Video generation method and system

Abstract

The invention provides a video generation method. The video generation method comprises the following steps: acquiring video data; obtaining an unprocessed single sampling picture frame set in the unprocessed video data according to the video data; obtaining each possible picture interference area in each unprocessed single sampling picture; collecting each surrounding possible picture interference area matched with each possible picture interference area, and calculating a sampling characteristic scalar; collecting a hierarchical characteristic target and a hierarchical characteristic value of each possible picture interference area, and calculating a target characteristic scalar; obtaining a characteristic scalar of each possible picture interference area; obtaining each correlation area of each possible picture interference area and a motion direction of each possible picture interference area; obtaining a related scalar of each possible picture interference area; and obtaining each interference region in each unprocessed single sampling picture through the characteristic scalar and the related scalar, and processing each interference region in each unprocessed single sampling picture.

Description

Technical Field

[0001] The present invention relates to the technical field of video generation, and in particular to a video generation method and a video generation system. Background Art

[0002] In the process of video generation, various factors often interfere with the generated video quality, which makes it difficult to distinguish the content in the video. In the existing video generation methods, most of them improve the video data by enhancing the video data, such as performing Fourier transform on the video data, adjusting the parameters of the video data, etc. However, while removing the interference area, it also destroys the sampling value of the normal area in the video data, resulting in a fuzzy video and unclear video. Summary of the invention

[0003] In order to solve the above technical problems, the present invention provides a video generation method, which can accurately remove the interference area in the unprocessed single sampled image, improve the positioning accuracy of the interference area, and maintain the sampling value of the normal area in the process of removing the interference area, thereby making the video data clearer.

[0004] The technical solution adopted by the present invention is as follows:

[0005] A video generation method comprises the following steps: obtaining video data, the video data comprising unprocessed video data; obtaining an unprocessed single-sampled picture frame set in the unprocessed video data according to the video data, the unprocessed single-sampled picture frame set comprising a plurality of unprocessed single-sampled pictures; obtaining each possible picture interference area in each unprocessed single-sampled picture through the sampling values ​​of the surrounding sampling element points of each sampling element point in each unprocessed single-sampled picture; collecting each surrounding possible picture interference area matched by each possible picture interference area, and calculating the sampling characteristic scalar of each possible picture interference area through the sampling values ​​of each possible picture interference area, the sampling values ​​of each surrounding possible picture interference area matched by each possible picture interference area, and the interval between each possible picture interference area and each matching surrounding possible picture interference area; collecting the hierarchical characteristic target and hierarchical characteristic value of each possible picture interference area, and calculating the sampling characteristic scalar of each possible picture interference area through the hierarchical characteristic value of each possible picture interference area, the sampling value of each possible picture interference area matched by each possible picture interference area The target characteristic scalar of each possible picture interference area is calculated by using the hierarchical characteristic target of the area and the hierarchical characteristic target of each surrounding possible picture interference area matched by each possible picture interference interference area; the characteristic scalar of each possible picture interference area is obtained through the sampling characteristic scalar and the target characteristic scalar; the relevant picture frame set of each unprocessed single picture match and the surrounding unprocessed single sampled pictures of each unprocessed picture match are collected, and each relevant area of ​​each possible picture interference area and the motion orientation of each possible picture interference area are obtained through each unprocessed picture in the relevant picture frame set of each unprocessed picture match and the surrounding unprocessed pictures of each unprocessed picture match; the relevant scalar of each possible picture interference area is obtained through each relevant area of ​​each possible picture interference area and the motion orientation of each possible picture interference area; each interference area in each unprocessed single sampled picture is obtained through the characteristic scalar and the relevant scalar, and each interference area in each unprocessed single sampled picture is processed.

[0006] In one embodiment of the present invention, the method of obtaining each possible image interference area in each unprocessed single sampled image through the sampling values ​​of the surrounding sampling points of each sampling point in each unprocessed single sampled image specifically includes: collecting sampling points of 8 sampling areas around each sampling point in each unprocessed single sampled image, and marking each surrounding sampling point of each sampling point in each unprocessed single sampled image; calculating the sampling difference between each sampling point and each surrounding sampling point of the matching sampling point, and marking each sampling difference value of each sampling point, wherein a single sampling point matches 8 sampling difference values; sorting out each sampling point of each sampling point The number of sampling difference values ​​that exceed the standard sampling difference critical point among the sampling difference values, and the number of sampling difference values ​​that exceed the standard sampling difference critical point among each sampling difference value of each sampling element point divided by the number of sampling areas around each sampling element point is marked as the sampling difference level of each sampling element point; for each sampling element point in each unprocessed single-sampled image, if the sampling difference level of any sampling element point is not less than the standard sampling difference critical point, and the number of surrounding sampling element points whose sampling difference level of each surrounding sampling element point of any sampling element point is not less than the standard sampling difference critical point exceeds 1, then this sampling element point is confirmed as a possible image interference area.

[0007] In one embodiment of the present invention, the method of collecting each surrounding possible picture interference area matched by each possible picture interference area, and calculating the sampling characteristic scalar of each possible picture interference area through the sampling value of each possible picture interference area, the sampling value of each surrounding possible picture interference area matched by each possible picture interference area, and the interval between each possible picture interference area and each surrounding possible picture interference area matched, specifically includes: collecting each possible picture interference area of ​​5 sampling areas around each possible picture interference area in each unprocessed single sampled picture, and marking them as surrounding possible picture interference areas of each possible picture interference area; sorting out the number of surrounding possible picture interference areas of each possible picture interference area; obtaining the Pythagorean metric value of each surrounding possible picture interference area of ​​each possible picture interference area and the matched possible picture interference area; obtaining the sampling characteristic scalar of each possible picture interference area in each unprocessed single sampled picture through the Pythagorean metric value of each surrounding possible picture interference area of ​​each possible picture interference area and the matched possible picture interference area, the sampling value of each possible picture interference area and the sampling value of each surrounding possible picture interference area matched by each possible picture interference area; calculating the sampling characteristic scalar of each possible picture interference area, wherein the expression of the sampling characteristic scalar is:

[0008]

[0009] Among them, Hi j The sampling characteristic scalar of the order i in the unprocessed single-sampled picture frame set and the order j in the unprocessed single-sampled picture frame set, Y i j represents the number of possible image interference areas around the order j possible image interference area in the order i of the unprocessed single sampled image frame set, f i j,k Represents the Pythagorean metric of the order k surrounding possible image interference regions matching the order j possible image interference regions in the unprocessed single sampled image frame set, N i j Represents the sampling values ​​of the possible image interference areas in the order i of the unprocessed single-sampled image frame set, N i j,k Represents the sampling value of the kth surrounding possible image interference area matched by the jth possible image interference area in the i-th order in the unprocessed single-sampled image frame set, and n is a positive integer.

[0010] In one embodiment of the present invention, the step of collecting the hierarchical characteristic target and hierarchical characteristic value of each possible image interference area specifically includes: for one possible image interference area of ​​one unprocessed single-sampled image in the unprocessed single-sampled image frame set, performing several moving processes on the line segment passing through the possible image interference area to obtain several characteristic line segments; for one of the characteristic line segments, accumulating the sampling differences between the possible image interference area and each surrounding possible image interference area of ​​the possible image interference area of ​​the characteristic line segment, and marking the accumulated value of the sampling differences as the sampling hierarchical value of the possible image interference area; marking the pole number in each sampling hierarchical value matched by the possible image interference area as the hierarchical characteristic target matched by the possible image interference area; marking the characteristic line segment matched by the pole number in each sampling hierarchical value matched by the possible image interference area and the degree of deviation in the 0° direction as the hierarchical characteristic target matched by the possible image interference area.

[0011] In one embodiment of the present invention, the expression of the target characteristic scalar of each possible picture interference area is:

[0012]

[0013] Among them, X i j The target characteristic scalar representing the order i of the unprocessed single-sampled picture frame set and the order j of the possible picture interference regions in the processed single-sampled picture, ψ i jrepresents the hierarchical characteristic target of the order i in the unprocessed single-sampled picture frame set and the order j in the unprocessed single-sampled picture, ψ i j,k represents the order in the unprocessed single-sampled image frame set, the order in the i-th unprocessed single-sampled image, the order in which the j-th possible image interference area matches, the hierarchical characteristic target of the k-th surrounding possible image interference area, F i j Represents the hierarchical characteristic values ​​of the sequential j possible image interference areas in the sequential i unprocessed single-sampled images in the unprocessed single-sampled image frame set.

