CN113542612B - Lens anti-shake method and device, computer equipment and storage medium - Google Patents
Lens anti-shake method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113542612B CN113542612B CN202111090319.4A CN202111090319A CN113542612B CN 113542612 B CN113542612 B CN 113542612B CN 202111090319 A CN202111090319 A CN 202111090319A CN 113542612 B CN113542612 B CN 113542612B
- Authority
- CN
- China
- Prior art keywords
- jitter
- lens
- target
- shake
- image
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000001629 suppression Effects 0.000 claims abstract description 136
- 238000011156 evaluation Methods 0.000 claims abstract description 47
- 238000012549 training Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000001502 supplementing effect Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000013441 quality evaluation Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
- H04N23/682—Vibration or motion blur correction
- H04N23/685—Vibration or motion blur correction performed by mechanical compensation
- H04N23/687—Vibration or motion blur correction performed by mechanical compensation by shifting the lens or sensor position
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
- H04N23/681—Motion detection
- H04N23/6811—Motion detection based on the image signal
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Adjustment Of Camera Lenses (AREA)
- Studio Devices (AREA)
Abstract
The application relates to a lens anti-shake method, a lens anti-shake device, a computer device and a storage medium. The method comprises the following steps: acquiring lens jitter information of a target lens; inputting the lens jitter information into an initial jitter suppression model to obtain jitter compensation parameters aiming at the target lens; adjusting the pose of the target lens according to the jitter compensation parameters to obtain an adjusted target lens; acquiring an image to be evaluated acquired through the adjusted target lens; if the image to be evaluated passes the definition evaluation, taking a jitter compensation parameter corresponding to the image to be evaluated as a target jitter compensation parameter; optimizing the initial jitter suppression model by adopting the target jitter compensation parameters to obtain a target jitter suppression model; the target jitter suppression model is used for performing jitter suppression operation on the target lens. By adopting the method, the anti-shake effect of the lens can be improved.
Description
Technical Field
The present application relates to the field of image technologies, and in particular, to a method and an apparatus for preventing camera shake, a computer device, and a storage medium.
Background
With the rapid development of the imaging technology, people are more and more pursuing to shoot high-quality images through a camera.
However, in the process of shooting, the camera is easy to shake, so that the camera is out of focus, and the shot image is not clear. In the conventional technology, technologies such as optical anti-shake and electronic anti-shake are often adopted to weaken the influence of camera shake on image definition, but the problem of poor quality of shot images caused by poor anti-shake effect still exists.
Therefore, the conventional technology has a problem of poor anti-shake effect of the lens.
Disclosure of Invention
In view of the above, it is desirable to provide a lens anti-shake method, apparatus, computer device and storage medium capable of improving the lens anti-shake effect.
A lens anti-shake method, the method comprising:
acquiring lens jitter information of a target lens;
inputting the lens jitter information into an initial jitter suppression model to obtain jitter compensation parameters aiming at the target lens;
adjusting the pose of the target lens according to the jitter compensation parameters to obtain an adjusted target lens;
acquiring an image to be evaluated acquired through the adjusted target lens;
if the image to be evaluated passes the definition evaluation, taking a jitter compensation parameter corresponding to the image to be evaluated as a target jitter compensation parameter;
optimizing the initial jitter suppression model by adopting the target jitter compensation parameters to obtain a target jitter suppression model; the target jitter suppression model is used for performing jitter suppression operation on the target lens.
In one embodiment, the inputting the lens shake information into an initial shake suppression model to obtain a shake compensation parameter for the target lens includes:
inputting the lens jitter information into the initial jitter suppression model to trigger the initial jitter suppression model to acquire a jitter compensation parameter table; the shake compensation parameters in the shake compensation parameter table are determined and obtained according to the focus depth range of the target lens;
and inquiring a shake compensation parameter corresponding to the lens shake information in the shake compensation parameter table through the initial shake suppression model.
In one embodiment, the jitter compensation parameter table records a corresponding relationship between the lens jitter information and a plurality of sets of jitter compensation parameters; the optimizing the initial jitter suppression model by using the target jitter compensation parameter to obtain a target jitter suppression model includes:
determining a jitter compensation parameter to be deleted in the plurality of groups of jitter compensation parameters; the jitter compensation parameters to be deleted are jitter compensation parameters except the target jitter compensation parameters in a plurality of groups of jitter compensation parameters;
deleting the corresponding relation between the lens jitter information and the jitter compensation parameters to be deleted in the jitter compensation parameter table to obtain an updated jitter compensation parameter table;
and obtaining the target jitter suppression model according to the updated jitter compensation parameter table.
In one embodiment, the target lens is connected with a lens driving motor, and the lens driving motor is further electrically connected with a motor driver; the adjusting the pose of the target lens according to the shake compensation parameter to obtain the adjusted target lens comprises:
generating a corresponding motor control signal according to the jitter compensation parameter;
sending the motor control signal to the motor driver; the motor driver is used for inputting corresponding current magnitude and change frequency to the lens driving motor according to the motor control signal so as to control the lens driving motor to adjust the pose of the target lens.
In one embodiment, the jitter compensation parameters have a plurality of sets, and the method further comprises:
if the image to be evaluated does not pass the definition evaluation, adjusting the pose of the target lens by adopting the next group of jitter compensation parameters of the jitter compensation parameters to obtain an adjusted target lens;
and returning to the step of acquiring the image to be evaluated acquired through the adjusted target lens until the image to be evaluated passes the definition evaluation.
In one embodiment, after the step of acquiring the image to be evaluated acquired through the adjusted target lens, the method further includes:
performing definition quantitative scoring on the image to be evaluated to obtain a definition score corresponding to the image to be evaluated;
if the definition score is smaller than a preset score threshold value, judging that the image to be evaluated does not pass the definition evaluation;
and if the definition score is greater than or equal to the preset score threshold, judging that the image to be evaluated passes the definition evaluation.
