Exposure adjustment method and related device, camera and storage medium

Abstract

The invention discloses an exposure adjustment method, a related device, a camera and a storage medium, and the method comprises the steps: carrying out the detection based on a current shot image of the camera, and responding to a detection result, representing that a first part and a second part appear in the current shot image, and enabling the first part to be located in a preset recognition region; obtaining a first weight factor based on the detection confidence of the first part and the ambient light intensity of the current shot image, and obtaining a second weight factor based on the detection confidence and the part state score of the second part, respectively weighting the first brightness of the first part and the second brightness of the second part in the current shot image based on the first weight factor and the second weight factor to obtain a first exposure parameter; and controlling the camera to perform exposure adjustment based on the first exposure parameter. According to the scheme, the compatibility of exposure adjustment can be improved, especially under the condition that two biological parts exist.

Description

Technical Field

[0001] This application relates to the field of camera control technology, and in particular to an exposure adjustment method and related apparatus, camera and storage medium. Background Technology

[0002] Identity recognition systems have been widely adopted in applications such as smart building access control. Currently, identity recognition systems primarily rely on the detection and identification of biometric features.

[0003] Existing technologies generally employ either single or two biometric identification methods. However, the former is susceptible to interference from factors such as lighting, angle, or occlusion, affecting the accuracy of identification. While the latter has made progress in combating interference, existing exposure strategies struggle to accommodate simultaneous identification of two biometric sites. Therefore, improving the compatibility of exposure adjustments, especially when two biometric sites are involved, has become a pressing issue. Summary of the Invention

[0004] The main technical problem addressed by this application is to provide an exposure adjustment method and related apparatus, camera, and storage medium that can improve the compatibility of exposure adjustment, especially in the presence of two biological sites.

[0005] To address the aforementioned technical problems, a first aspect of this application provides an exposure adjustment method, comprising: performing detection based on a currently captured image from a camera to obtain a detection result; wherein the detection result includes: whether a first part and a second part of a target object appear in the currently captured image, and whether the first part is located within a preset recognition area when it appears in the currently captured image, wherein the first part distinguishes different target objects based on internal physiological characteristics, and the second part distinguishes different target objects based on external morphological characteristics; in response to the detection result indicating that both the first part and the second part appear in the currently captured image and the first part is located within the preset recognition area, obtaining a first weighting factor based on the detection confidence of the first part and the ambient light intensity of the currently captured image, obtaining a second weighting factor based on the detection confidence and the part status score of the second part, and weighting the first brightness of the first part and the second brightness of the second part in the currently captured image based on the first weighting factor and the second weighting factor respectively to obtain a first exposure parameter; and controlling the camera to perform exposure adjustment based on the first exposure parameter.

[0006] To address the aforementioned technical problems, a second aspect of this application provides an exposure adjustment device, comprising: an image detection module, a parameter determination module, and a camera control module. The image detection module is used to perform detection based on a currently captured image from a camera to obtain a detection result; wherein the detection result includes: whether a first part and a second part of a target object appear in the currently captured image, and whether the first part is located within a preset recognition area when it appears in the currently captured image, wherein the first part distinguishes different target objects based on internal physiological characteristics, and the second part distinguishes different target objects based on external morphological characteristics; the parameter determination module is used to, in response to the detection result indicating that both the first part and the second part appear in the currently captured image and the first part is located within the preset recognition area, obtain a first weighting factor based on the detection confidence of the first part and the ambient light intensity of the currently captured image, obtain a second weighting factor based on the detection confidence and the part status score of the second part, and weight the first brightness of the first part and the second brightness of the second part in the currently captured image based on the first weighting factor and the second weighting factor respectively to obtain a first exposure parameter; the camera control module is used to control the camera to perform exposure adjustment based on the first exposure parameter.

[0007] To address the aforementioned technical problems, a third aspect of this application provides an electronic device comprising at least a memory and a processor coupled to each other, wherein the memory stores at least program instructions, and the processor executes the program instructions to implement the exposure adjustment method described in the first aspect.

[0008] To address the aforementioned technical problems, a fourth aspect of this application provides a camera that includes at least the electronic device described in the third aspect and a photosensitive device coupled to the electronic device.

[0009] To address the aforementioned technical problems, the fifth aspect of this application provides a computer-readable storage medium storing program instructions executable by a processor, the program instructions being used to implement the exposure adjustment method of the first aspect described above.

[0010] The above scheme performs detection based on the current captured image of the camera to obtain detection results. The detection results include: whether the first part and the second part of the target object appear in the current captured image, and whether the first part is located in a preset recognition area when it appears in the current captured image. The first part distinguishes different target objects based on internal physiological characteristics, and the second part distinguishes different target objects based on external morphological characteristics. In response to the detection result indicating that both the first part and the second part appear in the current captured image and the first part is located in the preset recognition area, a first weighting factor is obtained based on the detection confidence of the first part and the ambient light intensity of the current captured image. A second weighting factor is obtained based on the detection confidence and the part status score of the second part. The first brightness of the first part and the second brightness of the second part in the current captured image are weighted based on the first weighting factor and the second weighting factor, respectively, to obtain a first exposure parameter. Then, based on the first exposure parameter, the camera is controlled to adjust the exposure. Since, when both the first and second biological sites are detected and the first site is located within the preset recognition area, a first weighting factor for the first site's first brightness is determined by referring to the detection confidence level and ambient light intensity, and a second weighting factor for the second site's second brightness is determined by referring to the detection confidence level and site state score, this helps to fully consider different factors to determine the weighting factors for different biological sites. Therefore, the first exposure parameters are determined accordingly, and exposure control is performed, which can satisfy the imaging requirements of both the first and second sites as much as possible. Thus, the compatibility of exposure adjustment is improved, especially when two biological sites are present. Attached Figure Description

[0011] Figure 1 This is a flowchart illustrating an embodiment of the exposure adjustment method of this application; Figure 2 This is a flowchart illustrating an embodiment of the adaptive image parameter configuration switching method of this application; Figure 3 This is a schematic flowchart of an embodiment of controlling camera exposure adjustment according to this application; Figure 4 This is a schematic diagram of the framework of an embodiment of the exposure adjustment device of this application; Figure 5 This is a schematic diagram of the framework of an embodiment of the electronic device of this application; Figure 6 This is a schematic diagram of the frame of an embodiment of the camera of this application; Figure 7 This is a schematic diagram of a framework of an embodiment of the computer-readable storage medium of this application. Detailed Implementation

[0012] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0013] In the following description, specific details such as particular system architectures, interfaces, and technologies are presented for illustrative purposes rather than for limiting purposes, in order to provide a thorough understanding of this application.

