CN112584089A - Face brightness adjusting method and device, computer equipment and storage medium - Google Patents
Face brightness adjusting method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112584089A CN112584089A CN202110213508.XA CN202110213508A CN112584089A CN 112584089 A CN112584089 A CN 112584089A CN 202110213508 A CN202110213508 A CN 202110213508A CN 112584089 A CN112584089 A CN 112584089A
- Authority
- CN
- China
- Prior art keywords
- face
- brightness
- state
- current frame
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
- H04N7/15—Conference systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/73—Circuitry for compensating brightness variation in the scene by influencing the exposure time
Abstract
The application relates to a face brightness adjusting method, a device, computer equipment and a storage medium, wherein a moving distance between a first face area and a second face area is obtained, a face state in a current frame is judged according to the moving distance, exposure parameters corresponding to the current frame are adjusted according to a face brightness value and a face brightness threshold value in the current frame under the condition that the face state is in a stable state, and the exposure parameters corresponding to the current frame are maintained under the condition that the face state is in a moving state, wherein the face brightness threshold value is dynamically adjusted according to the face state; exposure parameter adjustment is carried out in a stable state of the face, the existing parameters are maintained in a moving state of the face, and therefore the phenomenon that the brightness of an output picture jumps obviously in the moving process of the face is avoided, and the picture brightness of a video conference is more stable and changes more smoothly.
Description
Technical Field
The present application relates to the field of image processing technologies for video conference systems, and in particular, to a method and an apparatus for adjusting human face brightness, a computer device, and a storage medium.
Background
Video conferencing technology is being widely applied, and in a video conferencing system, various problems such as insufficient exposure of human faces, overexposure of human faces and the like are caused due to the influence of external light, so that the quality of human face images in the video conferencing is seriously influenced. In the field of Automatic Exposure (AE), the brightness of the whole picture is adjusted to the set target brightness mainly by adjusting Exposure time, Exposure gain and aperture, so that the brightness balance of the whole picture is realized, the close-up image quality of people is influenced by various problems such as unclear face recognition, poor face image effect and the like, and the brightness of a face area is improved by providing an Exposure algorithm based on the face in the related technology.
However, in the face exposure algorithm in the related art, the jump of the brightness of the whole picture is obvious in the motion process of the face, and particularly in the field of video conferences, the brightness of the picture is often dim due to shaking of the head of a person, sudden interference of external light and the like in the characteristic process of the person, so that the output picture quality is seriously affected.
Aiming at the problem that the brightness jump of an output picture is obvious in the motion process of a human face in the related technology, an effective solution is not provided at present.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a face brightness adjustment method, apparatus, computer device and storage medium for solving the above technical problems.
According to an aspect of the present invention, there is provided a face brightness adjustment method, including:
acquiring a movement distance between a first face area and a second face area, wherein the face area of the same face in a current frame is the first face area, and the face area in a previous frame of the current frame is the second face area; and judging the face state in the current frame according to the movement distance, adjusting the exposure parameters corresponding to the current frame according to the face brightness value and the face brightness threshold value in the current frame under the condition that the face state is a stable state, and maintaining the exposure parameters corresponding to the current frame under the condition that the face state is a movement state, wherein the face brightness threshold value is dynamically adjusted according to the face state.
In one embodiment, in the case that a plurality of faces are included in the current frame, the method includes:
and distributing a weight value to each face region according to the ratio of the area of each face region to the area of the maximum face region, wherein the weight value is used for weighting and calculating the face brightness value.
In one embodiment, the determining the face state in the current frame according to the motion distance includes:
under the condition that the movement distance is smaller than or equal to a preset first movement threshold, judging that the face state in the current frame is a stable state;
and under the condition that the movement distance is larger than the first movement threshold, judging that the face state in the current frame is a movement state.
In one embodiment, when the face state is a stable state, adjusting the exposure parameter corresponding to the current frame according to the face brightness value in the current frame and the face brightness threshold includes:
adjusting the exposure parameter under the condition that a human face brightness error value is larger than a preset first human face brightness error threshold value, wherein the human face brightness error value is the difference value between the human face brightness value and a preset standard value, and the first human face brightness error threshold value is the difference value between the human face brightness threshold value and the preset standard value;
and under the condition that the face brightness error value is smaller than or equal to the first face brightness error threshold, accumulating the frame number, under the condition that the accumulated value of the frame number is larger than a preset first frame number threshold, updating the first motion threshold to a second motion threshold, and updating the first face brightness error threshold to a second face brightness error threshold, wherein the second motion threshold is larger than the first motion threshold, and the second face brightness error threshold is larger than the first face brightness error threshold.
In one embodiment, in a case that the face state is a motion state, after maintaining the exposure parameter, the method includes:
starting frame number accumulation under the condition that the face brightness error in the current frame is greater than a preset third face brightness error threshold;
and under the condition that the frame number accumulation is larger than a preset second frame number threshold, updating the first face brightness error threshold to a third face brightness error threshold, and adjusting the exposure parameter, wherein the third face brightness error threshold is larger than the first face brightness error threshold.
In one embodiment, after the adjusting the exposure parameter, the method further includes:
and updating the third face brightness error threshold value to the first face brightness error threshold value when the face brightness error is smaller than or equal to the third face brightness error threshold value.
In one embodiment, when the motion distance is greater than the first motion threshold, determining that the face state of the current frame is a motion state, and maintaining the exposure parameter includes:
maintaining the exposure parameter in a first number of image frames after the current frame if the movement distance is greater than a preset movement threshold upper limit.
In one embodiment, when the face state is a stable state, adjusting the exposure parameter corresponding to the current frame according to the face brightness value in the current frame and the face brightness threshold includes:
judging whether the global brightness of the current frame exceeds the range of upper and lower limit thresholds or not;
and stopping adjusting the exposure parameters under the condition that the global brightness exceeds the range of the upper and lower limit thresholds.
In one embodiment, in the case that a plurality of faces are included in the current frame, the method includes:
calculating the human face frame intersection ratio between the historical video frame and the current frame, and calculating to obtain the motion information of each human face in the current frame according to the human face frame intersection ratio;
and obtaining the movement distance based on the face movement information.