In one embodiment, the optimizing the initial jitter suppression model by using the target jitter compensation parameter to obtain a target jitter suppression model includes:
generating a model training sample according to the corresponding relation between the lens jitter information and the target jitter compensation parameter;
supplementing the model training sample to a sample parameter library to obtain a supplemented sample parameter library;
and training the initial jitter suppression model by adopting the supplemented sample parameter library to obtain the target jitter suppression model.
An anti-shake apparatus for a lens, the apparatus comprising:
the information acquisition module is used for acquiring lens jitter information of the target lens;
the information input module is used for inputting the lens jitter information into an initial jitter suppression model to obtain jitter compensation parameters aiming at the target lens;
the lens adjusting module is used for adjusting the pose of the target lens according to the jitter compensation parameters to obtain an adjusted target lens;
the image acquisition module is used for acquiring the image to be evaluated acquired through the adjusted target lens;
the parameter determination module is used for taking the jitter compensation parameter corresponding to the image to be evaluated as a target jitter compensation parameter if the image to be evaluated passes the definition evaluation;
the model optimization module is used for optimizing the initial jitter suppression model by adopting the target jitter compensation parameters to obtain a target jitter suppression model; the target jitter suppression model is used for performing jitter suppression operation on the target lens.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when executing the computer program.
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 above-mentioned method.
The lens anti-shake method, the device, the computer equipment and the storage medium acquire the lens shake information of the target lens; inputting lens jitter information into an initial jitter suppression model to obtain jitter compensation parameters aiming at the target lens; adjusting the pose of the target lens according to the shake compensation parameters to obtain an adjusted target lens; acquiring an image to be evaluated acquired through the adjusted target lens; if the image to be evaluated passes the definition evaluation, taking the jitter compensation parameter corresponding to the image to be evaluated as a target jitter compensation parameter; optimizing the initial jitter suppression model by adopting the target jitter compensation parameters to obtain a target jitter suppression model; therefore, when the lens in a shooting state shakes, the target shake suppression model can be adopted to quickly acquire the target shake compensation parameters corresponding to the lens shake information of the lens, so that the motor can be controlled to drive the lens to move reversely relative to the shaking direction by utilizing the target shake compensation parameters, the shaking of the lens is suppressed, and the anti-shaking effect of the lens is improved.
Drawings
FIG. 1 is a flowchart illustrating a lens anti-shake method according to an embodiment;
FIG. 2 is a block diagram of a camera anti-shake system in one embodiment;
FIG. 3 is a flowchart illustrating a lens anti-shake method according to another embodiment;
FIG. 4 is a logic flow diagram illustrating another lens anti-shake method according to an embodiment;
FIG. 5 is a block diagram of an embodiment of an anti-shake apparatus for lens;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
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.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, a first location can be termed a second location, and, similarly, a second location can be termed a first location, without departing from the scope of the present application. The first position and the second position are both positions, but they are not the same position.
In one embodiment, as shown in fig. 1, there is provided a lens anti-shake method, including the steps of:
in step S110, lens shake information of the target lens is acquired.
Wherein the lens shake information includes at least one of frequency information, amplitude information, and direction information.
The target lens may be a lens in a camera anti-shake system.
The lens can be, but is not limited to, various fixed focus lenses, zoom lenses, wide-angle lenses, standard lenses, and the like, and generally comprises a plurality of lenses and has an imaging function.
In particular implementations, to facilitate understanding by those skilled in the art, fig. 2 provides a camera anti-shake system in one embodiment. The camera anti-shake system includes an image sensor 210, a lens driving motor 220, a motor driver 230, a motion control sensor 240, a target lens 250, and a control unit 260; the motion control sensor 240 and the image sensor 210 are electrically connected to the control unit 260, the control unit 260 is electrically connected to the motor driver 230, the motor driver 230 is electrically connected to the lens driving motor 220, and the lens driving motor 220 is drivingly connected to the target lens 250; the motion control sensor 240 may be, but is not limited to, an acceleration sensor, a gyroscope, or the like; when shooting is performed by using the target lens 250, whether the target lens 250 shakes can be detected by the motion control sensor 240, and when the target lens 250 shakes, the motion control sensor 240 can send shaking information of the target lens 250 to the control unit 260, wherein the shaking information includes at least one of frequency information, amplitude information and direction information; the gyroscope can detect angular velocity information of the target lens 250 in one or more directions, so as to judge the shaking condition of the target lens 250 according to the detected angular velocity information, and send the output frequency of the acquired angular velocity information, the bandwidth of the angular velocity information and the measurement range of the angular velocity information to the control unit 260; the control Unit 260 may be, but not limited to, a CPU (Central Processing Unit), an MCU (micro controller Unit), and an ISP (Image Signal Processing).
Step S120, inputting the lens shake information to the initial shake suppression model to obtain a shake compensation parameter for the target lens.
The initial jitter suppression model is obtained by presetting the corresponding relation between the lens jitter information and the jitter compensation parameters, and is used for acquiring the jitter compensation parameters corresponding to the lens jitter information.
The shake compensation parameter is a parameter for compensating for shake generated in the target lens, and may include compensation offsets corresponding to different shake information target lenses.
In a specific implementation, after the control unit 260 receives the lens shake information of the target lens 250 sent by the motion control sensor 240, the lens shake information of the target lens 250 is input to the initial shake suppression model, and shake compensation parameters corresponding to the lens shake information are output from the initial shake suppression model; more than one set of shake compensation parameters corresponding to the lens shake information is provided.
And step S130, adjusting the pose of the target lens according to the shake compensation parameters to obtain the adjusted target lens.
Wherein the pose of the objective lens is the position and the posture of the objective lens 250.
In a specific implementation, when the target lens 250 shakes, the target lens 250 may shift a certain distance in a certain direction, and the lens driving motor 220 adjusts the position and posture of the target lens 250 according to an electrical signal obtained through the shake compensation parameter, and drives the target lens 250 to move, so that the target lens 250 compensates for a certain distance in the opposite direction of shaking, thereby obtaining the adjusted target lens 250.
