CN114026874A

CN114026874A - Video processing method and device, mobile device and readable storage medium

Info

Publication number: CN114026874A
Application number: CN202080044431.1A
Authority: CN
Inventors: 周娴; 李鑫超; 刘志鹏
Original assignee: SZ DJI Technology Co Ltd
Current assignee: SZ DJI Technology Co Ltd
Priority date: 2020-10-27
Filing date: 2020-10-27
Publication date: 2022-02-08
Also published as: WO2022087826A1

Abstract

The method comprises the steps of determining target information corresponding to picture parameters of a target picture in a video to be processed, wherein the target information is used for representing whether the picture parameters of the target picture meet preset requirements (101), screening the video to be processed according to the target information of the target picture contained in the video to be processed, wherein the screening comprises deleting the target picture which does not meet the preset requirements or one video clip (102) to which the target picture belongs, and finally generating the target video (103) according to the video to be processed after the screening. Therefore, when the video is processed, the pictures in the video are automatically screened according to the picture parameters of the pictures, so that the screening cost can be reduced to a certain extent, and the screening efficiency is improved.

Description

Video processing method and device, mobile device and readable storage medium

Technical Field

The invention belongs to the technical field of networks, and particularly relates to a video processing method, a video processing device, a mobile device and a readable storage medium.

Background

At present, videos are used as an excellent way for acquiring information, and the videos are generated under more and more scenes. In order to improve the quality of the video, it is often necessary to screen the pictures with poor quality in the video. In the existing mode, screening is usually performed directly through a manual screening mode. However, this screening method is costly and inefficient.

Disclosure of Invention

The invention provides a video processing method, a video processing device, a mobile device and a readable storage medium, which are used for solving the problems of higher screening cost and lower screening efficiency.

In order to solve the technical problem, the invention is realized as follows:

in a first aspect, an embodiment of the present invention provides a video processing method, where the method includes:

determining target information corresponding to picture parameters of a target picture in a video to be processed; the target information is used for representing whether picture parameters of the target picture meet preset requirements or not;

screening the video to be processed according to target information of a target picture contained in the video to be processed; the screening processing comprises deleting a target picture which does not meet the preset requirement or one of the video clips to which the target picture belongs;

and generating a target video according to the screened to-be-processed video.

In a second aspect, an embodiment of the present invention provides a video processing apparatus, which includes a memory and a processor;

the memory for storing program code;

the processor, invoking the program code, when executed, is configured to:

and generating a target video according to the screened to-be-processed video.

In a third aspect, an embodiment of the present invention provides a removable device, where the removable device is configured to perform the steps in the video processing method described in the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the following operations:

and generating a target video according to the screened to-be-processed video.

In the embodiment of the invention, target information corresponding to picture parameters of a target picture is determined for the target picture in a video to be processed, wherein the target information is used for representing whether the picture parameters of the target picture meet preset requirements or not, the video to be processed is screened according to the target information of the target picture contained in the video to be processed, the screening comprises deleting the target picture which does not meet the preset requirements or one of video clips to which the target picture belongs, and finally, the target video is generated according to the video to be processed after the screening. Therefore, when the video is processed, the pictures in the video are automatically screened according to the picture parameters of the pictures, so that the screening cost can be reduced to a certain extent, and the screening efficiency is improved.

Drawings

Fig. 1 is a flowchart illustrating steps of a video processing method according to an embodiment of the present invention;

FIG. 2 is a diagram illustrating a clipping process according to an embodiment of the present invention;

fig. 3 is a block diagram of a video processing apparatus according to an embodiment of the present invention;

FIG. 4 is a block diagram of a computing processing device provided by an embodiment of the invention;

fig. 5 is a block diagram of a portable or fixed storage unit according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Fig. 1 is a flowchart illustrating steps of a video processing method according to an embodiment of the present invention, where as shown in fig. 1, the method may include:

step 101, determining target information corresponding to picture parameters of a target picture in a video to be processed; the target information is used for representing whether picture parameters of the target picture meet preset requirements or not.

In the embodiment of the invention, the video to be processed can be the video with the need of screening the picture with poor quality. For example, the video to be processed may be a video shot by the user himself or a video downloaded from a network, which is not limited in the embodiment of the present invention. Further, a video may be essentially understood as a picture sequence formed by multiple frames of images, and a target picture in a video to be processed may be all pictures in the picture sequence or may be a partial picture in the picture sequence. The picture parameters of the target picture may be parameters capable of representing picture quality, and the number and the types of the specific picture parameters may be set according to actual requirements. For example, the picture parameter may be a degree of sharpness of the picture, a degree of exposure of the picture, or the like.

Further, the preset requirement may be a quality requirement that the picture parameter of the picture needs to meet. If the picture parameters of the picture meet the preset requirements, the picture quality is high, and the quality requirements can be met. On the contrary, if the picture parameter of the picture does not meet the preset requirement, the picture quality is poor, and the quality requirement cannot be met. The specific content of the preset requirement can be set according to the actual requirement. For example, the preset requirement may be that the degree of definition is greater than a preset definition threshold, or that the degree of exposure is within a preset degree of exposure, and so on. Further, the target information may be a tag (tag) capable of characterizing whether picture parameters of the target picture meet preset requirements. The specific content of the tag can be set according to actual requirements, and for example, numbers, letters, special symbols and the like can be used as the tag. And when the picture parameters meet the preset requirements, the specific content of the label is different from that when the picture parameters do not meet the preset requirements. For example, "0" may be used as a label indicating that the picture parameter of the target picture does not meet the preset requirement, and "1" may be used as a label indicating that the picture parameter of the target picture meets the preset requirement.

102, screening the video to be processed according to target information of a target picture contained in the video to be processed; and the screening process comprises deleting a target picture which does not meet the preset requirement or one of the video clips to which the target picture belongs.

When the screening processing is performed, for each target picture, whether the picture parameter of the target picture meets the preset condition or not can be determined according to the target information of the target picture. For example, it may be determined that the picture parameter does not satisfy the preset requirement if the target information is 0, and that the picture parameter satisfies the preset requirement if the target information is 1. Further, if the picture parameter of the target picture does not meet the preset requirement, the target picture may be determined as the target picture that does not meet the preset requirement. Accordingly, the target picture may be deleted or one of the video clips to which the target picture that does not meet the preset requirement belongs may be directly deleted. The video clip to which the target picture belongs may be a video clip including the target picture in the video to be processed, and the specific length of the video clip may be set according to actual requirements, which is not limited in the embodiment of the present invention.

