CN118317202A

CN118317202A - Image tuning method and device and electronic equipment

Info

Publication number: CN118317202A
Application number: CN202410488761.XA
Authority: CN
Inventors: 卢易
Original assignee: Hangzhou Hikrobot Co Ltd
Current assignee: Hangzhou Hikrobot Co Ltd
Filing date: 2024-04-22
Publication date: 2024-07-09

Abstract

The embodiment of the application provides an image tuning method, an image tuning device and electronic equipment, and relates to the technical field of image processing, wherein the method comprises the following steps: adjusting imaging parameters of the image acquisition equipment according to a preset parameter adjustment strategy; acquiring a plurality of first images acquired after imaging parameters are adjusted by image acquisition equipment; inputting a plurality of first images into a deep learning algorithm for processing to obtain first target images corresponding to optimal imaging parameters; a first imaging parameter of the image acquisition device is set in accordance with the first target image. The scheme can improve the reliability and the replicability of the image tuning flow.

Description

Image tuning method and device and electronic equipment

Technical Field

The present application relates to the field of image processing technologies, and in particular, to an image tuning method, an image tuning device, and an electronic device.

Background

The current image tuning flow is: traversing imaging parameters, and adjusting the image acquisition equipment to the traversed imaging parameters to acquire images; calculating an imaging effect of the acquired image; and adjusting the image acquisition equipment to the imaging parameters corresponding to the image with the optimal imaging effect.

When the scene is switched, the reference factor of the calculated imaging effect changes in the image tuning process, if the original reference factor is still used for calculating the imaging effect, the calculated imaging effect is not reliable any more, and the reliability and the replicability of the whole image tuning process are poor.

Disclosure of Invention

The embodiment of the application aims to provide an image tuning method, an image tuning device and electronic equipment, so as to improve the reliability and the replicability of an image tuning flow. The specific technical scheme is as follows:

in a first aspect, an embodiment of the present application provides an image tuning method, including:

Adjusting imaging parameters of the image acquisition equipment according to a preset parameter adjustment strategy;

Acquiring a plurality of first images acquired after the image acquisition equipment adjusts imaging parameters;

Inputting the plurality of first images into a deep learning algorithm for processing to obtain first target images corresponding to optimal imaging parameters;

and setting a first imaging parameter of the image acquisition equipment according to the first target image.

In some embodiments, the step of inputting the plurality of first images into a deep learning algorithm to obtain a first target image corresponding to an optimal imaging parameter includes:

inputting the plurality of first images into a deep learning algorithm for processing to obtain processing results of the plurality of first images;

and determining a first target image corresponding to the optimal imaging parameter from the plurality of first images according to the processing result of the plurality of first images.

In some embodiments, the number of first target images is a plurality;

The step of setting a first imaging parameter of the image acquisition device according to the first target image includes:

Outputting a plurality of first target images;

Receiving a first target image selected by the outside according to a plurality of first target images;

the imaging parameters of the image acquisition device are set to the first imaging parameters associated with the selected first target image.

In some embodiments, the method further comprises:

If the first target image selected by the outside is not received, randomly selecting one first target image from a plurality of first target images; the imaging parameters of the image acquisition device are set to the first imaging parameters associated with the selected first target image.

In some embodiments, the method further comprises:

registering at least one standard image marked with the processing result in the deep learning algorithm.

In some embodiments, the standard image comprises a first standard image and a second standard image;

The processing result of the first standard image is lower than a first preset value, the processing result of the second standard image is higher than a second preset value, and the first preset value is smaller than the second preset value; or (b)

The processing result of the target feature in the first standard image is lower than a first preset value, the processing result of the target feature in the second standard image is higher than a second preset value, and the first preset value is smaller than the second preset value; or (b)

The processing result of the preset area in the first standard image is lower than a first preset value, the processing result of the preset area in the second standard image is higher than a second preset value, and the first preset value is smaller than the second preset value.

In some embodiments, the step of adjusting the imaging parameters of the image capturing device according to a preset parameter adjustment strategy includes:

traversing imaging parameters along a first preset direction or a second preset direction according to a first step length from imaging parameters of a preset position, wherein the first preset direction is opposite to the second preset direction;

And adjusting imaging parameters of the image acquisition equipment to the traversed imaging parameters so that the image acquisition equipment acquires the first image according to the traversed imaging parameters.

In some embodiments, the step of traversing the imaging parameters from the imaging parameters at the preset position along the first preset direction or the second preset direction according to the first step length includes:

Traversing imaging parameters along a first preset direction according to a first step length from the imaging parameters of the preset position;

if the image processing result acquired along the first preset direction is in a decreasing trend, traversing the imaging parameters along the second preset direction according to the first step length.

If the image processing result acquired along the first preset direction shows a growing trend and the growing gradient is reduced, reducing the first step length;

And traversing the imaging parameters along a first preset direction according to the reduced first step length.

In some embodiments, the method further comprises:

Traversing the imaging parameters along the first preset direction or the second preset direction according to a second step length from the first imaging parameters, wherein the second step length is smaller than the first step length;

adjusting imaging parameters of the image acquisition equipment to the traversed imaging parameters so that the image acquisition equipment acquires a second image at the traversed imaging parameters;

Acquiring a plurality of second images acquired after the image acquisition equipment adjusts imaging parameters;

inputting the plurality of second images into a deep learning algorithm for processing to obtain a second target image corresponding to the optimal imaging parameters;

and setting a second imaging parameter of the image acquisition device according to the second target image.

In a second aspect, an embodiment of the present application provides an image tuning apparatus, including:

the adjusting module is used for adjusting imaging parameters of the image acquisition equipment according to a preset parameter adjusting strategy;

The acquisition module is used for acquiring a plurality of first images acquired after the image acquisition equipment adjusts imaging parameters;

The processing module is used for inputting the plurality of first images into a deep learning algorithm for processing to obtain a first target image corresponding to the optimal imaging parameters;

and the setting module is used for setting the first imaging parameters of the image acquisition equipment according to the first target image.