And step S140, acquiring the image to be evaluated acquired through the adjusted target lens.
The image to be evaluated is an image needing to be subjected to definition evaluation.
In a specific implementation, the target lens 250 may collect light in a shooting scene, and the image sensor 210 converts the light collected by the target lens 250 into an image, so that the control unit 260 may obtain the image collected by the target lens 250, and because there is more than one group of shake compensation parameters corresponding to lens shake information, the target lens 250 may sequentially perform image collection under adjustment of each shake compensation parameter, obtain each image to be evaluated corresponding to each shake compensation parameter, and perform image sharpness evaluation.
Step S150, if the image to be evaluated passes the definition evaluation, the jitter compensation parameter corresponding to the image to be evaluated is used as the target jitter compensation parameter.
In a specific implementation, the control unit 260 sequentially performs image quality evaluation on each image to be evaluated acquired by the target lens 250, so as to determine whether the image to be evaluated is clear, if the image to be evaluated meets a preset condition, it is determined that the image to be evaluated acquired by the target lens 250 passes through the definition evaluation, and a shake compensation parameter corresponding to the image to be evaluated is used as a target shake compensation parameter for the target lens 250.
Step S160, optimizing the initial jitter suppression model by adopting the target jitter compensation parameters to obtain a target jitter suppression model; the target jitter suppression model is used for performing jitter suppression operation on the target lens.
Wherein optimizing the initial jitter suppression model comprises at least one of adjusting the initial jitter suppression model or training the initial jitter suppression model.
In specific implementation, after a target shake compensation parameter corresponding to the lens shake information of the target lens 250 is determined, the corresponding relationship between the lens shake information and the shake compensation parameter in the initial shake suppression model can be optimized; if the initial jitter suppression model includes a parameter table recorded with a corresponding relationship between the lens jitter information and a plurality of sets of jitter compensation parameters, the parameter table may be adjusted according to a target jitter compensation parameter corresponding to the lens jitter information, so as to obtain a target jitter suppression model for the target lens 250; if the initial jitter suppression model comprises a neural network model to be trained, a training sample can be generated according to the lens jitter information and the corresponding target jitter compensation parameter, and the training sample is adopted to train the initial jitter suppression model, so that a target jitter suppression model for the target lens 250 is obtained; by the target jitter suppression model, jitter suppression on the target lens 250 can be quickly realized for jitter of the target lens 250 under different scenes.
In the lens anti-shake method, the lens shake information of the target lens is acquired; inputting lens jitter information into an initial jitter suppression model to obtain jitter compensation parameters aiming at the target lens; adjusting the pose of the target lens according to the shake compensation parameters to obtain an adjusted target lens; acquiring an image to be evaluated acquired through the adjusted target lens; if the image to be evaluated passes the definition evaluation, taking the jitter compensation parameter corresponding to the image to be evaluated as a target jitter compensation parameter; optimizing the initial jitter suppression model by adopting the target jitter compensation parameters to obtain a target jitter suppression model; therefore, when the lens in a shooting state shakes, the target shake suppression model can be adopted to quickly acquire the target shake compensation parameters corresponding to the lens shake information of the lens, so that the motor can be controlled to drive the lens to move reversely relative to the shaking direction by utilizing the target shake compensation parameters, the shaking of the lens is suppressed, and the anti-shaking effect of the lens is improved.
In another embodiment, inputting the lens shake information into the initial shake suppression model to obtain a shake compensation parameter for the target lens includes: inputting lens jitter information into an initial jitter suppression model to trigger the initial jitter suppression model to acquire a jitter compensation parameter table; the shake compensation parameters in the shake compensation parameter table are determined according to the focus depth range of the target lens; and inquiring a shake compensation parameter corresponding to the lens shake information in a shake compensation parameter table through the initial shake suppression model.
The initial jitter suppression model is obtained by presetting the corresponding relation between the lens jitter information and the jitter compensation parameters, and is used for acquiring the jitter compensation parameters corresponding to the lens jitter information.
The focus depth range may refer to a range of distances between the front and rear of the subject measured at the front edge of the target lens or other imager to obtain a sharp image.
In a specific implementation, the control unit 260 inputs the received lens shake information into the initial shake suppression model, and then the initial shake suppression model extracts a shake compensation parameter table recorded in the model, where shake compensation parameters corresponding to the lens shake information are stored in the shake compensation parameter table; the shake compensation parameter is determined according to the focus depth range of the target lens 250, and specifically, the control unit 260 may determine the value range of the shake compensation parameter according to the value range of the focus depth parameter; according to the value range of the jitter compensation parameter, the control unit 260 may allocate a plurality of corresponding sets of jitter compensation parameters to each set of lens jitter information and record the jitter compensation parameters in the jitter compensation parameter table, so that the jitter compensation parameter corresponding to the lens jitter information of the target lens 250 may be obtained according to the jitter compensation parameter table.
According to the technical scheme, the shake compensation parameters which are recorded in the shake compensation parameter table and correspond to the lens shake information input into the initial shake suppression model can be obtained through the shake compensation parameter table in the initial shake suppression model, namely, the shake compensation parameters corresponding to different lens shake information can be obtained, and therefore the accuracy of anti-shake operation on the lens can be improved.
In another embodiment, the jitter compensation parameter table records a corresponding relationship between the lens jitter information and a plurality of sets of jitter compensation parameters; optimizing the initial jitter suppression model by adopting the target jitter compensation parameters to obtain a target jitter suppression model, comprising the following steps of: determining jitter compensation parameters to be deleted in a plurality of groups of jitter compensation parameters; deleting the corresponding relation between the lens jitter information and the jitter compensation parameters to be deleted in the jitter compensation parameter table to obtain an updated jitter compensation parameter table; and obtaining the target jitter suppression model according to the updated jitter compensation parameter table.
The initial jitter suppression model is obtained by presetting the corresponding relation between the lens jitter information and the jitter compensation parameters, and is used for acquiring the jitter compensation parameters corresponding to the lens jitter information.