[0014] In this paper, the terms "system" and "network" are often used interchangeably. The term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the slash " / " generally indicates that the preceding and following related objects have an "or" relationship. Furthermore, "many" in this paper indicates two or more objects.

[0015] Please see Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the exposure adjustment method of this application. Specifically, it may include the following steps: Step S11: Perform detection based on the current image captured by the camera to obtain the detection result.

[0016] In this embodiment, the detection result includes: whether the first part and the second part of the target object appear in the currently captured image, and whether the first part is located within a preset recognition area when it appears in the currently captured image. That is, when the camera detects the currently captured image, the detection result may be that only the first part appears in the current captured image, only the second part appears in the current captured image, or both the first and second parts appear in the current captured image. Of course, during this process, when the first part appears in the current captured image, it may or may not be located within the preset recognition area. It should be noted that the camera is in normal detection mode, and the image uses a global exposure strategy. As a possible implementation example, to facilitate manual configuration of the exposure mode by the user, a first part exposure switch and a second part exposure switch can be set on the web or other interactive end side to ensure the principle of first part priority. Regardless of whether the second part exposure is enabled, as long as the first part is detected entering the preset recognition area, the camera's exposure mode switches from the global exposure strategy to exposure based on the first part area. Furthermore, by way of example, the process steps in the embodiments of this disclosure can be executed by electronic devices with video recording functions, such as cameras. Specifically, they can be executed by electronic devices with video recording functions, such as cameras, that integrate memory and processor. For details, please refer to the following disclosed embodiments of electronic devices and cameras, which will not be repeated here.

[0017] In an implementation scenario, a preset recognition region is a designated area that allows the camera to clearly identify the target object. This preset recognition region can be manually set, for example, in a static scene, the user can pre-define a fixed area in the camera's view (such as the area of ​​a door frame) and detect the target object only within this area; alternatively, it can be located using deep learning methods, such as using visual saliency algorithms to locate areas that attract attention. Other methods for setting preset recognition regions will not be listed here.

[0018] In one implementation scenario, to detect whether the first part is located within a preset recognition area, an object detection algorithm can be used to perform real-time detection on the currently captured image of the camera. There are many types of object detection algorithms. For example, traditional object detection algorithms rely on feature extractors and machine learning classifiers, such as the Haar feature extractor combined with the Adaboost algorithm; and deep learning-based algorithms such as Faster R-CNN and the YOLO series. Here, no specific algorithm is limited to object detection. As one possible implementation, based on the monocular intrinsic parameter data (such as focal length, imaging origin, distortion coefficients) obtained from dual-target calibration and the relative positional relationship between the two cameras (such as rotation matrix and translation vector), distortion and row alignment are performed on the left and right views. This ensures that the imaging origin coordinates of the left and right views are consistent, the optical axes of the two cameras are parallel, the left and right imaging planes are coplanar, and the epipolar lines are aligned. This ensures that a point in one image has the same row number as its corresponding point in another image. Matching corresponding image points of the same scene in the left and right views yields a disparity map. After obtaining the disparity data, depth information can be calculated using a formula. The method for calculating depth information can be expressed as: depth=(f*baseline) / disparity In the above formula, depth represents depth information; disparity represents parallax; baseline represents the center distance between the two cameras; and f represents the focal length. After obtaining the depth information, the physical distance from the first part to the camera can be determined. Based on this physical distance, it can be determined whether the first part is within the preset recognition area.

[0019] In one implementation scenario, the first part distinguishes different target objects based on their internal physiological characteristics. For example, the first part may include the palm, and the internal physiological characteristics may at least include the veins in the palm, etc. There is no limitation on the first part of the target object.

[0020] In one implementation scenario, the second part distinguishes different target objects based on their external morphological features, such as the face, iris, or retina. Here, the second part of the target object is not limited. As a possible implementation example, the second part can be the face, meaning it can include the eyes. It should be noted that before imaging the first and second parts, a warning can be issued in advance near the imaging range using prominent signage, voice prompts, or other means to inform the target object and other objects that identity verification is being performed using camera recognition or similar methods at their current location, and that video recording will be conducted within the imaging range. If there is no need to enter the current location, please avoid this imaging range; if you insist on entering this imaging range, it will be considered as authorizing video recording.

[0021] Step S12: In response to the detection result indicating that both the first part and the second part appear in the current captured image and the first part is located in the preset recognition area, a first weighting factor is obtained based on the detection confidence of the first part and the ambient light intensity of the current captured image, and a second weighting factor is obtained based on the detection confidence and the part status score of the second part. The first brightness of the first part and the second brightness of the second part in the current captured image are weighted based on the first weighting factor and the second weighting factor, respectively, to obtain the first exposure parameter.

[0022] In one implementation scenario, to obtain the detection confidence score, target detection can be performed based on the currently captured image to obtain the target region and confidence score of the first part in the currently captured image; feature extraction can be performed on the image data of the target region in the currently captured image to obtain the first image feature of the first part; classification prediction can be performed based on the first image feature to obtain the predicted probability value of the presence of the first part in the target region; the detection confidence score and the predicted probability value are fused to obtain the detection confidence score. As a possible implementation example, the detection confidence score can be obtained by weighting the confidence score and the predicted probability value. For ease of description, the calculation method of the detection confidence score can be expressed as: S_palm = w_1 * detection_confidence + w_2 * classification_probability In the above formula, S_palm represents the detection confidence of the first part, w_1 and w_2 represent the weight values ​​of the confidence score and the predicted probability value, respectively, and their sum is 1. detection_confidence represents the confidence score, and classification_probability represents the predicted probability value. The above method first performs target detection based on the currently captured image to obtain the target region of the first part in the current captured image and its confidence score. Second, based on the image data of the target region in the current captured image, feature extraction is performed to obtain the first image feature of the first part. Then, classification prediction is performed based on the first image feature to obtain the predicted probability value of the presence of the first part in the target region. Finally, the confidence score and the predicted probability value are fused to obtain the detection confidence. Because this method of calculating the detection confidence considers the weighted relationship between the confidence score and the predicted probability value, the accuracy of the detection confidence can be improved by properly configuring the weight values ​​between the confidence score and the predicted probability value. Of course, the above implementation method is only one possible way to obtain the detection confidence in practical applications. Other possible ways to obtain the detection confidence are not limited here. For example, when the accuracy requirements of the detection confidence are relatively relaxed, the confidence score obtained by performing target detection on the currently captured image can be directly used as the detection confidence. Other possible methods will not be listed one by one here.