[0014] In one embodiment of the present invention, the collecting of the related picture frame set matched by each unprocessed single picture and the surrounding unprocessed single sampling pictures matched by each unprocessed picture specifically includes: marking each unprocessed single sampling picture in the unprocessed single sampling picture frame set to obtain the order of each unprocessed single sampling picture in the unprocessed single sampling picture frame set, wherein the sequence number of the m unprocessed single sampling pictures in the unprocessed single sampling picture frame set is m; recording the number of unprocessed single sampling pictures in the unprocessed single sampling picture frame set, recorded as A, the order of the unprocessed single sampling pictures is marked as q, and the unprocessed single sampling pictures are marked as D q ; If q exceeds the first standard critical point P, the first related picture frame set matched by this unprocessed single sample picture is marked as [D q-P , D q-P+1 , ..., D q-1 ]; if q does not exceed the first standard critical point, the first related picture frame set matched by this unprocessed single sample picture is marked as [D1, ..., D q-1 ]; if q is 1, then the first related picture frame set of this unprocessed single sample picture matching is empty; if M minus m exceeds the first standard critical point, then the second related picture frame set of this unprocessed single sample picture matching is marked as [D q+1 , ..., D q+P-1 , D q+P ]; If A minus q does not exceed the first standard critical point, the second related picture frame set matched by this unprocessed single sample picture is marked as [D q+1 , ..., D A ]; if A minus q is 0, then the second related picture frame set matched by this unprocessed single sample picture is empty, where D q-P represents the unprocessed single-sampled picture with the order qP in the unprocessed single-sampled picture frame set, D q-P+1 represents the unprocessed single-sampled picture in the order of q-P+1 in the unprocessed single-sampled picture frame set, D q-1represents the q-1 unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, D q+1 represents the unprocessed single-sampled image with the order q+1 in the unprocessed single-sampled image frame set, D q+P-1 represents the unprocessed single-sampled image with the order q+P-1 in the unprocessed single-sampled image frame set, D q+P represents the unprocessed single-sampled picture with the order of q+P in the unprocessed single-sampled picture frame set, D A represents the unprocessed single-sampled picture with the order A in the unprocessed single-sampled picture frame set, and D1 represents the unprocessed single-sampled picture with the order 1 in the unprocessed single-sampled picture frame set; connect the second related picture frame set matching the unprocessed single-sampled picture with the first related picture frame set matching the unprocessed single-sampled picture, and mark the connected picture frame set as the related picture frame set matching the unprocessed single-sampled picture; if the order D of the unprocessed single-sampled picture is q If it is before sequence A, the unprocessed single-sampled picture with sequence q+1 in the unprocessed single-sampled picture frame set is marked as this unprocessed single-sampled picture D. q The surrounding unprocessed single-sampled images; if this unprocessed single-sampled image D q If the order is consistent with the order A, the unprocessed single-sampled picture with the order q-1 in the unprocessed single-sampled picture frame set is marked as this unprocessed single-sampled picture D q Surrounding unprocessed single sample images.

[0015] In one embodiment of the present invention, the method of obtaining each relevant area of ​​each possible picture interference area and the motion direction of each possible picture interference area through each unprocessed picture in the relevant picture frame set matched by each unprocessed picture and the surrounding unprocessed pictures matched by each unprocessed picture specifically includes: for a random possible picture interference area of ​​a random unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, the placeholder of this possible picture interference area on this unprocessed single-sampled picture is recorded as (r, s); collecting the sampling element points of the placeholder (r, s) of each unprocessed single-sampled picture in the relevant picture frame set matched by this unprocessed single-sampled picture, and marking them as the relevant area of ​​this possible picture interference area; collecting the sampling element points of the placeholder (r, s) in the surrounding unprocessed single-sampled pictures matched by this unprocessed single-sampled picture Each surrounding sampling element point of the 5 sampling areas of the sample point, and each surrounding sampling element point of the 5 sampling areas of the sampling element point occupying the place (r, s) in the surrounding unprocessed single sampling picture matched by this unprocessed single sampling picture is marked as the surrounding characteristic sampling element point of this possible picture interference area; the surrounding characteristic sampling element point of the minimum pole number matching of the sampling difference between this possible picture interference area and each surrounding characteristic sampling element point matched by this possible picture interference area is collected, and marked as the target surrounding characteristic sampling element point; the projection of the sampling element point occupying the place (r, s) in the surrounding unprocessed single sampling picture matched by this unprocessed single sampling picture and the target surrounding characteristic sampling element point is marked as the moving target of this possible picture interference area; the moving target of this possible picture interference area and the deviation degree in the 0° direction are collected, and marked as the moving direction of this possible picture interference area.

[0016] In one embodiment of the present invention, the expression of the relevant scalar is:

[0017]

[0018] Among them, G represents the relevant scalar of the possible image interference area, n represents a positive integer, B represents the number of relevant areas matched by the possible image interference area, D0 represents the sampling value of the possible image interference area, D1 c represents the sampling value of the th correlation area that may match the image interference area, β0 represents the motion direction that may match the image interference area, It represents the mean value of the surrounding motion orientation of the possible image interference area, and max represents the maximum value function.

[0019] In one embodiment of the present invention, the method of obtaining each interference area in each unprocessed single sampled image by using the characteristic scalar and the related scalar specifically includes: unifying the dimension of the characteristic scalar and the related scalar of each possible image interference area, and marking them as the edge label scalar and the related label scalar of each possible image interference area; gluing the edge label scalar of each possible image interference area and the related label scalar of the matching possible image interference area, and marking them as the unified scalar of each possible image interference area; if the unified scalar of each possible image interference area exceeds the second standard critical point, the matching possible image interference area is confirmed as an interference area.

[0020] A video generation system comprises: a first acquisition module, the first acquisition module is used to acquire video data, the video data includes unprocessed video data; a second acquisition module, the second acquisition module is used to acquire an unprocessed single-sampled picture frame set in the unprocessed video data according to the video data, the unprocessed single-sampled picture frame set includes a plurality of unprocessed single-sampled pictures; an acquisition module, the acquisition module is used to acquire each possible picture interference area in each unprocessed single-sampled picture through the sampling values ​​of the surrounding sampling elements of each sampling element point in each unprocessed single-sampled picture; a first calculation module, the first calculation module is used to acquire each surrounding possible picture interference area matched by each possible picture interference area, and calculate the sampling characteristic scalar of each possible picture interference area through the sampling value of each possible picture interference area, the sampling value of each surrounding possible picture interference area matched by each possible picture interference area, and the interval between each possible picture interference area and each matching surrounding possible picture interference area; a second calculation module, the second calculation module is used to acquire the hierarchical characteristic target and hierarchical characteristic value of each possible picture interference area, and calculate the sampling characteristic scalar of each possible picture interference area through the hierarchical characteristic value of each possible picture interference area, each The target characteristic scalar of each possible picture interference area is calculated based on the hierarchical characteristic target of the possible picture interference area and the hierarchical characteristic target of each surrounding possible picture interference area matched by each possible picture interference area; a third acquisition module, the third acquisition module is used to obtain the characteristic scalar of each possible picture interference area through the sampling characteristic scalar and the target characteristic scalar; a fourth acquisition module, the fourth acquisition module is used to collect the relevant picture frame set of each unprocessed single picture match and the surrounding unprocessed single sampled pictures of each unprocessed picture match, and obtain each relevant area of ​​each possible picture interference area and the motion orientation of each possible picture interference area through each unprocessed picture in the relevant picture frame set of each unprocessed picture match and the surrounding unprocessed pictures of each unprocessed picture match; a fifth acquisition module, the fifth acquisition module is used to obtain the relevant scalar of each possible picture interference area through each relevant area of ​​each possible picture interference area and the motion orientation of each possible picture interference area; a processing module, the processing module is used to obtain each interference area in each unprocessed single sampled picture through the characteristic scalar and the relevant scalar, and process each interference area in each unprocessed single sampled picture.

[0021] Beneficial effects of the present invention:

[0022] The present invention obtains video data, obtains an unprocessed single-sampled picture frame set in the unprocessed video data according to the video data, then obtains each possible picture interference area through each unprocessed single-sampled picture, calculates the sampling characteristic scalar and target characteristic scalar of each possible picture interference area, obtains the characteristic scalar through the sampling characteristic scalar and the target characteristic scalar, obtains the relevant scalar of each possible picture interference area by obtaining the relevant area and motion direction of each possible picture interference area, obtains each interference area in each unprocessed single-sampled picture through the characteristic scalar and the relevant scalar, and processes each interference area, thereby being able to accurately remove the interference area in the unprocessed single-sampled picture, improve the positioning accuracy of the interference area, and also maintain the sampling value of the normal area in the process of removing the interference area, so as to make the video data clearer. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of a video generation method according to an embodiment of the present invention;

[0024] Figure 2 FIG. 4 is a block diagram of a video generation system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Figure 1 The figure is a flowchart of a video generation method according to an embodiment of the present invention.

[0027] like Figure 1 As shown, the video generation method of the embodiment of the present invention includes the following steps:

[0028] S1, obtaining video data, where the video data includes unprocessed video data.

[0029] In one embodiment of the present invention, the video data may be obtained from a user input terminal, and includes unprocessed source video data or segments.

[0030] S2, obtaining an unprocessed single-sampled picture frame set in the unprocessed video data according to the video data, wherein the unprocessed single-sampled picture frame set includes a plurality of unprocessed single-sampled pictures.