And 103, generating a target video according to the screened to-be-processed video.

In the embodiment of the invention, the video to be processed is screened according to the target information of the target picture in the video to be processed, so that the pictures with poor quality contained in the video to be processed can be reduced, and the image quality of the screened video to be processed is improved. Accordingly, after the screening is completed, the target video is generated according to the video to be processed after the screening processing, and the finally generated target video can be ensured to have higher image quality. For example, when the target video is generated, the video to be processed after the screening process may be directly used as the target video.

In summary, the video processing method provided in the embodiment of the present invention may determine, for a target picture in a video to be processed, target information corresponding to a picture parameter of the target picture, where the target information is used to represent whether the picture parameter of the target picture meets a preset requirement, and perform a screening process on the video to be processed according to the target information of the target picture included in the video to be processed, where the screening process includes deleting the target picture that does not meet the preset requirement or one of video segments to which the target picture belongs, and finally, generate the target video according to the video to be processed after the screening process. Therefore, when the video is processed, the pictures in the video are automatically screened according to the picture parameters of the pictures, so that the screening cost can be reduced to a certain extent, and the screening efficiency is improved.

Optionally, in an implementation manner of the embodiment of the present invention, the picture parameter may include one or more of a blur degree, a jitter degree, an exposure degree, and a color change degree of the picture. Of course, the picture parameters may also include other kinds of parameters, which is not limited in the embodiment of the present invention.

Whether the whole picture is clear or not can be determined based on the fuzzy degree of the picture, whether the picture of the picture has a shaking problem or not can be determined based on the shaking degree of the picture, whether the brightness of the picture is proper or not can be determined based on the exposure degree of the picture, and whether the color difference of the picture is proper or not can be determined based on the color change degree of the picture. In an actual application scene, when a picture has blurs, image jitters, too high or too low brightness, and too high or too low color difference, the quality of the picture is often poor. Therefore, in the embodiment of the invention, by setting the fuzzy degree, the jitter degree, the exposure degree and/or the color change degree of the picture as the picture parameters, the pictures in the video to be repaired can be screened from the parameter dimensions subsequently, and the pictures with poor quality can be accurately deleted to a certain extent.

It should be noted that the more the types of picture parameters are, the more dimensions are referred to in the subsequent screening, and accordingly, the final screening result is more accurate, but the calculation amount is increased accordingly. Conversely, if the types of picture parameters are less, the dimensions referred to in the subsequent screening are less, and accordingly, the accuracy of the final screening result is reduced, but the calculation amount is smaller. Therefore, in specific implementation, the calculation amount that the hardware device can carry may be determined first, and the number of the selected picture parameters may be determined according to the calculation amount that the hardware device can carry, so as to ensure that the hardware device can operate normally. Wherein the number of the selected picture parameters is positively correlated with the bearable calculation amount.

When a plurality of picture parameters are selected, a plurality of target information corresponding to the picture parameters may be provided. For example, assuming that the blur degree, the shake degree, the exposure degree, and the color change degree are selected, the blur label information corresponding to the blur degree, the shake label information corresponding to the shake degree, the exposure label information corresponding to the exposure degree, and the color difference label information corresponding to the color change degree may be obtained. The fuzzy label information, the jitter label information, the exposure label information and the color difference label information are target information. The fuzzy label information can be used for representing whether the fuzzy degree of the target picture meets the preset requirement corresponding to the fuzzy degree, the shaking label information is used for representing whether the shaking degree of the target picture meets the preset requirement corresponding to the shaking degree, the exposure label information is used for representing whether the exposure degree of the target picture meets the preset requirement corresponding to the exposure degree, and the color difference label information is used for representing whether the color change degree of the target picture meets the preset requirement corresponding to the color change degree.

Optionally, in the embodiment of the present invention, the operation of performing screening processing on the video to be processed according to the target information of the target picture included in the video to be processed may be implemented by the following sub-steps:

substep (1): and segmenting the video to be processed to obtain a plurality of video segments.

For example, the video to be processed may be divided into video segments containing the same number of frames by using a preset division algorithm in an equal interval division manner. Or, the to-be-processed video may be randomly divided into video segments with different frame numbers by using a preset division algorithm according to a non-equal interval division manner, which is not limited in the embodiment of the present invention. Of course, other division manners may also be adopted to implement the division, which is not limited in the embodiment of the present invention.

Substep (2): and for each video clip, screening the video clip according to the target information of the target picture contained in the video clip.

In this step, the video clips may be used as processing units, and the screening process may be performed for each video clip. The screening process for the video clip may include deleting a target picture or the video clip that does not meet preset requirements in the video clip.

In the embodiment of the invention, when the screening processing is specifically carried out, the video to be processed is firstly segmented to obtain a plurality of video segments. And then, according to the target information of the target picture contained in the video clip, the video clip is taken as a processing unit to carry out screening processing on the video clip. Therefore, the video to be processed is divided into video segments with smaller granularity and then processed, so that the burden of each processing operation can be reduced to a certain extent, and the processing efficiency can be ensured to a certain extent.

Further, under the condition that the video to be processed is divided into the video segments, the video segments after the screening processing can be merged to obtain the target video when the subsequent operation of generating the target video according to the video to be processed after the screening processing is realized. Because the screening process deletes the pictures with poor quality in each video clip, the quality of the target video can be ensured to a certain extent by combining the video clips after the screening process to obtain the target video. Specifically, during merging, merging can be performed according to the sequence of each screened video segment in the video to be processed, so as to ensure that the finally obtained target video can be played normally.

Optionally, in an embodiment of the present invention, the video to be processed may be selected by the user. Specifically, before determining target information corresponding to the picture parameter of the target picture, receiving a selection operation of a user on a selectable video; determining the selectable video selected by the selection operation as the video to be processed; the selectable video is a video stored in the electronic device. Accordingly, after the target video is generated, the target video can be displayed to the user, so that the user can obtain the processing result in time, and the interaction effect is improved.