In one embodiment, before the obtaining of the movement distance between the first face region and the second face region, the method includes:
acquiring an intersection region of the face regions in a second number of image frames, and indicating that the intersection region is the first face region, wherein the second number of image frames are consecutive image frames, and the first image frame is the last frame in the second number of image frames.
According to another aspect of the present invention, there is also provided a face brightness adjustment apparatus, the apparatus including: the state judgment module, the exposure parameter adjusting module and the monitoring module:
the state judgment module is used for acquiring the movement distance between a first face area and a second face area, wherein the face area of the same face in the current frame is the first face area, and the face area in the previous frame of the current frame is the second face area;
the exposure parameter adjusting module is used for judging the face state in the current frame according to the movement distance, adjusting the exposure parameter corresponding to the current frame according to the face brightness value and the face brightness threshold value in the current frame under the condition that the face state is in a stable state, and maintaining the exposure parameter corresponding to the current frame under the condition that the face state is in a movement state;
the monitoring module is used for dynamically adjusting the face brightness threshold value according to the face state. In one embodiment, the apparatus further comprises a multi-face processing module:
the multi-face processing module is used for distributing a weight value to each face region according to the ratio of the area of each face region to the area of the maximum face region under the condition that the current frame comprises a plurality of faces, wherein the weight value is used for weighting and calculating the face brightness value.
According to another aspect of the present invention, there is also provided a computer device, including a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the above face brightness adjustment method when executing the computer program.
According to another aspect of the present invention, there is also provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above-described face brightness adjustment method.
The method, the device, the computer equipment and the storage medium for adjusting the face brightness acquire the movement distance between a first face area and a second face area, judge the face state in a current frame according to the movement distance, adjust the exposure parameter corresponding to the current frame according to the face brightness value in the current frame and the face brightness threshold value under the condition that the face state is a stable state, and maintain the exposure parameter corresponding to the current frame under the condition that the face state is a moving state, wherein the face brightness threshold value is dynamically adjusted according to the face state, the exposure parameter is adjusted under the stable state of the face, and the existing parameter is maintained under the moving state of the face, so that the phenomenon that the jump of the output image brightness is obvious in the moving process of the face is avoided, the image is dim, and the image brightness of a video conference is more stable and the change is smoother is avoided.
Drawings
FIG. 1 is a flow chart of a face brightness adjustment method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a face brightness adjustment method according to another embodiment of the present invention;
FIG. 3 is a flow diagram of steady state monitoring in accordance with one embodiment of the present invention;
FIG. 4 is a flow diagram of steady state monitoring in accordance with another embodiment of the present invention;
FIG. 5 is a flow chart of a face brightness adjustment method according to another embodiment of the present invention;
FIG. 6 is a flow diagram of motion state monitoring according to one embodiment of the present invention;
FIG. 7 is a schematic diagram of face region preprocessing according to one embodiment of the invention;
FIG. 8 is a block diagram of a face brightness adjustment mechanism according to one embodiment of the present invention;
FIG. 9 is a block diagram of a face brightness adjustment mechanism according to an embodiment of the present invention;
FIGS. 10a and 10b are schematic diagrams of a face frame cross-over ratio according to an embodiment of the present invention;
fig. 11 is a flow chart of the operation of the face state decision module in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The face brightness adjusting method can be applied to the application environment of a video conference, particularly can be applied to a camera part of the video conference, the camera comprises a processor and a computer program which is stored in a memory and can run on the processor, and the processor realizes the self-adaptive adjustment of the face brightness when executing the computer program, so that the adjustment of the exposure parameter of the camera part is realized.
In an embodiment, fig. 1 is a flowchart of a face brightness adjustment method according to an embodiment of the present invention, and as shown in fig. 1, a face brightness adjustment method is provided, which is described by taking a camera and a processor of a video conference system as an example, and includes the following steps:
step S110, a movement distance between the first face region and the second face region is obtained. The first face area and the second face area are positions of the same face in the current frame and the previous frame of the current frame. And (3) putting the two frames of images into the same coordinate system, comparing the positions of the face frames in the two frames of images and calculating the movement distance of the face, and optionally comparing the central positions of the face frames aiming at the same face in the two frames of images to obtain the movement distances of the faces in the current frame and the previous frame.
And step S120, judging the face state in the current frame according to the movement distance. In some embodiments, the process of determining the face state in the current frame according to the movement distance includes determining that the face state of the current frame is a stable state when the movement distance is less than or equal to a preset first movement threshold; and under the condition that the movement distance is greater than the first movement threshold value, judging that the face state of the current frame is a movement state. And the first motion threshold is adaptively adjusted according to the area size of the first face region. In the video conference, the distances between the seats of participants and the conference camera are different, so that the human face regions of the human faces of the participants in the video conference picture have larger difference, and therefore, the first motion threshold value for judging the human face state is adjusted according to the area of the human face region of the current frame of the videoThe judgment of the face state can be more accurate. Optionally, the width or height of the face frame is selected as the reference length, for example, half the width of the face frame is selected as the first motion threshold.
And step S130, under the condition that the human face state is a stable state, the processor adjusts the exposure parameters corresponding to the current frame according to the human face brightness value and the human face brightness threshold value in the current frame. Under the condition that the moving distance of the face in the front frame and the back frame is less than or equal to half of the width of the face frame, the face is judged to be in a stable state, and the statistics on the face brightness value is more accurate and credible, so that the exposure parameter can be adjusted according to the face brightness value. The face brightness threshold refers to a preset brightness threshold of face brightness, and the face brightness threshold may be preset and stored in the processor. When the exposure parameters are adjusted, the face brightness value of the current frame can be obtained, the face brightness value is compared with a preset face brightness threshold value, and when the face brightness threshold value is exceeded, the exposure is adjusted by changing the current exposure amount and matching with an aperture, exposure time and gain, so that the face brightness value in a picture is changed. The methods for adjusting the exposure parameters in the related art are applicable to the present embodiment. The face brightness threshold is dynamically adjusted according to the face state, for example, the face brightness threshold can be increased to improve the tolerance under the condition that the image is in a stable state for a long time.