In some embodiments, the processing module is specifically configured to:

In some embodiments, the number of first target images is a plurality;

the setting module is specifically configured to:

Outputting a plurality of first target images;

In some embodiments, the setting module is further configured to randomly select a first target image from a plurality of first target images if the first target image selected by the outside is not received; the imaging parameters of the image acquisition device are set to the first imaging parameters associated with the selected first target image.

In some embodiments, the apparatus further comprises:

and the registration module is used for registering at least one standard image marked with the processing result in the deep learning algorithm.

In some embodiments, the adjusting module is specifically configured to:

In some embodiments, the adjusting module is further configured to traverse the imaging parameters in the first preset direction or the second preset direction by a second step from the first imaging parameters, where the second step is smaller than the first step; adjusting imaging parameters of the image acquisition equipment to the traversed imaging parameters so that the image acquisition equipment acquires a second image at the traversed imaging parameters;

The acquisition module is also used for acquiring a plurality of second images acquired after the image acquisition equipment adjusts imaging parameters;

the processing module is further used for inputting the plurality of second images into a deep learning algorithm for processing to obtain a second target image corresponding to the optimal imaging parameters;

the setting module is further configured to set a second imaging parameter of the image capturing device according to the first target image.

In a third aspect, an embodiment of the present application provides an electronic device, including:

a memory for storing a computer program;

and a processor, configured to implement any of the methods provided in the first aspect when executing the program stored in the memory.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having a computer program stored therein, which when executed by a processor, implements any of the methods provided in the first aspect.

In a fifth aspect, embodiments of the present application also provide a computer program product comprising instructions which, when run on a computer, cause the computer to perform any of the methods provided in the first aspect above.

The embodiment of the application has the beneficial effects that:

According to the technical scheme provided by the embodiment of the application, after the imaging parameters of the image acquisition equipment are adjusted according to the preset parameter adjustment strategy, a plurality of first images acquired by the image acquisition equipment are input into a deep learning algorithm for quantization processing, so that a first target image corresponding to the optimal imaging parameters is obtained, and then the setting of the imaging parameters of the image acquisition equipment is completed according to the first target image, and tuning is completed. In the embodiment of the application, the depth learning algorithm has obvious advantages in adaptability to images and scenes, has good robustness to the images and the scenes, can accurately evaluate the images even if the scenes are switched, and improves the reliability and the replicability of the image tuning flow.

Of course, it is not necessary for any one product or method of practicing the application to achieve all of the advantages set forth above at the same time.

Drawings

In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the application, and other embodiments may be obtained according to these drawings to those skilled in the art.

Fig. 1 is a schematic flow chart of a first image tuning method according to an embodiment of the present application;

Fig. 2a is a first schematic diagram of an image tuning scene according to an embodiment of the present application;

fig. 2b is a second schematic diagram of an image tuning scene according to an embodiment of the present application;

Fig. 3 is a schematic diagram of a second flow chart of an image tuning method according to an embodiment of the present application;

fig. 4 is a third flowchart of an image tuning method according to an embodiment of the present application;

Fig. 5 is a schematic diagram of a portion of a fourth flow of an image tuning method according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of an image tuning device according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by the person skilled in the art based on the present application are included in the scope of protection of the present application.

The words appearing in the embodiments of the application are explained below.

One-touch tuning, i.e. image tuning: a process comprising a plurality of imaging parameter adjustment sub-processes, wherein a user only needs to click a button once to complete the adjustment operation of the plurality of sub-processes.

Imaging parameters: including parameters such as focal length, exposure, gain, gamma (gamma), light source, etc.

Automatic focusing: and adjusting the image acquisition device supporting focusing from the position of any focal length to the position of the focal length of clear image.

Automatic parameter adjustment: according to any scene, the process of meeting the next processing requirement of the image is achieved by automatically switching related parameters (such as exposure, gain, gamma, light source and the like).

Quick zooming: and the process of adjusting the focal length position of the image acquisition equipment to the position with clear images is quickly realized.

Deep learning: i.e. machine learning, also called artificial intelligence (ARTIFICIAL INTELLIGENCE, AI), extracts key information and new technologies such as classification by learning the intrinsic law of sample images.

The current image tuning process can be divided into automatic focusing and automatic parameter tuning, and is specifically as follows.

(1) And (5) automatically focusing. Judging whether the image is clear or not according to the definition (namely the imaging effect) of the image acquired by the image acquisition equipment; after the whole focusing process is completed by traversing, selecting a focal length position corresponding to the image with the highest definition as the clearest position of the image; the image acquisition device is adjusted to the focal position.

In practical application, the change trend of the definition is unstable, and the range of the definition calculated by each image acquisition device is different, and the definition accuracy is different. The above-mentioned multiple factors are combined, so that the result of automatic focusing is not accurate, and the portability and scene adaptability of the above-mentioned automatic focusing method are poor.

In addition, under the condition that the field of view of the image has depth of field, a plurality of sharp peaks exist in the whole focusing process; also, the evaluation criterion for whether or not the image is clear is definition, and at the time of high definition, the target feature or local area of real attention of the user may not be the clearest. Therefore, the above-described autofocus method is poor in reliability and reproducibility.

(2) And (5) automatically adjusting the ginseng. And judging whether the parameters of the image acquisition equipment are proper or not according to the imaging effect of the image acquired by the image acquisition equipment. The imaging effect of the image can be the average brightness of a certain area, or the confidence degree given by target feature algorithm processing in the image field. Selecting parameters corresponding to an image with the best imaging effect as optimal parameters after automatic adjustment through traversing parameters such as exposure, gain, gamma, light source and the like; the image acquisition device is adjusted to the optimal parameter.

In practical application, the region in the image is difficult to define, the scene adaptability of the parameter is poor, and the problem that the same parameter is over-exposed or the confidence value is unreliable is likely to occur when the scene or the target is changed. Moreover, because of lack of policy guidance, the traversing mode is long in time consumption and poor in targeting.