The videos stored in the electronic device can be displayed in the client, and the user can click the optional video to be processed to realize input selection operation. Accordingly, the electronic device may receive the selection operation and determine the selected selectable video as the video to be processed. It should be noted that, in the embodiment of the present invention, after the target information is determined, the target information may be added to each target picture and displayed to the user. The user can select the target picture to be deleted according to the requirement and the target information of the target picture. Accordingly, the electronic device can delete the target picture selected by the user. In this way, by displaying the target picture to which the target information is added to the user and autonomously deciding the target picture to be specifically deleted by the user, the flexibility of operation can be improved.

Optionally, before the operation of determining the target information corresponding to the picture parameter of the target picture for the target picture in the video to be processed, the following steps may be further performed in the embodiment of the present invention:

step A, determining the target picture according to pictures contained in the video to be processed; extracting the target pictures from the video to be processed, and adding timestamp information to each target picture; the timestamp information is used to characterize an order of the target picture in the target picture.

In this step, the occurrence time point of each target picture in the video to be processed may be used as the timestamp information. For example, assume that the target picture includes picture a, picture b, and picture c. Wherein, the appearance time points of the picture a, the picture b and the picture c are respectively as follows: 10 th, 15 th, 21 st second. Then the 10 th second, the 15 th second and the 21 st second can be regarded as the time stamp information containing the picture a, the picture b and the picture c, respectively. Further, when adding the timestamp information to each target picture, an association relationship between each target picture and the corresponding timestamp information may be established, or the corresponding timestamp information may be written into the target picture.

Correspondingly, after the operation of determining the target information corresponding to the picture parameter of the target picture for the target picture in the video to be processed, the following steps may be further performed: and step B, merging the target picture into the video to be processed according to the timestamp information of the target picture. In specific implementation, the position of the target picture can be determined according to the timestamp information, and then the target picture is inserted into the corresponding position. For example, picture a may be inserted into the video to be processed at the position of 10 seconds, picture b may be inserted into the video to be processed at the position of 15 seconds, and picture c may be inserted into the video to be processed at the position of 21 seconds.

It should be noted that, in the embodiment of the present invention, before the target picture is incorporated into the video to be processed, a third target picture whose all picture parameters do not meet the preset requirements may be determined, and then the third target picture may be deleted. The preset requirement may include one or more of a normal blur level, a normal shake level, a normal exposure level and a normal color change level. Specifically, for each picture parameter, it may be determined whether target information corresponding to the picture parameter is a label for representing that the picture parameter does not meet the preset requirement, and if so, it may be determined that none of the picture parameters meets the preset requirement. Further, if all picture parameters do not meet the preset requirements, it is indicated that the quality of the picture is poor, and therefore, the third target picture can be directly deleted before joining. Thus, the burden of subsequent screening processing can be reduced, unnecessary merging operation on the target pictures can be avoided, and the processing efficiency can be further ensured.

In the embodiment of the invention, the target picture is determined and the target picture is extracted before the operation of determining the target information corresponding to the picture parameter of the target picture. Therefore, the target picture is extracted independently, so that the interference of other pictures in the video to be processed can be avoided when the target information corresponding to the picture parameter of the target picture is determined subsequently, and the processing effect can be further ensured to a certain extent. Meanwhile, after the target information is determined according to the extracted target picture, the target picture is merged into the video to be processed, so that the follow-up steps can be carried out normally. And the timestamp information is added into the target picture, so that the target picture can be conveniently and rapidly merged into the video to be processed according to the timestamp information, and the processing effect is further ensured.

Optionally, in an embodiment of the present invention, the operation of determining the target picture according to the pictures included in the video to be processed may be implemented by the following sub-steps:

substep (3): under the condition that the total number of pictures contained in the video to be processed is larger than a first preset number threshold, selecting m pictures from the video to be processed as the target pictures according to a preset frame rate; the m is not greater than the first preset number threshold.

In this step, the first preset number threshold and the preset frame rate may be set according to actual requirements. The first preset number threshold may be a number of pictures required for implementing the screening. For example, the first predetermined number threshold may be 50, 60, etc. The preset frame rate may be 4 frames per second (fps). Specifically, the total number of pictures included in the video to be processed may be determined, and for example, the configuration information of the video to be processed may be read to obtain the total number. Then, whether the total quantity is larger than a first preset quantity threshold value is judged. If the total number is greater than the first preset number threshold, the total number of the pictures can be considered to be greater, and if all the pictures are directly taken as target pictures, excessive calculation amount is introduced. Therefore, the target pictures can be selected according to the preset frame rate, and accordingly, the target pictures can be correspondingly extracted subsequently. That is, frame extraction may be performed according to a preset frame rate to obtain m target pictures, and the m target pictures form a picture sequence.

Substep (4): and taking all pictures contained in the video to be processed as the target pictures when the total number is not greater than the first preset number threshold.

If the total number is not greater than the first preset number threshold, it means that if all the pictures are directly taken as target pictures, no excessive calculation amount is introduced. Therefore, all pictures can be directly used as target pictures without other processing. In this way, it is possible to avoid performing unnecessary other processing while achieving determination of the target picture.

In the embodiment of the invention, all pictures contained in the video to be processed are taken as the target pictures only when the total number is not greater than the first preset number threshold, and only part of the pictures are selected as the target pictures when the total number is greater than the first preset number threshold. Therefore, enough target pictures can be ensured to a certain extent under the condition of avoiding the excessive target pictures, and then more information can be provided for subsequent screening, and the screening effect is ensured.

Optionally, the preset requirements in the embodiment of the present invention may include preset requirements corresponding to the blur degree: the fuzzy degree is normal, and the preset requirements corresponding to the jitter degree are as follows: the preset requirements corresponding to the normal exposure degree of the jitter degree are as follows: the exposure degree is normal, and the preset requirements corresponding to the color change degree are as follows: the degree of color change is normal.

Further, the target information corresponding to the blur degree of the target picture can be determined through the following sub-steps:

substep (5): determining a first ratio of a first number of pixel points with the fuzzy confidence coefficient larger than a preset confidence coefficient threshold value in the target picture to the total pixel number of the target picture; determining fuzzy label information according to the size relation between the first ratio and a first preset ratio threshold; the fuzzy label information is used for representing whether the fuzzy degree of the target picture is normal or not.

In this step, the fuzzy confidence may be used to represent the probability that the pixel is a fuzzy pixel. Specifically, the target picture may be input into a preset blur detection module, and the blur detection module may be implemented based on a semantic segmentation network formed by a Convolutional Neural Network (CNN). In an actual application scenario, sample pictures with different fuzzy degrees can be obtained, and a neural network is trained by using the sample pictures to generate a fuzzy detection module. Further, when the method is used, the fuzzy detection module can extract the picture characteristics of the input target picture, and then the fuzzy confidence of each pixel point in the target picture is determined according to the extracted picture characteristics.

Further, the preset confidence threshold and the first preset ratio threshold may be set according to actual requirements, and for example, the preset confidence threshold may be 80%. The first preset ratio threshold may be 0.2. Further, if the fuzzy confidence of the pixel point is greater than the preset confidence threshold, it can be considered that the pixel point has a fuzzy problem, and the pixel point is a fuzzy pixel point. Correspondingly, in this step, the fuzzy confidence of each pixel point may be compared with a preset confidence threshold to determine the first number. And then dividing the first number by the total pixel number of the target picture to obtain a first ratio.

If the first ratio is greater than the first preset ratio threshold, the blurring degree of the target picture can be considered to be relatively serious, and accordingly, the blurring label information of the target picture can be set as the first blurring label. The first fuzzy label represents that the fuzzy degree of the target picture is abnormal. If the first ratio is not greater than the first preset ratio threshold, the blurring degree of the target picture can be considered to be within an acceptable range, and accordingly, the blurring label information of the target picture can be set as a second blurring label. And the second fuzzy label represents that the fuzzy degree of the target picture is normal. For example, the first fuzzy label may be "unclean" and the second fuzzy label may be "clear".

In the embodiment of the invention, whether the target picture is fuzzy or not is determined according to the proportion of the fuzzy pixel points in the target picture, and corresponding fuzzy label information is set. The accuracy of the judgment result of the fuzzy picture can be ensured to a certain extent, and the reliability of the set fuzzy label information can be ensured.

It should be noted that, in an actual application scene, the subject is mainly focused during the shooting process, and the background is intentionally blurred to highlight the subject. Therefore, the embodiment of the invention can also determine the background area in the target picture, and then detect the coincidence proportion of the fuzzy area and the background area; the fuzzy region is a region formed by pixel points of which the fuzzy confidence coefficient is greater than a preset confidence coefficient threshold value. And under the condition that the first ratio is greater than a first preset ratio threshold and the coincidence ratio is not greater than a preset coincidence ratio threshold, setting the fuzzy label information of the target picture as a first fuzzy label. The preset overlap ratio threshold may be set according to an actual requirement, for example, the preset overlap ratio threshold may be 90%, if the overlap ratio is greater than the preset overlap ratio threshold, the blurred region in the target picture may be considered to belong to a normal phenomenon, and if the overlap ratio is not greater than the preset overlap ratio threshold, the blurred region in the target picture may be considered to belong to a result of an abnormal factor.

In the embodiment of the invention, by detecting whether the fuzzy area is the background area, the first fuzzy label representing that the fuzzy degree is abnormal is set for the target picture only when the fuzzy area is not the background area (the coincidence proportion is not greater than the preset coincidence proportion threshold) and the first ratio is greater than the first preset ratio threshold. Therefore, the target picture can be prevented from being judged to be a picture with abnormal fuzzy degree by mistake under the condition that the background is fuzzy due to focusing, and improper fuzzy label information is further set for the target picture.

Further, the target information corresponding to the jitter degree of the target picture can be determined through the following sub-steps:

substep (6): the target picture is used as the input of a first preset classification model, and the jitter label information is determined according to the output category of the first preset classification model; the first preset classification model is used for classifying the pictures according to whether the shaking degree is normal or not.

In this step, the shake label information is used to represent whether the shake degree of the target picture is normal. The first predetermined classification model may be based on a CNN neural network, the first predetermined classification model may be obtained by training sample pictures with different jitter degrees (including normal jitter degrees and abnormal jitter degrees), and the first predetermined classification model may be learned through deep learning to distinguish whether the jitter degree of the picture is normal or not in the training process. Specifically, after the target picture is input into the first preset classification model, the first preset classification model can extract picture features of the input target picture, then judge whether the jitter degree of the target picture is normal according to the extracted picture features, and output the category. Correspondingly, if the output category of the first preset classification model is a category representing that the jitter degree is abnormal, the jitter label information of the target picture can be set as a first fuzzy label. If the output category of the first preset classification model is a category representing normal jitter degree, the jitter label information of the target picture can be set as a second fuzzy label. For example, the first jitter tag may be "reliable" and the second jitter tag may be "unreliable".

In the embodiment of the invention, the jitter label information is determined according to the output category of the first preset classification model, so that whether the target picture is jittered or not can be conveniently determined only by inputting the target picture into the first preset classification model, further the subsequent setting of the jitter label information can be facilitated, and the setting efficiency is improved.

Further, the target information corresponding to the exposure degree of the target picture can be determined through the following sub-steps:

substep (7): taking the target picture as the input of a second preset classification model, and determining exposure label information according to the output category of the second preset classification model; and the second preset classification model is used for classifying the pictures according to whether the exposure degree is normal or not.

In this step, the exposure tag information is used to represent whether the exposure degree of the target picture is normal. The second predetermined classification model may be based on a CNN neural network, and may be obtained by training sample pictures with different exposure degrees (including normal exposure degree and abnormal exposure degree), and the second predetermined classification model may learn, in the training process, the ability to distinguish whether the exposure degree of the picture is normal. Specifically, after the target picture is input into the second preset classification model, the second preset classification model can extract picture features of the input target picture, then judge whether the exposure degree of the target picture is normal according to the extracted picture features, and output the category. Accordingly, if the output category of the second preset classification model is a category representing that the exposure degree is abnormal, the exposure label information of the target picture may be set as the first exposure label. If the output category of the second preset classification model is a category representing normal exposure degree, the exposure label information of the target picture can be set as a second exposure label. For example, the first exposure label may be "exposure F" and the second exposure label may be "exposure R".

In the embodiment of the invention, the exposure label information is determined according to the output category of the second preset classification model, so that whether the target picture is abnormally exposed (overexposed and excessively dark) can be conveniently determined by inputting the target picture into the second preset classification model, the exposure label information can be conveniently and subsequently set, and the setting efficiency is improved.