In step S140, the processor maintains the exposure parameter corresponding to the current frame when the face state is the motion state. And under the condition that the movement distance is greater than the first movement threshold value, judging that the current frame is in a movement state, and maintaining the exposure parameters. The face brightness threshold is dynamically adjusted according to the face state, for example, the face brightness threshold is increased under the condition that the image is in a motion state for a long time so as to avoid the image brightness from changing too frequently. Under the condition that the movement distance is greater than the first movement threshold, the instantaneous movement amplitude of the current face is larger, and the calculated face brightness value is possibly influenced by environmental factors to have larger errors.
According to the face brightness adjusting method, the face brightness adjusting device, the computer equipment and the storage medium, the movement distance between the first face area and the second face area is obtained, and the exposure parameter is adjusted according to the face brightness value when the face state in the current frame is judged to be in a stable state according to the movement distance; when the face state is a motion state, maintaining the exposure parameters; exposure parameter adjustment is carried out in a stable state of the face, the existing parameters are maintained in a moving state of the face, and the phenomenon that the jump of the brightness of an output picture is obvious in the moving process of the face, so that the picture is dim and bright, and the brightness of the face in the picture in a video conference is more stable and changes more smoothly is avoided.
In one embodiment, in a case that a plurality of faces are included in a current frame, a weight value is assigned to each face region according to a ratio of an area of each face region to a maximum face region area, where the weight value is used for weighting and calculating the face brightness value. For example, the first face region is a face region corresponding to the first face in the current frame, and the first face is a face with the largest area in the current frame. In an actual application scene, the situation that a plurality of faces exist in a video picture often occurs, but the face brightness of each face in the picture is not required to be considered under the common situation of the video picture, so that the method cares about the largest target area in the image, only the area with the higher face area ratio is reserved for weight distribution, and the area with the too small face area ratio is ignored. When only one face appears in the image, concentrating all the weights in the area; when a plurality of faces appear in the image, the face with the largest face frame area is taken as a reference standard, and corresponding weight values are respectively distributed to other face areas. The weight value can be used for calculating the motion distance of multiple faces, the face brightness value and the like more accurately. For example, a first face region and a third face region exist in the current frame, the first face region corresponds to the first face and is a maximum face region, the third face region corresponds to the second face, and the weight of the second face is calculated according to the area ratio of the first face region to the third face region. In the step of calculating the face brightness value, the face brightness value is calculated according to the brightness value of each face and the weight of each face, and compared with the method of calculating the face brightness value through a preset fixed weight in the related technology, the face brightness value calculated by the scheme is more accurate and has better self-adaptability.
In an embodiment, fig. 2 is a flowchart of a face brightness adjustment method according to another embodiment of the present invention, and as shown in fig. 2, when a face state in a current frame is a stable state, adjusting an exposure parameter corresponding to the current frame according to a face brightness value in the current frame and a face brightness threshold includes:
step S210, when the face brightness error value is greater than a preset first face brightness error threshold, the processor adjusts the exposure parameter, where the face brightness error threshold is a difference between the face brightness threshold and a preset standard value, the preset standard value is a face brightness value with a better image display effect selected according to a scene of the video conference, and when the error between the brightness of the current frame of the image and the standard value is greater than the first face brightness error threshold, it indicates that the face brightness of the image has affected the video effect, and then an adjustment process of the exposure parameter is triggered.
Step S220, when the face brightness error value is smaller than or equal to the first face brightness error threshold, the processor accumulates the frame number, and when the frame number accumulated value is greater than a preset first frame number threshold, the processor updates the first motion threshold to a second motion threshold, and the first face brightness error threshold is updated to the second face brightness error threshold. And the second motion threshold is greater than the first motion threshold, and the second face brightness error threshold is greater than the first face brightness error threshold. The frame number accumulation and threshold value adjustment process is actually to monitor the face image in real time, and adjust the judgment threshold value in real time according to the state of the face on the picture.
For example, fig. 3 is a flow chart of steady state monitoring according to an embodiment of the present invention, as shown in fig. 3, the current frame is in steady state 1.
Step S310, judging whether the human face brightness error is larger than the human face brightness error threshold value;
Step S320, when the human face brightness error is less than or equal to the human face brightness error threshold valueIn case of (2), no adjustment is madeSetting exposure parameters, starting frame number accumulation by a processor, and enabling the accumulated human face brightness error not to be larger than the human face brightness error threshold valueWhen the accumulated number of frames is greater than the first frame number threshold and the face and the background both reach steady brightness during the process, it is determined that the target face in the current scene is always in a steady state, and the steady state 1 is updated to the steady state 2 in the next frame, optionally, the default experience of the first frame number threshold is set to 60. Simultaneously thresholding the first motionUpdate to the second motion thresholdSatisfy the following requirementsFirst face luminance error thresholdUpdated to a second face brightness error thresholdSatisfy the following requirements;
In step S330, the processor adjusts the exposure parameter and clears the frame number accumulation when the face brightness error value is greater than the preset first face brightness error threshold.
By the embodiment, the image frame can be switched to the stable state 2 in the stable state, and the system has a larger tolerance range in the stable state 2, so that higher system stability can be achieved.
In one embodiment, fig. 4 is a flowchart of a steady state monitoring method according to another embodiment of the present invention, and as shown in fig. 4, in the case that the current frame is in a steady state, adjusting the exposure parameter according to the face brightness value includes:
step S410, judging whether the global brightness of the current frame meets an upper limit threshold or a lower limit threshold;
step S420, stopping adjusting exposure parameters under the condition that the global brightness of the current frame meets an upper limit threshold or a lower limit threshold;
in step S430, the exposure parameter is adjusted when the global brightness of the current frame does not satisfy the upper threshold or the lower threshold.