[0031] In one embodiment of the present invention, the unprocessed video data may contain uninterrupted unprocessed single-sampled images, and the intervals between consecutive unprocessed single-sampled images are fixed numbers, wherein the single-sampled images are images with only one sampled color for the pixel color. Specifically, first, the unprocessed video data may be sampled and marked as unprocessed single-sampled images. Then, each unprocessed single-sampled image may be arranged according to the order in which the unprocessed single-sampled images appear, thereby obtaining an unprocessed single-sampled image frame set matched by the unprocessed video, and marking each unprocessed single-sampled image in the unprocessed single-sampled image frame set to obtain the serial number of each unprocessed single-sampled image in the unprocessed single-sampled image frame set. For example, the serial number of the first unprocessed single-sampled image in the unprocessed single-sampled image frame set may be marked as the Arabic numeral 1, and the serial number of the second unprocessed single-sampled image in the unprocessed single-sampled image frame set may be marked as the Arabic numeral 2.

[0032] S3, obtaining each possible picture interference area in each unprocessed single sampled picture through the sampling values ​​of the surrounding sampling points of each sampling point in each unprocessed single sampled picture.

[0033] Specifically, since the sampling element point is the basic component unit in the single sampling image, the sampling element points of the 8 sampling areas around each sampling element point in each unprocessed single sampling image can be collected, and each surrounding sampling element point of each sampling element point in each unprocessed single sampling image can be marked; the sampling difference between each sampling element point and each surrounding sampling element point of the matching sampling element point is calculated, and marked as each sampling difference value of each sampling element point, wherein a single sampling element point matches 8 sampling difference values; the number of sampling difference values ​​in each sampling difference value of each sampling element point that exceeds the standard sampling difference critical point is sorted out, and each sampling difference value of each sampling element point is marked as The number of sampling difference values ​​exceeding the standard sampling difference critical point divided by the number of sampling areas around each sampling element point is marked as the sampling difference level of each sampling element point; for each sampling element point in each unprocessed single sampling picture, if the sampling difference level of any sampling element point is not less than the standard sampling difference critical point, and the number of surrounding sampling element points whose sampling difference level of each surrounding sampling element point of any sampling element point is not less than the standard sampling difference critical point exceeds 1, then this sampling element point is confirmed as a possible picture interference area, wherein the picture interference area can be an interference area or a mottled area in the sampled picture, and the interference area can include noise and bad pixels.

[0034] In one embodiment of the present invention, for each sampling element point in each unprocessed single-sampled picture, if the sampling difference level of this sampling element point exceeds the standard sampling difference critical point, and the number of surrounding sampling element points that exceed the standard sampling difference critical point in the sampling difference level of each surrounding sampling element point of this sampling element point exceeds 1, then this sampling element point can be determined to be a possible picture interference area; if the sampling difference level of this sampling element point exceeds the standard sampling difference critical point, and the sampling difference level of each surrounding sampling element point of this sampling element point does not exceed the standard sampling difference critical point in the sampling difference level of each surrounding sampling element point, then this sampling element point can be determined to be an interference area; if the sampling difference level of this sampling element point does not exceed the standard sampling difference critical point, then this sampling element point can be determined to be a common interference area. In this way, each possible picture interference area in each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set can be obtained.

[0035] S4, collecting each surrounding possible picture interference area matched by each possible picture interference area, and calculating the sampling characteristic scalar of each possible picture interference area through the sampling value of each possible picture interference area, the sampling value of each surrounding possible picture interference area matched by each possible picture interference area, and the interval between each possible picture interference area and each matching surrounding possible picture interference area.

[0036] Specifically, each possible picture interference area of ​​the five sampling areas around each possible picture interference area in each unprocessed single sampled picture can be collected and marked as the surrounding possible picture interference areas of each possible picture interference area; the number of surrounding possible picture interference areas of each possible picture interference area is sorted out; the Pythagorean metric value of each surrounding possible picture interference area of ​​each possible picture interference area and the matching possible picture interference area is obtained; the sampling characteristic scalar of each possible picture interference area in each unprocessed single sampled picture is obtained through the Pythagorean metric value of each surrounding possible picture interference area of ​​each possible picture interference area and the matching possible picture interference area, the sampling value of each possible picture interference area and the sampling value of each surrounding possible picture interference area matched by each possible picture interference area; the sampling characteristic scalar of each possible picture interference area is calculated.

[0037] In one embodiment of the present invention, if the sampling difference between each possible picture interference area and each possible picture interference area around each possible picture interference area is higher, it can be explained that the probability that the matching possible picture interference area is interference is higher. It can be understood that the sampling value difference between the sampling element points at the same level is not obvious. If the interval between the possible picture interference area and each possible picture interference area around the matching possible picture interference area is tighter, and the sampling value difference between the possible picture interference area and each possible picture interference area around the matching possible picture interference area is obvious, it can be explained that the probability that this possible picture interference area is interference is higher. Therefore, each possible image interference area of ​​the five sampling areas of each possible image interference area in each unprocessed single sampled image can be collected and marked as the surrounding possible image interference areas of each possible image interference area, and then the number of surrounding possible image interference areas of each possible image interference area can be sorted out, and the Pythagorean metric value of each possible image interference area and each surrounding possible image interference area of ​​each possible image interference area matched can be calculated, and the Pythagorean metric value of each possible image interference area and each surrounding possible image interference area of ​​each possible image interference area matched can be obtained through each possible image interference area and each surrounding possible image interference area of ​​each possible image interference area matched, the sampling value of each possible image interference area, and the sampling value of each surrounding possible image interference area matched by each possible image interference area, so as to obtain the sampling characteristic scalar of each possible image interference area in each unprocessed single sampled image. Among them, the expression of the sampling characteristic scalar is:

[0038]

[0039] Among them, H i j The sampling characteristic scalar of the order i in the unprocessed single-sampled picture frame set and the order j in the unprocessed single-sampled picture frame set, Y i j represents the number of possible image interference areas around the order j possible image interference area in the order i of the unprocessed single sampled image frame set, f i j,k Represents the Pythagorean metric of the order k surrounding possible image interference regions matching the order j possible image interference regions in the unprocessed single sampled image frame set, N i j Represents the sampling values ​​of the possible image interference areas in the order i of the unprocessed single-sampled image frame set, N i j,k Represents the sampling value of the kth surrounding possible image interference area matched by the jth possible image interference area in the i-th order in the unprocessed single-sampled image frame set, and n is a positive integer.

[0040] Among them, H i j It can be expressed as the possibility that the sequential i unprocessed single-sampled picture frames in the sequence j possible picture interference areas in the unprocessed single-sampled pictures are interference.

[0041] S5, collecting the hierarchical characteristic targets and hierarchical characteristic values ​​of each possible picture interference area, and calculating the target characteristic scalar of each possible picture interference area through the hierarchical characteristic value of each possible picture interference area, the hierarchical characteristic target of each possible picture interference area, and the hierarchical characteristic target of each surrounding possible picture interference area matched by each possible picture interference area.

[0042] In one embodiment of the present invention, if the sampling level target difference between each possible picture interference area and the matching possible picture interference area surrounding the possible picture interference area is high and the No. 1 standard critical point sampling level of each possible picture interference area is high, it can be explained that the probability that the matching possible picture interference area is interference is high, wherein it can be understood that the finer the sampling level target difference between the sampling element points at the same level, the finer the sampling level of the sampling element point compared to the interference area.

[0043] In one embodiment of the present invention, the hierarchical characteristic target and hierarchical characteristic value of each possible image interference area are collected, which may specifically include: for one possible image interference area of ​​one of the unprocessed single-sampled images in the unprocessed single-sampled image frame set, the line segment passing through the possible image interference area is moved several times to obtain several characteristic line segments; for one of the characteristic line segments, the sampling differences between the possible image interference area and each surrounding possible image interference area of ​​the possible image interference area of ​​the characteristic line segment are accumulated, and the accumulated value of the sampling differences is marked as the sampling hierarchical value of the possible image interference area; the pole number in each sampling hierarchical value matched by the possible image interference area is marked as the hierarchical characteristic target matched by the possible image interference area; the characteristic line segment matched by the pole number in each sampling hierarchical value matched by the possible image interference area and the degree of deviation in the 0° direction are marked as the hierarchical characteristic target matched by the possible image interference area.

[0044] In one embodiment of the present invention, by obtaining the hierarchical characteristic targets and hierarchical characteristic values ​​matched by the possible picture interference area, the hierarchical characteristic values ​​and hierarchical characteristic targets matched by each possible picture interference area can be obtained, and the hierarchical characteristic values ​​and hierarchical characteristic targets matched by each surrounding possible picture interference area of ​​the possible picture interference area can be obtained.