Further, the target information corresponding to the color change degree of the target picture can be determined through the following sub-steps:

substep (8): determining a second ratio of a second number of pixel points of which the color values exceed a preset color value range to the total number of pixels in the target picture; determining color difference label information according to the magnitude relation between the second ratio and a second preset ratio threshold; and the color difference label information is used for representing whether the color change degree of the target picture is normal or not.

In an embodiment of the present invention, the color value of the pixel may be a color channel value of the pixel, for example, a red, green, and blue (RGB) color channel value. The preset color value range and the second preset ratio threshold can be set according to actual requirements. For example, the preset color value range may be determined according to the lowest color value and the highest color value in the plurality of pictures with normal color differences. The second preset ratio threshold may be based on a minimum ratio threshold that may affect the viewing experience of the user. If the color value falls into the preset color value range, the color of the pixel point can be considered to be normal, and if the color value does not fall into the preset color value range, the color of the pixel point can be considered to be abnormal.

Further, the color value of each pixel point in the target picture can be determined by using a color value detection algorithm. The color values are then compared to a predetermined range of color values to determine a second quantity. And then dividing the second number by the total pixel number of the target picture to obtain a second ratio.

If the second ratio is greater than the second preset ratio threshold, the color difference of the target picture can be considered to be abnormal, that is, the color change degree is abnormal. Accordingly, the color difference label information of the target picture may be set as the first color difference label. The first color difference label represents that the color change degree of the target picture is abnormal. If the second ratio is not greater than the second preset ratio threshold, the color change degree of the target picture can be considered to be normal, and accordingly, the color difference label information of the target picture can be set as the second color difference label. And the second color difference label represents that the color change degree of the target picture is normal. For example, the first Color difference label may be "Color F" and the second Color difference label may be "Color R".

In the embodiment of the invention, the proportion of the pixel points with abnormal colors in the target picture is determined, whether the color change degree of the target picture is normal or not is determined according to the proportion, and the corresponding color difference label information is set, so that the accuracy of the judgment result of the color difference of the picture can be ensured to a certain extent, and the reliability of the set color difference label information is ensured.

Optionally, in this embodiment of the present invention, the step of performing screening processing on the video segment according to the target information of the target picture included in the video segment may include:

substep (2 a): determining a third number of first target pictures in the video clip; the first target picture is a target picture which has target information representation picture parameters which do not meet the preset requirement and continuously appears.

In this step, the consecutive target pictures mean that the forward adjacent and/or backward adjacent pictures of the target picture in the video clip are also the target pictures. Specifically, the target picture whose picture parameter does not meet the preset requirement may be determined according to the target information of each target picture in the video segment. And then, taking the pictures of the target pictures, of which the continuously appeared picture parameters do not meet the preset requirements, as the first target pictures. The picture parameters do not meet the preset requirements, all the picture parameters do not meet the preset requirements, and part of the picture parameters do not meet the preset requirements. Accordingly, a target picture in which all picture parameters do not meet the preset requirement and which continuously appears may be used as the first target picture, for example, the target information may be: target pictures with a first fuzzy label of 'unclean', a first jitter label of 'project', a first exposure label of 'expose F' and a first Color difference label of 'Color F' which continuously appear are taken as first target pictures. Alternatively, a target picture which does not meet the preset requirement in part of picture parameters and appears continuously may be used as the first target picture.

For example, it is assumed that the video clip includes pictures 1 to 20. The target picture with the picture parameters not meeting the preset requirements comprises the following steps: pictures 1 to 10, 11, and 13. The pictures 1 to 10 are target pictures which continuously appear and have picture parameters which do not meet the preset requirements. Therefore, the pictures 1 to 10 can be determined as the first target pictures.

Substep (2 b): if the third number is larger than a second preset number threshold, rejecting n first target pictures; the n is less than the third number.

In this step, the second preset number threshold may be set according to actual requirements, and if the third number is greater than the second preset number threshold, it may be considered that if all the first target pictures are directly deleted, the subsequent problems of inconsistent front and back frames in the video and unsmooth video playing may occur at a high probability. Therefore, only a part of the first target picture may be culled. Specifically, n first target pictures may be randomly selected for deletion.

In the embodiment of the invention, n parts of first target pictures are removed by determining the first target pictures which continuously appear and the picture parameters do not meet the preset requirements under the condition that more first target pictures exist, so that the problem of unsmooth playing of subsequent videos caused by removal of too many continuous pictures can be avoided under the condition that low-quality pictures continuously appear.

Further, in the embodiment of the present invention, after n first target pictures are removed, a picture transition effect may be added to the remaining first target pictures, where the picture transition effect may be used to control a display effect when the first target pictures appear, and the picture transition effect may include one or more of right-out left-in, out-screw in, and in-out fade. Of course, the picture transition effect may also include other types of effects, which is not limited in this embodiment of the present invention. Therefore, the display effect of the first target picture during display can be improved to a certain extent by adding the picture transition effect to the remaining first target picture. It should be noted that, in the embodiment of the present invention, when an adding instruction sent by a user is received, an operation of adding a picture transition effect is performed, so that a problem that a finally generated target video cannot meet a user requirement due to an unnecessary adding operation can be avoided.

Further, in the embodiment of the present invention, after n first target pictures are removed, a transition video frame may be generated according to picture contents of the remaining first target pictures; the picture parameters of the transition video frame meet preset requirements, the picture similarity is larger than a preset similarity threshold, and the picture similarity is the similarity between the picture content of the transition video frame and the picture content of the remaining first target picture. The preset similarity threshold may be set according to actual requirements, and for example, the preset similarity threshold may be 99%. Then, a transition video frame is added in the remaining first target picture. In the embodiment of the invention, high-quality pictures with similar contents are further inserted into the rest first target pictures, so that the problems of inconsistent front and back pictures in the video and unsmooth video playing caused by the elimination of the first target pictures can be avoided to a greater extent while the image quality of the video is ensured to a certain extent.

Optionally, in the embodiment of the present invention, before the sub-step (2a), the following steps may be further performed:

substep (2 c): determining a third ratio of a fourth number of second target pictures contained in the video clip to a total number of pictures in the video clip; the second target picture is a target picture of which the target information representation picture parameters do not meet the preset requirements.