The target jitter suppression model comprises a corresponding relation between lens jitter information and target jitter compensation parameters.
The jitter compensation parameters to be deleted are jitter compensation parameters except for the target jitter compensation parameters in the plurality of groups of jitter compensation parameters.
And the target jitter compensation parameter is used for carrying out jitter suppression operation on the target lens.
In the specific implementation, the control unit 260 evaluates the definition of the image to be evaluated acquired by the target lens 250, determines the jitter compensation parameters corresponding to the image to be evaluated, which is evaluated by the definition, as target jitter compensation parameters, and according to the target jitter compensation parameters, the control unit 260 deletes the jitter compensation parameters other than the target jitter compensation parameters from the jitter compensation parameter table acquired by the initial jitter suppression model, i.e. only maintains the corresponding relationship between the lens jitter information of the target lens 250 and the target jitter compensation parameters, so that the lens jitter information of the target lens 250 only corresponds to one group of jitter compensation parameters, obtains an updated initial jitter suppression model, determines the target jitter suppression model, and when the target lens 250 shakes, the control unit 260 will quickly obtain the target shake compensation parameters corresponding to the lens shake information from the target shake suppression model according to the lens shake information, and perform shake compensation processing on the target lens 250.
In the technical scheme of this embodiment, a shake compensation parameter table of an initial shake suppression model is deleted for shake compensation parameters except for the target shake compensation parameter in a plurality of groups of shake compensation parameters, and only the corresponding relationship between lens shake information and the target shake compensation parameter is reserved in the shake compensation parameter table, so that the initial shake suppression model is updated to obtain a target shake suppression model; therefore, when the target lens shakes, the target shake compensation parameters corresponding to the lens shake information can be rapidly output from the target shake suppression model according to the lens shake information, the offset of the target lens is compensated, the influence caused by the shake of the target lens is weakened, and the anti-shake effect of the target lens is effectively improved.
In another embodiment, the target lens is connected with a lens driving motor, and the lens driving motor is also electrically connected with the motor driver; adjusting the pose of the target lens according to the shake compensation parameters to obtain an adjusted target lens, comprising: generating a corresponding motor control signal according to the jitter compensation parameter; sending a motor control signal to a motor driver; the motor driver is used for inputting corresponding current magnitude and change frequency to the lens driving motor according to the motor control signal so as to control the lens driving motor to adjust the pose of the target lens.
Wherein, the lens driving motor may be a voice coil motor.
The motor driver may be a driving chip.
And the pose of the target lens is the position and the posture of the target lens.
In a specific implementation, the target lens 250 is connected to a lens driving motor 220, the lens driving motor 220 is further electrically connected to a motor driver 230, and the motor driver 230 is connected to the control unit 260; after acquiring the shake compensation parameter, the control unit 260 sends a motor control signal to the motor driver 230, and the motor driver 230 generates an electrical signal for controlling the lens driving motor 220 according to the motor control signal; in this embodiment, the electrical signal is a current signal, a voltage signal, or another type of electrical signal, the motor driver 230 inputs a current magnitude and a current change frequency to the lens driving motor 220, and the lens driving motor 220 can drive the target lens 250 to move after receiving the current signal, so as to adjust the position and the posture of the target lens 250.
Specifically, the shake compensation parameter includes compensation offsets corresponding to different shake information target lenses 250, the compensation offsets being distances that the target lenses 250 need to move in a certain direction in order to reduce a shake-induced deviation. After receiving the motor control signal generated according to the jitter compensation parameter, the motor driver 230 generates a corresponding current signal and inputs the current signal to the lens driving motor 220; the current signal comprises a signal intensity and a direction mark corresponding to the compensation offset; the compensation offset can be determined according to any point position of the plane where the target lens 250 is located, for example, according to the center of the target lens 250, or according to other points on the target lens 250; for example, if the position of the optical center of the target lens 250 is the first position when the camera anti-shake system is stationary, and the second position is the position of the optical center of the target lens 250 after the lens driving motor 220 drives the target lens 250 to move, that is, the offset includes a vector distance between the first position and the second position, therefore, the current signal received by the lens driving motor 220 includes a signal strength and a direction indicator, the signal strength is used to indicate the magnitude of the output current, according to the magnitude of the signal strength, the lens driving motor 220 can push the target lens 250 to move different distances, and generally, the larger the current is in the same time range, the larger the distance the lens driving motor 220 drives the target lens 250 to move is; the smaller the current, the smaller the distance that the lens driving motor 220 drives the target lens 250 to move; the direction flag is used to indicate a driving direction of the target lens 250; the lens driving motor 220 may be powered on according to the direction identifier and the signal strength included in the current signal, and drive the target lens 250 to move by a distance corresponding to the compensation offset in the direction opposite to the shake, so as to compensate the offset of the target lens 250 caused by the shake, to eliminate the offset caused by the shake of the target lens 250, and to complete the operation of adjusting the position and the posture of the target lens 250.
According to the technical scheme of the embodiment, the motor driver sends the motor control signal corresponding to the jitter compensation parameter to the motor driver, and the motor driver inputs the corresponding current signal to the lens driving motor according to the motor control signal; therefore, the lens driving motor can control the target lens to move for a certain distance in the direction opposite to the shaking direction, so that the offset of the target lens caused by shaking can be compensated, the deviation of the target lens caused by shaking is reduced, and the accuracy of anti-shaking compensation processing of the target lens can be improved.
In another embodiment, the jitter compensation parameters have a plurality of sets, the method further comprising: if the image to be evaluated does not pass the definition evaluation, adjusting the pose of the target lens by adopting the next group of shake compensation parameters of the shake compensation parameters to obtain an adjusted target lens; and returning to the step of acquiring the image to be evaluated acquired through the adjusted target lens until the image to be evaluated passes the definition evaluation.
The definition evaluation is used for evaluating whether the definition of the image to be evaluated reaches a preset condition.