[0023] In a specific implementation scenario, the confidence score can be obtained by performing target detection on the currently captured image, and at the same time, the position of the first part in the currently captured image can also be obtained. The confidence score represents the probability that the detected target object part is the first part.

[0024] In a specific real-time scenario, the predicted probability value can be obtained by classifying and predicting the first image features of the first part. For example, after obtaining the first image features of the first part, the image features of the first part are classified and predicted. That is, the image features of the first part are input into a classifier, which includes but is not limited to support vector machines, neural networks, etc., and then a predicted probability value is obtained. This predicted probability value represents the probability that the currently captured image is the first part.

[0025] In one implementation scenario, ambient light intensity can be obtained by mapping scene brightness values, which in turn can be determined by the image brightness value of the currently captured image and the shutter speed and gain value of the camera when capturing the image. For ease of description, ambient light intensity can be denoted as Lux. The mapping coefficient Ratio between the actual illuminance and brightness values ​​under a standard environment can be measured using a lux meter. Therefore, the ambient light intensity Lux can be expressed as: Lux = Lumia * Ratio In the above formula, Lux refers to ambient light intensity, and Lumia refers to scene brightness value. As a possible implementation example, the scene brightness value can be calculated as follows: Lumia = sht*gain*1024 / ev In the above formula, `sht` refers to the shutter speed, measured in milliseconds; `gain` refers to the gain value, measured in multiples; and `ev` refers to the brightness value of the currently captured image. Furthermore, as mentioned earlier, this represents a mapping relationship, expressed as follows: Ratio=Lux_standard / Lumia_standard In the above formula, Lux_standard refers to the actual illuminance value measured by a lux meter under a standard environment; Lumia_standard refers to the luminance value under a standard environment. For example, several sets of actual illuminance and luminance values ​​under a standard environment can be obtained in advance to fit the above mapping relationship. In this method, the ambient light intensity is obtained by mapping the scene luminance value, which is determined by the image luminance value of the currently captured image and the shutter speed and gain value of the camera when capturing the currently captured image. Because the ambient light intensity is obtained by mapping, the problem of excessive calculation error due to differences in light source type can be avoided as much as possible.

[0026] In one implementation scenario, the first weighting factor can be calculated from the detection confidence and the ambient light intensity of the currently captured image. Specifically, the first weighting factor can be positively correlated with the detection confidence and negatively correlated with the ambient light intensity. As a possible implementation example, the calculation of the first weighting factor q can be expressed as follows: q = 0.9S_palm - 0.1*Lux In the above formula, S_palm represents the detection confidence level, and Lux ​​represents the ambient light intensity. Of course, the above example is merely one possible calculation method for the first weighting factor in practical applications; other possible calculation methods are not limited here, nor will they be listed one by one. In the above method, the first weighting factor can be calculated from the detection confidence level and the ambient light intensity of the currently captured image. The first weighting factor can also be positively correlated with the detection confidence level and negatively correlated with the ambient light intensity. Since the first weighting factor dynamically allocates weights based on the detection confidence level and the ambient light intensity of the currently captured image, the reliability of the first weighting factor can be improved.

[0027] In one implementation scenario, as mentioned earlier, the second part can be the face, which includes the eyes. To obtain a part status score, keypoint detection can be performed on the currently captured image to obtain several eye keypoints. Based on these keypoints, the eye opening value is calculated, and feature extraction is performed on the image data surrounding these keypoints in the currently captured image to obtain second image features. These second image features include at least one of eye texture features and eye color features. Finally, a score prediction is performed based on the eye opening value and the second image features to obtain the part status score. This method first performs keypoint detection on the currently captured image to obtain several eye keypoints. Second, based on these keypoints, the eye opening value is calculated. Then, feature extraction is performed on the image data surrounding these keypoints in the currently captured image to obtain second image features, which include at least one of eye texture features and eye color features. Finally, a score prediction is performed based on the eye opening value and the second image features to obtain the part status score. By considering multiple dimensions such as eye opening value and second image features, the accuracy and scene adaptability of the part status score can be significantly improved. Of course, the above example is only one possible implementation method for obtaining part status scores in practical applications. Other possible implementation methods are not limited here. For example, the second part can also be a part other than the face. Other possible acquisition methods will not be listed one by one here.

[0028] In a specific implementation scenario, key points can be detected in the currently captured image based on machine learning algorithms such as those in the Dlib machine vision library and deep learning algorithms such as MTCNN (Multi-task Cascaded Convolutional Networks) to obtain several key points for the eyes. The algorithms for detecting key points for the eyes will not be listed here.

[0029] In a specific implementation scenario, after the key points of the eyes are detected by the key point detection algorithm, the distance between the upper and lower eyelids can be calculated based on the key points of the eyes to obtain the eye opening value.

[0030] In a specific implementation scenario, after calculating the eye opening value and extracting the second image features, a scoring prediction model can be used to predict the score of the eye opening value and the second image features, thereby obtaining a site status score. It should be noted that the scoring model used for score prediction includes, but is not limited to, regression models and neural networks. For example, the larger the eye opening value, the higher the E value, indicating a better second site status.

[0031] In one implementation scenario, the second weighting factor is obtained from the detection confidence and the location score of the second site. Specifically, the second weighting factor can be negatively correlated with the detection confidence and positively correlated with the location status score. For example, the calculation method of the second weighting factor p can be expressed as: p = 0.7*(1 - S_palm) + 0.3E In the above formula, S_palm represents the detection confidence of the first part, and E represents the part status score of the second part. Of course, the above example is only one possible calculation method for the second weighting factor in practical applications; other possible calculation methods are not limited here, nor will they be listed one by one. In the above method, the second weighting factor can be obtained from the detection confidence and the part score of the second part. The second weighting factor can also be negatively correlated with the detection confidence and positively correlated with the part status score. Since the second weighting factor dynamically allocates weights based on the detection confidence and the part score of the second part, the reliability of the second weighting factor can be improved.