The image tuning flow has higher dependence on the scene, quality and imaging efficiency of the sample image. And when the scene is switched, the reference factor for calculating the imaging effect changes in the image tuning flow, if the imaging effect is still calculated by using the original reference factor, the calculated imaging effect is not reliable any more, and the reliability and the replicability of the whole image tuning flow are poor.

To solve the above-mentioned problems, embodiments of the present application provide an image tuning method, which may be applied to an image capturing device or an electronic device connected to the image capturing device. The electronic device may be a mobile terminal, a personal computer, a server, a cluster, or the like, which is not limited thereto. For ease of understanding, the following description uses the electronic device as an execution body, and is not limited thereto.

In the image tuning method, after the imaging parameters of the image acquisition equipment are adjusted according to the preset parameter adjustment strategy, the electronic equipment inputs a plurality of first images acquired by the image acquisition equipment into the deep learning algorithm for quantization processing, so that a first target image corresponding to the optimal imaging parameters is obtained, and further, the setting of the imaging parameters of the image acquisition equipment is completed according to the first target image, and tuning is completed. In the embodiment of the application, the depth learning algorithm has obvious advantages in adaptability to images and scenes, has good robustness to the images and the scenes, can accurately evaluate the images even if the scenes are switched, and improves the reliability and the replicability of the image tuning flow.

The image tuning method provided by the embodiment of the application is described in detail below through a specific embodiment.

As shown in fig. 1, a first flowchart of an image tuning method according to an embodiment of the present application is shown, and the method includes the following steps.

Step S11, adjusting imaging parameters of the image acquisition equipment according to a preset parameter adjustment strategy;

step S12, acquiring a plurality of first images acquired after imaging parameters are adjusted by the image acquisition equipment;

Step S13, inputting a plurality of first images into a deep learning algorithm for processing to obtain first target images corresponding to optimal imaging parameters;

step S14, setting a first imaging parameter of the image acquisition device according to the first target image.

According to the technical scheme provided by the embodiment of the application, after the imaging parameters of the image acquisition equipment are adjusted according to the preset parameter adjustment strategy, the electronic equipment inputs a plurality of first images acquired by the image acquisition equipment into a depth learning algorithm for quantization processing, so that a first target image corresponding to the optimal imaging parameters is obtained, and then the setting of the imaging parameters of the image acquisition equipment is completed according to the first target image, and tuning is completed. In the embodiment of the application, the depth learning algorithm has obvious advantages in adaptability to images and scenes, has good robustness to the images and the scenes, can accurately evaluate the images even if the scenes are switched, and improves the reliability and the replicability of the image tuning flow.

In the above step S11, the image capturing device may be a fisheye camera, a ball camera, a gun camera, or other types of cameras. This is not limited. Imaging parameters may include, but are not limited to, parameters including focal length, exposure, gain, gamma, light source, and the like.

The preset parameter adjustment strategy is a strategy for adjusting imaging parameters preset by the electronic equipment. The preset parameter adjustment strategy may be traversing the imaging parameters and adjusting, or adjusting according to a preset imaging parameter list, etc., which is not limited.

Taking a preset parameter adjustment strategy as an example of traversing imaging parameters and adjusting, the electronic equipment traverses the imaging parameters one by one, and adjusts the imaging parameters of the image acquisition equipment into the traversed imaging parameters. For example, in the auto-focus process, the electronic device traverses the focal length positions one by one, and adjusts the focal length position of the image capturing device to the traversed focal length position. For another example, in the automatic parameter adjustment process, the electronic device traverses the exposure parameters one by one, and adjusts the exposure parameters of the image acquisition device to the traversed exposure parameters.

After the image acquisition device adjusts the imaging parameters, an image, such as a first image, can be acquired under the adjusted imaging parameters. Correspondingly, the electronic device acquires a first image acquired by the image acquisition device.

In the embodiment of the application, a user can instruct the electronic equipment to finish the adjustment of parameters such as focal length, exposure, gain, gamma, light source and the like by clicking a button. As shown in fig. 2a, the display interface of the user side displays imaging parameters such as focal length, exposure, gain, etc. to be adjusted. After the user detects that the user clicks the button 1, the electronic device is instructed to execute the steps S11 to S14, and adjustment of imaging parameters such as focal length, exposure parameters, gain and the like of the image acquisition device is completed, so that image tuning is completed.

In the embodiment of the application, the user can instruct the electronic equipment to finish the adjustment of the selected imaging parameters by selecting one or more imaging parameters to be adjusted and clicking a button. As shown in fig. 2b, the display interface of the user side displays imaging parameters such as focal length, exposure, gain, etc. After detecting that the user selects one or more imaging parameters (focal length and exposure parameters are selected in fig. 2 b) and clicking the button 1, the user side instructs the electronic device to execute the steps S11 to S14, and completes the adjustment of the focal length and exposure parameters of the image acquisition device, namely completes the image tuning.

In the embodiment of the application, the electronic device can actively execute the steps S11 to S14 on the image acquisition device after detecting that the image acquisition device is started, so as to complete the adjustment of the focal length and the exposure parameters of the image acquisition device.

In the embodiment of the application, the triggering time of image tuning and the number of imaging parameters adjusted by one image tuning flow are not limited.

In the step S12, each time the image acquisition device acquires a first image, the electronic device may acquire a first image, thereby improving the real-time performance of the electronic device in acquiring the first image.

The electronic equipment can acquire a plurality of first images at a time so as to reduce the interaction times between the image acquisition equipment and the electronic equipment and improve the safety.

In the above step S13, the deep learning algorithm is a deep learning algorithm trained in advance. The deep learning algorithm may be implemented by a convolutional neural network, a cyclic neural network, or a deep neural network, which is not limited.

The training process of the deep learning algorithm may include:

Step one, a plurality of sample images with different imaging effects are obtained, wherein the plurality of sample images comprise a plurality of images with good imaging effects to poor imaging effects, and any other supplementary sample images can be also included. The sample image is marked with the processing result of the imaging effect. In order to meet the requirements of users, the processing result of the sample image annotation is the processing result of the target feature or local area and other concerned information in the sample image. The imaging effect may be clear or brightness, etc. When the imaging effect is clear, the sample image is clear, the imaging effect is better, the processing result is higher, the sample image is not clear, the imaging effect is worse, and the processing result is lower; when the imaging effect is brightness, the higher the brightness of the sample image, the better the imaging effect, the higher the processing result, the lower the brightness of the sample image, the worse the imaging effect, and the lower the processing result. The processing results may be expressed as confidence, scoring, or other quantitative values of the imaging effect, among other values that may be used to guide the next strategy.

The value range of the processing result can be set according to the actual requirement. For example, the value of the treatment result may be in the range of 0 to 1, 0 to 10, 0 to 100, or the like.

And secondly, inputting the plurality of sample images into a deep learning algorithm to obtain a prediction processing result of the plurality of sample images.

Step three, performing iterative training on the deep learning algorithm according to the prediction processing results and the labeling processing results of the plurality of sample images, wherein the iterative training is specifically as follows:

determining a loss value according to the prediction processing result and the labeling processing result of the plurality of sample images; judging whether the loss value is smaller than a preset loss threshold value or not, and judging whether the iteration number is larger than or equal to the preset iteration number or not; if the loss value is smaller than a preset loss threshold value or the iteration number is greater than or equal to the preset iteration number, ending the iterative training of the deep learning algorithm, and taking the current deep learning algorithm as a deep learning algorithm to be applied subsequently; otherwise, the loss value is larger than or equal to a preset loss threshold value, the iteration times are smaller than the preset iteration times, the iteration times are increased by 1, and parameters of the deep learning algorithm are adjusted by adopting a back propagation algorithm, a gradient descent algorithm and the like, and the second step is executed.

Through training the deep learning algorithm, the deep learning algorithm can fully learn the change rule of the imaging effect, further accurately quantitatively judge the imaging effect, and the robustness to the scene and the image is better. The electronic equipment integrates the trained deep learning algorithm, performs deep learning processing on the image acquired in real time to guide an adjusting strategy or determine an adjusting effect, and completes a one-key tuning process.

In order to further improve the robustness of the deep learning algorithm to the scene and the image, the electronic device can continuously enrich the sample image, so that the processing result obtained by the processing of the deep learning algorithm is infinitely close to the value or effect wanted by the user in the actual application scene, and the reliability of the one-key tuning process is further improved.

In the embodiment of the present application, the electronic device for training the deep learning algorithm may be the same as or different from the electronic device for executing the image tuning method, which is not limited.

After the deep learning algorithm is trained, the electronic device can input the acquired multiple first images into the deep learning algorithm for processing, and the deep learning algorithm outputs the image corresponding to the optimal imaging parameter, namely the first target image.

In step S14, after the first target image is obtained, the electronic device sets the effective imaging parameters of the image capturing device, such as the first imaging parameters, using the first target image. That is, the imaging parameters of the subsequent image capturing device are set to the first imaging parameters, and the image capturing device captures an image in accordance with the first imaging parameters.

In the embodiment of the present application, the number of the first target images may be one or more. When the number of the first target images is a plurality of, after the plurality of first target images are obtained, the electronic device may randomly select one first target image from the first target images, and set the imaging parameter of the image capturing device to the first imaging parameter associated with the selected first target image. In the embodiment of the application, the imaging parameters associated with the image are imaging parameters used when the image acquisition equipment acquires the image.

The electronic device may also set imaging parameters of the image capturing device in other manners, which are not limited.

In some embodiments, as shown in fig. 3, an embodiment of the present application further provides an image tuning method, which may include the following steps.

Step S31, adjusting imaging parameters of the image acquisition equipment according to a preset parameter adjustment strategy;

step S32, acquiring a plurality of first images acquired after imaging parameters are adjusted by the image acquisition equipment;

step S33, inputting a plurality of first images into a deep learning algorithm for processing to obtain processing results of the plurality of first images;

Step S34, determining a first target image corresponding to the optimal imaging parameter from the plurality of first images according to the processing results of the plurality of first images;

step S35, setting a first imaging parameter of the image acquisition device according to the first target image.

The steps S31 to S32 and S35 are the same as the steps S11 to S12 and S14, and will not be described in detail here.

In the technical scheme provided by the embodiment of the application, the image is associated with the imaging parameters. And the electronic equipment selects a first image corresponding to the optimal imaging parameters, namely a first target image, according to the processing result of the deep learning algorithm on the first image. This ensures the imaging effect of the image acquired by the image acquisition device in real time.

In step S33 described above, the deep learning algorithm outputs an intermediate result of determining the first target image, that is, a result of processing a plurality of first images.

In the step S34, the electronic device may determine the first target image corresponding to the optimal imaging parameter from the plurality of first images according to the preset determination policy. The preset judgment strategy can be set according to actual requirements. For example, the electronic device may select a first image with the highest processing result as the first target image corresponding to the optimal imaging parameter.

For example, the electronic device obtains images 1 to 5 (first images), and inputs the images 1 to 5 into the deep learning algorithm for processing, respectively, to obtain a processing result 1 of the image 1, a processing result 2 of the image 2, a processing result 3 of the image 3, a processing result 4 of the image 4, and a processing result 5 of the image 5. Processing result 1> processing result 2> processing result 3> processing result 4> processing result 5. The electronic device may set the imaging parameter of the image acquisition device to the imaging parameter associated with the image 1 by using the image 1 corresponding to the processing result 1 as the first target image.

The electronic device may also select, from the plurality of first images, a plurality of first images with processing results higher than a preset threshold, as the first target image corresponding to the optimal imaging parameter.

The electronic device may also determine the first target image in other ways, which are not limited.

In some embodiments, in order to meet the application scenario and the user requirement, the step S14 or the step S35 may be: outputting a plurality of first target images; receiving a first target image selected by the outside according to a plurality of first target images; the imaging parameters of the image acquisition device are set to the first imaging parameters associated with the selected first target image.

In the embodiment of the application, the first target image has a plurality of images. The electronic device may output the plurality of first target images to the display or transmit the plurality of first target images to the designated user side. The user can select the first target image through a keyboard, a mouse, a touch screen or the like according to the output of the plurality of first target images, and the first target image is sent to the electronic equipment. At this time, the first target image acquired by the electronic device is an image which meets the requirements of the user and is decided by the user, so that the image acquired by the image acquisition device can be ensured to be close to the application scene and the requirements of the user to the greatest extent. In addition, the problems that the imaging effect change trend is unstable, a plurality of peaks exist in the image tuning process, and the image tuning effect is poor are avoided.

In some embodiments, if the externally selected first target image is not received, the electronic device may select one first target image from the plurality of first target images by adopting a preset default manner; the imaging parameters of the image acquisition device are set to the first imaging parameters associated with the selected first target image. For example, one first target image is randomly selected from a plurality of first target images; or selecting one first target image with the earliest acquisition time from the plurality of first target images.

In the embodiment of the application, the electronic device can preset a waiting time, namely a preset time. After a plurality of first target images are output and waiting for a preset time, the electronic equipment still does not receive the externally selected first target images, and then the fact that the externally selected first target images are not received is determined. The electronic device may directly select a first target image from the plurality of first target images without waiting to ensure subsequent image acquisition.

In some embodiments, to unify the criteria for the processing results, the electronic device may acquire at least one standard image for labeling the processing results, and register the standard image with the deep learning algorithm before executing step S11. Therefore, the deep learning algorithm can acquire the judgment standard of the imaging effect in the current scene, so that the processing result of the image acquired in real time can be accurately quantized according to the standard image.

The electronic device registers a standard image containing the target feature with the deep learning algorithm. Subsequently, the higher the feature matching degree of the image input by the electronic equipment and the standard image is, the more the input image accords with the standard image, and the more the processing result of the image output by the deep learning algorithm is close to the processing result of the standard image marking; otherwise, the further the processing result of the image is output by the deep learning algorithm, the further the processing result of the standard image label is.

For example, the electronic device registers a plurality of standard images with the deep learning algorithm. And if the feature matching degree of one image input by the electronic equipment in the deep learning algorithm and the first standard image is highest, the deep learning algorithm can use the processing result of the first standard image label as the processing result of the input image.

For another example, the electronic device registers a plurality of standard images with the deep learning algorithm. The electronic equipment calculates the feature matching degree of one image and each standard image of the input deep learning algorithm, the deep learning algorithm takes the feature matching degree as a weight, and the processing results of the standard images are weighted and summed to obtain the processing result of the input image and output.

In the embodiment of the application, the standard image comprises a first standard image and a second standard image. The first standard image and the second standard image are evaluated as follows:

first, the whole image is used as an evaluation criterion. That is, the processing result of the first standard image is lower than a first preset value, the processing result of the second standard image is higher than a second preset value, and the first preset value is smaller than the second preset value.

In the mode, the deep learning algorithm can learn the difference between good imaging effect and poor imaging effect in the current scene, so that the evaluation accuracy of the image acquired in real time can be further quantized.

And secondly, the processing result of the target feature in the first standard image is lower than a first preset value, the processing result of the target feature in the second standard image is higher than a second preset value, and the first preset value is smaller than the second preset value.

Wherein the target may be a person, animal, vehicle, etc. The first standard image and the second standard image contain target features of interest to the user. The electronic equipment registers the image containing the target feature in the deep learning algorithm in advance, so that the adjusted image acquisition equipment can acquire the target feature with good imaging effect.

And thirdly, the processing result of the preset area in the first standard image is lower than a first preset value, the processing result of the preset area in the second standard image is higher than a second preset value, and the first preset value is smaller than the second preset value.

The preset area is an interested area. The electronic equipment registers the image containing the preset area in the deep learning algorithm in advance, the deep learning algorithm can learn the imaging effect condition of the preset area in the current scene, and the adjusted image acquisition equipment can acquire the preset area with good imaging effect.

In the embodiment of the application, the electronic device can register one or more standard images in the deep learning algorithm according to the implementation requirement, for example, the electronic device can register the standard images, the standard images containing target features, the standard images containing preset areas and the like in the deep learning algorithm. For each standard image, the electronic device may register one or more first standard images, and one or more second standard images with the deep learning algorithm.

In some embodiments, as shown in fig. 4, an embodiment of the present application further provides an image tuning method, which may include the following steps.

Step S41, starting from imaging parameters of a preset position, traversing the imaging parameters along a first preset direction or a second preset direction according to a first step length, wherein the first preset direction is opposite to the second preset direction;

Step S42, adjusting imaging parameters of the image acquisition equipment to the traversed imaging parameters so that the image acquisition equipment acquires a first image at the traversed imaging parameters;

step S43, acquiring a plurality of first images acquired after imaging parameters are adjusted by the image acquisition equipment;

Step S44, inputting a plurality of first images into a deep learning algorithm for processing to obtain first target images corresponding to optimal imaging parameters;

step S45, setting a first imaging parameter of the image acquisition device according to the first target image.

The steps S43 to S45 are the same as the steps S12 to S14, and will not be described here again.

In the technical scheme provided by the embodiment of the application, the electronic equipment presets the adjusting position (preset position) and the adjusting step length (first step length), thereby meeting the adjusting requirements of different imaging parameters and expanding the application scene of image tuning.

In step S41, the electronic device sets the adjustment position in advance, that is, the preset position. The preset position may be a position at which the imaging parameter is minimized or a position at which the imaging parameter is maximized, for example, a position at which the focal length is minimized or a position at which the focal length is maximized. This may enable a traversal-automatic tuning of the imaging parameters.

The preset position may also be a position at which the intermediate magnitude of the imaging parameter is made, or a position at which the last adjustment is made to optimize the imaging effect. This may enable fast tuning of imaging parameters.

The first step may be a step of a fixed size, or may be a step that increases gradually, for example, the difference between the step of the current traversal and the step of the last traversal is a preset step difference. The preset step difference is set according to actual requirements.

The first preset direction is a direction in which the imaging parameter is increased, and the second preset direction is a direction in which the imaging parameter is decreased; or the first preset direction is a direction in which the imaging parameter is reduced, and the second preset direction is a direction in which the imaging parameter is increased.

When the image is tuned, the electronic equipment starts from imaging parameters at preset positions, and traverses the imaging parameters along a first preset direction according to a first step length or traverses the imaging parameters along a second preset direction.

In the step S42, the electronic device adjusts the imaging parameters of the image capturing device to the imaging parameters of the current traversal every time the electronic device traverses to one imaging parameter. And the image acquisition equipment acquires one or more first images according to the imaging parameters traversed at the time. The image acquisition device sends the acquired first image to the electronic device. And the electronic equipment inputs the first image into a deep learning algorithm for processing to obtain a processing result of the first image.

In addition, the electronic device adjusts the imaging parameters of the image acquisition device to the imaging parameters traversed at this time, and continues to execute step S41 to traverse the imaging parameters until the traversal is completed.

In some embodiments, in order to improve the image tuning efficiency, the step S41 may be: traversing imaging parameters along a first preset direction according to a first step length from the imaging parameters of the preset position; if the image processing result acquired along the first preset direction is in a decreasing trend, traversing the imaging parameters along the second preset direction according to the first step length.

In the embodiment of the application, the electronic equipment starts from the imaging parameters of the preset position and traverses the imaging parameters along the first preset direction according to the first step length. In the process of traversing imaging parameters along a first preset direction, the electronic equipment acquires an image processing result acquired along the first preset direction and analyzes the change trend of the image processing result.

When the change trend of the image processing result is a decreasing trend, the electronic equipment switches the traversing direction when the optimal imaging parameter is not in the first preset direction, and traverses the imaging parameter along the second preset direction according to the first step length. When the change trend of the image processing result is an increasing trend, the optimal imaging parameters are indicated to be in a first preset direction, and the electronic equipment continues to traverse the imaging parameters along the first preset direction according to the first step length.

The direction of the next focusing is guided through the change trend of the processing result, so that the image tuning can be conveniently and rapidly completed, and the image tuning efficiency is improved.

In some embodiments, in order to improve the image tuning efficiency, the step S41 may be: traversing imaging parameters along a first preset direction according to a first step length from the imaging parameters of the preset position; if the image processing result acquired along the first preset direction shows a growing trend and the growing gradient is reduced, reducing the first step length; and traversing the imaging parameters along a first preset direction according to the reduced first step length.

When the change trend of the image processing result is an increasing trend, the optimal imaging parameters are indicated to be in a first preset direction, and the electronic equipment continues to traverse the imaging parameters along the first preset direction according to the first step length. And when the growth gradient is reduced, the position where the imaging effect is optimal is indicated to be reached, the electronic equipment reduces the first step length in order to avoid over-tuning, and the imaging parameters are traversed along the first preset direction according to the reduced first step length. Here, the electronic device may decrease the first step by a preset step threshold, or by a random value, without limitation, each time the imaging parameter is traversed.

The direction of the next focusing is guided through the change trend of the processing result, so that the image tuning can be conveniently and rapidly completed, and the image tuning efficiency is improved. Meanwhile, when the position with the optimal imaging effect is to be reached, the electronic equipment reduces the first step length of traversing the imaging parameters, so that the problem of over-tuning can be effectively avoided.

In some embodiments, in order to further improve the imaging effect, as shown in fig. 5, an image tuning method is further provided in an embodiment of the present application, and the method may include the following steps.

Step S51, starting from the first imaging parameters, traversing the imaging parameters along a first preset direction or a second preset direction according to a second step length, wherein the second step length is smaller than the first step length;

Step S52, adjusting imaging parameters of the image acquisition equipment to the traversed imaging parameters so that the image acquisition equipment acquires a second image at the traversed imaging parameters;

Step S53, acquiring a plurality of second images acquired after the image acquisition equipment adjusts imaging parameters;

step S54, inputting a plurality of second images into a deep learning algorithm for processing to obtain second target images corresponding to optimal imaging parameters;

step S55, setting second imaging parameters of the image acquisition device according to the second target image.

In the embodiment of the present application, after step S14, step S35 or step S45, the electronic device continues to use the smaller second step size, and continues to execute step S51. The specific details of the above steps S51 to S55 can be seen from the above description of fig.1 to fig. 4, which is different in that the first step size is converted into the second step size, the first image is converted into the second image, the first target image is converted into the second target image, and the first imaging parameter is converted into the second imaging parameter.

By applying the technical scheme provided by the embodiment of the application, after coarse adjustment according to the first step length, the electronic equipment is fine-adjusted according to the second step length, so that the imaging parameters with optimal imaging effect can be more accurately found, and the imaging effect of the acquired image is improved.

The image tuning method provided by the embodiment of the application is described in detail below from two aspects of focusing and parameter tuning.

(1) The deep learning algorithm is trained.

The electronic device acquires a plurality of sample images from good imaging to poor imaging, as well as other supplemental sample images. The sample images may be labeled with target features and regions of interest. The electronic device iteratively trains a deep learning algorithm by using the acquired plurality of sample images. See for details the description of step S13.

(2) Focusing.

A, traversing type automatic focusing.

1) Before starting to traverse the focal position, the electronic device registers at least one sharp image and at least one unclear image with the deep learning algorithm. If there are explicit target features, the electronic device may preferentially register images containing the target features. If focusing of a local region of interest is involved, the above mentioned sharp/unclear response is the case of the region of interest in the image.

2) The electronic equipment starts to traverse the focal length positions, and the step of each focal length position can be fixed in step length or can be gradually increased in step length; and inputting the images obtained in the traversal process into a deep learning algorithm for processing, and obtaining the processing result of each image. The processing result may be a clear confidence. The deep learning algorithm is the deep learning algorithm trained in the step (1).