In a specific implementation, after the image sensor 210 converts the light collected by the target lens 250 into an image to be evaluated, the control unit 260 performs sharpness evaluation on the image to be evaluated. When the control unit 260 determines that the current image to be evaluated does not reach the preset condition, that is, does not pass the definition evaluation, the control unit 260 adjusts the position and the posture of the target lens 250 according to the next group of shake compensation parameters by using the next group of shake compensation parameters of the shake compensation parameters corresponding to the current image to be evaluated which does not pass the definition evaluation, controls the target lens 250 to acquire a new image to be evaluated, and executes the image definition evaluation operation again; if the new image to be evaluated still fails in the sharpness evaluation, the step of "obtaining the next group of jitter compensation parameters of the jitter compensation parameters corresponding to the image to be evaluated that does not pass the sharpness evaluation" is returned to be executed until the image to be evaluated corresponding to the jitter compensation parameters obtained by the control unit 260 passes the sharpness evaluation, and the image sharpness evaluation operation is ended.
According to the technical scheme of the embodiment, the images to be evaluated corresponding to the jitter compensation parameters are sequentially acquired, and the definition of the images to be evaluated is evaluated until the images to be evaluated corresponding to the adopted jitter compensation parameters are evaluated through the definition, so that the images acquired by the target lens are evaluated through the definition, and the definition of the images acquired by the target lens is improved.
In another embodiment, after the step of acquiring the image to be evaluated acquired through the adjusted target lens, the method further includes: carrying out definition quantitative scoring on the image to be evaluated to obtain a definition score corresponding to the image to be evaluated; if the definition score is smaller than a preset score threshold value, judging that the image to be evaluated does not pass the definition evaluation; and if the definition score is greater than or equal to a preset score threshold value, judging that the image to be evaluated passes the definition evaluation.
The definition quantitative scoring method is completed by evaluating the image quality of the image to be evaluated.
In a specific implementation, after the control unit 260 acquires the image to be evaluated acquired by the adjusted target lens 250, the definition of the image is quantitatively scored through an image quality evaluation method, so as to obtain a definition score corresponding to the image to be evaluated. The image quality evaluation method may be, but is not limited to, a calculation model such as PSNR (Peak Signal to Noise Ratio), SSIM (Structural Similarity Index), MS-SSIM (Multi Scale Structural Similarity Index), and the like. When the definition score of the image to be evaluated is greater than or equal to a score threshold value set in advance, the control unit 260 judges that the definition of the image to be evaluated meets a preset condition, namely the image to be evaluated is an image up to the standard through definition evaluation; if the sharpness score of the image to be evaluated is smaller than the preset score threshold, the control unit 260 determines that the image to be evaluated does not pass the sharpness evaluation and is an image which does not reach the standard.
According to the technical scheme of the embodiment, the definition quantitative scoring is carried out on the image to be evaluated through the preset scoring threshold value, so that the definition score corresponding to the image to be evaluated is obtained, and is compared with the preset scoring threshold value to judge whether the image to be evaluated passes the definition evaluation; and then, according to the definition evaluation judgment result of the image with evaluation, whether the target lens is focused accurately can be evaluated, and the image collected by the target lens is clear enough.
In another embodiment, optimizing the initial jitter suppression model by using the target jitter compensation parameter to obtain a target jitter suppression model, includes: generating a model training sample according to the corresponding relation between the lens jitter information and the target jitter compensation parameter; supplementing the model training sample to a sample parameter library to obtain a supplemented sample parameter library; and training the initial jitter suppression model by adopting the supplemented sample parameter library to obtain a target jitter suppression model.
The initial jitter suppression model may be a neural network model to be trained.
Wherein, the model training sample is a labeled sample.
The sample parameter library includes a corresponding relationship between the lens jitter information and the corresponding target jitter compensation parameter.
In a specific implementation, the initial jitter suppression model is a neural network model established in advance. The control unit 260 may generate a model training sample for training the initial shake suppression model according to each group of lens shake information and a target shake compensation parameter corresponding to each group of lens shake information; the control unit 260 uses the lens shake information as a sample feature in the neural network model, and uses the target shake compensation parameter as a sample label in the neural network model. The control unit 260 supplements the model training sample to the sample parameter library to obtain a supplemented sample parameter library, and then trains the initial jitter suppression model according to the model training sample in the supplemented sample parameter library to obtain a target jitter suppression model. Specifically, the control unit 260 inputs the lens shake information to the initial shake suppression model to obtain a predicted shake compensation parameter; and adjusting model parameters of the initial jitter suppression model based on the difference between the predicted jitter compensation parameter and the target jitter compensation parameter until the adjusted initial jitter suppression model meets a preset training end condition, thereby obtaining the target jitter suppression model.
According to the technical scheme of the embodiment, a model training sample is generated according to each group of lens jitter information and a target jitter compensation parameter corresponding to each group of lens jitter information, the model training sample is supplemented into a sample parameter library, and finally an initial jitter suppression model is trained by using the supplemented sample parameter library; therefore, the target shake suppression model can be obtained, when the target lens in a shooting state shakes, the target shake suppression model can be adopted to quickly acquire the target shake compensation parameters corresponding to the lens shake information of the target lens, so that the target shake compensation parameters can be utilized to control the motor to drive the target lens to move reversely relative to the shaking direction, the offset caused by shaking of the target lens can be accurately compensated, and the reliability of shake suppression operation for the target lens can be improved.