[0032] In one implementation scenario, the first exposure parameter can be obtained by weighting the first brightness of the first part and the second brightness of the second part in the currently captured image using a weighting function based on the first weighting factor and the second weighting factor, respectively. The weighting function of the first exposure parameter Y_final can be expressed as: Y_final = pY_face + qY_palm In the above formula, Y_palm is the first brightness of the first part in the currently captured image, q is the first weighting factor, Y_face is the second brightness of the second part in the currently captured image, and p is the second weighting factor.

[0033] Step S13: Based on the first exposure parameter, control the camera to adjust the exposure.

[0034] In one implementation scenario, as a possible approach, after calculating the first exposure parameter, the camera can be controlled to adjust the exposure based on the first exposure parameter. Please refer to [reference needed]. Figure 2 , Figure 2 This is a flowchart illustrating an embodiment of the adaptive image parameter configuration switching method of this application. Figure 2 The adaptive dimming strategies for the first and second parts are demonstrated. Of course... Figure 2The example shown is merely one possible case in practical application; other possible scenarios will not be illustrated here. Alternatively, as another possible implementation, when the detection result indicates that both the first and second parts appear in the currently captured image and the first part is located within a preset recognition area, before controlling the camera to adjust the exposure based on the first exposure parameter, a fifth exposure parameter can be obtained by predicting the first brightness of the first part to prioritize imaging the first part. After adjusting the exposure based on the fifth exposure parameter, at least one of the following—ambient light intensity, detection confidence, part status score, first brightness, and second brightness—is updated (e.g., only one, any two, or more than one can be updated). It should be noted that the update process can be referred to the aforementioned acquisition process, which will not be repeated here. Based on this, the step of obtaining a first weighting factor based on the detection confidence of the first part and the ambient light intensity of the currently captured image can be performed to obtain the first exposure parameter; then, based on the first exposure parameter, the camera is controlled to adjust the exposure of the second part. The above method first adjusts the camera's exposure based on the initial exposure parameters. After ensuring the first part is clearly visible, the camera then adjusts the exposure of the second part appropriately to make it as identifiable as possible. This dimming method prioritizes making the first part clear and identifiable before making targeted exposure adjustments to the second part, which helps improve the accuracy of biometric identification.

[0035] It should be noted that although the above only discloses the exposure adjustment method when the detection result indicates that both the first and second parts appear in the currently captured image and the first part is located in the preset recognition area, in other possible situations (e.g., when the detection result indicates that only the second part appears in the currently captured image), a pre-configured exposure mode (e.g., global exposure, or other configurations) can be used, or different exposure strategies can be adopted depending on the situation. The exposure adjustment method for other situations is not limited here. The following describes the different exposure strategies adopted for different situations. Of course, the following description is only one possible implementation example in practical applications and is not limited to this. Other possible implementation methods will not be listed here.

[0036] In one implementation scenario, when the detection result indicates that only the second part appears in the currently captured image, a second exposure parameter for prioritizing the imaging of the second part can be obtained based on the second brightness of the second part. This second exposure parameter is obtained by mapping the second brightness of the second part to the optimal exposure parameter under different lighting conditions. Then, based on the second exposure parameter, the camera's exposure is adjusted. For example, if the second part is a face, exposure is prioritized based on the brightness of the face area. The face brightness is mapped according to the relationship between facial image features under different lighting conditions and the optimal exposure parameter to obtain the exposure parameters for prioritizing the imaging of the face. Then, based on the face's exposure parameters, the camera's exposure is adjusted to ensure the face area is clearly identifiable. This method, by mapping the second part to the second brightness, obtains the second exposure parameter for prioritizing the imaging of the second part. The second exposure parameter is obtained by mapping the second brightness of the second part to the optimal exposure parameter under different lighting conditions, and then the camera's exposure is adjusted based on the second exposure parameter. This method of mapping the second part to the optimal exposure parameter under different lighting conditions results in higher accuracy for the second exposure parameter.

[0037] In one implementation scenario, when the detection result indicates that only the first part appears in the currently captured image, it can be determined whether the first part is located within a preset recognition area based on the detection result. If the first part is not located within the preset recognition area, a third exposure parameter can be obtained based on global exposure, and the camera's exposure can be adjusted based on this third exposure parameter. If the first part is located within the preset recognition area, a fourth exposure parameter can be obtained by predicting the first brightness of the first part and the first image feature of the first part in the currently captured image based on the exposure parameter model of the first part, and the camera's exposure can be adjusted based on this fourth exposure parameter. The exposure parameter model is trained based on the relationship between the first part and the optimal exposure parameter under different lighting conditions and part features. In other words, when the first part appears within the camera's detection range, it can be further determined whether the first part is within the camera's preset recognition area, and different exposure adjustment strategies can be applied to different situations. This method, by determining whether the first part is within the camera's detection range and applying different exposure strategies accordingly, effectively improves the efficiency of exposure adjustment.

[0038] In a specific implementation scenario, when the first part is not located within the preset recognition area, the camera can employ a global exposure strategy to obtain a third exposure parameter, and then adjust the camera's exposure based on this parameter. In other words, when the first part appears within the camera's detection range but is not within its preset recognition area, the camera maintains global exposure mode and continues to perform exposure detection on the target object. For example, if the first part includes a hand, and the hand appears within the camera's detection range but is not within the preset recognition area, the camera maintains global exposure mode.

[0039] In a specific implementation scenario, when the first part is located within a preset recognition area, as mentioned earlier, an adaptive image parameter configuration switching is employed. Based on the exposure parameter model of the first part, the first brightness of the first part and the first image features of the first part in the currently captured image are predicted to obtain a fourth exposure parameter. Further, based on the fourth exposure parameter, the camera is controlled to adjust the exposure. The exposure parameter model is trained by analyzing the relationship between the first part and the optimal exposure parameter under different lighting conditions and part features. Taking a hand as an example, when the hand appears within the camera's detection range and is located within the preset recognition area, an adaptive image parameter configuration switching is employed. Based on the hand's exposure parameter model, the brightness of the hand area and the image features of the hand are predicted to obtain the current exposure parameter of the hand. Based on the hand's exposure parameter, the camera is controlled to adjust the exposure. Furthermore, during the exposure parameter adjustment process, near-infrared light can be used to illuminate the hand, and the ISP (Image Signal Processor) parameters can be adjusted to highlight the palm veins as much as possible.

[0040] In one implementation scenario, for all the above possible situations, as long as the detection result includes the first part appearing in the currently captured image and the first part being located in the preset recognition area, the current shooting scene of the camera can be further determined based on the ambient light intensity; based on the current shooting scene, the current exposure parameters of the camera can be adaptively adjusted.

[0041] In a specific implementation scenario, as mentioned earlier, before adaptively adjusting the camera's current exposure parameters, the ambient light intensity for target detection is determined first, i.e., the ambient brightness. Ambient brightness can be categorized into three cases: ambient brightness Lux is less than the lux_min threshold (which can be considered a nighttime scene), ambient brightness Lux is greater than the lux_max threshold (which can be considered a wide dynamic range scene), and ambient brightness Lux is between lux_min and lux_max (which can be considered a daytime scene).

[0042] In a specific implementation scenario, please refer to the relevant documents. Figure 3 , Figure 3 This is a schematic flowchart illustrating an embodiment of controlling camera exposure adjustment according to this application. Figure 3 As shown, when the ambient brightness (Lux) is less than the lux_min threshold, it is judged as a night scene, and a nighttime linear configuration can be used. For example, the current exposure parameters can be adjusted as follows: reduce the base brightness, adjust the gamma coefficient, and adjust the infrared lights to reduce the surface brightness of the first part. Specifically, it is recommended to appropriately reduce the base brightness by 20%-30%, adjust the gamma coefficient to 1.0, and improve the sharpness by 10%-20%. Brightness reduction can be achieved, and the infrared lights can be automatically adjusted to reduce the surface brightness of the first part, making the internal feature information more clearly presented.

[0043] In a specific implementation scenario, when the ambient brightness (Lux) exceeds the lux_max threshold (i.e., the ambient brightness is relatively bright, and the dynamic range (the difference between the brightest and darkest areas in the environment) is large (dynamic range greater than wdr_thr0), it can be identified as a wide dynamic range (WDR) scene. In this case, a WDR configuration can be adopted. For example, the current exposure parameters can be adjusted as follows: increase the base brightness, adjust the gamma coefficient, increase the noise reduction parameters, enable the WDR module to set the WDR intensity parameters, and increase the infrared illumination intensity to enhance the surface brightness of the first area. For instance, one could appropriately increase the base brightness by 20%-30%, adjust the gamma value to 1.0, increase the noise reduction parameters by 10%-20%, enable the WDR module, and set the WDR intensity to 30%. In a WDR scene, the main concern is preventing the first area from being too dark in backlit conditions; therefore, it is necessary to increase the intensity of the infrared lights to improve the brightness of the first area.

[0044] In a specific implementation scenario, when the ambient brightness (Lux) is between lux_min and lux_max, and the dynamic range is small (less than wdr_thr0), it can be determined to be a daytime scene. In this case, a daytime linear configuration can be used. For example, the current exposure parameters can be adjusted as follows: reduce the base brightness, adjust the gamma coefficient, and keep other parameters unchanged. For instance, the base brightness can be appropriately reduced by 20%-30%, the gamma coefficient adjusted to 1.0, and other parameters kept unchanged. This is generally for indoor scenes where the base brightness value is guaranteed.

[0045] In one implementation scenario, the camera can be configured with a polling function for the target to be detected, setting a certain time interval for polling and identifying the target. For example, a polling frequency of 1 second can be set to ensure that the target to be detected is always within the recognition time. The polling frequency is not limited here.

[0046] It should be noted that the above examples are merely possible implementation examples of exposure adjustment methods. Other possible methods are not limited here, nor will they be listed one by one.

[0047] The above scheme performs detection based on the current captured image of the camera to obtain detection results. The detection results include: whether the first part and the second part of the target object appear in the current captured image, and whether the first part is located in a preset recognition area when it appears in the current captured image. The first part distinguishes different target objects based on internal physiological characteristics, and the second part distinguishes different target objects based on external morphological characteristics. In response to the detection result indicating that both the first part and the second part appear in the current captured image and the first part is located in the preset recognition area, a first weighting factor is obtained based on the detection confidence of the first part and the ambient light intensity of the current captured image. A second weighting factor is obtained based on the detection confidence and the part status score of the second part. The first brightness of the first part and the second brightness of the second part in the current captured image are weighted based on the first weighting factor and the second weighting factor, respectively, to obtain a first exposure parameter. Then, based on the first exposure parameter, the camera is controlled to adjust the exposure. Since, when both the first and second biological sites are detected and the first site is located within the preset recognition area, a first weighting factor for the first site's first brightness is determined by referring to the detection confidence level and ambient light intensity, and a second weighting factor for the second site's second brightness is determined by referring to the detection confidence level and site state score, this helps to fully consider different factors to determine the weighting factors for different biological sites. Therefore, the first exposure parameters are determined accordingly, and exposure control is performed to meet the imaging requirements of both the first and second sites as much as possible. Thus, the compatibility of exposure adjustment is improved, especially when two biological sites are present.

[0048] Please see Figure 4 , Figure 4This is a schematic diagram of an embodiment of the exposure adjustment device of this application. The exposure adjustment device 40 includes an image detection module 41, used to perform detection based on the currently captured image of the camera to obtain a detection result; wherein, the detection result includes: whether the first part and the second part of the target object appear in the currently captured image, and whether the first part is located in a preset recognition area when the first part appears in the currently captured image, the first part distinguishes different target objects by internal physiological characteristics, and the second part distinguishes different target objects by external morphological characteristics; the exposure adjustment device 40 also includes a parameter determination module 42, used to, in response to the detection result indicating that both the first part and the second part appear in the currently captured image and the first part is located in the preset recognition area, obtain a first weighting factor based on the detection confidence of the first part and the ambient light intensity of the currently captured image, and obtain a second weighting factor based on the detection confidence and the part status score of the second part, and weight the first brightness of the first part and the second brightness of the second part in the currently captured image based on the first weighting factor and the second weighting factor respectively to obtain a first exposure parameter; the exposure adjustment device 40 also includes a camera control module 43, used to control the camera to perform exposure adjustment based on the first exposure parameter.