For example, if the current frame is in steady state 1, the luminance error is greater than the face luminance error thresholdThe processor will adjust the exposure parameters for the next frame of image. However, if the global brightness is detected to meet the upper threshold or the lower threshold, the processor stops brightness adjustment to avoid causing over exposure or over darkness of the whole image and ensure the whole visual effect of the image. The global brightness refers to the overall brightness of the background of the current image frame; the upper threshold is an overall brightness value indicating overexposure of the current frame overall image, the lower threshold is an overall brightness value indicating too dark of the current frame overall image, and a range of the overall brightness value formed from the lower threshold to the upper threshold is an upper and lower threshold range.
In an embodiment, fig. 5 is a flowchart of a face brightness adjustment method according to another embodiment of the present invention, and as shown in fig. 5, in the case that the current frame is in a motion state, maintaining the exposure parameters includes:
step S510, under the condition that the face brightness error is larger than a preset third face brightness error threshold, accumulating the continuous frame number of which the face brightness error is larger than the preset third face brightness error threshold by the processor;
in step S520, the processor updates the first face brightness error threshold to the third face brightness error threshold and adjusts the exposure parameter when the frame number accumulation is greater than the preset second frame number threshold.
For example, fig. 6 is a flow chart of motion state monitoring according to an embodiment of the present invention, as shown in fig. 6, the current frame is in motion state 1, and the camera maintains the exposure parameters of the last stable frame. On the other hand, the processor still counts the human face brightness error in real time and executes the following processes:
step S610, judging whether the human face brightness error is larger than a third human face brightness error threshold value;
Step S620, if the face brightness error of the current frame is larger than the third face brightness error threshold valueIf so, the processor immediately starts frame number accumulation;
step S630, when the accumulated value of the continuous frames is greater than the threshold value of the second frame, the motion state 1 is updated to the motion state 2, optionally, the threshold value of the second frame is set to be 8 according to the experience value;
step S640, the human face brightness error threshold valueUpdated to the third face brightness error thresholdAnd adjusting the exposure parameter of the next frame, and clearing the accumulated frame number.
The motion state monitoring process provided by the embodiment avoids the phenomenon that the exposure adjustment is still not triggered due to the fact that the face is too bright or too dark obviously in the motion process, and meanwhile, the face brightness tolerance in the motion state is enlarged, so that the face brightness is more stable in the face motion state.
In one embodiment, after step S640, in the case that the face brightness error is less than or equal to the third face brightness error threshold, the third face brightness error threshold is updated to the first face brightness error threshold. For example, when the face brightness error is not greater than the face brightness error thresholdThen, the motion state 2 is updated to the motion state 1, and the human face brightness error threshold valueThen updated to the human face brightness error threshold value. The mechanism is favorable for adjusting the brightness threshold value in time according to the current face brightness value, so that whether the exposure parameter is operated in the motion state can be adjusted in time, and the face brightness is more stable.
In one embodiment, in the case that the moving distance is greater than the first moving threshold, determining that the current frame is in a moving state, and maintaining the exposure parameter includes: in the case where the movement distance is greater than the preset movement threshold upper limit, the exposure parameter is maintained in a first number of image frames following the current frame. For example, in case of sudden face motion excessive, such as moving out of a picture or face detection abnormality, i.e. no face region is captured, in order to avoid abnormal picture brightness, the present embodiment increases a first number of frames to maintain the previous exposure parameter, and optionally, the first number is set to 8 according to an empirical value. When the face is detected again, the camera and the processor system enter a normal face state judgment and exposure adjustment process; if the frame number is exceeded, no human face information is detected, and the process enters the AE exposure adjustment flow of the picture brightness. The embodiment enables the picture to still keep stable brightness in the process of large-scale movement of the human face.
In one embodiment, before obtaining the moving distance between the first face region and the second face region, the method includes: acquiring intersection areas of the face areas in a second number of image frames, and indicating the intersection areas as the first face areas, wherein the second number of image frames are continuous image frames.
Fig. 7 is a schematic diagram of face region preprocessing according to an embodiment of the present invention, and as shown in fig. 7, in this embodiment, a protection mechanism is provided in which a stable face detection frame is added in an image preprocessing stage, and optionally, intersection-taking processing is performed on every 4 frames of an acquired image frame, and an intersection part is taken as a final preselected region for all face detection results detected in 4 consecutive frames. In practical application, the problem that a face rectangular frame given by a face detection algorithm has large difference is often encountered in continuous video frames with a still face, so that the brightness value of real-time face statistics can obviously jump, and the finally presented face brightness consistency is poor.
It should be understood that, although the steps in the flowcharts of fig. 1 to 6 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-6 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
According to another aspect of the present invention, fig. 8 is a block diagram of a face brightness adjustment device according to an embodiment of the present invention, and fig. 8 provides a face brightness adjustment device 80, which includes a motion state determination module 82, an exposure parameter adjustment module 84, and a monitoring module 86:
the state determination module 82 is configured to obtain a movement distance between a first face region and a second face region, where a face region of the same face in a current frame is the first face region, and a face region in a previous frame of the current frame is the second face region;
the exposure parameter adjusting module 84 is configured to determine a face state in the current frame according to the motion distance, adjust an exposure parameter corresponding to the current frame according to a face brightness value and a face brightness threshold in the current frame when the face state is in a stable state, and maintain the exposure parameter corresponding to the current frame when the face state is in a motion state;
the monitoring module 86 is configured to dynamically adjust the face brightness threshold according to the face state. In one embodiment, the face brightness adjusting device further comprises a plurality of face processing modules: the multi-face processing module is used for distributing a weight value to each face region according to the ratio of the area of each face region to the area of the maximum face region in the current frame, wherein the weight value is used for weighting and calculating the face brightness value. For example, it is indicated that the first face region is a face region corresponding to a first face in the current frame, and the first face is a face with the largest area in the current frame; and calculating the weight of the second face according to the area ratio of the first face area to the third face area in the current frame, and calculating the face brightness value according to the brightness value of each face in the current frame and the weight of each face, wherein the third face area is the face area corresponding to the second face in the current frame.