In this step, a target picture whose picture parameters do not meet the preset requirements may be determined according to the target information of each target picture in the video segment, so as to obtain a second target picture. The specific determination method may refer to the description in the foregoing related steps, and is not described herein again. Then, the number of the determined second target pictures may be counted to obtain a fourth number. Then, a ratio of the fourth number to the total number of pictures in the video segment may be calculated to obtain a third ratio.

Substep (2 d): and determining a third preset ratio threshold and a third preset number threshold.

Substep (2 e): if the third ratio is greater than the third preset ratio threshold and/or the fourth number is greater than the third preset number threshold, discarding the video clip.

In the embodiment of the present invention, the third preset ratio threshold and the third preset number threshold may be set according to actual requirements, if the third ratio is greater than the third preset ratio threshold, it may be considered that the proportion of the low quality pictures in the video segment is large, and if the fourth number is greater than the third preset number threshold, it may be considered that the number of the low quality pictures in the video segment is large, and it may be determined that the overall quality of the video segment is poor, and therefore, the video segment may be directly discarded.

Meanwhile, the overall quality of the video clip is measured by the proportion of the low-quality second target pictures and two dimensions of the specific quantity, so that the situation that a plurality of second target pictures exist in the video clip and are not recognized due to too much overall quantity of the pictures in the video clip can be avoided, the situation that subjectively the number of the second target pictures is less, but the second target pictures occupy larger proportion but are not recognized relative to the video clip is avoided, and the accuracy of determining the video clip with poor sorting quality is further ensured.

It should be noted that, in the embodiment of the present invention, video segments of which the third ratio is greater than the third preset ratio threshold and/or the fourth number is greater than the third preset number threshold may also be displayed to a user, a selection operation of the user for the video segments is received, and then the video segment selected by the selection operation is deleted, so as to ensure flexibility of the user operation.

In the embodiment of the invention, by determining the proportion or the specific quantity of the second target pictures with poor quality in each video clip, the video clip is directly discarded under the condition that the proportion or the specific quantity of the second target pictures with poor quality is higher, namely the overall quality of the video clip is poor, so that the calculation amount of subsequent related operations can be reduced to a certain extent, and the processing resources are saved. It should be noted that the substep described above may be performed before substep (2a) or after substep (2 a). Optionally, it may be performed before the sub-step (2a), so that unnecessary culling operation can be avoided, and processing resources can be saved to a greater extent.

Optionally, in this embodiment of the present invention, the step of determining the third preset ratio threshold and the third preset number threshold may include: substep (2d 1): determining a third preset ratio threshold value and a third preset quantity threshold value corresponding to the video clip template according to the video clip template corresponding to the video to be processed; the third preset ratio thresholds corresponding to different video clip templates are different, the third preset number thresholds corresponding to different video clip templates are different, and the third preset ratio thresholds and the third preset number thresholds are related to the video content types corresponding to the video clip templates.

The video processing method in the embodiment of the invention can be applied to automatic video editing scenes. Generally, in order to improve the video clipping effect, it is often necessary to remove the waste (lower quality pictures) in the video. Therefore, the useless slice elimination in the video clip can be realized based on the video processing method in the embodiment of the invention, so that the efficiency of the video clip and the subsequent viewing experience are improved. Meanwhile, compared with a manual rejection detection mode, the automatic rejection mode provided by the embodiment of the invention can be carried out in real time on line, so that the time consumption of rejection can be reduced to a certain extent, and the timeliness of processing is ensured. For example, taking target parameters including a blur degree, a jitter degree and an exposure degree as an example, fig. 2 is a schematic diagram of a clipping process provided by an embodiment of the present invention. As shown in fig. 2, a user may select a material (to-be-processed video) first, and then perform frame extraction according to a preset frame rate to obtain a picture sequence composed of target pictures. And then, determining fuzzy label information, shaking label information and exposure label information of the target picture through a CNN network, recombining the target picture and the label information into the video to be processed according to the timestamp information of the target picture, and selecting a segment suitable for clipping according to a clipping template preferred by a user or a selected clipping template. Wherein the segments suitable for clipping may be the video segments remaining after being discarded through the above sub-step (2 e).

Further, the video clip template corresponding to the video to be processed may be selected from the selectable clip templates. The selectable clip template may be a template preset in the electronic device and may be used for performing video clipping, for example, the selectable clip template may include a sports template, a gourmet template, a dynamic template, and the like. The selection may be according to user preferences, for example, a clip template commonly used by the user may be determined according to the user's historical usage record. And then determining the common clip template as a video clip template corresponding to the video to be processed. Or, the selectable clip template may be directly displayed to the user, and the selectable clip template selected by the user is determined as the video clip template corresponding to the video to be processed. Further, a third preset ratio threshold and a third preset number threshold corresponding to the video clip template corresponding to the video to be processed may be searched in a preset correspondence between the video clip template and the threshold.

In order to improve the visual effect of the video, when the video is edited, the video is often edited according to a video editing template. The clipping modes of the video clip templates are often different corresponding to different video content types. For example, the corresponding video content type is dynamic content, for example, a video clip template highlighting a motion process of a motion subject in a video, for example, a motion template and a dynamic template, when clipping is performed by using these templates, continuity of a video image is often emphasized, and since the content in such a video image is often in a motion state, a user is more difficult to perceive a low-quality image. When the templates are used for clipping, the appearance details of the main body in the video picture are often emphasized, and in this case, the motion amplitude of the content in the video picture is often smaller, so that a user can more easily perceive a low-quality picture. Correspondingly, in the embodiment of the invention, different thresholds can be set for different video clip templates according to the picture characteristics of each video clip template. For example, when the video content type corresponding to the video clip template is dynamic content, a higher third preset ratio threshold and a third preset number threshold are set, and when the video content type corresponding to the video clip template is dynamic content, a lower third preset ratio threshold and a third preset number threshold are set.

In the embodiment of the invention, different third preset ratio threshold values and third preset quantity threshold values are correspondingly set for different video clip templates according to the video content types corresponding to the video clip templates, and corresponding threshold values are selected to screen video segments according to the currently used video clip template during clipping, so that the screening operation can be more adaptive to the current clipping requirements to a certain extent, and the effect of segment screening is further improved.