[0049] In the above scheme, the exposure adjustment device 40 performs detection based on the current captured image of the camera to obtain detection results. The detection results include: whether the first part and the second part of the target object appear in the current captured image, and whether the first part is located in a preset recognition area when it appears in the current captured image. The first part distinguishes different target objects based on internal physiological characteristics, and the second part distinguishes different target objects based on external morphological characteristics. In response to the detection results indicating that both the first part and the second part appear in the current captured image and the first part is located in the preset recognition area, a first weighting factor is obtained based on the detection confidence of the first part and the ambient light intensity of the current captured image. A second weighting factor is obtained based on the detection confidence and the part status score of the second part. The first brightness of the first part and the second brightness of the second part in the current captured image are weighted based on the first weighting factor and the second weighting factor, respectively, to obtain a first exposure parameter. Then, based on the first exposure parameter, the camera is controlled to perform exposure adjustment. Since, when both the first and second biological sites are detected and the first site is located within the preset recognition area, a first weighting factor for the first site's first brightness is determined by referring to the detection confidence level and ambient light intensity, and a second weighting factor for the second site's second brightness is determined by referring to the detection confidence level and site state score, this helps to fully consider different factors to determine the weighting factors for different biological sites. Therefore, the first exposure parameters are determined accordingly, and exposure control is performed to meet the imaging requirements of both the first and second sites as much as possible. Thus, the compatibility of exposure adjustment is improved, especially when two biological sites are present.

[0050] In some disclosed embodiments, the exposure adjustment device 40 includes a target detection module for performing target detection based on the currently captured image to obtain a target region and confidence score of a first part in the currently captured image; the exposure adjustment device 40 includes a first extraction module for performing feature extraction based on image data of the target region in the currently captured image to obtain a first image feature of the first part; the exposure adjustment device 40 includes a classification prediction module for performing classification prediction based on the first image feature to obtain a predicted probability value of the presence of the first part in the target region; and the exposure adjustment device 40 includes a parameter fusion module for fusing the confidence score and the predicted probability value to obtain a detection confidence level.

[0051] In some disclosed embodiments, the exposure adjustment device 40 includes a key point detection module for detecting key points based on the currently captured image to obtain a plurality of eye key points; the exposure adjustment device 40 includes an opening calculation module for calculating an eye opening value based on the plurality of eye key points; the exposure adjustment device 40 includes a second extraction module for extracting features based on image data surrounding the plurality of eye key points in the currently captured image to obtain a second image feature; wherein the second image feature includes at least one of eye texture features and eye color features; the exposure adjustment device 40 includes a scoring prediction module for predicting a score based on the eye opening value and the second image feature to obtain a part status score.

[0052] In some disclosed embodiments, the exposure adjustment device 40 includes a parameter mapping module, which is used to obtain a second exposure parameter for prioritizing imaging the second part based on the second brightness of the second part when the detection result indicates that only the second part appears in the currently captured image; wherein the second exposure parameter is obtained by mapping the second brightness of the second part to the mapping relationship between the second part under different lighting conditions and the optimal exposure parameter; the camera control module 43 is also used to control the camera to perform exposure adjustment based on the second exposure parameter.

[0053] In some disclosed embodiments, the exposure adjustment device 40 includes a position determination module, used to determine whether the first part is located in a preset recognition area based on the detection result when the detection result indicates that only the first part appears in the currently captured image; the exposure adjustment device 40 includes a global exposure module, used to obtain a third exposure parameter based on the global exposure in response to the first part not being located in the preset recognition area; the exposure adjustment device 40 includes a prediction control module, used to predict the first brightness of the first part and the first image feature of the first part in the currently captured image based on the exposure parameter model of the first part, to obtain a fourth exposure parameter, and to control the camera to perform exposure adjustment based on the fourth exposure parameter; wherein, the exposure parameter model is trained based on the relationship between the first part and the optimal exposure parameter under different lighting conditions and part features.

[0054] In some disclosed embodiments, the exposure adjustment device 40 includes a scene determination module for determining the current shooting scene of the camera based on the ambient light intensity; the exposure adjustment device 40 includes an adaptive adjustment module for adaptively adjusting the current exposure parameters of the camera based on the current shooting scene.

[0055] In some disclosed embodiments, the adaptive adjustment module includes a first adjustment submodule, used to perform the following adjustments to the current exposure parameters when the current shooting scene is a night scene: reduce the base brightness, adjust the gamma coefficient, and adjust the infrared lamp to reduce the surface brightness of the first part; the adaptive adjustment module includes a second adjustment submodule, used to perform the following adjustments to the current exposure parameters when the current shooting scene is a daytime scene: reduce the base brightness, adjust the gamma coefficient, and keep other parameters unchanged; the adaptive adjustment module includes a third adjustment submodule, used to perform the following adjustments to the current exposure parameters when the current shooting scene is a wide dynamic range scene: increase the base brightness, adjust the gamma coefficient, increase the noise reduction parameter, enable the wide dynamic range module to set the wide dynamic range intensity parameter, and increase the illumination intensity of the infrared lamp to enhance the surface brightness of the first part.

[0056] In some disclosed embodiments, the exposure adjustment device 40 includes a priority prediction module for predicting based on a first brightness of a first part to obtain a fifth exposure parameter for prioritizing imaging of the first part; the exposure adjustment device 40 includes a parameter update module for updating at least one of ambient light intensity, detection confidence, part status score, first brightness, and second brightness after controlling the camera to perform exposure adjustment based on the fifth exposure parameter, and performing a step of obtaining a first weighting factor based on the detection confidence of the first part and the ambient light intensity of the currently captured image to obtain the first exposure parameter; the camera control module 43 is specifically used to control the camera to perform exposure adjustment on the second part based on the first exposure parameter.

[0057] In some disclosed embodiments, the first part includes the palm, and the internal physiological features include at least palmar veins; and / or, the second part is the face, and the second part contains eyes; and / or, the first weighting factor is positively correlated with the detection confidence and negatively correlated with the ambient light intensity; and / or, the second weighting factor is negatively correlated with the detection confidence and positively correlated with the part status score; and / or, the ambient light intensity is obtained by mapping the scene brightness value, and the scene brightness value is determined by the image brightness value of the currently captured image and the shutter speed and gain value of the camera when capturing the currently captured image.

[0058] Please see Figure 5 , Figure 5This is a schematic diagram of an embodiment of the electronic device of this application. The electronic device 50 includes at least a memory 51 and a processor 52 coupled to each other. The memory 51 stores at least program instructions, and the processor 52 is used to execute the program instructions to implement the steps in any of the exposure adjustment method embodiments described above. For details, please refer to the foregoing disclosed embodiments, which will not be repeated here.

[0059] Specifically, processor 52 controls itself and memory 51 to implement the steps in any of the exposure adjustment method embodiments described above. Processor 52 can also be referred to as a CPU (Central Processing Unit). Processor 52 may be an integrated circuit chip with signal processing capabilities. Processor 52 can also be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor. Furthermore, processor 52 can be implemented using integrated circuit chips.

[0060] In the above scheme, the electronic device 50 performs detection based on the current captured image of the camera to obtain detection results. The detection results include: whether the first part and the second part of the target object appear in the current captured image, and whether the first part is located in a preset recognition area when it appears in the current captured image. The first part distinguishes different target objects based on internal physiological characteristics, and the second part distinguishes different target objects based on external morphological characteristics. In response to the detection result indicating that both the first part and the second part appear in the current captured image and the first part is located in the preset recognition area, a first weighting factor is obtained based on the detection confidence of the first part and the ambient light intensity of the current captured image. A second weighting factor is obtained based on the detection confidence and the part status score of the second part. The first brightness of the first part and the second brightness of the second part in the current captured image are weighted based on the first weighting factor and the second weighting factor, respectively, to obtain a first exposure parameter. Then, based on the first exposure parameter, the camera is controlled to adjust the exposure. Since, when both the first and second biological sites are detected and the first site is located within the preset recognition area, a first weighting factor for the first site's first brightness is determined by referring to the detection confidence level and ambient light intensity, and a second weighting factor for the second site's second brightness is determined by referring to the detection confidence level and site state score, this helps to fully consider different factors to determine the weighting factors for different biological sites. Therefore, the first exposure parameters are determined accordingly, and exposure control is performed to meet the imaging requirements of both the first and second sites as much as possible. Thus, the compatibility of exposure adjustment is improved, especially when two biological sites are present.

[0061] Please see Figure 6 , Figure 6 This is a schematic diagram of a frame of an embodiment of the camera of this application. The camera 60 includes at least the electronic device 50 in the above embodiments and a photosensitive device 61 coupled to the electronic device 50. Of course, as a possible implementation example, the camera 60 may also include other component devices, such as a flash (not shown). The specific structure of the camera 60 can be found in the related technical details in the art, and will not be described in detail here.

[0062] In the above scheme, the camera 60 performs detection based on the currently captured image to obtain detection results. The detection results include: whether the first part and the second part of the target object appear in the currently captured image, and whether the first part is located in a preset recognition area when it appears in the currently captured image. The first part distinguishes different target objects based on internal physiological characteristics, and the second part distinguishes different target objects based on external morphological characteristics. In response to the detection result indicating that both the first part and the second part appear in the currently captured image and the first part is located in the preset recognition area, a first weighting factor is obtained based on the detection confidence of the first part and the ambient light intensity of the currently captured image. A second weighting factor is obtained based on the detection confidence and the part status score of the second part. The first brightness of the first part and the second brightness of the second part in the currently captured image are weighted based on the first weighting factor and the second weighting factor, respectively, to obtain a first exposure parameter. Then, based on the first exposure parameter, the camera 60 is controlled to adjust the exposure. Since, when both the first and second biological sites are detected and the first site is located within the preset recognition area, a first weighting factor for the first site's first brightness is determined by referring to the detection confidence level and ambient light intensity, and a second weighting factor for the second site's second brightness is determined by referring to the detection confidence level and site state score, this helps to fully consider different factors to determine the weighting factors for different biological sites. Therefore, the first exposure parameters are determined accordingly, and exposure control is performed to meet the imaging requirements of both the first and second sites as much as possible. Thus, the compatibility of exposure adjustment is improved, especially when two biological sites are present.

[0063] Please see Figure 7 , Figure 7 This is a schematic diagram of a framework of an embodiment of the computer-readable storage medium of this application. The computer-readable storage medium 70 stores program instructions 71 that can be executed by a processor. The program instructions 71 are used to implement the steps in any of the above-described exposure adjustment method embodiments.

[0064] In the above scheme, the computer-readable storage medium 70 performs detection based on the current captured image of the camera to obtain detection results. The detection results include: whether the first part and the second part of the target object appear in the current captured image, and whether the first part is located in a preset recognition area when it appears in the current captured image. The first part distinguishes different target objects based on internal physiological characteristics, and the second part distinguishes different target objects based on external morphological characteristics. In response to the detection result indicating that both the first part and the second part appear in the current captured image and the first part is located in the preset recognition area, a first weighting factor is obtained based on the detection confidence of the first part and the ambient light intensity of the current captured image. A second weighting factor is obtained based on the detection confidence and the part status score of the second part. The first brightness of the first part and the second brightness of the second part in the current captured image are weighted based on the first weighting factor and the second weighting factor, respectively, to obtain a first exposure parameter. Then, based on the first exposure parameter, the camera is controlled to adjust the exposure. Since, when both the first and second biological sites are detected and the first site is located within the preset recognition area, a first weighting factor for the first site's first brightness is determined by referring to the detection confidence level and ambient light intensity, and a second weighting factor for the second site's second brightness is determined by referring to the detection confidence level and site state score, this helps to fully consider different factors to determine the weighting factors for different biological sites. Therefore, the first exposure parameters are determined accordingly, and exposure control is performed to meet the imaging requirements of both the first and second sites as much as possible. Thus, the compatibility of exposure adjustment is improved, especially when two biological sites are present.

[0065] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0066] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0067] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the exposure adjustment method described above is merely illustrative. For instance, the first part is not limited to a certain body part, as long as it satisfies the requirement of distinguishing different target objects by internal physiological characteristics. In actual implementation, different biological parts can be selected according to user needs. Similarly, the second part is not limited to a certain body part, as long as it satisfies the requirement of distinguishing different target objects by external morphological characteristics.

[0068] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0069] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0070] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0071] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

Claims

1. An exposure adjustment method, characterized in that, include: The detection is performed based on the current captured image of the camera to obtain the detection result; wherein, the detection result includes: whether the first part and the second part of the target object appear in the current captured image, and whether the first part is located in a preset recognition area when the first part appears in the current captured image, wherein the first part distinguishes different target objects by internal physiological characteristics, and the second part distinguishes different target objects by external morphological characteristics; In response to the detection result indicating that both the first part and the second part appear in the currently captured image and the first part is located in the preset recognition area, a first weighting factor is obtained based on the detection confidence of the first part and the ambient light intensity of the currently captured image, and a second weighting factor is obtained based on the detection confidence and the part status score of the second part. Furthermore, a first exposure parameter is obtained by weighting the first brightness of the first part and the second brightness of the second part in the currently captured image based on the first weighting factor and the second weighting factor, respectively. Based on the first exposure parameter, the camera is controlled to adjust its exposure.