For the specific limitation of the face brightness adjusting device, reference may be made to the above limitation on the face brightness adjusting method, and details are not described here. All or part of the modules in the face brightness adjusting device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
The face brightness adjusting device acquires a movement distance between a first face area and a second face area, judges a face state in a current frame according to the movement distance, adjusts exposure parameters corresponding to the current frame according to a face brightness value and a face brightness threshold value in the current frame under the condition that the face state is a stable state, and maintains the exposure parameters corresponding to the current frame under the condition that the face state is a movement state, wherein the face brightness threshold value is dynamically adjusted according to the face state; the exposure parameters are adjusted in a stable state of the human face, the existing parameters are maintained in a moving state of the human face, and the condition that the fluctuation of an exposure algorithm causes the flickering of the picture is avoided, so that the picture brightness of the video conference is more stable and the change is smoother.
In a specific embodiment, fig. 9 is a block diagram of a face brightness adjustment apparatus according to an embodiment of the present invention, and as shown in fig. 9, there is provided a face brightness adjustment apparatus 90, which includes a face frame preprocessing module 91, a multi-face statistics module 92, a motion state determination module 93, a face state determination module 94, an exposure parameter adjustment module 95, and a monitoring module 96, where the monitoring module 96 includes a stable state monitoring module 97 and a motion state monitoring module 98.
The face frame preprocessing module 91 can effectively eliminate the interference information in the face coordinates and extract the face frame with the effective face. In the face frame preprocessing module 91, face coordinates in an image are acquired by a face detection algorithm based on deep learning. And then taking the intersection part of all the results detected in the continuous 4 frames as a final face area.
After the multi-face counting module 92 obtains the face coordinates, corresponding weights are respectively set according to the face areas in order to balance the image quality of all the faces. In the processing process, the largest target face area in the image is most concerned, the face area with the medium face area ratio is reserved, and the face area with the small area ratio is directly ignored. When only one face appears in the image, all weights are concentrated in this region. When a plurality of faces appear in the image, the maximum face is taken as a reference standard, and corresponding weight values are respectively distributed to other face areas, wherein the weight calculation mode is as follows:
the first step is as follows: calculating the ratio of the reference standard (maximum face area) to the face of each preselected area in the image by formula 1 and formula 2:
Wherein the content of the first and second substances,as the ratio of each candidate face region to the largest face region,the area of the largest face region counted in one picture is obtained. Thus, of the largest face areaOf faces in other preselected areas。
The second step is that: the weight function is calculated using a gaussian function as shown in equation 3, as follows,
Wherein the content of the first and second substances,for the weight value of each candidate region, in the present embodiment, 1 is taken for a, 1 is taken for b, and 0.6 is taken for c according to an empirically set coefficient. As can be seen from the formula 3, the closer the area of the region is to the maximum face area, the larger the weight of the region is, and the weight of each face can be effectively balanced through a Gaussian function, so that effective distinguishing is realized, and the self-adaptability is better compared with the traditional method for artificially setting the mean weight.
Comparing the face information recorded in the reference historical video frame, and calculating the face motion information in the current frame, wherein the face motion information comprises the following steps: transverse displacement, longitudinal displacement, displacement distance and movement direction; therefore, the movement distance between the first face region and the second face region can be determined based on the face movement information. In contrast toReferring to the historical video frame, the maximum face area movement condition of the historical video frame and the current frame is judged by calculating the intersection ratio, fig. 10a and 10B are schematic diagrams of the intersection ratio of the face frames according to one embodiment of the present invention, as shown in fig. 10a and 10B, a is the face frame orientation in the previous frame of the current frame, B is the face frame orientation of the current frame, C is the intersection area of the two,indicating a "cross-over ratio" value. When in useIf the difference is greater than 0, as shown in fig. 10a, it indicates that the largest face in the historical video frame and the largest face in the current frame are the same target, and they can be used for comparing and calculating to obtain motion information; when in useAnd if the value is equal to 0, as shown in fig. 10B, where a and B do not intersect, it indicates that the maximum face area in the historical video frame and the current frame cannot correspond to each other or the face motion in the previous and subsequent frames moves violently instantaneously, and there is no value of reference comparison.
The face state determination module 94 determines the motion state of the face region based on the information determined by the above modules, and adjusts the exposure parameters of the next frame of image according to the error by referring to the brightness values and weights of all the face regions. Fig. 11 is a flowchart of the work of the face state determination module according to an embodiment of the present invention, and as shown in fig. 11, the work of the face state determination module includes:
step S112, determining a motion state, wherein the determining the motion state comprises:
in the process of judging the motion state of the current frame image, if only one face is detected in the current frame image, the motion distance of the face region obtained by calculation in the preprocessing and a first motion threshold value are directly usedAnd (6) comparing. If the movement distance is not greater than the first movement thresholdThen, the motion state of the current frame is determined to be the stable state 1. When the movement distance is larger than the first movement thresholdThen the motion state of the current frame is determined to be motion state 1, wherein the first motion threshold valueThe size can be adjusted in a self-adaptive way according to the size of the face area, wherein the w and h distribution represents the width and height of the face area,representing the entire frame image size. And if a plurality of faces are detected in the current frame image, taking the motion state of the largest face area as the motion state of the current frame. Calculated by equation 4:
Wherein, when the maximum human face area is larger than 0.2 times of the whole frame image, the first motion threshold valueIs 0.25 times the minimum value of w and h; otherwise, the first motion thresholdIs 0.5 times the minimum value of w and h.
Step S114, face brightness statistics and error calculation:
according to the motion state obtained in step S112, if the current frame is in the stable state 1, it can be inferred that the current face area is relatively stable, and the face brightness value counted at this time is more accurate and reliable. If the current frame is in the motion state 1, it indicates that the instantaneous motion amplitude of the current face is large, and the face brightness value calculated at this time may be influenced by environmental factors and have a large error.