Fig. 3 is a block diagram of a video processing apparatus according to an embodiment of the present invention, where the apparatus may include: a memory 301 and a processor 302. The memory 301 is used for storing program codes. The processor 302, invoking the program code, when executed, is configured to: determining target information corresponding to picture parameters of a target picture in a video to be processed; the target information is used for representing whether picture parameters of the target picture meet preset requirements or not; screening the video to be processed according to target information of a target picture contained in the video to be processed; the screening processing comprises deleting a target picture which does not meet the preset requirement or one of the video clips to which the target picture belongs; and generating a target video according to the screened to-be-processed video. Specifically, the specific implementation process of each operation executed by the processor 302 may refer to the related description in the foregoing method embodiment, and is not described herein again.

Optionally, the picture parameter includes one or more of a blur degree, a jitter degree, an exposure degree, and a color change degree of the picture. Optionally, the processor 302 is further configured to: segmenting the video to be processed to obtain a plurality of video segments; and for each video frequency band, screening the video clips according to the target information of the target pictures contained in the video clips. Optionally, the processor 302 is further configured to: for a target picture in a video to be processed, before determining target information corresponding to picture parameters of the target picture, determining the target picture according to a picture contained in the video to be processed; extracting the target pictures from the video to be processed, and adding timestamp information to each target picture; the timestamp information is used for characterizing the order of the target picture in the target picture; and for a target picture in a video to be processed, after determining target information corresponding to picture parameters of the target picture, merging the target picture into the video to be processed according to timestamp information of the target picture. Optionally, the processor 302 is further configured to: under the condition that the total number of pictures contained in the video to be processed is larger than a first preset number threshold, selecting m pictures from the video to be processed as the target pictures according to a preset frame rate; the m is not greater than the first preset number threshold; and taking all pictures contained in the video to be processed as the target pictures when the total number is not greater than the first preset number threshold. Optionally, the processor 302 is further configured to: determining a first ratio of a first number of pixel points with the fuzzy confidence coefficient larger than a preset confidence coefficient threshold value in the target picture to the total pixel number of the target picture; determining fuzzy label information according to the size relation between the first ratio and a first preset ratio threshold; the fuzzy label information is used for representing whether the fuzzy degree of the target picture is normal or not; and/or determining the jitter label information according to the output category of the first preset classification model by taking the target picture as the input of the first preset classification model; the first preset classification model is used for classifying the pictures according to whether the jitter degree is normal or not; and/or determining exposure label information according to the output category of a second preset classification model by taking the target picture as the input of the second preset classification model; the second preset classification model is used for classifying the pictures according to whether the exposure degree is normal or not; and/or determining a second ratio of a second number of pixel points with color values exceeding a preset color value range to the total pixel number in the target picture; determining color difference label information according to the magnitude relation between the second ratio and a second preset ratio threshold; and the color difference label information is used for representing whether the color change degree of the target picture is normal or not.

Optionally, the processor 302 is further configured to: determining a third number of first target pictures in the video clip; the first target picture is a target picture which has target information representation picture parameters which do not meet the preset requirement and continuously appears; if the third number is larger than a second preset number threshold, rejecting n first target pictures; the n is less than the third number. Optionally, the processor 302 is further configured to: adding a picture transition effect to the rest first target pictures; wherein the picture transition effect comprises one or more of right-out left-in, out-of-screw in, and fade-in and fade-out. Optionally, the processor 302 is further configured to: determining a third ratio of a fourth number of second target pictures contained in the video clip to a total number of pictures in the video clip; the second target picture is a target picture of which the target information representation picture parameters do not meet the preset requirements; determining a third preset ratio threshold and a third preset number threshold; if the third ratio is greater than the third preset ratio threshold and/or the fourth number is greater than the third preset number threshold, discarding the video clip.

Optionally, the processor 302 is further configured to: determining a third preset ratio threshold value and a third preset quantity threshold value corresponding to the video clip template according to the video clip template corresponding to the video to be processed; the third preset ratio thresholds corresponding to different video clip templates are different, the third preset number thresholds corresponding to different video clip templates are different, and the third preset ratio thresholds and the third preset number thresholds are related to the video content types corresponding to the video clip templates. Optionally, the processor 302 is further configured to: determining a third target picture with all picture parameters not meeting the preset requirements; deleting the third target picture; wherein the preset requirements comprise one or more of normal blurring degree, normal shaking degree, normal exposure degree and normal color change degree. Optionally, the processor 302 is further configured to: and merging the video clips after the screening treatment to obtain the target video. Optionally, the processor 302 is further configured to: for a target picture in a video to be processed, receiving a selection operation of a user on an optional video before determining target information corresponding to picture parameters of the target picture; determining the selectable video selected by the selection operation as the video to be processed; the selectable videos are videos stored in the electronic equipment; and according to the video to be processed after the screening processing, generating a target video, and then displaying the target video to the user.

In summary, the video processing apparatus provided in the embodiment of the present invention determines, for a target picture in a video to be processed, target information corresponding to a picture parameter of the target picture, where the target information is used to represent whether the picture parameter of the target picture meets a preset requirement, and performs a screening process on the video to be processed according to the target information of the target picture included in the video to be processed, where the screening process includes deleting the target picture that does not meet the preset requirement or one of video segments to which the target picture belongs, and finally, generates the target video according to the video to be processed after the screening process. Therefore, when the video is processed, the pictures in the video are automatically screened according to the picture parameters of the pictures, so that the screening cost can be reduced to a certain extent, and the screening efficiency is improved. Further, an embodiment of the present invention further provides a mobile device, where the mobile device includes a video acquisition device, and the mobile device is configured to acquire a video to be processed through the video acquisition device, and process the video to be processed according to the video processing method. Optionally, the mobile device is a drone and/or a drone vehicle. Further, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each step in the video processing method, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort. The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or digital signal processor may be used in practice to implement some or all of the functionality of some or all of the components in a computing processing device according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

For example, fig. 4 is a block diagram of a computing processing device provided in an embodiment of the present invention, and as shown in fig. 4, fig. 4 shows a computing processing device that can implement the method according to the present invention. The computing processing device conventionally includes a processor 710 and a computer program product or computer-readable medium in the form of a memory 720. The memory 720 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 720 has a storage space 730 for program code for performing any of the method steps of the above-described method. For example, the storage space 730 for the program codes may include respective program codes respectively for implementing various steps in the above methods. The program code can be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. Such a computer program product is typically a portable or fixed storage unit as described with reference to fig. 5. The memory unit may have memory segments, memory spaces, etc. arranged similarly to memory 720 in the computing processing device of fig. 4. The program code may be compressed, for example, in a suitable form. Typically, the memory unit comprises computer readable code, i.e. code that can be read by a processor, such as 710, for example, which when executed by a computing processing device causes the computing processing device to perform the steps of the method described above. The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. Reference herein to "one embodiment," "an embodiment," or "one or more embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the invention. Moreover, it is noted that instances of the word "in one embodiment" are not necessarily all referring to the same embodiment. In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A method of video processing, the method comprising:

and generating a target video according to the screened to-be-processed video.

2. The method of claim 1, wherein the picture parameters comprise one or more of a blur level, a jitter level, an exposure level, and a color variation level of the picture.

3. The method according to claim 1 or 2, wherein the performing the filtering process on the video to be processed according to the target information of the target picture included in the video to be processed comprises:

segmenting the video to be processed to obtain a plurality of video segments;

and for each video frequency band, screening the video clips according to the target information of the target pictures contained in the video clips.

4. The method according to any one of claims 1 to 3, wherein before determining target information corresponding to picture parameters of a target picture in a video to be processed, the method further comprises: determining the target picture according to pictures contained in the video to be processed; extracting the target pictures from the video to be processed, and adding timestamp information to each target picture; the timestamp information is used for characterizing the order of the target picture in the target picture;

after determining target information corresponding to picture parameters of a target picture in a video to be processed, the method further comprises: and merging the target picture into the video to be processed according to the timestamp information of the target picture.

5. The method according to claim 4, wherein the determining the target picture according to the pictures included in the video to be processed comprises:

under the condition that the total number of pictures contained in the video to be processed is larger than a first preset number threshold, selecting m pictures from the video to be processed as the target pictures according to a preset frame rate; the m is not greater than the first preset number threshold;

and taking all pictures contained in the video to be processed as the target pictures when the total number is not greater than the first preset number threshold.

6. The method according to claim 1 or 2, wherein the determining, for a target picture in the video to be processed, target information corresponding to a picture parameter of the target picture comprises:

determining a first ratio of a first number of pixel points with the fuzzy confidence coefficient larger than a preset confidence coefficient threshold value in the target picture to the total pixel number of the target picture; determining fuzzy label information according to the size relation between the first ratio and a first preset ratio threshold; the fuzzy label information is used for representing whether the fuzzy degree of the target picture is normal or not;

and/or determining the jitter label information according to the output category of the first preset classification model by taking the target picture as the input of the first preset classification model; the first preset classification model is used for classifying the pictures according to whether the jitter degree is normal or not;

and/or determining exposure label information according to the output category of a second preset classification model by taking the target picture as the input of the second preset classification model; the second preset classification model is used for classifying the pictures according to whether the exposure degree is normal or not;

and/or determining a second ratio of a second number of pixel points with color values exceeding a preset color value range to the total pixel number in the target picture; determining color difference label information according to the magnitude relation between the second ratio and a second preset ratio threshold; and the color difference label information is used for representing whether the color change degree of the target picture is normal or not.

7. The method according to claim 3, wherein the performing the filtering process on the video clip according to the target information of the target picture included in the video clip comprises:

determining a third number of first target pictures in the video clip; the first target picture is a target picture which has target information representation picture parameters which do not meet the preset requirement and continuously appears;

if the third number is larger than a second preset number threshold, rejecting n first target pictures; the n is less than the third number.

8. The method according to claim 7, wherein after said culling n of said first target pictures, the method further comprises:

adding a picture transition effect to the rest first target pictures;

wherein the picture transition effect comprises one or more of right-out left-in, out-of-screw in, and fade-in and fade-out.

9. The method of claim 7, further comprising:

determining a third ratio of a fourth number of second target pictures contained in the video clip to a total number of pictures in the video clip; the second target picture is a target picture of which the target information representation picture parameters do not meet the preset requirements;

determining a third preset ratio threshold and a third preset number threshold;

if the third ratio is greater than the third preset ratio threshold and/or the fourth number is greater than the third preset number threshold, discarding the video clip.

10. The method of claim 9, wherein determining the third predetermined ratio threshold and the third predetermined number threshold comprises:

determining a third preset ratio threshold value and a third preset quantity threshold value corresponding to the video clip template according to the video clip template corresponding to the video to be processed;

the third preset ratio thresholds corresponding to different video clip templates are different, the third preset number thresholds corresponding to different video clip templates are different, and the third preset ratio thresholds and the third preset number thresholds are related to the video content types corresponding to the video clip templates.

11. The method according to claim 4, wherein before merging the target picture into the video to be processed according to the timestamp information of the target picture, the method further comprises:

determining a third target picture with all picture parameters not meeting the preset requirements;

deleting the third target picture;

wherein the preset requirements comprise one or more of normal blurring degree, normal shaking degree, normal exposure degree and normal color change degree.

12. The method according to claim 3, wherein the generating the target video according to the to-be-processed video after the filtering process comprises:

and merging the video clips after the screening treatment to obtain the target video.

13. The method according to claim 1, wherein before determining target information corresponding to picture parameters of a target picture in the video to be processed, the method further comprises: receiving the selection operation of a user on the selectable video; determining the selectable video selected by the selection operation as the video to be processed; the selectable videos are videos stored in the electronic equipment;

after the target video is generated according to the video to be processed after the screening process, the method further includes: displaying the target video to the user.

14. A video processing apparatus, characterized in that the apparatus comprises a memory and a processor;

the memory for storing program code;

the processor, invoking the program code, when executed, is configured to:

and generating a target video according to the screened to-be-processed video.

15. A mobile device, characterized in that it comprises a video acquisition device for acquiring a video to be processed by means of said video acquisition device, said video to be processed being processed according to the video processing method of any one of claims 1 to 13.

16. The method of claim 14, wherein the mobile device is a drone and/or a drone vehicle.

17. A computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, performs the operations of:

and generating a target video according to the screened to-be-processed video.