2. The method according to claim 1, characterized in that, The steps for obtaining the detection confidence level include: Target detection is performed based on the currently captured image to obtain the target region and confidence score of the first part in the currently captured image; Based on the image data of the target region in the currently captured image, feature extraction is performed to obtain the first image feature of the first part; Based on the first image features, classification and prediction are performed to obtain the predicted probability value of the existence of the first part in the target region; The detection confidence is obtained by fusing the confidence score and the predicted probability value.

3. The method according to claim 1, characterized in that, The second part contains eyes, and the steps for obtaining the status score of the part include: Based on the currently captured image, key point detection is performed to obtain several key points of the eye. Based on the aforementioned key eye points, an eye opening value is calculated, and feature extraction is performed on the image data surrounding the key eye points in the currently captured image to obtain a second image feature; wherein, the second image feature includes at least one of eye texture features and eye color features; A score is obtained by predicting the condition of the affected area based on the eye opening value and the second image features.

4. The method according to claim 1, characterized in that, When the detection result indicates that only the second region appears in the currently captured image, the method further includes: Based on the second brightness of the second region, a second exposure parameter for prioritizing imaging of the second region is obtained; wherein, the second exposure parameter is obtained by mapping the second brightness to the mapping relationship between the second region under different lighting conditions and the optimal exposure parameter; Based on the second exposure parameter, the camera is controlled to adjust its exposure.

5. The method according to claim 1, characterized in that, When the detection result indicates that only the first region appears in the currently captured image, the method further includes: Based on the detection results, it is determined whether the first part is located in the preset recognition area; In response to the first part not being located in the preset recognition area, a third exposure parameter is obtained based on global exposure, and the camera is controlled to adjust the exposure based on the third exposure parameter; In response to the first part being located in the preset recognition area, a first brightness of the first part and a first image feature of the first part in the current captured image are predicted based on the exposure parameter model of the first part to obtain a fourth exposure parameter, and the camera is controlled to adjust the exposure based on the fourth exposure parameter; wherein, the exposure parameter model is trained based on the relationship between the first part and the optimal exposure parameter under different lighting conditions and part features.

6. The method according to claim 1, characterized in that, If the detection result includes the first part appearing in the currently captured image and the first part being located within the preset recognition area, the method further includes: Based on the ambient light intensity, the current shooting scene of the camera is determined; Based on the current shooting scene, the camera's current exposure parameters are adaptively adjusted.

7. The method according to claim 6, characterized in that, The current shooting scene is any one of a night scene, a day scene, or a wide dynamic range scene. The adaptive adjustment of the camera's current exposure parameters based on the current shooting scene includes: When the current shooting scene is the night scene, the current exposure parameters are adjusted as follows: reduce the base brightness, adjust the gamma coefficient, and adjust the infrared lamp to reduce the surface brightness of the first part; And / or, if the current shooting scene is the daytime scene, the current exposure parameters are adjusted as follows: the base brightness is reduced, the gamma coefficient is adjusted, and other parameters are kept unchanged; And / or, if the current shooting scene is the wide dynamic range scene, the current exposure parameters are adjusted as follows: increase the base brightness, adjust the gamma coefficient, increase the noise reduction parameter, enable the wide dynamic range module to set the wide dynamic range intensity parameter, and increase the irradiation intensity of the infrared lamp to enhance the surface brightness of the first part.

8. The method according to claim 1, characterized in that, When the detection result indicates that both the first part and the second part appear in the currently captured image and the first part is located within the preset recognition area, the method further includes the following steps before controlling the camera to adjust the exposure based on the first exposure parameter: Based on the first brightness of the first region, a fifth exposure parameter is obtained for prioritizing imaging of the first region. After adjusting the camera's exposure based on the fifth exposure parameter, update at least one of the ambient light intensity, the detection confidence, the part status score, the first brightness, and the second brightness, and perform the step of obtaining the first weighting factor based on the detection confidence of the first part and the ambient light intensity of the currently captured image to obtain the first exposure parameter. The step of controlling the camera to adjust the exposure based on the first exposure parameter includes: Based on the first exposure parameter, the camera is controlled to adjust the exposure of the second part.

9. The method according to any one of claims 1 to 8, characterized in that, The first part includes the palm, and the internal physiological features include at least the palmar veins; And / or, the second part is a face, and the second part contains eyes; And / or, the first weighting factor is positively correlated with the detection confidence and negatively correlated with the ambient light intensity; And / or, the second weighting factor is negatively correlated with the detection confidence and positively correlated with the site status score; And / or, the ambient light intensity is obtained by mapping the scene brightness value, which is determined by the image brightness value of the currently captured image and the shutter speed and gain value of the camera when capturing the currently captured image.

10. An exposure adjustment device, characterized in that, include: An image detection module is used to perform detection based on the current captured image of the camera and obtain detection results; wherein, the detection results include: whether the first part and the second part of the target object appear in the current captured image, and whether the first part is located in a preset recognition area when the first part appears in the current captured image, wherein the first part distinguishes different target objects based on internal physiological characteristics, and the second part distinguishes different target objects based on external morphological characteristics; The parameter determination module is configured to, in response to the detection result indicating that both the first part and the second part appear in the currently captured image and the first part is located in the preset recognition area, obtain a first weighting factor based on the detection confidence of the first part and the ambient light intensity of the currently captured image, obtain a second weighting factor based on the detection confidence and the part status score of the second part, and weight the first brightness of the first part and the second brightness of the second part in the currently captured image based on the first weighting factor and the second weighting factor respectively to obtain a first exposure parameter; The camera control module is used to control the camera to adjust the exposure based on the first exposure parameter.

11. An electronic device, characterized in that, It includes at least a memory and a processor coupled to each other, wherein the memory stores at least program instructions, and the processor executes the program instructions to implement the exposure adjustment method according to any one of claims 1 to 9.

12. A camera, characterized in that, It includes at least the electronic device as described in claim 11 and a photosensitive device coupled to the electronic device.

13. A computer-readable storage medium, characterized in that, The device stores program instructions that can be executed by a processor, the program instructions being used to implement the exposure adjustment method according to any one of claims 1 to 9.

Images