3) After the focal length position is traversed, the electronic equipment screens one or more images with highest clear confidence from the clear confidence of all the images obtained in the step 2); when the screening is carried out to obtain an image, the electronic equipment executes the step 5); when the screening results in a plurality of images, the electronic device executes step 4).

4) When a plurality of images are obtained through screening, the electronic equipment outputs the images, and a user selects one of the images according to the use scene to serve as the sharpest image. When the user does not select, the electronic device designates one of the plurality of images as the sharpest image.

5) When the clearest image is determined, the electronic equipment extracts a corresponding focal length position according to the image, sets and validates the focal length position for the image acquisition equipment, and completes traversing type automatic focusing.

And B, quick zooming.

2) The electronic equipment traverses the focal length position forwards or backwards from any focal length position in the middle or the focal length position which is the most clear last time, and inputs the images obtained in the traversing process into a deep learning algorithm for processing, so that the clear confidence of each image is obtained. The deep learning algorithm is the deep learning algorithm trained in the step (1), and the clear confidence is the processing result of the deep learning algorithm. In the embodiment of the application, the processing result of the deep learning algorithm is only taken as an example for illustration, and the method is not limited.

3) The electronic equipment judges the change trend of the clear confidence according to the set of clear confidence obtained in the step 2); if the clear confidence level is good, continuing to traverse the focal length position along the same direction; if the clear confidence level is poor, adjusting to traverse the focal length position along the reverse direction;

4) The electronic equipment adjusts the step length and the direction of traversal through the clear confidence obtained by the deep learning process, finds the focus position associated with the clearest image, sets and takes effect on the focus position for the image acquisition equipment, and completes the quick zooming.

(3) And (5) automatically adjusting the ginseng.

1) Before the parameters are traversed, the electronic device registers at least one image with good imaging effect and at least one image with poor imaging effect to the deep learning algorithm. If there are explicit target features, the electronic device may preferentially register images containing the target features. If focusing of a local region of interest is involved, the imaging effect described above is good/bad in response to the situation of the region of interest in the image.

2) And according to a preset parameter adjustment strategy, the electronic equipment starts to traverse parameters, and the images obtained in the traversal process are input into a deep learning algorithm for processing, so that the grading value of each image is obtained. The deep learning algorithm is the deep learning algorithm trained in the step (1), and the scoring value is the processing result of the deep learning algorithm. In the embodiment of the application, only the processing result of the deep learning algorithm is taken as an example for explanation, and the method is not limited.

3) After the parameter traversal is completed, the electronic equipment obtains the grading values of all the images from the step 2), and screens one or more images with the highest grading values; when the screening is carried out to obtain an image, the electronic equipment executes the step 5); when the screening results in a plurality of images, the electronic device executes step 4).

4) When a plurality of images are obtained through screening, the electronic equipment outputs the images, and a user selects one of the images according to a use scene as an image with optimal parameters. When the user does not select, the electronic device designates one of the plurality of images as an image of the optimal parameters.

5) When the image of the optimal parameter is determined, the electronic equipment extracts the corresponding optimal parameter according to the image, sets and validates the optimal parameter for the image acquisition equipment, and completes the traversal type automatic parameter adjustment.

In the embodiment of the application, the deep learning algorithms used in the focusing and the parameter adjusting can be the same or different. The focusing and parameter adjusting can be a first coarse adjustment process. After the focusing and parameter adjustment are completed, the electronic equipment can also perform secondary fine adjustment, namely secondary traversal fine adjustment is performed in a step interval before and after the position of the imaging parameter, so that more accurate imaging parameters are obtained.

After the image tuning is completed, the electronic equipment can record and save the obtained optimal imaging parameters, so that the subsequent rapid completion of the image tuning is facilitated.

Corresponding to the above image tuning method, the embodiment of the present application further provides an image tuning device, as shown in fig. 6, where the device includes:

an adjustment module 61, configured to adjust imaging parameters of the image capturing device according to a preset parameter adjustment policy;

an acquisition module 62, configured to acquire a plurality of first images acquired after the image acquisition device adjusts imaging parameters;

The processing module 63 is configured to input a plurality of first images into a deep learning algorithm for processing, so as to obtain a first target image corresponding to the optimal imaging parameter;

a setting module 64 is configured to set a first imaging parameter of the image capturing device according to the first target image.

In some embodiments, the processing module 63 may be specifically configured to:

Inputting a plurality of first images into a deep learning algorithm for processing to obtain processing results of the plurality of first images;

and determining a first target image corresponding to the optimal imaging parameter from the plurality of first images according to the processing results of the plurality of first images.

In some embodiments, the number of first target images is a plurality;

The setting module 64 may specifically be configured to: outputting a plurality of first target images; receiving a first target image selected by the outside according to a plurality of first target images; the imaging parameters of the image acquisition device are set to the first imaging parameters associated with the selected first target image.

In some embodiments, the setting module 64 may be further configured to randomly select one first target image from the plurality of first target images if the first target image selected by the outside is not received; the imaging parameters of the image acquisition device are set to the first imaging parameters associated with the selected first target image.

In some embodiments, the image tuning apparatus may further include:

In some embodiments, the adjustment module 61 may be specifically configured to:

and adjusting the imaging parameters of the image acquisition device to the traversed imaging parameters so that the image acquisition device acquires the first image according to the traversed imaging parameters.

In some embodiments, the adjustment module 61 may be further configured to traverse the imaging parameters in the first preset direction or the second preset direction, starting from the first imaging parameters, according to a second step size, the second step size being smaller than the first step size; adjusting imaging parameters of the image acquisition equipment to the traversed imaging parameters so that the image acquisition equipment acquires a second image at the traversed imaging parameters;

the acquisition module 62 is further configured to acquire a plurality of second images acquired after the image acquisition device adjusts the imaging parameters;

The processing module 63 is further configured to input a plurality of second images into a deep learning algorithm for processing, so as to obtain a second target image corresponding to the optimal imaging parameter;

The setting module 64 may also be configured to set a second imaging parameter of the image acquisition device based on the first target image.