In another embodiment, as shown in fig. 3, a lens anti-shake method is provided, which is described by taking the method as an example applied to the control unit 260 in fig. 2, and includes the following steps: in step S302, lens shake information of the target lens is acquired. Step S304, inputting the lens shake information into the initial shake suppression model to trigger the initial shake suppression model to acquire a shake compensation parameter table; and the shake compensation parameters in the shake compensation parameter table are determined and obtained according to the focusing depth of field range of the target lens. Step S306, querying a shake compensation parameter corresponding to the lens shake information in the shake compensation parameter table through the initial shake suppression model. And S308, adjusting the pose of the target lens according to the shake compensation parameters to obtain the adjusted target lens. And step S310, acquiring the image to be evaluated acquired through the adjusted target lens. In step S312, if the image to be evaluated passes the sharpness evaluation, the shake compensation parameter corresponding to the image to be evaluated is used as the target shake compensation parameter. Step S314, the jitter compensation parameter table records the corresponding relationship between the lens jitter information and the multiple sets of jitter compensation parameters; determining a jitter compensation parameter to be deleted in the plurality of groups of jitter compensation parameters; the jitter compensation parameters to be deleted are jitter compensation parameters except the target jitter compensation parameters in a plurality of groups of jitter compensation parameters. Step S316, deleting the correspondence between the lens shake information and the shake compensation parameter to be deleted in the shake compensation parameter table, to obtain an updated shake compensation parameter table. Step S318, obtaining the target jitter suppression model according to the updated jitter compensation parameter table. It should be noted that, for the specific limitations of the above steps, reference may be made to the above specific limitations of a lens anti-shake method.
To facilitate understanding by those skilled in the art, fig. 4 provides a logic flow diagram of another lens anti-shake method; firstly, a control unit acquires lens shaking information of a target lens through a motion control sensor; the lens shake information comprises at least one of frequency information, amplitude information and direction information; then, the control unit combines the initial jitter suppression model to output a group of jitter compensation parameters for driving a Voice Coil Motor (VCM) to control the movement of the target lens so as to suppress the relative movement of the target lens; the initial jitter suppression model comprises the corresponding relation between lens jitter information and a plurality of groups of jitter compensation parameters; then, according to the group of shake compensation parameters, the VCM motor drives the target lens to move, and the image sensor collects an image shot by focusing of the target lens; secondly, the control unit carries out definition evaluation on the focusing result of the image; if the image passes the definition evaluation, taking the jitter compensation parameter corresponding to the image as a target jitter compensation parameter; then, generating model training samples according to each group of lens shaking information and target shaking compensation parameters corresponding to each group of lens shaking information, and supplementing the model training samples to a sample parameter library to obtain a supplemented sample parameter library; finally, optimizing the initial jitter suppression model by adopting the supplemented sample parameter library to obtain a target jitter suppression model; the target jitter suppression model is used for performing jitter suppression operation on a target lens; if the image does not pass the definition evaluation, the next group of shake compensation parameters of the shake compensation parameters corresponding to the current image are obtained through the initial shake suppression model, the steps of driving the target lens to move by the VCM motor and acquiring the image shot by focusing of the target lens by the image sensor are returned until the focusing result of the acquired image passes the definition evaluation, and the whole process is ended.
It should be understood that although the steps in the flowcharts of fig. 1, 3 and 4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order 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, 3 and 4 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 5, there is provided a lens anti-shake apparatus including: an information acquisition module 510, an information input module 520, a lens adjustment module 530, an image acquisition module 540, a parameter determination module 550, and a model optimization module 560, wherein:
an information obtaining module 510, configured to obtain lens shake information of the target lens.
An information input module 520, configured to input the lens shake information to an initial shake suppression model, so as to obtain a shake compensation parameter for the target lens.
And a lens adjusting module 530, configured to adjust the pose of the target lens according to the shake compensation parameter, so as to obtain an adjusted target lens.
And an image obtaining module 540, configured to obtain an image to be evaluated, which is acquired through the adjusted target lens.
A parameter determining module 550, configured to, if the image to be evaluated passes the sharpness evaluation, take a shake compensation parameter corresponding to the image to be evaluated as a target shake compensation parameter.
A model optimization module 560, configured to optimize the initial jitter suppression model by using the target jitter compensation parameter to obtain a target jitter suppression model; the target jitter suppression model is used for performing jitter suppression operation on the target lens.
In one embodiment, the information input module 520 is specifically configured to input the lens shake information to the initial shake suppression model to trigger the initial shake suppression model to obtain a shake compensation parameter table; the shake compensation parameters in the shake compensation parameter table are determined and obtained according to the focus depth range of the target lens; and inquiring a shake compensation parameter corresponding to the lens shake information in the shake compensation parameter table through the initial shake suppression model.
In one embodiment, the jitter compensation parameter table records a corresponding relationship between the lens jitter information and a plurality of sets of jitter compensation parameters; the model optimization module 560 is specifically configured to determine a jitter compensation parameter to be deleted from the multiple sets of jitter compensation parameters; the jitter compensation parameters to be deleted are jitter compensation parameters except the target jitter compensation parameters in a plurality of groups of jitter compensation parameters; deleting the corresponding relation between the lens jitter information and the jitter compensation parameters to be deleted in the jitter compensation parameter table to obtain an updated jitter compensation parameter table; and obtaining the target jitter suppression model according to the updated jitter compensation parameter table.
In one embodiment, the target lens is connected with a lens driving motor, and the lens driving motor is further electrically connected with a motor driver; the lens adjusting module 530 is specifically configured to generate a corresponding motor control signal according to the jitter compensation parameter; sending the motor control signal to the motor driver; the motor driver is used for inputting corresponding current magnitude and change frequency to the lens driving motor according to the motor control signal so as to control the lens driving motor to adjust the pose of the target lens.
In one embodiment, the shake compensation parameters have a plurality of sets, and the lens anti-shake apparatus further includes: a lens readjustment module, configured to adjust the pose of the target lens by using a next set of shake compensation parameters of the shake compensation parameters if the image to be evaluated fails to pass the sharpness evaluation, so as to obtain an adjusted target lens; and the return module is used for returning to the step of acquiring the image to be evaluated acquired through the adjusted target lens until the image to be evaluated passes the definition evaluation.
In one embodiment, the lens anti-shake apparatus further includes: the grading module is used for carrying out definition quantitative grading on the image to be evaluated to obtain a definition grade corresponding to the image to be evaluated; the judging module is used for judging that the image to be evaluated does not pass the definition evaluation if the definition score is smaller than a preset score threshold; and if the definition score is greater than or equal to the preset score threshold, judging that the image to be evaluated passes the definition evaluation.
In one embodiment, the model optimization module 560 is further configured to generate a model training sample according to a correspondence between the lens shake information and a target shake compensation parameter; supplementing the model training sample to a sample parameter library to obtain a supplemented sample parameter library; and training the initial jitter suppression model by adopting the supplemented sample parameter library to obtain the target jitter suppression model.
For specific definition of a lens anti-shake apparatus, refer to the definition of a lens anti-shake method above, and will not be described herein again. Each module in the lens anti-shake apparatus may be wholly or partially implemented by software, hardware, or 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.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing the lens anti-shake data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a lens anti-shake method.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, the computer program, when executed by the processor, causing the processor to perform the steps of a lens anti-shake method as described above. The steps of a lens anti-shake method herein may be steps in a lens anti-shake method of the above-mentioned embodiments.
In one embodiment, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the processor is caused to execute the steps of the lens anti-shake method. The steps of a lens anti-shake method herein may be steps in a lens anti-shake method of the above-mentioned embodiments.
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 can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
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 (10)
1. A lens anti-shake method is characterized by comprising the following steps:
acquiring lens jitter information of a target lens;
inputting the lens jitter information into an initial jitter suppression model to obtain jitter compensation parameters aiming at the target lens;
adjusting the pose of the target lens according to the jitter compensation parameters to obtain an adjusted target lens;
acquiring an image to be evaluated acquired through the adjusted target lens;
if the image to be evaluated passes the definition evaluation, taking a jitter compensation parameter corresponding to the image to be evaluated as a target jitter compensation parameter;
optimizing the initial jitter suppression model by adopting the target jitter compensation parameters to obtain a target jitter suppression model; the target jitter suppression model is used for performing jitter suppression operation on the target lens.
2. The method according to claim 1, wherein the inputting the lens shake information into an initial shake suppression model to obtain a shake compensation parameter for the target lens comprises:
inputting the lens jitter information into the initial jitter suppression model to trigger the initial jitter suppression model to acquire a jitter compensation parameter table; the shake compensation parameters in the shake compensation parameter table are determined and obtained according to the focus depth range of the target lens;
and inquiring a shake compensation parameter corresponding to the lens shake information in the shake compensation parameter table through the initial shake suppression model.
3. The method according to claim 2, wherein the jitter compensation parameter table records a corresponding relationship between the lens jitter information and a plurality of sets of jitter compensation parameters; the optimizing the initial jitter suppression model by using the target jitter compensation parameter to obtain a target jitter suppression model includes:
determining a jitter compensation parameter to be deleted in the plurality of groups of jitter compensation parameters; the jitter compensation parameters to be deleted are jitter compensation parameters except the target jitter compensation parameters in a plurality of groups of jitter compensation parameters;
deleting the corresponding relation between the lens jitter information and the jitter compensation parameters to be deleted in the jitter compensation parameter table to obtain an updated jitter compensation parameter table;
and obtaining the target jitter suppression model according to the updated jitter compensation parameter table.
4. The method of claim 1, wherein a lens driving motor is connected to the target lens, the lens driving motor further electrically connected to a motor driver; the adjusting the pose of the target lens according to the shake compensation parameter to obtain the adjusted target lens comprises:
generating a corresponding motor control signal according to the jitter compensation parameter;
sending the motor control signal to the motor driver; the motor driver is used for inputting corresponding current magnitude and change frequency to the lens driving motor according to the motor control signal so as to control the lens driving motor to adjust the pose of the target lens.
5. The method of claim 1, wherein the jitter compensation parameters have a plurality of sets, the method further comprising:
if the image to be evaluated does not pass the definition evaluation, adjusting the pose of the target lens by adopting the next group of jitter compensation parameters of the jitter compensation parameters to obtain an adjusted target lens;
and returning to the step of acquiring the image to be evaluated acquired through the adjusted target lens until the image to be evaluated passes the definition evaluation.
6. The method of claim 5, wherein after the step of acquiring the image to be evaluated captured by the adjusted target shot, the method further comprises:
performing definition quantitative scoring on the image to be evaluated to obtain a definition score corresponding to the image to be evaluated;
if the definition score is smaller than a preset score threshold value, judging that the image to be evaluated does not pass the definition evaluation;
and if the definition score is greater than or equal to the preset score threshold, judging that the image to be evaluated passes the definition evaluation.
7. The method of claim 1, wherein optimizing the initial jitter suppression model using the target jitter compensation parameter to obtain a target jitter suppression model comprises:
generating a model training sample according to the corresponding relation between the lens jitter information and the target jitter compensation parameter;
supplementing the model training sample to a sample parameter library to obtain a supplemented sample parameter library;
and training the initial jitter suppression model by adopting the supplemented sample parameter library to obtain the target jitter suppression model.