When the brightness value of a certain face area is counted, the face area is adaptively divided into a plurality of sub-areas, and the areas can be divided into the following sub-areas according to the face distribution: calculating the face brightness value of a single face area according to formula 5 for the face internal area and the face boundary area:
Wherein i represents the ith sub-region of the face region division,representing the weight value corresponding to the ith sub-region of the face,a luminance value representing the corresponding sub-area,is the final brightness value of the face region.
Calculating the face brightness value of the current frame according to the formula 6 according to the obtained brightness value of the single face region:
Wherein n represents the number of the face regions obtained after the current frame is preprocessed,represents the weight ratio of each face area,a luminance value representing the ith personal face region statistic. Therefore, the face brightness statistic value of the whole image can be obtained.
According to step S114, the face brightness value and the target brightness value of the current frame are obtainedThe difference of (a) and (b), optionally,set to 50, the luminance error is obtained:
Step S116, adjusting exposure parameters, wherein the process of adjusting the exposure parameters includes: if the motion state of the current frame is the stable state 1 and the brightness error is not detectedGreater than the human face brightness error thresholdAdjusting the exposure parameter of the next frame of image through an AE exposure adjusting module; when the brightness error is aboveNot greater than the face brightness error thresholdThe exposure parameters of the last frame image before stabilization will be maintained.
If the motion state of the current frame is motion state 1, recordingRecording current brightness errorAnd fixing the current exposure parameter, and updating historical frame information by using the current frame to ensure that the exposure of the moving human face is stable.
The exposure parameter adjusting module 95 obtains the current exposure according to the photometric system, and adjusts the exposure to obtain the brightness of the image by matching with the aperture, the exposure time, and the gain. And the exposure node adjusts the aperture, the gain and the exposure time of different effective nodes, and obtains the target exposure brightness according to the set exposure route.
The monitoring module 96 will monitor the final performance of the face image in real time, and avoid the poor face obtained by the system through timely state update. If when detecting the human face motion, the whole brightness of the image keeps stable, the human face effect is not good enough due to external light interference and other environmental factors, and the monitoring module feeds back in time to adjust. The monitoring module 96 includes a steady state monitoring module 97 and a motion state monitoring module 98.
When the current frame is in the stable state 1 and the luminance error is greater than the face luminance error threshold, the exposure parameter adjusting module 95 adjusts the exposure parameter of the next frame image. However, if the steady state monitoring module 97 detects that the overall brightness of the image background has met the upper limit or the lower limit, the exposure parameter adjustment module 95 is stopped by feedback to avoid causing overexposure or over-darkness of the overall image, and ensure the overall visual effect of the image.
When the current frame is in a stable state 1, the human face brightness error is not greater than the human face brightness error threshold valueIn this case, the steady state monitoring module 97 accumulates the number of on frames. When the accumulated number of frames is greater than the threshold of the number of frames and the face and the background reach the brightness steady state in the process, it is determined that the target face in the current scene is always in the steady state, the steady state monitoring module 97 updates the next frame from the steady state 1 to the steady state 2, and meanwhile, the first motion threshold is setUpdate to the second motion thresholdSatisfy the following requirementsHuman face luminance error thresholdUpdated to a face brightness error thresholdSatisfy the following requirements. In steady state 2, the system has a larger tolerance range to achieve higher stability of the system.
When the current frame is in the motion state 1, the exposure parameter adjusting module 95 keeps the exposure parameter of the previous stable frame, and at this time, the motion state monitoring module 98 still counts the face brightness error in real time, and when the face brightness error of the current frame is greater than the face brightness error threshold valueIn case of (2), the frame number accumulation is started immediately. When the accumulated value of the continuous frames is greater than the threshold value of the frames, the motion state monitoring module 98 updates the motion state 1 of the next frame to the motion state 2, and the threshold value of the human face brightness errorUpdated to a face brightness error thresholdAnd adjusting the exposure parameter of the next frame. When the human face brightness error is not larger than the human face brightness error threshold valueThen, the motion state 2 is updated to the motion state 1, and the human face brightness error threshold valueThen updated to the human face brightness error threshold value. Satisfy the human face brightness error thresholdThe motion brightness tolerance is enlarged, the phenomenon that the obvious face is over-bright or over-dark during the motion process and is not triggered by exposure is avoided, and the mechanism is favorable for timely adjusting the face exposure during the motion process.
In addition, when sudden face movement is excessive, such as moving out of a picture, or face detection is abnormal, such as when a face area is not captured, in order to avoid abnormal picture brightness, the monitoring module 96 adds 8 frames of pictures to maintain the previous exposure parameters, and when the face is detected again, the normal face state judgment and exposure adjustment flow is performed; if no human face information is detected in more than 8 frames of pictures, the system enters an AE exposure adjusting module for adjusting the brightness of the whole picture.
The specific embodiment provides a method and a device suitable for adaptive adjustment of brightness of multiple faces. After the face coordinates in the image are detected through an intelligent algorithm, the face coordinates are further stabilized through a preprocessing module, motion information is obtained, the motion state of the current image is judged according to the motion information obtained through calculation, and real-time adjustment is carried out according to an exposure algorithm, so that the face brightness achieves the best effect. In addition, the scheme is additionally provided with a monitoring module, and the stable exposure of the face brightness is realized by detecting and counting the conditions such as multi-face interference, motion interference, environment brightness interference and the like in real time. The method is suitable for various complex environments, wherein the image preprocessing module, the multi-face counting module and the face state judging module can better give consideration to the luminance of the face module and the whole picture, the face luminance is improved, and the luminance balance is realized; in addition, on the basis of self-adaptive adjustment of the face brightness, the overall brightness of the face image in the motion process can be effectively and stably maintained. When the face is in a moving state, the moving state and the stable state of the face are detected in real time, the face exposure module is called back, the background is considered, and stable image quality under various scenes is obtained.
In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the processor implements the above-mentioned face brightness adjustment method.
