises any one of the following: motion trigger and non-motion trigger. The control module is configured to determine a parameter group corresponding to a current scene according to the multi-factor trigger condition, and perform camera exposure control based on the parameter group to match the image brightness of a camera picture with the lighting condition of the current scene; wherein the parameter group comprises at least one of the following: a metering weight position, an exposure gain, an exposure time, an exposure convergence speed, and a target brightness; when the first factor trigger condition comprises an outdoor trigger, and the third factor trigger condition comprises a face backlight trigger, the metering weight position in the parameter group is set to a face area, and the exposure convergence speed is reduced from a first speed to a second speed; when the first factor trigger condition comprises an outdoor trigger, the second factor trigger condition comprises a highlight trigger, and the third factor trigger condition comprises a non-face trigger, the target brightness in the parameter group is reduced; when the first factor trigger condition comprises a dark light trigger or an outdoor trigger, and the fourth factor trigger condition comprises a motion trigger, the upper limit of the exposure time in the parameter group is set to a first threshold, and the upper limit threshold of the exposure gain in the parameter group is increased; the first speed corresponds to a first convergence speed adjustment strategy. According to the first convergence speed adjustment strategy, the current exposure index is adjusted until the current exposure index is a target exposure index, comprising: calculating a first difference value between an exposure index under a previous frame and the target exposure index, and a second difference value between an average exposure index under n previous frames and the target exposure index; when the first difference value is equal to the second difference value, a product of the first difference value and a first coefficient is taken as an adjustment step length under a current frame; wherein the first coefficient is used to adjust the convergence speed; when the first difference value is not equal to the second difference value, and the signs of the first difference value and the second difference value are the same, a product of the difference value with a smaller absolute value and the first coefficient is taken as the adjustment step length under the current frame; when the first difference value is not equal to the second difference value, and the signs of the first difference value and the second difference value are not the same, a product of the first difference value and the first coefficient is taken as the adjustment step length under the current frame; for the adjustment step length under the current frame, when the adjustment step length satisfies a first condition, the adjustment step length is updated to a basic adjustment step length; wherein the first condition is that the adjustment step length is smaller than the basic adjustment step length, and the signs of the first difference value and the second difference value are the same; when the adjustment step length does not satisfy the first condition, the adjustment step length is optimized: when the sum of the adjustment step length and an exposure index under a current frame is smaller than a corresponding threshold value than the difference between the target exposure index, the exposure index of the current frame is directly adjusted to the target exposure index.

8. A camera characterized by, The camera comprises the exposure control device of claim 7.

9. An electronic device, comprising: comprising: a memory, a processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory, so that the processor executes the method of any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer-executable instructions which, when executed by a processor, implement the method of any one of claims 1-6.

11. A computer program product, characterised in that, A computer program which, when executed by a processor, implements the method of any one of claims 1-6.

Images