According to the technical scheme provided by the embodiment of the application, after the imaging parameters of the image acquisition equipment are adjusted according to the preset parameter adjustment strategy, a plurality of first images acquired by the image acquisition equipment are input into a deep learning algorithm for quantization processing, so that a first target image corresponding to the optimal imaging parameters is obtained, and further, the setting of the imaging parameters of the image acquisition equipment is completed according to the first target image, and tuning is completed. In the embodiment of the application, the depth learning algorithm has obvious advantages in adaptability to images and scenes, has good robustness to the images and the scenes, can accurately evaluate the images even if the scenes are switched, and improves the reliability and the replicability of the image tuning flow.

In the technical scheme of the application, related operations such as acquisition, storage, use, processing, transmission, provision, disclosure and the like of the personal information of the user are performed under the condition that the authorization of the user is obtained.

Note that the deep learning model in this embodiment is not a deep learning model for a specific user, and does not reflect personal information of a specific user.

Corresponding to the image tuning method, the embodiment of the application also provides an electronic device, as shown in fig. 7, including:

A memory 71 for storing a computer program;

The processor 72 is configured to execute the program stored in the memory 71, and implement the following steps: adjusting imaging parameters of the image acquisition equipment according to a preset parameter adjustment strategy; acquiring a plurality of first images acquired after imaging parameters are adjusted by image acquisition equipment; inputting a plurality of first images into a deep learning algorithm for processing to obtain first target images corresponding to optimal imaging parameters; and setting a first imaging parameter of the image acquisition device according to the first target image.

The electronic device may further comprise a communication bus and/or a communication interface, through which the processor 72, the communication interface, and the memory 71 communicate with each other.

The communication bus mentioned above for the electronic device may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.

The communication interface is used for communication between the electronic device and other devices.

The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.

The processor may be a general-purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components.

In yet another embodiment of the present application, a computer readable storage medium is provided, in which a computer program is stored, which when executed by a processor, implements any of the above-mentioned image tuning methods.

In yet another embodiment of the present application, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the image tuning methods of the above embodiments.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, tape), an optical medium (e.g., DVD), or a Solid state disk (Solid STATE DISK, SSD), etc.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, electronic devices, storage media, and program product embodiments, the description is relatively simple as it is substantially similar to method embodiments, as relevant points are found in the partial description of method embodiments.

The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. An image tuning method, the method comprising:

2. The method of claim 1, wherein the step of inputting the plurality of first images into a deep learning algorithm to obtain a first target image corresponding to an optimal imaging parameter comprises:

3. The method of claim 1, wherein the number of first target images is a plurality of sheets;

Outputting a plurality of first target images;

4. A method according to claim 3, characterized in that the method further comprises:

5. The method according to any one of claims 1-4, further comprising:

6. The method of claim 5, wherein the standard image comprises a first standard image and a second standard image;

7. The method of claim 1, wherein the step of adjusting the imaging parameters of the image acquisition device according to a preset parameter adjustment strategy comprises:

8. The method of claim 7, wherein the step of traversing the imaging parameters in the first preset direction or the second preset direction in a first step from the imaging parameters at the preset position comprises:

9. The method of claim 7, wherein the step of traversing the imaging parameters in the first preset direction or the second preset direction in a first step from the imaging parameters at the preset position comprises:

10. The method according to any one of claims 7-9, further comprising:

11. An image tuning apparatus, the apparatus comprising:

12. The apparatus of claim 11, wherein the device comprises a plurality of sensors,

The processing module is specifically configured to: inputting the plurality of first images into a deep learning algorithm for processing to obtain processing results of the plurality of first images; determining a first target image corresponding to the optimal imaging parameter from the plurality of first images according to the processing results of the plurality of first images; or (b)

The number of the first target images is a plurality;

the setting module is specifically configured to: outputting a plurality of first target images; receiving a first target image selected by the outside according to a plurality of first target images; setting imaging parameters of the image acquisition device to first imaging parameters associated with the selected first target image; or (b)

The setting module is further configured to randomly select a first target image from a plurality of first target images if the first target image selected by the outside is not received; setting imaging parameters of the image acquisition device to first imaging parameters associated with the selected first target image; or (b)

The apparatus further comprises: the registration module is used for registering at least one standard image marked with the processing result in the deep learning algorithm; or (b)

The standard images comprise a first standard image and a second standard image;

The processing result of the preset area in the first standard image is lower than a first preset value, the processing result of the preset area in the second standard image is higher than a second preset value, and the first preset value is smaller than the second preset value; or (b)

The adjusting module is specifically configured to: traversing imaging parameters along a first preset direction or a second preset direction according to a first step length from imaging parameters of a preset position, wherein the first preset direction is opposite to the second preset direction; adjusting imaging parameters of the image acquisition equipment to the traversed imaging parameters so that the image acquisition equipment acquires a first image according to the traversed imaging parameters; or (b)

The adjusting module is specifically configured to: traversing imaging parameters along a first preset direction according to a first step length from the imaging parameters of the preset position; if the image processing result acquired along the first preset direction shows a decreasing trend, traversing imaging parameters along a second preset direction according to a first step length; or (b)

The adjusting module is specifically configured to: traversing imaging parameters along a first preset direction according to a first step length from the imaging parameters of the preset position; if the image processing result acquired along the first preset direction shows a growing trend and the growing gradient is reduced, reducing the first step length; traversing imaging parameters along a first preset direction according to the reduced first step length; or (b)

The adjusting module is further configured to traverse the imaging parameters along the first preset direction or the second preset direction according to a second step size from the first imaging parameters, where the second step size is smaller than the first step size; adjusting imaging parameters of the image acquisition equipment to the traversed imaging parameters so that the image acquisition equipment acquires a second image at the traversed imaging parameters;

13. An electronic device, comprising:

a memory for storing a computer program;

A processor for implementing the method of any of claims 1-10 when executing a program stored on a memory.

14. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed by a processor, implements the method of any of claims 1-10.