8. An anti-shake apparatus for a lens, the apparatus comprising:
the information acquisition module is used for acquiring lens jitter information of the target lens;
the information input module is used for inputting the lens jitter information into an initial jitter suppression model to obtain jitter compensation parameters aiming at the target lens;
the lens adjusting module is used for adjusting the pose of the target lens according to the jitter compensation parameters to obtain an adjusted target lens;
the image acquisition module is used for acquiring the image to be evaluated acquired through the adjusted target lens;
the parameter determination module is used for taking the jitter compensation parameter corresponding to the image to be evaluated as a target jitter compensation parameter if the image to be evaluated passes the definition evaluation;
the model optimization module is used for optimizing the initial jitter suppression model by adopting the target jitter compensation parameters to obtain a target jitter suppression model; the target jitter suppression model is used for performing jitter suppression operation on the target lens.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. 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 method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111090319.4A CN113542612B (en) | 2021-09-17 | 2021-09-17 | Lens anti-shake method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111090319.4A CN113542612B (en) | 2021-09-17 | 2021-09-17 | Lens anti-shake method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113542612A CN113542612A (en) | 2021-10-22 |
| CN113542612B true CN113542612B (en) | 2021-11-23 |
Family
ID=78093355
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111090319.4A Active CN113542612B (en) | 2021-09-17 | 2021-09-17 | Lens anti-shake method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113542612B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115103108A (en) * | 2022-06-06 | 2022-09-23 | Oppo广东移动通信有限公司 | Anti-shake processing method, anti-shake processing device, electronic equipment and computer-readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103543572A (en) * | 2012-07-16 | 2014-01-29 | 鸿富锦精密工业（深圳）有限公司 | Camera lens jitter compensation system and camera lens jitter compensation method |
| CN103685950A (en) * | 2013-12-06 | 2014-03-26 | 华为技术有限公司 | Method and device for preventing shaking of video image |
| CN110769147A (en) * | 2018-07-25 | 2020-02-07 | 北京小米移动软件有限公司 | Shooting method and electronic equipment |
| CN111246089A (en) * | 2020-01-14 | 2020-06-05 | Oppo广东移动通信有限公司 | Jitter compensation method and apparatus, electronic device, computer-readable storage medium |
| CN111726537A (en) * | 2020-07-10 | 2020-09-29 | 广东小天才科技有限公司 | Anti-shake device of camera module, anti-shake control method and device and electronic equipment |
| CN113038006A (en) * | 2021-03-05 | 2021-06-25 | 昆山丘钛光电科技有限公司 | Anti-shake control method, electronic device, and storage medium |
| CN113163120A (en) * | 2021-04-21 | 2021-07-23 | 安徽清新互联信息科技有限公司 | Transformer-based video anti-shake method |
| CN113239975A (en) * | 2021-04-21 | 2021-08-10 | 洛阳青鸟网络科技有限公司 | Target detection method and device based on neural network |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3525448B8 (en) * | 2016-12-02 | 2022-02-23 | Hangzhou Hikvision Digital Technology Co., Ltd. | Anti-shake method for camera and camera |
| CN111355872B (en) * | 2018-12-24 | 2021-09-07 | 华为技术有限公司 | Camera module, anti-shake subassembly and terminal |
-
2021
- 2021-09-17 CN CN202111090319.4A patent/CN113542612B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103543572A (en) * | 2012-07-16 | 2014-01-29 | 鸿富锦精密工业（深圳）有限公司 | Camera lens jitter compensation system and camera lens jitter compensation method |
| CN103685950A (en) * | 2013-12-06 | 2014-03-26 | 华为技术有限公司 | Method and device for preventing shaking of video image |
| CN110769147A (en) * | 2018-07-25 | 2020-02-07 | 北京小米移动软件有限公司 | Shooting method and electronic equipment |
| CN111246089A (en) * | 2020-01-14 | 2020-06-05 | Oppo广东移动通信有限公司 | Jitter compensation method and apparatus, electronic device, computer-readable storage medium |
| CN111726537A (en) * | 2020-07-10 | 2020-09-29 | 广东小天才科技有限公司 | Anti-shake device of camera module, anti-shake control method and device and electronic equipment |
| CN113038006A (en) * | 2021-03-05 | 2021-06-25 | 昆山丘钛光电科技有限公司 | Anti-shake control method, electronic device, and storage medium |
| CN113163120A (en) * | 2021-04-21 | 2021-07-23 | 安徽清新互联信息科技有限公司 | Transformer-based video anti-shake method |
| CN113239975A (en) * | 2021-04-21 | 2021-08-10 | 洛阳青鸟网络科技有限公司 | Target detection method and device based on neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113542612A (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5877809A (en) | Method of automatic object detection in image | |
| CN100570471C (en) | Focus adjusting method and focus adjusting apparatus | |
| JP4695972B2 (en) | Image processing apparatus, imaging apparatus, and image processing method | |
| US10218996B2 (en) | Motion vector detection apparatus and method of controlling motion vector detection apparatus | |
| CN108833795B (en) | Focusing method and device of image acquisition equipment | |
| CN107018288A (en) | Control device and picture pick-up device | |
| CN103179340B (en) | Imaging device, auto focusing method and its program | |
| JP2015104016A (en) | Subject detection apparatus, imaging apparatus, subject detection apparatus control method, subject detection apparatus control program, and storage medium | |
| TW201541141A (en) | Auto-focus system for multiple lens and method thereof | |
| CN104980664A (en) | Image processing apparatus and control method thereof and image capturing apparatus | |
| KR20050025063A (en) | Object tracking method and object tracking apparatus | |
| JPWO2012132129A1 (en) | Imaging apparatus, imaging method, and program | |
| CN113542612B (en) | Lens anti-shake method and device, computer equipment and storage medium | |
| US20070058049A1 (en) | Image sensing apparatus and method of controlling the same | |
| JP6504899B2 (en) | CONTROL DEVICE, OPTICAL DEVICE, IMAGING DEVICE, AND CONTROL METHOD | |
| JP5127692B2 (en) | Imaging apparatus and tracking method thereof | |
| CN114697528A (en) | Image processor, electronic device and focusing control method | |
| US20120033888A1 (en) | Image processing system, image processing method, and computer readable medium | |
| CN110365971B (en) | Test system and method for automatically positioning optimal fixed focus | |
| CN114040107B (en) | Intelligent automobile image shooting system, intelligent automobile image shooting method, intelligent automobile image shooting vehicle and intelligent automobile image shooting medium | |
| CN106454066B (en) | Image processing apparatus and control method thereof | |
| US11394877B2 (en) | Control apparatus, image pickup apparatus, and control method | |
| CN101651778B (en) | Imaging apparatus and control method therefor | |
| CN111279352A (en) | Three-dimensional information acquisition system through ball throwing exercise and camera parameter calculation method | |
| CN112585946A (en) | Image shooting method, image shooting device, movable platform and storage medium |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Gao Feng Inventor after: Xu Wu Inventor after: Lv Jiangbo Inventor after: Shen Xiaoyong Inventor before: Gao Feng Inventor before: Xu Wu Inventor before: Lv Jiangbo Inventor before: Shen Xiaoyong Inventor before: Jia Jiaya |