[0045] In one embodiment of the present invention, because the hierarchical characteristic value and the hierarchical characteristic target can represent the probability that the possible picture interference region is interference, the target characteristic scalar of the possible picture interference region can be obtained through the hierarchical characteristic value matched by the possible picture interference region, the hierarchical characteristic target matched by the possible picture interference region, and the hierarchical characteristic target matched by each surrounding possible picture interference region of the possible picture interference region. The expression of the target characteristic scalar can be:

[0046]

[0047] Among them, X i j The target characteristic scalar representing the order i of the unprocessed single-sampled picture frame set and the order j of the possible picture interference regions in the processed single-sampled picture, ψ i j represents the hierarchical characteristic target of the order i in the unprocessed single-sampled picture frame set and the order j in the unprocessed single-sampled picture, ψ i j,k represents the order in the unprocessed single-sampled image frame set, the order in the i-th unprocessed single-sampled image, the order in which the j-th possible image interference area matches, the hierarchical characteristic target of the k-th surrounding possible image interference area, F i j Represents the hierarchical characteristic values ​​of the sequential j possible image interference areas in the sequential i unprocessed single-sampled images in the unprocessed single-sampled image frame set.

[0048] Among them, X i j It can represent the possibility that the sequential i possible picture interference areas in the unprocessed single-sampled picture frame set and the sequential j possible picture interference areas in the unprocessed single-sampled pictures are interference.

[0049] S6, obtaining a characteristic scalar of each possible image interference area by sampling the characteristic scalar and the target characteristic scalar.

[0050] In one embodiment of the present invention, because both the sampling characteristic scalar and the target characteristic scalar can indicate the possibility that the possible picture interference area is interference, the sampling characteristic scalar and the matching target characteristic scalar of each possible picture interference area in each unprocessed single sampled picture in the unprocessed single sampled picture frame set can be multiplied, and the result of the operation can be marked as the characteristic scalar.

[0051] S7, collect the related picture frame set of each unprocessed single picture match and the surrounding unprocessed single sampled pictures of each unprocessed picture match, and obtain the motion direction of each related area of ​​each possible picture interference area and each possible picture interference area through each unprocessed picture in the related picture frame set of each unprocessed picture match and the surrounding unprocessed pictures of each unprocessed picture match.

[0052] In one embodiment of the present invention, collecting the related picture frame set matched by each unprocessed single picture and the surrounding unprocessed single sampling pictures matched by each unprocessed picture may specifically include: marking each unprocessed single sampling picture in the unprocessed single sampling picture frame set to obtain the order of each unprocessed single sampling picture in the unprocessed single sampling picture frame set, wherein the order number of the m unprocessed single sampling pictures in the unprocessed single sampling picture frame set is m; recording the number of unprocessed single sampling pictures in the unprocessed single sampling picture frame set, which is recorded as A, the order of the unprocessed single sampling pictures is marked as q, and the unprocessed single sampling pictures are marked as D q ; If q exceeds the first standard critical point P, the first related picture frame set matched by this unprocessed single sample picture is marked as [D q-P , D q-P+1 , ..., D q-1 ]; if q does not exceed the first standard critical point, the first related picture frame set matched by this unprocessed single sample picture is marked as [D1, ..., D q-1 ]; if q is 1, then the first related picture frame set of this unprocessed single sample picture matching is empty; if M minus m exceeds the first standard critical point, then the second related picture frame set of this unprocessed single sample picture matching is marked as [D q+1 , ..., D q+P-1 , D q+P ]; If A minus q does not exceed the first standard critical point, the second related picture frame set matched by this unprocessed single sample picture is marked as [D q+1 , ..., D A ]; if A minus q is 0, then the second related picture frame set matched by this unprocessed single sample picture is empty, where D q-P represents the unprocessed single-sampled picture with the order qP in the unprocessed single-sampled picture frame set, D q-P+1 represents the unprocessed single-sampled picture in the order of q-P+1 in the unprocessed single-sampled picture frame set, D q-1 represents the q-1 unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, D q+1 represents the unprocessed single-sampled image with the order q+1 in the unprocessed single-sampled image frame set, D q+P-1represents the unprocessed single-sampled image with the order q+P-1 in the unprocessed single-sampled image frame set, D q+P represents the unprocessed single-sampled picture with the order of q+P in the unprocessed single-sampled picture frame set, D A represents the unprocessed single-sampled picture with the order A in the unprocessed single-sampled picture frame set, and D1 represents the unprocessed single-sampled picture with the order 1 in the unprocessed single-sampled picture frame set; connect the second related picture frame set matching the unprocessed single-sampled picture with the first related picture frame set matching the unprocessed single-sampled picture, and mark the connected picture frame set as the related picture frame set matching the unprocessed single-sampled picture; if the order D of the unprocessed single-sampled picture is q If it is before sequence A, the unprocessed single-sampled picture with sequence q+1 in the unprocessed single-sampled picture frame set is marked as this unprocessed single-sampled picture D. q The surrounding unprocessed single-sampled images; if this unprocessed single-sampled image D q If the order is consistent with the order A, the unprocessed single-sampled picture with the order q-1 in the unprocessed single-sampled picture frame set is marked as this unprocessed single-sampled picture D q Surrounding unprocessed single sample images.

[0053] Thus, a related picture frame set and another related picture frame set matched by each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set can be obtained, as well as the surrounding unprocessed single-sampled pictures of each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set. Then, another related picture frame set matched by the unprocessed single-sampled picture can be connected with a related picture frame set matched by the unprocessed single-sampled picture, and each unprocessed single-sampled picture in the related picture frame set matched by the unprocessed single-sampled picture and the related picture frame set matched by the unprocessed single-sampled picture can be marked.

[0054] In one embodiment of the present invention, each relevant area of ​​each possible picture interference area and the motion direction of each possible picture interference area are obtained through each unprocessed picture in the relevant picture frame set matched by each unprocessed picture and the surrounding unprocessed pictures matched by each unprocessed picture, which may specifically include: for a random possible picture interference area of ​​a random unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, the placeholder of this possible picture interference area on this unprocessed single-sampled picture is recorded as (r, s); the sampling element points of the placeholder (r, s) of each unprocessed single-sampled picture in the relevant picture frame set matched by this unprocessed single-sampled picture are collected, and marked as the relevant area of ​​this possible picture interference area; the sampling element points of the placeholder (r, s) in the surrounding unprocessed single-sampled pictures matched by this unprocessed single-sampled picture are collected. Each surrounding sampling element point of the 5 sampling areas, and mark each surrounding sampling element point of the 5 sampling areas of the sampling element point occupying (r, s) in the surrounding unprocessed single sampling image matched by the unprocessed single sampling image as the surrounding characteristic sampling element point of this possible image interference area; collect the surrounding characteristic sampling element point matched with the minimum pole number of the sampling difference between this possible image interference area and each surrounding characteristic sampling element point matched by this possible image interference area, and mark them as the target surrounding characteristic sampling element point; mark the projection of the sampling element point occupying (r, s) in the surrounding unprocessed single sampling image matched by the unprocessed single sampling image and the target surrounding characteristic sampling element point as the moving target of this possible image interference area; collect the moving target of this possible image interference area and the deviation degree in the 0° direction, and mark them as the moving direction of this possible image interference area.

[0055] S8, obtaining a correlation scalar of each possible picture interference area through each correlation area of ​​each possible picture interference area and the motion direction of each possible picture interference area.

[0056] In one embodiment of the present invention, step S7 can be used to obtain the motion orientation of the possible picture interference area of ​​each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set and the motion orientation of each surrounding possible picture interference area matched by each possible picture interference area of ​​each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, and the average of the motion orientations of each surrounding possible picture interference area matched by each possible picture interference area can be obtained through calculation.

[0057] Further, the sampling value of each relevant area matched by each possible picture interference area of ​​each unprocessed single-sampled picture and the motion orientation of each possible picture interference area of ​​each unprocessed single-sampled picture may indicate the possibility that the possible picture interference area is interference, and if the deviation between the motion orientation of each possible picture interference area and each matched surrounding possible picture interference area is more obvious, it can be said that the possibility that the matched possible picture interference area is interference is more obvious; if the sampling value difference between each possible picture interference area and each matched relevant area is more obvious, it can also be said that the possibility that the matched possible picture interference area is interference is more obvious. Therefore, the relevant scalar of each possible picture interference area of ​​each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set can be obtained through the sampling value of each relevant area matched by each possible picture interference area of ​​each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, the motion orientation of the surrounding possible picture interference areas matched by each possible picture interference area, and the motion orientation of each possible picture interference area, wherein the expression of the relevant scalar can be:

[0058]

[0059] Among them, G represents the relevant scalar of the possible image interference area, n represents a positive integer, B represents the number of relevant areas matched by the possible image interference area, D0 represents the sampling value of the possible image interference area, D1 c represents the sampling value of the th correlation area that may match the image interference area, β0 represents the motion direction that may match the image interference area, It represents the mean value of the surrounding motion orientation of the possible image interference area, and max represents the maximum value function.

[0060] The higher the value of G is, the higher the possibility that the possible image interference area is interference.

[0061] S9, obtaining each interference area in each unprocessed single sampled image through the characteristic scalar and the related scalar, and processing each interference area in each unprocessed single sampled image.

[0062] In one embodiment of the present invention, each interference area in each unprocessed single sampled image is obtained through characteristic scalars and related scalars, which may specifically include: unifying the dimension of the characteristic scalars and related scalars of each possible image interference area, and marking them as the edge label scalar and the related label scalar of each possible image interference area; gluing the edge label scalar of each possible image interference area and the related label scalar of the matching possible image interference area, and marking them as the unified scalar of each possible image interference area; if the unified scalar of each possible image interference area exceeds the second standard critical point, the matching possible image interference area is confirmed as an interference area.

[0063] Therefore, interference can be cleared through each possible image interference area of ​​each unprocessed single-sampled image in the acquired unprocessed single-sampled image frame set, and the interference area can be adjusted and processed through the sampling values ​​of the normal area around the interference.

[0064] According to the video generation method of the embodiment of the present invention, by acquiring video data, an unprocessed single-sampled picture frame set in the unprocessed video data is acquired according to the video data, and then each possible picture interference area is acquired through each unprocessed single-sampled picture, and the sampling characteristic scalar and target characteristic scalar of each possible picture interference area are calculated, and the characteristic scalar is acquired through the sampling characteristic scalar and the target characteristic scalar, and the correlation scalar of each possible picture interference area is acquired by acquiring the correlation area and motion direction of each possible picture interference area, and each interference area in each unprocessed single-sampled picture is acquired through the characteristic scalar and the correlation scalar, and each interference area is processed, thereby accurately removing the interference area in the unprocessed single-sampled picture, improving the positioning accuracy of the interference area, and maintaining the sampling value of the normal area in the process of removing the interference area, so that the video data is clearer.

[0065] In order to implement the video generation method of the above embodiment, the embodiment of the present invention further provides a video generation system.

[0066] like Figure 2As shown, the video generation system of the embodiment of the present invention includes: a first acquisition module 100, a second acquisition module 200, a collection module 300, a first calculation module 400, a second calculation module 500, a third acquisition module 600, a fourth acquisition module 700, a fifth acquisition module 800 and a processing module 900, wherein the first acquisition module 100 is used to acquire video data, and the video data includes unprocessed video data; the second acquisition module 200 is used to acquire an unprocessed single-sampled picture frame set in the unprocessed video data according to the video data, and the unprocessed single-sampled picture frame set includes a plurality of unprocessed single-sampled pictures; the collection module 300 is used to acquire video data, and the video data includes unprocessed video data; ... Module 300 is used to obtain each possible image interference area in each unprocessed single sampled image through the sampling values ​​of the surrounding sampling points of each sampling point in each unprocessed single sampled image; the first calculation module 400 is used to collect each surrounding possible image interference area matched by each possible image interference area, and calculate the sampling characteristic scalar of each possible image interference area through the sampling value of each possible image interference area, the sampling value of each surrounding possible image interference area matched by each possible image interference area, and the interval between each possible image interference area and each matching surrounding possible image interference area; the second calculation module 500 is used to collect The hierarchical characteristic target and hierarchical characteristic value of each possible picture interference area, and the target characteristic scalar of each possible picture interference area is calculated through the hierarchical characteristic value of each possible picture interference area, the hierarchical characteristic target of each possible picture interference area and the hierarchical characteristic target of each surrounding possible picture interference area matched by each possible picture interference interference area; the third acquisition module 600 is used to obtain the characteristic scalar of each possible picture interference area through the sampling characteristic scalar and the target characteristic scalar; the fourth acquisition module 700 is used to collect the relevant picture frame set of each unprocessed single picture match and the surrounding unprocessed single sampled pictures of each unprocessed picture match, and obtain each relevant area of ​​each possible picture interference area and the motion orientation of each possible picture interference area through each unprocessed picture in the relevant picture frame set of each unprocessed picture match and the surrounding unprocessed pictures of each unprocessed picture match; the fifth acquisition module 800 is used to obtain the relevant scalar of each possible picture interference area through each relevant area of ​​each possible picture interference area and the motion orientation of each possible picture interference area; the processing module 900 is used to obtain each interference area in each unprocessed single sampled picture through the characteristic scalar and the relevant scalar, and process each interference area in each unprocessed single sampled picture.

[0067] In one embodiment of the present invention, the first video data acquisition module 100 may acquire video data from a user input terminal, wherein the video data includes unprocessed source video data or segments.

[0068] In one embodiment of the present invention, the unprocessed video data may contain uninterrupted unprocessed single-sampled images, and the intervals between consecutive unprocessed single-sampled images are fixed. The second acquisition module 200 can also be specifically used to: sample the unprocessed video data and mark them as unprocessed single-sampled images; arrange each unprocessed single-sampled image in the order of their appearance, thereby obtaining an unprocessed single-sampled image frame set matched by the unprocessed video, and mark each unprocessed single-sampled image in the unprocessed single-sampled image frame set to obtain the serial number of each unprocessed single-sampled image in the unprocessed single-sampled image frame set. For example, the serial number of the first unprocessed single-sampled image in the unprocessed single-sampled image frame set can be marked as Arabic numeral 1, and the serial number of the second unprocessed single-sampled image in the unprocessed single-sampled image frame set can be marked as Arabic numeral 2.

[0069] In one embodiment of the present invention, the acquisition module 300 may be further specifically used to: acquire sampling element points of eight sampling areas around each sampling element point in each unprocessed single sampling picture, and mark them as each surrounding sampling element point of each sampling element point in each unprocessed single sampling picture; calculate the sampling difference between each sampling element point and each surrounding sampling element point of the matching sampling element point, and mark them as each sampling difference value of each sampling element point, wherein a single sampling element point matches eight sampling difference values; sort out the number of sampling difference values ​​exceeding the standard sampling difference critical point in each sampling difference value of each sampling element point, and divide the number of sampling difference values ​​exceeding the standard sampling difference critical point in each sampling difference value of each sampling element point by the number of sampling areas around each sampling element point to mark the sampling difference level of each sampling element point; for each sampling element point in each unprocessed single sampling picture, if the sampling difference level of any sampling element point is not less than the standard sampling difference critical point, and the number of surrounding sampling element points whose sampling difference level of each surrounding sampling element point is not less than the standard sampling difference critical point exceeds one, then the sampling element point is confirmed as a possible image interference area.

[0070] In one embodiment of the present invention, for each sampling element point in each unprocessed single-sampled picture, if the sampling difference level of this sampling element point exceeds the standard sampling difference critical point, and the number of surrounding sampling element points that exceed the standard sampling difference critical point in the sampling difference level of each surrounding sampling element point of this sampling element point exceeds 1, then this sampling element point can be determined to be a possible picture interference area; if the sampling difference level of this sampling element point exceeds the standard sampling difference critical point, and the sampling difference level of each surrounding sampling element point of this sampling element point does not exceed the standard sampling difference critical point in the sampling difference level of each surrounding sampling element point, then this sampling element point can be determined to be an interference area; if the sampling difference level of this sampling element point does not exceed the standard sampling difference critical point, then this sampling element point can be determined to be a common interference area. In this way, each possible picture interference area in each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set can be obtained.

[0071] In one embodiment of the present invention, the first calculation module 400 can also be specifically used to: collect each possible picture interference area of ​​the five sampling areas around each possible picture interference area in each unprocessed single sampled picture, and mark them as the surrounding possible picture interference areas of each possible picture interference area; sort out the number of surrounding possible picture interference areas of each possible picture interference area; obtain the Pythagorean measure value of each surrounding possible picture interference area of ​​each possible picture interference area and the matching possible picture interference area; obtain the sampling characteristic scalar of each possible picture interference area in each unprocessed single sampled picture through the Pythagorean measure value of each surrounding possible picture interference area of ​​each possible picture interference area and the matching possible picture interference area, the sampling value of each possible picture interference area and the sampling value of each surrounding possible picture interference area matched by each possible picture interference area; calculate the sampling characteristic scalar of each possible picture interference area.

[0072] In one embodiment of the present invention, if the sampling difference between each possible picture interference area and each possible picture interference area around each possible picture interference area is higher, it can be explained that the probability that the matching possible picture interference area is interference is higher. It can be understood that the sampling value difference between the sampling element points at the same level is not obvious. If the interval between the possible picture interference area and each possible picture interference area around the matching possible picture interference area is tighter, and the sampling value difference between the possible picture interference area and each possible picture interference area around the matching possible picture interference area is obvious, it can be explained that the probability that this possible picture interference area is interference is higher. Therefore, each possible image interference area of ​​the five sampling areas of each possible image interference area in each unprocessed single sampled image can be collected and marked as the surrounding possible image interference areas of each possible image interference area, and then the number of surrounding possible image interference areas of each possible image interference area can be sorted out, and the Pythagorean metric value of each possible image interference area and each surrounding possible image interference area of ​​each possible image interference area matched can be calculated, and the Pythagorean metric value of each possible image interference area and each surrounding possible image interference area of ​​each possible image interference area matched can be obtained through each possible image interference area and each surrounding possible image interference area of ​​each possible image interference area matched, the sampling value of each possible image interference area, and the sampling value of each surrounding possible image interference area matched by each possible image interference area, so as to obtain the sampling characteristic scalar of each possible image interference area in each unprocessed single sampled image. Among them, the expression of the sampling characteristic scalar is:

[0073]

[0074] Among them, H i j The sampling characteristic scalar of the order i in the unprocessed single-sampled picture frame set and the order j in the unprocessed single-sampled picture frame set, Y i j represents the number of possible image interference areas around the order j possible image interference area in the order i of the unprocessed single sampled image frame set, f i j,k Represents the Pythagorean metric of the order k surrounding possible image interference regions matching the order j possible image interference regions in the unprocessed single sampled image frame set, N i j Represents the sampling values ​​of the possible image interference areas in the order i of the unprocessed single-sampled image frame set, N i j,k Represents the sampling value of the kth surrounding possible image interference area matched by the jth possible image interference area in the i-th order in the unprocessed single-sampled image frame set, and n is a positive integer.

[0075] Among them, H i j It can be expressed as the possibility that the sequential i unprocessed single-sampled picture frames in the sequence j possible picture interference areas in the unprocessed single-sampled pictures are interference.

[0076] In one embodiment of the present invention, if the sampling level target difference between each possible picture interference area and the matching possible picture interference area surrounding the possible picture interference area is high and the No. 1 standard critical point sampling level of each possible picture interference area is high, it can be explained that the probability that the matching possible picture interference area is interference is high, wherein it can be understood that the finer the sampling level target difference between the sampling element points at the same level, the finer the sampling level of the sampling element point compared to the interference area.

[0077] In one embodiment of the present invention, the second calculation module 500 can also be specifically used for: for one possible picture interference area of ​​one of the unprocessed single-sampled pictures in the unprocessed single-sampled picture frame set, the line segment passing through the possible picture interference area is moved several times to obtain several characteristic line segments; for one of the characteristic line segments, the sampling differences between the possible picture interference area and each surrounding possible picture interference area of ​​the possible picture interference area of ​​the characteristic line segment are accumulated, and the accumulated value of the sampling differences is marked as the sampling level value of this possible picture interference area; the pole number in each sampling level value matched by this possible picture interference area is marked as the level characteristic target matched by this possible picture interference area; the characteristic line segment matched by the pole number in each sampling level value matched by this possible picture interference area and the degree of deviation in the 0° direction are marked as the level characteristic target matched by this possible picture interference area.

[0078] In one embodiment of the present invention, by obtaining the hierarchical characteristic targets and hierarchical characteristic values ​​matched by the possible picture interference area, the hierarchical characteristic values ​​and hierarchical characteristic targets matched by each possible picture interference area can be obtained, and the hierarchical characteristic values ​​and hierarchical characteristic targets matched by each surrounding possible picture interference area of ​​the possible picture interference area can be obtained.

[0079] In one embodiment of the present invention, because the hierarchical characteristic value and the hierarchical characteristic target can represent the probability that the possible picture interference region is interference, the second calculation module 500 can obtain the target characteristic scalar of the possible picture interference region through the hierarchical characteristic value matched by the possible picture interference region, the hierarchical characteristic target matched by the possible picture interference region, and the hierarchical characteristic target matched by each surrounding possible picture interference region of the possible picture interference region. The expression of the target characteristic scalar can be:

[0080]

[0081] Among them, Xi j The target characteristic scalar representing the order i of the unprocessed single-sampled picture frame set and the order j of the possible picture interference regions in the processed single-sampled picture, ψ i j represents the hierarchical characteristic target of the order i in the unprocessed single-sampled picture frame set and the order j in the unprocessed single-sampled picture, ψ i j,k represents the order in the unprocessed single-sampled image frame set, the order in the i-th unprocessed single-sampled image, the order in which the j-th possible image interference area matches, the hierarchical characteristic target of the k-th surrounding possible image interference area, F i j Represents the hierarchical characteristic values ​​of the sequential j possible image interference areas in the sequential i unprocessed single-sampled images in the unprocessed single-sampled image frame set.

[0082] Among them, X i j It can represent the possibility that the sequential i possible picture interference areas in the unprocessed single-sampled picture frame set and the sequential j possible picture interference areas in the unprocessed single-sampled pictures are interference.

[0083] In one embodiment of the present invention, because both the sampling characteristic scalar and the target characteristic scalar can indicate the possibility that the possible picture interference area is interference, the sampling characteristic scalar and the matching target characteristic scalar of each possible picture interference area in each unprocessed single sampled picture in the unprocessed single sampled picture frame set can be multiplied by the third acquisition module 600, and the result of the operation is marked as a characteristic scalar.

[0084] In one embodiment of the present invention, the fourth acquisition module 700 can also be specifically used to: for each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, mark each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set to obtain the order of each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, wherein the sequence number of the m unprocessed single-sampled pictures in the unprocessed single-sampled picture frame set is m; record the number of unprocessed single-sampled pictures in the unprocessed single-sampled picture frame set, recorded as A, the order of the unprocessed single-sampled pictures is marked as q, and the unprocessed single-sampled pictures are marked as D q ; If q exceeds the first standard critical point P, the first related picture frame set matched by this unprocessed single sample picture is marked as [D q-P , D q-P+1 , ..., D q-1 ]; if q does not exceed the first standard critical point, the first related picture frame set matched by this unprocessed single sample picture is marked as [D1, ..., D q-1]; if q is 1, then the first related picture frame set of this unprocessed single sample picture matching is empty; if M minus m exceeds the first standard critical point, then the second related picture frame set of this unprocessed single sample picture matching is marked as [D q+1 , ..., D q+P-1 , D q+P ]; If A minus q does not exceed the first standard critical point, the second related picture frame set matched by this unprocessed single sample picture is marked as [D q+1 , ..., D A ]; if A minus q is 0, then the second related picture frame set matched by this unprocessed single sample picture is empty, where D q-P represents the unprocessed single-sampled picture with the order qP in the unprocessed single-sampled picture frame set, D q-P+1 represents the unprocessed single-sampled picture in the order of q-P+1 in the unprocessed single-sampled picture frame set, D q-1 represents the q-1 unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, D q+1 represents the unprocessed single-sampled image with the order q+1 in the unprocessed single-sampled image frame set, D q+P-1 represents the unprocessed single-sampled image with the order q+P-1 in the unprocessed single-sampled image frame set, D q+P represents the unprocessed single-sampled picture with the order of q+P in the unprocessed single-sampled picture frame set, D A represents the unprocessed single-sampled picture with the order A in the unprocessed single-sampled picture frame set, and D1 represents the unprocessed single-sampled picture with the order 1 in the unprocessed single-sampled picture frame set; connect the second related picture frame set matching the unprocessed single-sampled picture with the first related picture frame set matching the unprocessed single-sampled picture, and mark the connected picture frame set as the related picture frame set matching the unprocessed single-sampled picture; if the order D of the unprocessed single-sampled picture is q If it is before sequence A, the unprocessed single-sampled picture with sequence q+1 in the unprocessed single-sampled picture frame set is marked as this unprocessed single-sampled picture D. q The surrounding unprocessed single-sampled images; if this unprocessed single-sampled image D q If the order is consistent with the order A, the unprocessed single-sampled picture with the order q-1 in the unprocessed single-sampled picture frame set is marked as this unprocessed single-sampled picture D q Surrounding unprocessed single sample images.

[0085] Thus, a related picture frame set and another related picture frame set matched by each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, as well as the surrounding unprocessed single-sampled pictures of each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set can be obtained through the fourth acquisition module 700. Then, another related picture frame set matched by the unprocessed single-sampled picture can be connected with a related picture frame set matched by the unprocessed single-sampled picture, and each unprocessed single-sampled picture in the related picture frame set matched by the unprocessed single-sampled picture and the related picture frame set matched by the unprocessed single-sampled picture can be marked.

[0086] In one embodiment of the present invention, the fourth acquisition module 700 obtains each relevant area of ​​each possible picture interference area and the motion direction of each possible picture interference area through each unprocessed picture in the relevant picture frame set matched by each unprocessed picture and the surrounding unprocessed pictures matched by each unprocessed picture, which may specifically include: for a random possible picture interference area of ​​a random unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, the placeholder of this possible picture interference area on this unprocessed single-sampled picture is recorded as (r, s); collecting the sampling element points of the placeholder (r, s) of each unprocessed single-sampled picture in the relevant picture frame set matched by this unprocessed single-sampled picture, and marking them as the relevant area of ​​this possible picture interference area; collecting the placeholder (r, s) of the surrounding unprocessed single-sampled pictures matched by this unprocessed single-sampled picture Each surrounding sampling point of the 5 sampling areas of the sampling point, and each surrounding sampling point of the 5 sampling areas of the sampling point occupying the place (r, s) in the surrounding unprocessed single sampling picture matched by the unprocessed single sampling picture is marked as the surrounding characteristic sampling point of this possible picture interference area; the surrounding characteristic sampling point of the minimum pole number matching of the sampling difference between this possible picture interference area and each surrounding characteristic sampling point matched by this possible picture interference area is collected, and marked as the target surrounding characteristic sampling point; the projection of the sampling point occupying the place (r, s) in the surrounding unprocessed single sampling picture matched by the unprocessed single sampling picture and the target surrounding characteristic sampling point is marked as the moving target of this possible picture interference area; the moving target of this possible picture interference area and the deviation degree in the 0° direction are collected, and marked as the moving direction of this possible picture interference area.

[0087] In one embodiment of the present invention, the fourth acquisition module 700 can be used to obtain the motion orientation of the possible picture interference area of ​​each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set and the motion orientation of each surrounding possible picture interference area matched by each possible picture interference area of ​​each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, and the average of the motion orientations of each surrounding possible picture interference area matched by each possible picture interference area can be obtained through calculation.

[0088] Further, the sampling value of each relevant area matched by each possible picture interference area of ​​each unprocessed single-sampled picture and the motion orientation of each possible picture interference area of ​​each unprocessed single-sampled picture may indicate the possibility that the possible picture interference area is interference, and if the deviation between the motion orientation of each possible picture interference area and each matched surrounding possible picture interference area is more obvious, it can be said that the possibility that the matched possible picture interference area is interference is more obvious; if the sampling value difference between each possible picture interference area and each matched relevant area is more obvious, it can also be said that the possibility that the matched possible picture interference area is interference is more obvious. Therefore, the fifth acquisition module 800 can obtain the relevant scalar of each possible picture interference area of ​​each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set through the sampling value of each relevant area matched by each possible picture interference area of ​​each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, the motion orientation of the surrounding possible picture interference areas matched by each possible picture interference area, and the motion orientation of each possible picture interference area, wherein the expression of the relevant scalar can be:

[0089]

[0090] Among them, G represents the relevant scalar of the possible image interference area, n represents a positive integer, B represents the number of relevant areas matched by the possible image interference area, D0 represents the sampling value of the possible image interference area, D1 c represents the sampling value of the th correlation area of ​​the possible image interference area matching, β0 represents the motion direction of the possible image interference area matching, β represents the average of the surrounding motion directions of the possible image interference area matching, and max represents the maximum value function.

[0091] The higher the value of G is, the higher the possibility that the possible image interference area is interference.

[0092] In one embodiment of the present invention, the processing module 900 can also be specifically used to: unify the dimensions of the characteristic scalar and related scalar of each possible image interference area, and mark them as the edge label scalar and related label scalar of each possible image interference area; glue the edge label scalar of each possible image interference area and the related label scalar of the matching possible image interference area, and mark them as the unified scalar of each possible image interference area; if the unified scalar of each possible image interference area exceeds the second standard critical point, the matching possible image interference area is confirmed as an interference area.

[0093] Thus, interference can be cleared from each possible picture interference area of ​​each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set obtained by the processing module 900, and the interference area can be adjusted and processed by the sampling values ​​of the normal area around the interference.

[0094] To summarize, the embodiment of the present invention acquires video data through a first acquisition module, and a second acquisition module acquires an unprocessed single-sampled picture frame set in the unprocessed video data according to the video data, and then acquires each possible picture interference area through a collection module, and calculates the sampling characteristic scalar and target characteristic scalar of each possible picture interference area through a first calculation module and a second calculation module, and acquires the characteristic scalar through a third acquisition module, and acquires the relevant scalar of each possible picture interference area through a fourth acquisition module, and acquires each interference area in each unprocessed single-sampled picture through a fifth acquisition module, and finally processes each interference area through a processing module, thereby being able to accurately remove the interference area in the unprocessed single-sampled picture, improve the positioning accuracy of the interference area, and maintain the sampling value of the normal area in the process of removing the interference area, thereby making the video data clearer.

[0095] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of these features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0096] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0097] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0098] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with this embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0099] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0100] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0101] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0102] A person of ordinary skill in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0103] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0104] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A video generation method, characterized in that: The following steps are involved: Acquiring video data, wherein the video data includes unprocessed video data; Acquire an unprocessed single-sampled picture frame set in the unprocessed video data according to the video data, wherein the unprocessed single-sampled picture frame set includes a plurality of unprocessed single-sampled pictures; Obtain each possible picture interference area in each unprocessed single sampled picture through the sampling values ​​of the surrounding sampling element points of each sampling element point in each of the unprocessed single sampled pictures; Collect each surrounding possible picture interference area matched by each possible picture interference area, and calculate the sampling characteristic scalar of each possible picture interference area through the sampling value of each possible picture interference area, the sampling value of each surrounding possible picture interference area matched by each possible picture interference area, and the interval between each possible picture interference area and each matching surrounding possible picture interference area; Collecting the hierarchical characteristic target and hierarchical characteristic value of each possible picture interference area, and calculating the target characteristic scalar of each possible picture interference area through the hierarchical characteristic value of each possible picture interference area, the hierarchical characteristic target of each possible picture interference area, and the hierarchical characteristic target of each surrounding possible picture interference area matched by each possible picture interference area; Acquire a characteristic scalar of each of the possible picture interference areas through the sampled characteristic scalar and the target characteristic scalar; Collecting the related picture frame set of each unprocessed single picture match and the surrounding unprocessed single sampled pictures of each unprocessed picture match, and obtaining the motion orientation of each related area of ​​each possible picture interference area and each possible picture interference area through each unprocessed picture in the related picture frame set of each unprocessed picture match and the surrounding unprocessed pictures of each unprocessed picture match; Obtaining a correlation scalar of each possible picture interference area through each correlation area of ​​each possible picture interference area and the motion direction of each possible picture interference area; Each interference region in each unprocessed single-sampled image is obtained by using the characteristic scalar and the related scalar, and each interference region in each unprocessed single-sampled image is processed.

2. The video generation method according to claim 1, characterized in that: The step of obtaining each possible picture interference area in each unprocessed single sampled picture by using the sampling values ​​of the surrounding sampling points of each sampling point in each unprocessed single sampled picture specifically includes: Collect sampling points of 8 sampling areas around each sampling point in each unprocessed single sampling picture, and mark them as each surrounding sampling point of each sampling point in each unprocessed single sampling picture; Calculate the sampling difference between each sampling element point and each surrounding sampling element point of the matching sampling element point, and mark it as each sampling difference value of each sampling element point, wherein a single sampling element point matches 8 sampling difference values; The number of sampling difference values ​​exceeding the standard sampling difference critical point in each sampling difference value of each sampling element point is sorted out, and the number of sampling difference values ​​exceeding the standard sampling difference critical point in each sampling difference value of each sampling element point is divided by the number of sampling areas around each sampling element point to mark the sampling difference level of each sampling element point; For each sampling element point in each unprocessed single-sampled image, if the sampling distinction level of any sampling element point is not less than the standard sampling distinction critical point, and the number of surrounding sampling element points whose sampling distinction level is not less than the standard sampling distinction critical point exceeds 1, then this sampling element point is confirmed as a possible image interference area.

3. The video generation method according to claim 2, characterized in that: The collecting of each surrounding possible picture interference area matched by each possible picture interference area, and calculating the sampling characteristic scalar of each possible picture interference area through the sampling value of each possible picture interference area, the sampling value of each surrounding possible picture interference area matched by each possible picture interference area, and the interval between each possible picture interference area and each matching surrounding possible picture interference area, specifically includes: Collect each possible image interference area of ​​5 sampling areas around each possible image interference area in each unprocessed single sampled image, and mark them as possible image interference areas around each possible image interference area; Sorting out the number of possible image interference areas around each possible image interference area; Obtaining the Pythagorean metric value of each of the possible image interference areas and each surrounding possible image interference area of ​​the matching possible image interference area; Obtaining a sampling characteristic scalar of each possible picture interference area in each unprocessed single sampled picture through the Pythagorean metric value of each possible picture interference area and each surrounding possible picture interference area matched by each possible picture interference area, the sampling value of each possible picture interference area, and the sampling value of each surrounding possible picture interference area matched by each possible picture interference area; Calculate the sampling characteristic scalar of each possible image interference area, where the expression of the sampling characteristic scalar is: Among them, H i j The sampling characteristic scalar of the order i in the unprocessed single-sampled picture frame set and the order j in the unprocessed single-sampled picture frame set, Y i j represents the number of possible image interference areas around the order j possible image interference area in the order i of the unprocessed single sampled image frame set, f i j,k Represents the Pythagorean metric of the order k surrounding possible image interference regions matching the order j possible image interference regions in the unprocessed single sampled image frame set, N i j Represents the sampling values ​​of the possible image interference areas in the order i of the unprocessed single-sampled image frame set, N i j,k Represents the sampling value of the kth surrounding possible image interference area matched by the jth possible image interference area in the i-th order in the unprocessed single-sampled image frame set, and n is a positive integer.

4. The video generation method according to claim 3, characterized in that: The collecting of the hierarchical characteristic target and hierarchical characteristic value of each possible image interference area specifically includes: For one possible image interference area of ​​one of the unprocessed single-sampled images in the unprocessed single-sampled image frame set, a line segment passing through the possible image interference area is moved several times to obtain several characteristic line segments; For one of the characteristic line segments, accumulating the sampling differences between the possible picture interference area and each surrounding possible picture interference area of ​​the possible picture interference area of ​​the characteristic line segment, and marking the accumulated value of the sampling differences as the sampling level value of the possible picture interference area; Mark the pole number in each sampling level value of the possible image interference region match as the level characteristic target of the possible image interference region match; The characteristic line segments of the pole number matching in each sampling level value of this possible image interference area matching and the degree of deviation in the 0° direction are marked as the level characteristic targets of this possible image interference area matching.

5. The video generation method according to claim 4, characterized in that: The expression of the target characteristic scalar of each possible image interference area is: Among them, X i j The target characteristic scalar representing the order i of the unprocessed single-sampled picture frame set and the order j of the possible picture interference regions in the processed single-sampled picture, ψ i j represents the hierarchical characteristic target of the order i in the unprocessed single-sampled picture frame set and the order j in the unprocessed single-sampled picture, ψ i j,k represents the order in the unprocessed single-sampled image frame set, the order in the i-th unprocessed single-sampled image, the order in which the j-th possible image interference area matches, the hierarchical characteristic target of the k-th surrounding possible image interference area, F i j Represents the hierarchical characteristic values ​​of the sequential j possible image interference areas in the sequential i unprocessed single-sampled images in the unprocessed single-sampled image frame set.

6. The video generation method according to claim 5, characterized in that: The collecting of the relevant picture frame set of each unprocessed single picture matching and the surrounding unprocessed single sampling pictures of each unprocessed picture matching specifically includes: For each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, mark each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set to obtain the sequence of each unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, wherein the sequence number of the m unprocessed single-sampled pictures in the unprocessed single-sampled picture frame set is m; Record the number of unprocessed single-sampled images in the unprocessed single-sampled image frame set, denoted as A, the order of the unprocessed single-sampled images is marked as q, and the unprocessed single-sampled images are marked as D q ; If q exceeds the first standard critical point P, the first related picture frame set matched by this unprocessed single sample picture is marked as [D q-P , D q-P+1 , ..., D q-1 ]; if q does not exceed the first standard critical point, the first related picture frame set matched by this unprocessed single sample picture is marked as [D1, ..., D q-1 ]; if q is 1, then the first related picture frame set of this unprocessed single sample picture matching is empty; if M minus m exceeds the first standard critical point, then the second related picture frame set of this unprocessed single sample picture matching is marked as [D q+1 , ..., D q+P-1 , D q+P ]; If A minus q does not exceed the first standard critical point, the second related picture frame set matched by this unprocessed single sample picture is marked as [D q+1 , ..., D A ]; if A minus q is 0, then the second related picture frame set matched by this unprocessed single sample picture is empty, where D q-P represents the unprocessed single-sampled picture with the order qP in the unprocessed single-sampled picture frame set, D q-P+1 represents the unprocessed single-sampled picture in the order of q-P+1 in the unprocessed single-sampled picture frame set, D q-1 represents the q-1 unprocessed single-sampled picture in the unprocessed single-sampled picture frame set, D q+1 represents the unprocessed single-sampled image with the order q+1 in the unprocessed single-sampled image frame set, D q+P-1 represents the unprocessed single-sampled image with the order q+P-1 in the unprocessed single-sampled image frame set, D q+P represents the unprocessed single-sampled picture with the order of q+P in the unprocessed single-sampled picture frame set, D A represents the unprocessed single-sampled picture with the order of A in the unprocessed single-sampled picture frame set, and D1 represents the unprocessed single-sampled picture with the order of 1 in the unprocessed single-sampled picture frame set; Connecting the second related picture frame set of the unprocessed single sampled picture matching with the first related picture frame set of the unprocessed single sampled picture matching, and marking the connected picture frame set as the related picture frame set of the unprocessed single sampled picture matching; If this does not process the order of single-sampled images D q If it is before sequence A, the unprocessed single-sampled picture with sequence q+1 in the unprocessed single-sampled picture frame set is marked as this unprocessed single-sampled picture D. q The surrounding unprocessed single-sampled images; if this unprocessed single-sampled image D q If the order is consistent with the order A, the unprocessed single-sampled picture with the order q-1 in the unprocessed single-sampled picture frame set is marked as this unprocessed single-sampled picture D q Surrounding unprocessed single sample images.

7. The video generation method according to claim 6, characterized in that: The obtaining of the motion orientation of each related area of ​​each possible picture interference area and each possible picture interference area through each unprocessed picture in the related picture frame set matched by each unprocessed picture and the surrounding unprocessed pictures matched by each unprocessed picture specifically includes: For a random possible image interference region of a random unprocessed single-sampled image in the unprocessed single-sampled image frame set, the placeholder of the possible image interference region on the unprocessed single-sampled image is recorded as (r, s); Collect the sampling element points of each unprocessed single sampled picture in the related picture frame set matched by the unprocessed single sampled picture (r, s), and mark them as the related area of ​​the possible picture interference area; Collect each of the five sampling regions of the sampling point occupying the place (r, s) in the surrounding unprocessed single sampling picture matched by the unprocessed single sampling picture, and mark each of the five sampling regions of the sampling point occupying the place (r, s) in the surrounding unprocessed single sampling picture matched by the unprocessed single sampling picture as the surrounding characteristic sampling point of the possible picture interference area; Collect the surrounding characteristic sampling element point that matches the minimum number of sampling differences between the possible image interference area and each surrounding characteristic sampling element point that matches the possible image interference area, and mark them as target surrounding characteristic sampling element points; Mark the sampling element points occupying the position (r, s) in the surrounding unprocessed single sampling images matched by the unprocessed single sampling images and the projections of the characteristic sampling element points around the target as the moving targets in the possible image interference area; The deviation degree between the moving target in this possible image interference area and the 0° direction is collected and marked as the moving direction of this possible image interference area.

8. The video generation method according to claim 7, characterized in that: The expressions for the relevant scalars are: Among them, G represents the relevant scalar of the possible image interference area, n represents a positive integer, B represents the number of relevant areas matched by the possible image interference area, D0 represents the sampling value of the possible image interference area, D1 c represents the sampling value of the th correlation area that may match the image interference area, β0 represents the motion direction that may match the image interference area, It represents the mean value of the surrounding motion orientation of the possible image interference area, and max represents the maximum value function.

9. The video generation method according to claim 7, characterized in that: The obtaining of each interference region in each unprocessed single-sampled image by using the characteristic scalar and the related scalar specifically includes: Unify the dimension of the characteristic scalar and the related scalar of each possible image interference area, and mark them as the edge scalar and the related scalar of each possible image interference area; The edge label scalar of each possible image interference area and the related label scalar of the matching possible image interference area are glued together and marked as a unified scalar of each possible image interference area; If the unified scalar of each possible image interference region exceeds the second standard critical point, the matching possible image interference region is confirmed as an interference region.

10. A video generation system, characterized in that: include: A first acquisition module, the first acquisition module is used to acquire video data, the video data includes unprocessed video data; A second acquisition module, the second acquisition module is used to acquire an unprocessed single-sampled picture frame set in the unprocessed video data according to the video data, wherein the unprocessed single-sampled picture frame set includes a plurality of unprocessed single-sampled pictures; A collection module, the collection module is used to obtain each possible picture interference area in each unprocessed single sampled picture through the sampling values ​​of the surrounding sampling points of each sampling point in each unprocessed single sampled picture; A first calculation module, the first calculation module is used to collect each surrounding possible picture interference area matched by each possible picture interference area, and calculate the sampling characteristic scalar of each possible picture interference area through the sampling value of each possible picture interference area, the sampling value of each surrounding possible picture interference area matched by each possible picture interference area, and the interval between each possible picture interference area and each matching surrounding possible picture interference area; A second calculation module, the second calculation module is used to collect the hierarchical characteristic target and hierarchical characteristic value of each possible picture interference area, and calculate the target characteristic scalar of each possible picture interference area through the hierarchical characteristic value of each possible picture interference area, the hierarchical characteristic target of each possible picture interference area, and the hierarchical characteristic target of each surrounding possible picture interference area matched by each possible picture interference area; A third acquisition module, the third acquisition module is used to acquire a characteristic scalar of each of the possible picture interference areas through the sampled characteristic scalar and the target characteristic scalar; A fourth acquisition module, the fourth acquisition module is used to collect the relevant picture frame set of each unprocessed single picture match and the surrounding unprocessed single sampled pictures of each unprocessed picture match, and obtain the motion direction of each relevant area of ​​each possible picture interference area and each possible picture interference area through each unprocessed picture in the relevant picture frame set of each unprocessed picture match and the surrounding unprocessed pictures of each unprocessed picture match; A fifth acquisition module, the fifth acquisition module is used to acquire a related scalar of each possible picture interference area through each related area of ​​each possible picture interference area and a motion direction of each possible picture interference area; A processing module is used to obtain each interference area in each unprocessed single sample picture through the characteristic scalar and the related scalar, and process each interference area in each unprocessed single sample picture.

Images