The computer equipment for adjusting the face brightness acquires the movement distance between a first face area and a second face area, judges the face state in the current frame according to the movement distance, adjusts the exposure parameters corresponding to the current frame according to the face brightness value and the face brightness threshold value in the current frame under the condition that the face state is in a stable state, and maintains the exposure parameters corresponding to the current frame under the condition that the face state is in a moving state, wherein the face brightness threshold value is dynamically adjusted according to the face state; the exposure parameters are adjusted in a stable state of the human face, the existing parameters are maintained in a moving state of the human face, and the condition that the fluctuation of an exposure algorithm causes the flickering of the picture is avoided, so that the picture brightness of the video conference is more stable and the change is smoother.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the above-mentioned face brightness adjustment method.
The computer storage medium for adjusting the face brightness obtains a movement distance between a first face area and a second face area, judges a face state in a current frame according to the movement distance, adjusts exposure parameters corresponding to the current frame according to a face brightness value and a face brightness threshold value in the current frame under the condition that the face state is a stable state, and maintains the exposure parameters corresponding to the current frame under the condition that the face state is a movement state, wherein the face brightness threshold value is dynamically adjusted according to the face state; the exposure parameters are adjusted in a stable state of the human face, the existing parameters are maintained in a moving state of the human face, and the condition that the fluctuation of an exposure algorithm causes the flickering of the picture is avoided, so that the picture brightness of the video conference is more stable and the change is smoother.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (14)
1. A face brightness adjusting method is characterized by comprising the following steps:
acquiring a movement distance between a first face area and a second face area, wherein the face area of the same face in a current frame is the first face area, and the face area in a previous frame of the current frame is the second face area;
judging the face state in the current frame according to the movement distance; under the condition that the face state is a stable state, adjusting exposure parameters corresponding to the current frame according to the face brightness value and a face brightness threshold value in the current frame; and maintaining the exposure parameter corresponding to the current frame under the condition that the face state is a motion state, wherein the face brightness threshold value is dynamically adjusted according to the face state.
2. The method according to claim 1, wherein in the case where a plurality of faces are included in the current frame, the method comprises:
and distributing a weight value to each face region according to the ratio of the area of each face region to the area of the maximum face region, wherein the weight value is used for weighting and calculating the face brightness value.
3. The method of claim 1, wherein determining the face state in the current frame according to the motion distance comprises:
under the condition that the movement distance is smaller than or equal to a preset first movement threshold, judging that the face state in the current frame is a stable state;
and under the condition that the movement distance is larger than the first movement threshold, judging that the face state in the current frame is a movement state.
4. The method of claim 3, wherein, in a case that the face state is a stable state, adjusting the exposure parameters corresponding to the current frame according to the face brightness value in the current frame and a face brightness threshold comprises:
adjusting the exposure parameter under the condition that a human face brightness error value is larger than a preset first human face brightness error threshold value, wherein the human face brightness error value is the difference value between the human face brightness value and a preset standard value, and the first human face brightness error threshold value is the difference value between the human face brightness threshold value and the preset standard value;
and under the condition that the face brightness error value is smaller than or equal to the first face brightness error threshold, accumulating the frame number, under the condition that the accumulated value of the frame number is larger than a preset first frame number threshold, updating the first motion threshold to a second motion threshold, and updating the first face brightness error threshold to a second face brightness error threshold, wherein the second motion threshold is larger than the first motion threshold, and the second face brightness error threshold is larger than the first face brightness error threshold.
5. The method according to claim 4, wherein after maintaining the exposure parameter in the case that the face state is a motion state, the method comprises:
starting frame number accumulation under the condition that the face brightness error value in the current frame is greater than a preset third face brightness error threshold;
and under the condition that the frame number accumulation is larger than a preset second frame number threshold, updating the first face brightness error threshold to a third face brightness error threshold, and adjusting the exposure parameter, wherein the third face brightness error threshold is larger than the first face brightness error threshold.
6. The method of claim 5, wherein after the adjusting the exposure parameters, the method further comprises:
and updating the third face brightness error threshold value to the first face brightness error threshold value when the face brightness error is smaller than or equal to the third face brightness error threshold value.
7. The method of claim 3, wherein in a case that the motion distance is greater than the first motion threshold, determining that the face state of the current frame is a motion state, and maintaining the exposure parameter comprises:
maintaining the exposure parameter in a first number of image frames after the current frame if the movement distance is greater than a preset movement threshold upper limit.
8. The method of claim 1, wherein, in a case that the face state is a stable state, adjusting the exposure parameters corresponding to the current frame according to the face brightness value in the current frame and a face brightness threshold comprises:
judging whether the global brightness of the current frame reaches or exceeds the range of upper and lower limit thresholds;
and stopping adjusting the exposure parameters when the global brightness reaches or exceeds the upper and lower limit threshold range.
9. The method according to claim 1, wherein in a case where a plurality of faces are included in the current frame, the obtaining of the movement distance between the first face region and the second face region comprises:
calculating the human face frame intersection ratio between the historical video frame and the current frame, and calculating to obtain the motion information of each human face in the current frame according to the human face frame intersection ratio;
and acquiring the movement distance based on the face movement information.
10. The method of claim 1, wherein prior to obtaining the movement distance between the first face region and the second face region, the method comprises:
acquiring an intersection region of the face regions in a second number of image frames, indicating that the intersection region is the first face region, wherein the second number of image frames are continuous image frames.
11. The human face brightness adjusting device is characterized by comprising a state judging module, an exposure parameter adjusting module and a monitoring module:
the state judgment module is used for acquiring the movement distance between a first face area and a second face area, wherein the face area of the same face in the current frame is the first face area, and the face area in the previous frame of the current frame is the second face area;
the exposure parameter adjusting module is used for judging the face state in the current frame according to the movement distance, adjusting the exposure parameter corresponding to the current frame according to the face brightness value and the face brightness threshold value in the current frame under the condition that the face state is in a stable state, and maintaining the exposure parameter corresponding to the current frame under the condition that the face state is in a movement state;
the monitoring module is used for dynamically adjusting the face brightness threshold value according to the face state.
12. The apparatus of claim 11, further comprising a multi-face processing module:
the multi-face processing module is configured to, when the current frame includes a plurality of faces, assign a weight value to each face region according to a ratio of an area of each face region to a maximum face region area, where the weight value is used to calculate a face brightness value in a weighted manner.
13. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the face brightness adjustment method according to any one of claims 1 to 10 when executing the computer program.
14. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the face brightness adjustment method according to any one of claims 1 to 10.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011434510 | 2020-12-10 | ||
CN2020114345101 | 2020-12-10 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112584089A true CN112584089A (en) | 2021-03-30 |
CN112584089B CN112584089B (en) | 2021-05-07 |
Family
ID=75114048
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110213508.XA Active CN112584089B (en) | 2020-12-10 | 2021-02-26 | Face brightness adjusting method and device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112584089B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113766260A (en) * | 2021-08-24 | 2021-12-07 | 武汉瓯越网视有限公司 | Face automatic exposure optimization method, storage medium, electronic device and system |
CN113891530A (en) * | 2021-09-28 | 2022-01-04 | 佛山电器照明股份有限公司 | Intelligent illumination regulation and control method, equipment and system |
CN113923372A (en) * | 2021-06-25 | 2022-01-11 | 荣耀终端有限公司 | Exposure adjusting method and related equipment |
WO2023015992A1 (en) * | 2021-08-09 | 2023-02-16 | 荣耀终端有限公司 | Exposure parameter adjustment method, and device and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120262599A1 (en) * | 2010-04-07 | 2012-10-18 | Apple Inc. | Dynamic Exposure Metering Based on Face Detection |
CN105516589A (en) * | 2015-12-07 | 2016-04-20 | 凌云光技术集团有限责任公司 | Intelligent exposure method and system based on face recognition |
CN106210523A (en) * | 2016-07-22 | 2016-12-07 | 浙江宇视科技有限公司 | A kind of exposure adjustment method and device |
CN109308469A (en) * | 2018-09-21 | 2019-02-05 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
CN110708472A (en) * | 2019-11-07 | 2020-01-17 | 重庆紫光华山智安科技有限公司 | Control method, system and equipment for inhibiting exposure of moving bright light source |
CN112040108A (en) * | 2020-09-16 | 2020-12-04 | 重庆紫光华山智安科技有限公司 | Mixed light supplement control method, system, medium and terminal for face snapshot camera |
-
2021
- 2021-02-26 CN CN202110213508.XA patent/CN112584089B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120262599A1 (en) * | 2010-04-07 | 2012-10-18 | Apple Inc. | Dynamic Exposure Metering Based on Face Detection |
CN105516589A (en) * | 2015-12-07 | 2016-04-20 | 凌云光技术集团有限责任公司 | Intelligent exposure method and system based on face recognition |
CN106210523A (en) * | 2016-07-22 | 2016-12-07 | 浙江宇视科技有限公司 | A kind of exposure adjustment method and device |
CN109308469A (en) * | 2018-09-21 | 2019-02-05 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
CN110708472A (en) * | 2019-11-07 | 2020-01-17 | 重庆紫光华山智安科技有限公司 | Control method, system and equipment for inhibiting exposure of moving bright light source |
CN112040108A (en) * | 2020-09-16 | 2020-12-04 | 重庆紫光华山智安科技有限公司 | Mixed light supplement control method, system, medium and terminal for face snapshot camera |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113923372A (en) * | 2021-06-25 | 2022-01-11 | 荣耀终端有限公司 | Exposure adjusting method and related equipment |
WO2023015992A1 (en) * | 2021-08-09 | 2023-02-16 | 荣耀终端有限公司 | Exposure parameter adjustment method, and device and storage medium |
CN113766260A (en) * | 2021-08-24 | 2021-12-07 | 武汉瓯越网视有限公司 | Face automatic exposure optimization method, storage medium, electronic device and system |
CN113891530A (en) * | 2021-09-28 | 2022-01-04 | 佛山电器照明股份有限公司 | Intelligent illumination regulation and control method, equipment and system |
Also Published As
Publication number | Publication date |
---|---|
CN112584089B (en) | 2021-05-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112584089B (en) | Face brightness adjusting method and device, computer equipment and storage medium | |
CN109936698B (en) | Automatic exposure control method and device, electronic equipment and storage medium | |
US8605945B2 (en) | Multi-mode region-of-interest video object segmentation | |
CN110505412B (en) | Method and device for calculating brightness value of region of interest | |
CN110248112B (en) | Exposure control method of image sensor | |
US8265392B2 (en) | Inter-mode region-of-interest video object segmentation | |
US8494267B2 (en) | Image processing device, image processing method, and program for normalizing a histogram | |
CN108253596B (en) | Air supply method of air conditioner, air conditioner and computer readable storage medium | |
CN105338235B (en) | A kind of automatic aperture adjusting method and device | |
CN112954315B (en) | Image focusing measurement method and system for security camera | |
CN111770285B (en) | Exposure brightness control method and device, electronic equipment and storage medium | |
CN108322666B (en) | Method and device for regulating and controlling camera shutter, computer equipment and storage medium | |
CN105827993B (en) | Adjust the method and system of image exposure degree | |
US8164685B2 (en) | Image pickup apparatus which performs aperture value control for a multiple exposure image, and recording medium | |
CN111614909B (en) | Automatic exposure control method, equipment and storage medium | |
CN111711767B (en) | Automatic exposure control method and electronic equipment | |
CN110610176A (en) | Exposure self-adaptive adjusting method based on face brightness | |
CN109996063B (en) | Video image screen splash detection method and device, computer equipment and storage medium | |
CN111970484B (en) | Operation and maintenance system and operation and maintenance method suitable for video monitoring equipment | |
CN114302226B (en) | Intelligent cutting method for video picture | |
CN114245003B (en) | Exposure control method, electronic device and storage medium | |
KR102011402B1 (en) | Intelligent Face Recognition and Tracking System and Method to Distribute GPU Resource using CUDA | |
CN115474038A (en) | Camera shielding detection method and device, electronic equipment and storage medium | |
CN109982030B (en) | Target object snapshot method and device, video monitoring equipment and storage medium | |
CN112839183B (en) | Environment self-adaptive face image recognition method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |