CN116563429A - Animation design processing supervision system and method based on cloud computing - Google Patents
Animation design processing supervision system and method based on cloud computing Download PDFInfo
- Publication number
- CN116563429A CN116563429A CN202310703711.4A CN202310703711A CN116563429A CN 116563429 A CN116563429 A CN 116563429A CN 202310703711 A CN202310703711 A CN 202310703711A CN 116563429 A CN116563429 A CN 116563429A
- Authority
- CN
- China
- Prior art keywords
- image
- abnormal
- picture
- comparison
- images
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012545 processing Methods 0.000 title claims abstract description 14
- 238000013461 design Methods 0.000 title claims abstract description 13
- 230000002159 abnormal effect Effects 0.000 claims abstract description 202
- 230000008439 repair process Effects 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000012938 design process Methods 0.000 claims description 11
- 230000009466 transformation Effects 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims 1
- 230000008859 change Effects 0.000 description 14
- 230000008569 process Effects 0.000 description 7
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses an animation design processing supervision system and method based on cloud computing, which relate to the technical field of animation design supervision, wherein a comparison interval is set, images in the range of the current position comparison interval are subjected to content recognition, recognized contents are classified, similarity between images in a later image and images in a former image of the same kind of contents is calculated, a first position difference value is obtained, the comparison interval is moved, a second position difference value is calculated, offset difference values of images of the same kind of contents in the first comparison position and the second comparison position are calculated, an abnormal image is primarily judged, the abnormal image is screened, the image range and the image range threshold of the abnormal image are compared, the artificially constructed abnormal image is removed, the screened abnormal image is set as an image to be repaired, a repair reference image is set for the images adjacent to the abnormal image, and the image to be repaired.
Description
Technical Field
The invention relates to the technical field of animation design supervision, in particular to an animation design processing supervision system and method based on cloud computing.
Background
Viewers can find out the situation of sudden image misalignment or image loss details of character images in animation pictures during the process of watching the animation, and the situation is commonly called picture collapse. The picture is an image of the final surface of the animation, and the manuscript of the animation is drawn by a painter in a pen-to-pen manner, so that a place which is missed is unavoidable. The traditional supervision adopts a manual supervision mode, such as setting up a picture supervision post, and checking pictures again. The one-step animation is composed of a large number of pictures, the face is difficult to achieve by manpower auditing, and the situation of image misalignment still exists in the actual projection process of the animation. Therefore, an automatic and intelligent animation design processing supervision system and method are needed.
The animation creator applies the super-realistic expression method in the animation design process, so that the change characteristics of the animation picture are different from the picture shot from the real world, and although the picture supervision method for the picture shot from the real world exists in the prior art, the animation creator cannot be directly applied to the supervision of the animation picture.
Disclosure of Invention
The invention aims to provide an animation design processing supervision system and method based on cloud computing, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an animation design processing supervision system and method based on cloud computing, wherein the method comprises the following steps:
1. an animation design processing supervision method based on cloud computing, which is characterized by comprising the following steps:
step S100: setting a comparison interval and the length of the comparison interval, arranging all pictures forming the animation according to the display time sequence, giving each picture a sequence number according to the sequence, setting the position of the current comparison interval as a first comparison position, identifying the pictures in the range of the current position comparison interval, classifying the content, calculating the similarity of different images of the same content in two adjacent pictures, and calculating the first position difference value of each image;
step S200: moving the comparison section to a second comparison position along the picture display direction, repeating the similarity calculation step in the step S100 to obtain second position difference values of each content, extracting content types which appear in the step S100, calculating offset difference values of the same content, and performing picture-by-picture movement on the comparison section, wherein each second comparison position is used as a first comparison position before the next comparison section moves;
step S300: step S100 and step S200 are cycled, abnormal images in all images are judged, the image range with the abnormal images is defined, and erroneous judgment images in the abnormal images are removed;
step S400: setting the screened abnormal image as an image to be repaired, setting a repair reference image for images adjacent to the abnormal image, repairing the image to be repaired, comparing images representing the same content in an abnormal picture range and images in a non-abnormal picture range, extracting abnormal and non-abnormal difference characteristics representing the same content image, repairing the abnormal image through the non-abnormal image, and repairing the abnormal picture from two ends of the abnormal picture range to the middle of the abnormal picture range;
step S500: when repairing to the remaining image to be repaired in the abnormal picture range, two repaired abnormal images adjacent to the abnormal picture are used as repairing reference images, and the images to be repaired are repaired together.
Further, the step of calculating the first position difference value of the image in step S100 includes:
step S101: setting a comparison interval K, and L for the length of K k Represented by, wherein L k =k 1 F, f represents the length of one frame, k 1 Representing the number of frames of the overlay picture of the comparison interval K, wherein each picture in the animation has the same size;
step S102: fixing the position of the current comparison interval, wherein when the comparison interval K is aligned with the head and the tail of the picture, the position of the current comparison interval is a first comparison position;
step S103: content identification is carried out on all pictures in the first comparison position, images representing various contents in different pictures are identified, and the images are classified according to the contents represented by the images;
step S104: calculating similarity of one of the images in the following picture and the image in the preceding picture according to the picture sequenceFirst position difference value D of each image 1 Wherein, the method comprises the steps of, wherein,d i representing the result of the ith comparison similarity between the image of a certain content in the next picture and the image in the previous picture in the first comparison position, wherein n represents k 1 N times of comparison results are included in each picture frame, n is less than k 1 。
Successive pictures constituting the animation have a certain relationship, and for the consistency of expression, the same content in adjacent pictures has a similar relationship, and the content is as follows: the character model of the animation main body and the model of the person or object appearing in the animation background picture. And in the defined comparison interval range, carrying out similarity comparison on continuous images of the same content, wherein the similarity comparison method is to calculate the similarity of a later image and a previous image of the same content, and the change of the content image in each time in a normal picture is stable, so that the average change value of the similarity in the comparison interval is obtained by dividing the sum of the similarities by the comparison times, and whether the images in the comparison interval have a stable change relation is measured by the average change value of the similarity.
Further, step S200 includes:
step S201: the comparison section moves the length of one picture frame along the direction of the picture display sequence to reach a second comparison position;
step S202: repeating the method of calculating the first position difference value in step S104, and calculating the second position difference value D of the first position difference value of the same content image 2 ;
Step S203: calculating offset difference values g of the same content image at a first comparison position and a second comparison position, wherein g= |D 2 -D 1 |;
And (3) calculating the average change value of the similarity of each content corresponding image in the comparison interval again after the comparison interval moves by one picture length each time, calculating the influence of the image in the next picture on the average change value of the similarity along with the movement of the comparison interval, representing by an offset difference value g, and reflecting the influence of the image in the picture newly entering the comparison interval on the average change of the similarity by comparing the average change of the similarity in the current position with the average change of the previous similarity.
Further, the method for judging the abnormal image in step S300 includes:
step S301: setting an abnormal image determination first threshold value mu 1 When the offset difference g of the image satisfies the condition g > mu 1 When the comparison section at the second comparison position has an abnormal image, judging that the image corresponding to the content of the picture where the first frame of the comparison section is located is the abnormal image, wherein the first frame is located at the first frame in the moving direction of the comparison section;
step S302: the frame range S in which the abnormal image exists is calculated, and the expression of S is (x 1 ,x 2 ) Wherein x is 1 To appear g > mu 1 When comparing the sequence number, x of the picture frame corresponding to the first frame of the section 2 =x 2 ’-k 1 ,x 2 ' means that g > mu is present 1 After that, the g value is reduced to g < mu 1 When comparing the sequence number k of the frame where the first frame of the section is 1 Representing the number of the coverage frames of the comparison interval;
with further movement of the comparison section, the offset difference value is kept larger than the first threshold value for judging the abnormal image due to the fact that the abnormal image exists in the comparison section, when the comparison section moves further, the comparison section does not have the abnormal image, at the moment, the offset difference value returns to be lower than the first threshold value for judging the abnormal image again, and the position section of the comparison section is recorded in the process that the offset difference value is larger than the first threshold value for judging the abnormal image to smaller than the first threshold value for judging the abnormal image from the beginning.
Further, the step of removing the erroneous determination abnormality image in step S300 includes:
step S303: setting a picture range threshold S c Removing a first erroneous judgment image, wherein the first erroneous judgment image is an abnormal image, and the picture range S of the abnormal image is smaller than S c An abnormal image corresponding to the abnormal picture range;
step S304: setting abnormal image judgmentDetermining a second threshold mu 2 In the picture range of the extracted abnormal image, g & gtmu appears 2 When the frame is compared with the frame corresponding to the first frame of the section, an abnormal image in the frame is extracted;
step S305: extracting textures of the abnormal image, and calculating the texture occupancy rate eta of the abnormal image, wherein eta=c 1 /c 2 Wherein c 1 Representing the number of pixels occupied by the texture portion of the abnormal image, c 2 The total number of pixels of the abnormal image is represented,
step S306: setting a texture duty cycle threshold eta 0 Removing a second misjudgment image, wherein the second misjudgment image is an image with the texture ratio of the image being greater than a texture ratio threshold;
unlike the image shot in the real world, the animation picture has an artificially structured exaggeration picture, and in the process of artificially structuring the exaggeration picture, artistic expression techniques such as exaggeration deformation, spatial distortion, contrast highlighting and the like are adopted; in the similarity comparison, the "abnormal pictures" at these artifacts are removed;
the artificially constructed abnormal images are more stable in picture presentation than the real abnormal images generated by picture quality problems, the real abnormal images are regarded as random generation, when the abnormal images pass through a comparison section, the change of offset difference values is slower from increasing to decreasing, the artificially constructed exaggerated pictures are part of animation works in essence and are created for viewing by audiences, after the picture similarity undergoes a large fluctuation, the images are quickly stabilized, and in the change process, the comparison section is shorter than the offset difference value exceeding threshold value section of the abnormal images, so that the abnormal images and the artificially constructed exaggerated images can be distinguished by comparing the length of the offset difference values exceeding a first threshold value of the abnormal images;
further analysis of the anomaly images, comparing the texture of the images, and when an image has a rich texture, considering that such an image is carefully designed by a designer, and is not generated by random or random smearing by a painter or animation generation software, excluding the possibility that an image having a texture ratio of the anomaly image greater than a texture ratio threshold is an anomaly image.
Further, the repairing step in step S400 includes:
step S401: extracting sequence number x of picture frame 1 Position anomaly image A and picture frame number x 1 -1 a non-abnormal image B corresponding to an abnormal image at the position, wherein the image B is used as a restoration reference image for restoring the image a, the image a and the image B reach the maximum boundary coincidence through plane transformation, when the maximum boundary coincidence relation between the image a and the image B is obtained, a plane transformation matrix H is formed on the image a, and the transformed image of the image a is marked as A 2 Wherein A is 2 =H·A;
Step S402: acquiring image B and image A 2 Is used for calculating the mapping rho of texture differences * Wherein ρ is * =H -1 ρ, wherein H -1 An inverse transform representing H;
step S403: combining the texture difference with the image A to generate a substitute image A of the image A * ;
Step S404: following the method from step S401 to step S403, the sequence number x is counted from the picture frame 2 Abnormal image of position along x 2 To x 1 The direction of (3) is used for repairing the abnormal image.
Further, step S500 includes:
step S501: three images in the arrangement sequence are respectively represented by an image P, an image Q and an image R, wherein the image P and the image R are repaired abnormal images, the image Q is an abnormal image to be repaired, and the image P and the image R are used as repair reference images of the repair image Q;
step S502: dividing the image Q into blocks, wherein each image block of the image Q is respectively matched with the nearest image block from the image P and the image R, repairing the image blocks respectively according to the methods from the step S401 to the step S403, and recombining the repaired image blocks into the image Q according to the positions corresponding to the image blocks before repairing 2 ;
Step S503: for image Q 2 Smoothing and noise reduction processing is carried out on textures to generate an image Q 3 Image Q 3 The substitute original image Q is saved in the picture sequence.
In order to better realize the method, the animation design processing supervision system based on cloud computing is also provided, which comprises: the system comprises an abnormal image comparison module, an erroneous judgment removal module and an abnormal image restoration module, wherein the abnormal image comparison module is used for comparing and primarily judging an abnormal image, the erroneous judgment removal module is used for screening and removing non-abnormal images which are erroneously judged to be the abnormal image, and the abnormal image restoration module is used for restoring the abnormal image after the erroneous judgment is removed.
Further, the abnormal picture comparison module includes: the device comprises a comparison section control unit, a similarity calculation unit, an offset difference value calculation unit, an abnormal value judgment unit, an abnormal image positioning unit and an abnormal image picture range generation unit, wherein the comparison section control unit is used for controlling the length of a comparison section and controlling the comparison section to move in an animation picture sequence, the similarity calculation unit is used for calculating the similarity of an image of a later picture and an image of a previous picture, the offset difference value calculation unit is used for calculating an offset difference value, the abnormal value judgment unit is used for judging the abnormal value in the offset difference value, the abnormal image positioning unit is used for positioning the sequence number of a picture frame corresponding to a first frame of the comparison section, and the abnormal image picture range generation unit is used for generating an abnormal image picture range.
Further, the abnormal picture repair unit includes: the image block comparison unit is used for carrying out block comparison on the abnormal image.
Compared with the prior art, the invention has the following beneficial effects: according to the invention, the comparison interval is set, the average similarity of images in the comparison interval is calculated, then the comparison interval is moved, the change of the image similarity is calculated, the images newly entering the comparison interval picture are obtained, the influence on the average change of the similarity is generated, the abnormal images are primarily judged, then the image anomalies caused by the exaggerated images of the structures are considered to be removed from the abnormal images, the image anomalies caused by the reduced picture manufacturing quality are obtained, the adjacent images of the abnormal images are used as repair reference images, the abnormal images are repaired, the continuity of picture content is ensured, the automatic identification of the abnormal images is realized, and whether the abnormal images are artificial structures is further distinguished, so that the automatic image processing method fits the actual use scene and the actual use requirements in the related fields.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of an animation design process supervision system based on cloud computing;
FIG. 2 is a schematic flow chart of an animation design process supervision method based on cloud computing;
fig. 3 is a schematic diagram of movement of a comparison interval of an animation design processing supervision method based on cloud computing.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, 2 and 3, the present invention provides the following technical solutions: :
step S100: setting a comparison interval and the length of the comparison interval, arranging all pictures forming the animation according to the display time sequence, giving each picture a sequence number according to the sequence, setting the position of the current comparison interval as a first comparison position, identifying the pictures in the range of the current position comparison interval, classifying the content, calculating the similarity of different images of the same content in two adjacent pictures, and calculating the first position difference value of each image;
wherein, the first position difference value calculating step of the image in step S100 includes:
step S101: setting a comparison interval K, and L for the length of K k Represented by, wherein L k =k 1 F, f represents the length of one frame, k 1 Representing the number of frames of the overlay picture of the comparison interval K, wherein each picture in the animation has the same size;
step S102: fixing the position of the current comparison interval, wherein when the comparison interval K is aligned with the head and the tail of the picture, the position of the current comparison interval is a first comparison position;
step S103: content identification is carried out on all pictures in the first comparison position, images representing various contents in different pictures are identified, and the images are classified according to the contents represented by the images;
step S104: according to the picture sequence, calculating the similarity between the image of one content in the next picture and the image in the previous picture, and calculating the first position difference value D of each image 1 Wherein, the method comprises the steps of, wherein,d i representing the result of the ith comparison similarity between the image of a certain content in the next picture and the image in the previous picture in the first comparison position, wherein n represents k 1 N times of comparison results are included in each picture frame, n is less than k 1 。
Step S200: moving the comparison section to a second comparison position along the picture display direction, repeating the similarity calculation step in the step S100 to obtain second position difference values of each content, extracting content types which appear in the step S100, calculating offset difference values of the same content, and performing picture-by-picture movement on the comparison section, wherein each second comparison position is used as a first comparison position before the next comparison section moves;
step S201: the comparison section moves the length of one picture frame along the direction of the picture display sequence to reach a second comparison position;
step S202: repeating the method of calculating the first position difference value in step S104, and calculating the second position difference value D of the first position difference value of the same content image 2 ;
Step S203: calculating offset difference values g of the same content image at a first comparison position and a second comparison position, wherein g= |D 2 -D 1 |;
Fig. 3 shows a schematic diagram of movement of a comparison section, wherein 01, 02, 03, 04, 05, 06, 07 and 08 respectively represent 8 pictures with serial numbers of 01, 02, 03, 04, 05, 06, 07 and 08 respectively, each picture has a length of f, the length of the comparison section is 4f, and the arrow direction is the movement direction of the comparison section.
Step S300: step S100 and step S200 are cycled, abnormal images in all images are judged, the image range with the abnormal images is defined, and erroneous judgment images in the abnormal images are removed;
the step of determining the abnormal image in step S300 includes:
step S301: setting an abnormal image determination first threshold value mu 1 When the offset difference g of the image satisfies the condition g > mu 1 When the comparison section at the second comparison position has an abnormal image, judging that the image corresponding to the content of the picture where the first frame of the comparison section is located is the abnormal image, wherein the first frame is located at the first frame in the moving direction of the comparison section;
step S302: the frame range S in which the abnormal image exists is calculated, and the expression of S is (x 1 ,x 2 ) Wherein x is 1 To appear g > mu 1 When comparing the sequence number, x of the picture frame corresponding to the first frame of the section 2 =x 2 ’-k 1 ,x 2 ' means that g > mu is present 1 After that, the g value is reduced to g < mu 1 When comparing the sequence number k of the frame where the first frame of the section is 1 Indicating the number of overlay frames of the comparison interval.
The step S300 of removing the erroneous determination abnormality image includes:
step S303: setting a picture range threshold S c Removing a first erroneous judgment image, wherein the first erroneous judgment image is an abnormal image, and the picture range S of the abnormal image is smaller than S c An abnormal image corresponding to the abnormal picture range;
step S303: setting a picture range threshold S c Removing a first erroneous judgment image, wherein the first erroneous judgment image is an abnormal image, and the picture range S of the abnormal image is smaller than S c An abnormal image corresponding to the abnormal picture range;
step S304: setting an abnormal image determination second threshold value mu 2 In the picture range of the extracted abnormal image, g & gtmu appears 2 When the frame is compared with the frame corresponding to the first frame of the section, an abnormal image in the frame is extracted;
step S305: extracting textures of the abnormal image, and calculating the texture occupancy rate eta of the abnormal image, wherein eta=c 1 /c 2 Wherein c 1 Representing the number of pixels occupied by the texture portion of the abnormal image, c 2 The total number of pixels of the abnormal image is represented,
step S306: setting a texture duty cycle threshold eta 0 And removing a second erroneous judgment image, wherein the second erroneous judgment image is an image of which the texture ratio of the image is larger than the texture ratio threshold value.
Step S400: setting the screened abnormal image as an image to be repaired, setting a repair reference image for images adjacent to the abnormal image, repairing the image to be repaired, comparing images of the same content in an abnormal picture range and images in a non-abnormal picture range, extracting abnormal and non-abnormal difference characteristics of the images of the same content, repairing the abnormal image through the non-abnormal image, and repairing the abnormal picture from two ends of the abnormal picture range to the middle of the abnormal picture range;
the repairing step in step S400 includes:
step S401: extracting sequence number x of picture frame 1 Position anomaly image A and picture frame number x 1 -1 position anomaly image pairThe corresponding abnormal image B is used as a restoration reference image for restoring the image A, the image A and the image B reach the maximum boundary coincidence through plane transformation, when the maximum boundary coincidence relation between the image A and the image B is obtained, a plane transformation matrix H is formed on the image A, and the transformed image of the image A is marked as A 2 Wherein A is 2 =H·A;
Step S402: acquiring image B and image A 2 Is used for calculating the mapping rho of texture differences * Wherein ρ is * =H -1 ρ, wherein H -1 An inverse transform representing H;
step S403: combining the texture difference with the image A to generate a substitute image A of the image A * ;
Step S404: following the method from step S401 to step S403, the sequence number x is counted from the picture frame 2 Abnormal image of position along x 2 To x 1 The direction of (3) is used for repairing the abnormal image.
Step S500: when repairing to the remaining image to be repaired in the abnormal picture range, two repaired abnormal images adjacent to the abnormal picture are used as repair reference images, and the images to be repaired are repaired together;
wherein, step S500 includes:
step S501: three images in the arrangement sequence are respectively represented by an image P, an image Q and an image R, wherein the image P and the image R are repaired abnormal images, the image Q is an abnormal image to be repaired, and the image P and the image R are used as repair reference images of the repair image Q;
step S502: dividing the image Q into blocks, wherein each image block of the image Q is respectively matched with the nearest image block from the image P and the image R, repairing the image blocks respectively according to the methods from the step S401 to the step S403, and recombining the repaired image blocks into the image Q according to the positions corresponding to the image blocks before repairing 2 ;
Step S503: for image Q 2 Smoothing and noise reduction processing is carried out on textures to generate an image Q 3 Image Q 3 The substitute original image Q is saved in the picture sequence.
Wherein, the system includes:
the system comprises an abnormal image comparison module, an erroneous judgment removal module and an abnormal image restoration module, wherein the abnormal image comparison module is used for comparing and primarily judging an abnormal image, the erroneous judgment removal module is used for screening and removing non-abnormal images which are erroneously judged to be the abnormal image, and the abnormal image restoration module is used for restoring the abnormal image after the erroneous judgment is removed.
Wherein, unusual picture compares the module includes: the device comprises a comparison section control unit, a similarity calculation unit, an offset difference value calculation unit, an abnormal value judgment unit, an abnormal image positioning unit and an abnormal image picture range generation unit, wherein the comparison section control unit is used for controlling the length of a comparison section and controlling the comparison section to move in an animation picture sequence, the similarity calculation unit is used for calculating the similarity of an image of a later picture and an image of a previous picture, the offset difference value calculation unit is used for calculating an offset difference value, the abnormal value judgment unit is used for judging the abnormal value in the offset difference value, the abnormal image positioning unit is used for positioning the sequence number of a picture frame corresponding to a first frame of the comparison section, and the abnormal image picture range generation unit is used for generating an abnormal image picture range.
Wherein the abnormal picture repairing unit includes: the image block comparison unit is used for carrying out block comparison on the abnormal image.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An animation design processing supervision method based on cloud computing, which is characterized by comprising the following steps:
step S100: setting a comparison interval and the length of the comparison interval, arranging all pictures forming the animation according to the display time sequence, giving each picture a sequence number according to the sequence, setting the position of the current comparison interval as a first comparison position, identifying the pictures in the range of the current position comparison interval, classifying the content, calculating the similarity of different images of the same content in two adjacent pictures, and calculating the first position difference value of each image;
step S200: moving the comparison section to a second comparison position along the picture display direction, repeating the similarity calculation step in the step S100 to obtain second position difference values of all the contents, extracting the contents which appear in the step S100, calculating offset difference values of the same kind of contents, and moving the comparison section picture by picture, wherein each second comparison position is used as a first comparison position before the next comparison section moves;
step S300: step S100 and step S200 are cycled, abnormal images in all images are judged, the image range with the abnormal images is defined, and erroneous judgment images in the abnormal images are removed;
step S400: setting the screened abnormal image as an image to be repaired, setting a repair reference image for images adjacent to the abnormal image, repairing the image to be repaired, comparing images representing the same content in an abnormal picture range and images in a non-abnormal picture range, extracting abnormal and non-abnormal difference characteristics representing the same content image, repairing the abnormal image through the non-abnormal image, and repairing the abnormal picture from two ends of the abnormal picture range to the middle of the abnormal picture range;
step S500: when repairing to the remaining image to be repaired in the abnormal picture range, two repaired abnormal images adjacent to the abnormal picture are used as repairing reference images, and the images to be repaired are repaired together.
2. The method according to claim 1, wherein the step of calculating the first position difference value of the image in step S100 includes:
step S101: setting a comparison interval K, and L for the length of K k Represented by, wherein L k =k 1 F, f represents the length of one frame, k 1 Representing the number of frames of the overlay picture of the comparison interval K, wherein each picture in the animation has the same size;
step S102: fixing the position of the current comparison interval, wherein when the comparison interval K is aligned with the head and the tail of the picture, the position of the current comparison interval is a first comparison position;
step S103: content identification is carried out on all pictures in the first comparison position, images representing various contents in different pictures are identified, and the images are classified according to the contents represented by the images;
step S104: according to the picture sequence, calculating the similarity between the image of one content in the next picture and the image in the previous picture, and calculating the first position difference value D of each image 1 Wherein, the method comprises the steps of, wherein,d i representing the result of the ith comparison similarity between the image of a certain content in the next picture and the image in the previous picture in the first comparison position, wherein n represents k 1 N times of comparison results are included in each picture frame, n is less than k 1 。
3. The method of monitoring and controlling an animation design process based on cloud computing according to claim 2, wherein step S200 comprises:
step S201: the comparison section moves the length of one picture frame along the direction of the picture display sequence to reach a second comparison position;
step S202: repeating the method of calculating the first position difference value in step S104, and calculating the second position difference value D of the first position difference value of the same content image 2 ;
Step S203: calculating offset difference values g of the same content image at a first comparison position and a second comparison position, wherein g= |D 2 -D 1 |。
4. The method for supervising the animation design process based on cloud computing as claimed in claim 3, wherein the step of determining the abnormal image in step S300 comprises:
step S301: setting an abnormal image determination first threshold value mu 1 When the offset difference g of the image satisfies the condition g > mu 1 When the comparison section at the second comparison position has an abnormal image, judging that the image corresponding to the content of the picture where the first frame of the comparison section is located is the abnormal image, wherein the first frame is located at the first frame in the moving direction of the comparison section;
step S302: the frame range S in which the abnormal image exists is calculated, and the expression of S is (x 1 ,x 2 ) Wherein x is 1 To appear g > mu 1 When comparing the sequence number, x of the picture frame corresponding to the first frame of the section 2 =x 2 ’-k 1 ,x 2 ' means that g > mu is present 1 After that, the g value is reduced to g < mu 1 When comparing the frame of the first frame of the sectionSequence number k 1 Indicating the number of overlay frames of the comparison interval.
5. The method according to claim 3, wherein in step S300, the step of removing the erroneous determination abnormality image includes:
step S303: setting a picture range threshold S c Removing a first erroneous judgment image, wherein the first erroneous judgment image is an abnormal image, and the picture range S of the abnormal image is smaller than S c An abnormal image corresponding to the abnormal picture range;
step S304: setting an abnormal image determination second threshold value mu 2 In the picture range of the extracted abnormal image, g & gtmu appears 2 When the frame is compared with the frame corresponding to the first frame of the section, an abnormal image in the frame is extracted;
step S305: extracting textures of the abnormal image, and calculating the texture occupancy rate eta of the abnormal image, wherein eta=c 1 /c 2 Wherein c 1 Representing the number of pixels occupied by the texture portion of the abnormal image, c 2 The total number of pixels of the abnormal image is represented,
step S306: setting a texture duty cycle threshold eta 0 And removing a second erroneous judgment image, wherein the second erroneous judgment image is an image of which the texture ratio of the image is larger than the texture ratio threshold value.
6. The method for supervising the animation design process based on cloud computing as claimed in claim 4, wherein the repairing step in step S400 comprises:
step S401: extracting sequence number x of picture frame 1 Position anomaly image A and picture frame number x 1 -1 a non-abnormal image B corresponding to an abnormal image at the position, wherein the image B is used as a restoration reference image for restoring the image a, the image a and the image B reach the maximum boundary coincidence through plane transformation, when the maximum boundary coincidence relation between the image a and the image B is obtained, a plane transformation matrix H is formed on the image a, and the transformed image of the image a is marked as A 2 Wherein A is 2 =H·A;
Step S402: acquiring image B and image A 2 Is used for calculating the mapping rho of texture differences * Wherein ρ is * =H -1 ρ, wherein H -1 An inverse transform representing H;
step S403: combining the texture difference with the image A to generate a substitute image A of the image A * ;
Step S404: following the method from step S401 to step S403, the sequence number x is counted from the picture frame 2 Abnormal image of position along x 2 To x 1 The direction of (3) is used for repairing the abnormal image.
7. The method of supervising an animation design process based on cloud computing as claimed in claim 6, wherein the step S500 comprises:
step S501: three images in the arrangement sequence are respectively represented by an image P, an image Q and an image R, wherein the image P and the image R are repaired abnormal images, the image Q is an abnormal image to be repaired, and the image P and the image R are used as repair reference images of the repair image Q;
step S502: dividing the image Q into blocks, wherein each image block of the image Q is respectively matched with the nearest image block from the image P and the image R, repairing the image blocks respectively according to the methods from the step S401 to the step S403, and recombining the repaired image blocks into the image Q according to the positions corresponding to the image blocks before repairing 2 ;
Step S503: for image Q 2 Smoothing and noise reduction processing is carried out on textures to generate an image Q 3 Image Q 3 The substitute original image Q is saved in the picture sequence.
8. An animation design process supervision system applied to the cloud computing-based animation design process supervision method as defined in any one of claims 1 to 7, wherein the system comprises: the system comprises an abnormal image comparison module, an erroneous judgment removal module and an abnormal image restoration module, wherein the abnormal image comparison module is used for comparing and primarily judging an abnormal image, the erroneous judgment removal module is used for screening and removing non-abnormal images which are erroneously judged to be the abnormal image, and the abnormal image restoration module is used for restoring the abnormal image after the erroneous judgment is removed.
9. The animation design process supervision system according to claim 8, wherein the abnormal picture comparison module comprises: the device comprises a comparison section control unit, a similarity calculation unit, an offset difference value calculation unit, an abnormal value judgment unit, an abnormal image positioning unit and an abnormal image picture range generation unit, wherein the comparison section control unit is used for controlling the length of a comparison section and controlling the comparison section to move in an animation picture sequence, the similarity calculation unit is used for calculating the similarity of an image of a later picture and an image of a previous picture, the offset difference value calculation unit is used for calculating an offset difference value, the abnormal value judgment unit is used for judging the abnormal value in the offset difference value, the abnormal image positioning unit is used for positioning the sequence number of a picture frame corresponding to a first frame of the comparison section, and the abnormal image picture range generation unit is used for generating an abnormal image picture range.
10. An animation design process supervision system according to claim 9, wherein the abnormal picture repairing unit comprises: the image block comparison unit is used for carrying out block comparison on the abnormal image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310703711.4A CN116563429B (en) | 2023-06-14 | 2023-06-14 | Animation design processing supervision system and method based on cloud computing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310703711.4A CN116563429B (en) | 2023-06-14 | 2023-06-14 | Animation design processing supervision system and method based on cloud computing |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116563429A true CN116563429A (en) | 2023-08-08 |
CN116563429B CN116563429B (en) | 2023-10-27 |
Family
ID=87491710
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310703711.4A Active CN116563429B (en) | 2023-06-14 | 2023-06-14 | Animation design processing supervision system and method based on cloud computing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116563429B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111898486A (en) * | 2020-07-14 | 2020-11-06 | 浙江大华技术股份有限公司 | Method and device for detecting abnormity of monitoring picture and storage medium |
CN115346060A (en) * | 2022-08-03 | 2022-11-15 | 深圳绿米联创科技有限公司 | Picture abnormity identification method and device, electronic equipment and storage medium |
CN116189038A (en) * | 2022-12-23 | 2023-05-30 | 深圳鲲云信息科技有限公司 | Picture abnormality judging method, device, equipment and storage medium |
-
2023
- 2023-06-14 CN CN202310703711.4A patent/CN116563429B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111898486A (en) * | 2020-07-14 | 2020-11-06 | 浙江大华技术股份有限公司 | Method and device for detecting abnormity of monitoring picture and storage medium |
CN115346060A (en) * | 2022-08-03 | 2022-11-15 | 深圳绿米联创科技有限公司 | Picture abnormity identification method and device, electronic equipment and storage medium |
CN116189038A (en) * | 2022-12-23 | 2023-05-30 | 深圳鲲云信息科技有限公司 | Picture abnormality judging method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN116563429B (en) | 2023-10-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Park et al. | Double JPEG detection in mixed JPEG quality factors using deep convolutional neural network | |
US6912313B2 (en) | Image background replacement method | |
CN102368821B (en) | Adaptive noise intensity video denoising method and system thereof | |
EP1805715B1 (en) | A method and system for processing video data | |
CN110807396B (en) | Face changing video tampering detection method and system based on illumination direction consistency | |
JP2015528960A (en) | Form recognition method and form recognition apparatus | |
CN109544475A (en) | Bi-Level optimization method for image deblurring | |
CN111008651A (en) | Image reproduction detection method based on multi-feature fusion | |
CN117237279A (en) | Blind quality evaluation method and system for non-uniform distortion panoramic image | |
CN115909160A (en) | Method and device for detecting depth video frame insertion and computer readable storage medium | |
CN116563429B (en) | Animation design processing supervision system and method based on cloud computing | |
CN116580182B (en) | Method, system, equipment and storage medium for automatically-adjusted target detection | |
CN112560734A (en) | Method, system, device and medium for detecting reacquired video based on deep learning | |
CN107798676B (en) | No-reference image quality perception method established based on multi-scale natural scene statistics | |
CN114677638B (en) | Detection method based on deep learning and clustering crowd abnormal aggregation | |
CN112446245A (en) | Efficient motion characterization method and device based on small displacement of motion boundary | |
JP2004519048A (en) | Method and apparatus for improving object boundaries extracted from stereoscopic images | |
CN114549703B (en) | Quick-action image generation method, system, device and storage medium | |
CN113938671B (en) | Image content analysis method, image content analysis device, electronic equipment and storage medium | |
Zhang et al. | Detecting digital image forgeries through weighted local entropy | |
CN114677670A (en) | Automatic identification and positioning method for identity card tampering | |
JP6524398B1 (en) | Video processing apparatus, video processing system, video processing method and program | |
JP2011113177A (en) | Method and program for structuring three-dimensional object model | |
Hassan et al. | Texture based Image Splicing Forgery Recognition using a Passive Approach | |
CN117011288B (en) | Video quality diagnosis method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |