CN114827730A - Video cover selecting method, device, equipment and storage medium - Google Patents
Video cover selecting method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114827730A CN114827730A CN202210411941.9A CN202210411941A CN114827730A CN 114827730 A CN114827730 A CN 114827730A CN 202210411941 A CN202210411941 A CN 202210411941A CN 114827730 A CN114827730 A CN 114827730A
- Authority
- CN
- China
- Prior art keywords
- frame
- action
- score
- processed
- angle
- 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 28
- 238000010586 diagram Methods 0.000 claims description 46
- 238000012937 correction Methods 0.000 claims description 11
- 238000010187 selection method Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 210000004394 hip joint Anatomy 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 210000001503 joint Anatomy 0.000 description 3
- 230000001154 acute effect Effects 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 210000002414 leg Anatomy 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 210000000689 upper leg Anatomy 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 235000011888 snacks Nutrition 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/458—Scheduling content for creating a personalised stream, e.g. by combining a locally stored advertisement with an incoming stream; Updating operations, e.g. for OS modules ; time-related management operations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/485—End-user interface for client configuration
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/485—End-user interface for client configuration
- H04N21/4858—End-user interface for client configuration for modifying screen layout parameters, e.g. fonts, size of the windows
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a video cover selecting method, a device, equipment and a storage medium, wherein the method comprises the following steps: acquiring a key frame to be processed in a video, and determining the facing angle of a target character in the key frame to be processed, wherein the key frame to be processed has a plurality of frames; identifying a first posture action of a target person, and acquiring a preset picture matched with the first posture action; correcting each action angle of the second posture action of the reference character in the preset picture according to the facing angle, and determining the action score of the first posture action according to the facing angle and each corrected action angle; and determining the position score of the target person in the key frames to be processed, and selecting the video cover of the video from each key frame to be processed according to the action score and the position score. The method and the system enable the selected video cover to be more accurate and meet the requirements of users.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a video cover selecting method, device, equipment and storage medium.
Background
Currently, when determining a video cover, video cover selection is performed based on user attribute characteristics. And generating templates for the video covers correspondingly generated by the users according to different attribute characteristics of the users. For example, the user is an individual user a, and the attribute feature of the user a is historical shopping habits: if the user likes to buy snacks, the template generated for the video cover correspondingly generated by the user can include the following screening conditions: and 4, the gourmet is sequentially generated into video covers containing various gourmets based on the video cover generation template. As another example, the user is company b, and the attribute characteristics of company b are the type of company b: for a movie company, the generated template for the video cover corresponding to the company b may include the following filtering conditions: and the star character and the scene picture are generated into a video cover containing a certain star character and a certain scene picture based on the video cover generation template. However, because the angles and positions of the shot persons are different, the best position of the shot person cannot be selected, and when the images are scored, the images cannot be scored accurately due to the angles, so that the accuracy of the selected video cover is low.
Disclosure of Invention
The embodiment of the invention provides a video cover selection method, a device, equipment and a storage medium, and aims to solve the technical problems that the optimal figure position cannot be selected due to different angles and positions of the photographed figures, and the accuracy of the selected video cover is low due to the fact that the picture scoring cannot be accurately performed due to the angles when the picture scoring is performed.
The embodiment of the invention provides a video cover selection method, which comprises the following steps:
acquiring a key frame to be processed in a video, and determining the facing angle of a target character in the key frame to be processed, wherein the key frame to be processed has multiple frames;
identifying a first posture action of the target person, and acquiring a preset picture matched with the first posture action;
correcting each action angle of the second posture action of the reference character in the preset picture according to the facing angle, and determining the action score of the first posture action according to the facing angle and each corrected action angle;
and determining the position score of the target person in the key frames to be processed, and selecting a video cover of the video from each key frame to be processed according to the action score and the position score.
In an embodiment, the step of correcting each motion angle of the second gesture motion of the reference person in the preset picture according to the facing angle includes:
extracting a first action frame point line graph of the second posture action, wherein the first action frame point line graph is formed by connecting lines of all joint points of the reference person;
rotating the first action frame point diagram according to a preset direction, the central axis of the first action frame point diagram and the facing angle to obtain a second action frame point diagram, wherein the central axis is a connecting line of midpoints between a neck joint and a hip joint;
acquiring an included angle between each joint point and the central axis in the second action frame point diagram;
and taking the included angle between each joint point and the central axis as each corrected action angle.
In one embodiment, the step of determining the action score of the first gesture action according to the facing angle and each of the action angles after correction comprises:
acquiring a maximum facing angle in facing angles of a target person in each to-be-processed key frame, a maximum action angle in each action angle after correction and a preset weight value corresponding to each action angle after correction;
determining an angle score of each corrected action angle according to the facing angle, the maximum action angle, each corrected action angle and the preset weight value;
determining a comparison score of the first posture action and the corrected second posture action of the target person in each key frame to be processed according to each angle score;
and determining the action score of the first gesture action according to each comparison score.
In one embodiment, the step of determining the position score of the target person in the key frame to be processed comprises:
determining intersection points of picture golden section points in the video, wherein the number of the intersection points is at least two;
determining golden section point scores of the region where the target character is located in the key frame to be processed relative to the intersection points;
and determining the position score according to the golden section point score of the area where the target person is located relative to each intersection point.
In one embodiment, the step of determining golden section point scores of the region of the target person in the key frame to be processed relative to the intersection points comprises:
constructing a golden section point frame set, wherein the golden section point frame set comprises first frame numbers of a plurality of golden section point frames and frame number intervals related to the first frame numbers;
when the second frame number of the key frame to be processed is within the frame number interval, determining a plurality of picture scores of the key frame to be processed according to the first frame number, each second frame number, and the maximum value and the minimum value of each frame number interval;
determining the golden section point score from a plurality of the picture scores.
In one embodiment, the step of constructing a golden section frame set comprises:
constructing a two-dimensional coordinate system in the video, selecting at least two of a positive direction of a transverse axis, a negative direction of the transverse axis, a positive direction of a longitudinal axis and a negative direction of the longitudinal axis of the two-dimensional coordinate system as target directions, and marking an intersection point of a golden section point of a picture in the two-dimensional coordinate system according to the target directions;
acquiring a starting frame and an ending frame from each key frame to be processed, and constructing a connecting line segment between the target person contained in the starting frame and the target person contained in the ending frame in the two-dimensional coordinate system;
determining the tangent point of each intersection point and the connecting line segment by taking each intersection point as the circle center, and selecting the video frame positioned at each tangent point as a golden section point frame;
determining a first frame number of each golden section point frame according to the length of each connecting line segment, the distance between each tangent point and the target figure contained in the initial frame, the number of frames of the key frame to be processed and a third frame number of the initial frame;
establishing a frame number interval of a third frame number of the initial frame and a fourth frame number corresponding to the ending frame based on each connecting line segment, and associating each frame number interval with the corresponding first frame number to obtain a plurality of association relations;
and generating the golden section point frame set according to a plurality of incidence relations.
In one embodiment, the step of selecting a video cover of the video from each of the to-be-processed key frames according to the action score and the position score includes:
drawing n line segments corresponding to the n kinds of dimensionality scores so as to enable one ends of the n line segments to be intersected at a central point; wherein the n kinds of dimensionality scores comprise the action score and the position score, and n is more than or equal to 2;
according to the n dimensionality scores of the target person in the key frame to be processed, correspondingly increasing each line segment along the direction far away from the central point;
sequentially connecting one end of each increased line segment, which is far away from the central point, to obtain a scoring polygon corresponding to each key frame to be processed;
and selecting a video cover of the video from each key frame to be processed according to the area of each scoring polygon.
In addition, to achieve the above object, the present invention further provides a video cover selecting apparatus, including:
the information acquisition module is used for acquiring a key frame to be processed in a video and determining the facing angle of a target person in the key frame to be processed, wherein the key frame to be processed has multiple frames;
the action recognition module is used for recognizing a first posture action of the target person and acquiring a preset picture matched with the first posture action;
the score calculation module is used for correcting each action angle of the second gesture action of the reference character in the preset picture according to the facing angle and determining the action score of the first gesture action according to the facing angle and each corrected action angle;
and the cover selecting module is used for determining the position score of the target character in the key frames to be processed and selecting the video cover of the video from each key frame to be processed according to the action score and the position score.
In addition, to achieve the above object, the present invention also provides a terminal device, including: the video cover selecting program is stored on the memory and can run on the processor, and the video cover selecting program realizes the steps of the video cover selecting method when being executed by the processor.
In addition, to achieve the above object, the present invention further provides a storage medium having a video cover selection program stored thereon, wherein the video cover selection program, when executed by a processor, implements the steps of the video cover selection method described above.
The technical scheme of the video cover selection method, the device, the equipment and the storage medium provided by the embodiment of the invention at least has the following technical effects or advantages:
the invention obtains the multi-frame key frame to be processed in the video, then according to the facing angle of the target person in the key frame to be processed, correcting each action angle of the second posture action of the reference character in the preset picture matched with the first posture action of the target character, then determining the action score of the first posture action according to the facing angle and each action angle after correction, then determining the position score of the target character in the key frames to be processed, and selecting the video cover of the video from each key frame to be processed according to the action score and the position score corresponding to each key frame to be processed, thereby solving the problem that the optimal character position can not be selected due to different angles and positions of the shot characters, and when the picture is scored, the picture scoring cannot be accurately performed due to the angle, so that the accuracy of the selected video cover is not high. According to the method, multiple scoring dimensions (at least comprising action scoring and position scoring) are introduced, namely, action scoring is carried out on the target character through the orientation angle of the target character in the key frame to be processed, position scoring is carried out on the position of the target character in the key frame to be processed, comprehensive scoring is carried out on the key frame to be processed in the video, then the video cover is selected from the key to be processed according to the comprehensive scoring, the accuracy and the quality of video cover selection are improved, and the selected video cover is more accurate and better meets the requirements of users.
Drawings
FIG. 1 is a schematic diagram of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a video cover selection method according to an embodiment of the present invention;
FIG. 3 is a schematic view illustrating a process of calculating an action score according to the video cover selecting method of the present invention;
FIG. 4 is a diagram of a keyframe to be processed according to the present invention;
FIG. 5 is a schematic diagram of a default picture according to the present invention;
FIG. 6 is a diagram illustrating an example of a point diagram of an action frame in a default picture according to the present invention;
FIG. 7 is another diagram illustrating a point diagram of an action frame in a default picture according to the present invention;
FIG. 8 is a schematic view illustrating a process of calculating a position score according to the video cover selecting method of the present invention;
FIG. 9 is a schematic view of a two-dimensional coordinate system of the present invention;
FIG. 10 is another schematic view of a two-dimensional coordinate system of the present invention;
FIG. 11 is a schematic diagram illustrating a process for constructing a scoring polygon according to the present invention;
FIG. 12 is a schematic view of a scoring polygon according to the present invention;
FIG. 13 is a functional block diagram of a video cover selecting apparatus according to the present invention.
Detailed Description
In order to better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
As shown in fig. 1, fig. 1 is a schematic structural diagram of a hardware operating environment according to an embodiment of the present invention.
It should be noted that fig. 1 is a schematic structural diagram of a hardware operating environment of the terminal device.
As an implementation manner, as shown in fig. 1, an embodiment of the present invention relates to a terminal device, where the terminal device includes: a processor 1001, such as a CPU, a memory 1002, and a communication bus 1003. The communication bus 1003 is used to implement connection communication among these components.
The memory 1002 may be a high-speed RAX memory or a non-volatile memory (non-volatile XeXory), such as a disk memory. As shown in fig. 1, a memory 1002 as a storage medium may include a video cover selecting program; and the processor 1001 may be configured to call the video cover selection program stored in the memory 1002, and perform at least the following operations:
acquiring a key frame to be processed in a video, and determining the facing angle of a target character in the key frame to be processed, wherein the key frame to be processed has multiple frames;
identifying a first posture action of the target person, and acquiring a preset picture matched with the first posture action;
correcting each action angle of the second posture action of the reference character in the preset picture according to the facing angle, and determining the action score of the first posture action according to the facing angle and each corrected action angle;
and determining the position score of the target person in the key frames to be processed, and selecting a video cover of the video from each key frame to be processed according to the action score and the position score.
While a logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in an order different than that shown or described herein.
As shown in fig. 2, in an embodiment of the present invention, the method for selecting a video cover includes the following steps:
step S210: the method comprises the steps of obtaining a key frame to be processed in a video, and determining the facing angle of a target character in the key frame to be processed.
In this embodiment, the video should be understood as a video that needs to be provided with a video cover, such as a sports video, a music video, a cartoon video, a recorded video, and the like. Specifically, in the early stage of setting a video cover for a video, a large number of wonderful pictures with specified subjects need to be collected, the wonderful pictures corresponding to the subjects are scored, then different subjects are associated with the corresponding wonderful pictures and the scores, for example, the subject is a football goal, the wonderful pictures are game pictures shot by football players, the scores of the game pictures are 8 points, the game pictures and the scores are associated with the football goal and stored in a preprocessing library (i.e., a database), wherein the wonderful pictures are called preset pictures, and the subjects are preset subjects. If the cover needs to be set for the video, the video theme is input, then the preset theme matched with the video theme is searched from the preprocessing library, the corresponding preset picture with the highest score is obtained according to the searched preset theme, and then the decision on how to set the video cover for the video is made according to the obtained preset picture.
The key frame to be processed is provided with a plurality of frames and is an alternative picture for setting a video cover in the video. Typically, several frames of key frames (I-frames) are included in the captured video, and the several frames of key frames may be all continuous or partially continuous. Generating a set P by a plurality of frames of key frames, carrying out image recognition on all key frames in the set P according to the video theme, selecting key frames containing the video theme from the set P, and generating a set C by the selected key frames containing the video theme, for example, the set C contains key frames of football players. Then, the key frames in the set C need to be screened to obtain the key frames to be processed.
The screening process comprises the following steps: and performing quality detection on all key frames in the set C, filtering out the key frames with unqualified quality, and putting the key frames with qualified quality into the set B, wherein the key frames in the set B are the key frames to be processed, namely the key frames are used for selecting the video cover. If the key frame in the set C meets the quality anomaly detection rule, the quality is not met, if the key frame in the set C does not meet the quality anomaly detection rule, the quality is met, and the quality anomaly detection rule is as follows:
the proportion of the element E occupying the whole figure is less than 20% or more than 50%;
the brightness of the whole image is too dark or too bright;
blurring the whole image;
element E is positioned too far to the side in the figure;
the manner in which element E is shown in the figure is reversed.
Wherein, the element E is a target object to be identified, and the target object may be a person, an object, or the like.
After a key frame to be processed in a video is acquired, a target character in the key frame to be processed is identified, and the facing angle of the target character in the key frame to be processed is calculated.
Step S220: and identifying a first posture action of the target person, and acquiring a preset picture matched with the first posture action.
After the key frame to be processed in the video is acquired, the gesture action of the target person in the key frame to be processed is identified, and in order to distinguish from the gesture action in the preset picture, the gesture action is referred to as a first gesture action in the embodiment. Assuming that a keyframe to be processed is shown in fig. 4, the recognition result of the first gesture motion is the motion shown in fig. 4, fig. 4 is a shouting motion of a football player with both hands open, both legs open and slightly backward, i.e. the first gesture motion, the first gesture motion can be outlined by a motion frame point diagram, which can be understood as a matchmaker diagram, i.e. the motion frame point diagram is formed by connecting lines of all joints of a human body.
And further searching a preset image matched with the target person and the recognition result from the preprocessing library according to the recognition result of the first gesture motion. For example, fig. 4 is a key frame to be processed about a soccer player, i.e. the subject is a soccer player, the first gesture motion is a shouting motion with both hands open, both legs open and a little backward, the preset picture searched from the preprocessing library needs to be a soccer player, and the second gesture motion of the soccer player in the preset picture is the same as the first gesture motion, but the reference character and the target character may face at different angles in the picture, i.e. the motion angles of the two may be different. The searched preset picture is a preset picture matched with the first gesture motion and the football player in the preprocessing library, and the searched preset picture has multiple frames. For example, the preset pictures searched for are shown in fig. 5.
Step S230: and correcting each action angle of the second posture action of the reference character in the preset picture according to the facing angle, and determining the action score of the first posture action according to the facing angle and each corrected action angle.
After a preset picture matched with the first posture action is obtained, the preset picture comprises a reference character, the reference character and a target character in the key frame to be processed are the same, namely the subjects are the same, each action angle of the second posture action is different from that of the first posture action, the action angle refers to an included angle between a joint point of the character and a central axis, and the central axis is a connecting line of midpoints between neck joints and hip joints.
For the selection of the video cover, the invention introduces two scoring dimensions, namely the action score of the gesture action of the target person and the position score of the target person in the key frame to be processed.
The determination of the action score needs to be obtained based on a preset picture, and specifically, each action angle of the second posture action of the reference character in the preset picture is corrected according to the facing angle of the target character in the key frame to be processed, so that the facing angle of the reference character in the preset picture is as close as possible to the facing angle of the target character. And calculating the action score of the first posture action of the target character according to the facing angle and the corrected action angles. The key frame to be processed has multiple frames, and the action score of the first posture action of the target character in each frame of the key frame to be processed needs to be calculated according to the mode.
Step S240: and determining the position score of the target person in the key frames to be processed, and selecting a video cover of the video from each key frame to be processed according to the action score and the position score.
In this embodiment, after the action score of the first gesture of the target person in each frame of the to-be-processed key frame is calculated, the position score of the target person in the corresponding to-be-processed key frame is calculated, where the position score may be understood as the position of the target person in the to-be-processed key frame and the score in the whole to-be-processed key frame.
On one hand, after the action score and the position score corresponding to each frame of key frames to be processed are obtained respectively, a scoring polygon is constructed according to the action score and the position score. The action score and the position score can be used as the lengths of two line segments, namely a first line segment and a second line segment, the first line segment and the second line segment are intersected at one point, and one ends, far away from the intersection point, of the first line segment and the second line segment are connected to form a scoring polygon, wherein the scoring polygon is a triangle, and particularly is a scoring triangle. Wherein the scoring triangle may be one of a right triangle, an obtuse triangle, and an acute triangle.
After the scoring triangles corresponding to each frame of the key frame to be processed are built, the area of each scoring triangle is calculated, and then the comprehensive score of each frame of the key frame to be processed is represented by the area of each scoring triangle, namely the area is equal to the comprehensive score. The selection rule of the video cover is to take the maximum value in each comprehensive score, namely to select the key frame to be processed with the maximum comprehensive score in each comprehensive score as the video cover of the video. For example, there are 3 key frames to be processed, which are S11, S12, and S13, respectively, and the corresponding composite scores are Z11, Z12, and Z13, where Z11< Z12< Z13, and then S13 is selected as the video cover of the video.
On the other hand, after the action score and the position score corresponding to each frame of key frames to be processed are obtained respectively, the action score and the position score corresponding to each frame of key frames to be processed are weighted and calculated to obtain a score weighted sum, and then the score weighted sum represents the comprehensive score of each frame of key frames to be processed through the score weighted sum corresponding to each frame of key frames to be processed, namely the score weighted sum is the comprehensive score. The selection rule of the video cover is to take the maximum value in each comprehensive score, namely to select the key frame to be processed with the maximum comprehensive score in each comprehensive score as the video cover of the video. For example, there are 3 key frames to be processed, which are S21, S22, and S23, respectively, and the corresponding composite scores are Z21, Z22, and Z23, where Z21< Z22< Z23, and then S23 is selected as the video cover of the video.
According to the technical scheme, a plurality of scoring dimensions (action scores and position scores) are introduced, namely, action scoring is performed on the target person according to the orientation angle of the target person in the key frame to be processed, position scoring is performed on the position of the target person in the key frame to be processed, then comprehensive scoring is performed on the key frame to be processed in the video based on the action scoring and the position scoring, and the video cover is selected from the key frame to be processed according to the comprehensive scoring, so that the accuracy and the quality of video cover selection are improved, and the selected video cover is more accurate and better meets the user requirements.
As shown in fig. 3, according to the first embodiment, the correcting the motion angles of the second gesture motion of the reference person in the preset picture according to the facing angles includes the following steps:
step S231: extracting a first action frame point line graph of the second posture action, wherein the first action frame point line graph is formed by connecting lines of all joint points of the reference person;
step S232: rotating the first action frame point diagram according to a preset direction, the central axis of the first action frame point diagram and the facing angle to obtain a second action frame point diagram, wherein the central axis is a connecting line of midpoints between a neck joint and a hip joint;
step S233: acquiring an included angle between each joint point and the central axis in the second action frame point diagram;
step S234: and taking the included angle between each joint point and the central axis as each corrected action angle.
As shown in fig. 4 and 5, fig. 4 is a keyframe to be processed, the soccer player of fig. 4 is a target character, and the first gesture motion is a point diagram of a motion frame connecting all joints in fig. 4, i.e., a matchmaker; fig. 5 is a preset picture matched with the first posture motion, the football player in fig. 5 is a reference character, and the second posture motion is a motion frame point diagram connecting all the joint points in fig. 5, namely a matchmaker. The action frame point line graph corresponding to the second gesture motion is called a first action frame point line graph, and the independent first action frame point line graphs are shown in the left graph of fig. 6 and the left graph of fig. 7.
After the first action frame point diagram of the second gesture action is extracted, the first action frame point diagram is rotated according to the preset direction, the central axis of the first action frame point diagram and the facing angle, namely the central axis is used as a rotating axis, the first action frame point diagram is rotated along the preset direction by the facing angle, and the rotated first action frame point diagram, namely the second action frame point diagram, is obtained, the facing angle of the second action frame point diagram is close to that of the action frame point diagram in the key frame to be processed, and the second action frame point diagram and the action frame point diagram in the key frame to be processed are similar. Wherein, the rotation process is shown in fig. 6 and 7, the right side of fig. 6 shows a second action frame point line graph, the right side of fig. 7 shows a top view, the preset direction in fig. 6 and 7 is counterclockwise, and the facing angle is 45 °; the central axis is the line connecting the midpoints between the neck joint and the hip joint, and the dotted lines in the left diagram of fig. 6 and the left diagram of fig. 7 are the central axes.
After the second action frame point diagram is obtained, the included angle between each joint point and the central axis in the second action frame point diagram, namely the included angle between the connecting line between every two adjacent joint points and the central axis, is obtained, each action angle after correction is obtained, namely the included angle between each joint point and the central axis in the second action frame point diagram is equal to each action angle after correction. As shown in the right diagram of fig. 6, the angle between the connecting line of the two dots and the dotted line is an action angle.
Further, according to the first embodiment, the step of determining the action score of the first gesture action according to the facing angle and each of the action angles after correction includes:
acquiring a maximum facing angle in facing angles of a target person in each to-be-processed key frame, a maximum action angle in each action angle after correction and a preset weight value corresponding to each action angle after correction;
determining an angle score of each corrected action angle according to the facing angle, the maximum action angle, each corrected action angle and the preset weight value;
determining a comparison score of the first posture action and the corrected second posture action of the target person in each key frame to be processed according to each angle score;
and determining the action score of the first gesture action according to each comparison score.
Referring to fig. 6 and 7, the corrected operation angle, i.e., the rotated angle between the thigh and the hip joint, is described as an example, the rotated angle between the thigh and the hip joint is denoted as D ', the facing angle is θ, and the calculation process of D' is as follows:
D′＝360°-(∠AB″S1A∠S1B″C″)；
∠AB″S1＝arAtan(AS1/B″S1)；
∠S1B″C″＝90°AarAtan(S1S2/(C″S2-B″S1))；
according to the right diagram of fig. 7, B "S1 ═ AB 'Aos θ ═ ABAos θ ═ BS1Aos θ, AB' ═ AB ═ BS 1;
C″S2＝AC′Aosθ＝ACAosθ＝CS2Aosθ；
angle AB "S1 ═ arAtan (AS1/(BS1Aos θ)), AC ═ CS2 according to the right diagram of fig. 7;
substituting B 'S1 and C' S2 into the formula:
∠S1B″C″＝90°AarAtan(S1S2/(CS2Aosθ-BS1Aosθ)；
D′＝360°-(∠AB″S1A∠S1B″C″)＝360°-((arAtan(AS1/(BS1Aosθ)))A90°AarAtan(S1S2/(CS2Aosθ-BS1Aosθ))。
the AS1, the BS1, the S1S2, the CS2 and the BS1 are known parameters in a preset image, do not need to be calculated, have a facing angle theta and are obtained by calculating key frames to be processed.
And calculating each corrected action angle according to the calculation method of D'. And calculating the angle score An of each corrected action angle according to the following formula:
An＝(1-|Dn-D′n|/MAX(D′n,D′n))Qn；
wherein Dn represents a facing angle corresponding to the nth frame of the key frame to be processed, D 'n represents an nth action angle after modification in the preset picture, Qn represents a preset weight value corresponding to the nth action angle after modification, and MAX (Dn, D' n) represents a maximum facing angle in the n frames of the key frame to be processed and a maximum action angle after modification in the preset picture.
Based on each to-be-processed key frame, after the angle of each corrected action angle in the preset picture is obtained, calculating a comparison score of a first posture action in each to-be-processed key frame and a second posture action corrected in each preset picture, wherein the comparison score calculation formula is as follows:
after the comparison score of the first posture action in each key frame to be processed and the second posture action corrected in each preset picture is obtained, namely, a plurality of preset pictures corresponding to one key frame to be processed are obtained, and then the maximum comparison score is determined as the action score of the first posture action corresponding to the key frame to be processed, so that the action score of the first posture action corresponding to all the key frames to be processed can be obtained through calculation according to the calculation mode.
As shown in fig. 8, the determination of the position score of the target person in the key frame to be processed according to the first embodiment includes the following steps:
step S241: and determining the intersection point of the golden section point of the picture in the video.
Each video has a plurality of picture golden section points, namely, 2 picture golden section points are respectively arranged in the length direction and the width direction of the video, namely, the picture golden section points comprise the left side and the right side in the length direction and are arranged above and below in the width direction. The intersection point of the golden section point of the picture in the length direction and the golden section point of the picture in the width direction is the intersection point, and the number of the intersection points is at least two, and specifically 4. The golden section points have the significance that objects look harmoniously in proportion and better visual enjoyment is brought to people, and the golden section points represent the display positions of the objects in the video very suitably, so that the objects displayed in the video of people look harmoniously in proportion and better visual enjoyment is brought to people.
Step S242: and determining golden section point scores of the region where the target person is located in the key frame to be processed relative to the intersection points.
Step S243: and determining the position score according to the golden section point score of the area where the target person is located relative to each intersection point.
After the intersection points of the picture golden section points are determined, golden section point scores of the area where the target person is located in the key frame to be processed relative to each intersection point are calculated based on the intersection points of the picture golden section points. Since there are a plurality of intersections and a plurality of golden section point scores are obtained, the score ranking the golden section point scores in the top determines the determination position score. The location score is determined, for example, from the maximum gold point score, i.e., the maximum gold point score is the location score.
Specifically, step S242 includes the following steps:
constructing a golden section point frame set, wherein the golden section point frame set comprises first frame numbers of a plurality of golden section point frames and frame number intervals related to the first frame numbers;
when the second frame number of the key frame to be processed is within the frame number interval, determining a plurality of picture scores of the key frame to be processed according to the first frame number, each second frame number, and the maximum value and the minimum value of each frame number interval;
determining the golden section point score from a plurality of the picture scores.
The golden section point frame set comprises first frame numbers of a plurality of golden section point frames and frame number intervals related to the first frame numbers. The golden section point frame refers to a video frame close to the intersection point of the golden section point of the picture, and the video frame can be a common frame in the video, and can also be a key frame and the like. The first frame number refers to the frame number of the golden section frame, and the frame number interval includes the starting frame number and the ending frame number in all the key frames to be processed, for example, the first frame number is C, the starting frame number is a, the ending frame number is B, and the frame number interval W is [ a, B ], that is, C and W have an association relationship.
The frame number of the key frame to be processed is marked as a second frame number, which is denoted as F, the first frame number is denoted as Fg, the starting frame is denoted as Fs, the ending frame number is denoted as Fe, namely the maximum value of the frame number interval is Fe, and the minimum value is Fs. And after each F is obtained, judging whether the F is in a frame number interval, if so, calculating a plurality of picture scores corresponding to each key frame to be processed according to each F, each Fg and Fs and Fe corresponding to each Fg, and then determining the maximum picture score as a golden section point score for determining the area where the target person is located in the key frame to be processed relative to each intersection point. The calculation formula of the picture score T is as follows:
further, the process of constructing the golden section point frame set includes:
constructing a two-dimensional coordinate system in the video, selecting at least two of a positive direction of a transverse axis, a negative direction of the transverse axis, a positive direction of a longitudinal axis and a negative direction of the longitudinal axis of the two-dimensional coordinate system as target directions, and marking an intersection point of a golden section point of a picture in the two-dimensional coordinate system according to the target directions;
acquiring a starting frame and an ending frame from each key frame to be processed, and constructing a connecting line segment between the target person contained in the starting frame and the target person contained in the ending frame in the two-dimensional coordinate system;
determining the tangent point of each intersection point and the connecting line segment by taking each intersection point as the circle center, and selecting the video frame positioned at each tangent point as a golden section point frame;
determining a first frame number of each golden section point frame according to the length of each connecting line segment, the distance between each tangent point and the target figure contained in the initial frame, the number of frames of the key frame to be processed and a third frame number of the initial frame;
establishing a frame number interval of a third frame number of the initial frame and a fourth frame number corresponding to the ending frame based on each connecting line segment, and associating each frame number interval with the corresponding first frame number to obtain a plurality of association relations;
and generating the golden section point frame set according to a plurality of incidence relations.
As shown in fig. 9 and 10, since there are a plurality of intersection points of the picture golden section points, there are a plurality of ways of determining the intersection points of the picture golden section points. A two-dimensional coordinate system is constructed in a video, the origin of the two-dimensional coordinate system is (0,0), and according to the actual requirement setting, the method is set in the mode in fig. 9 and fig. 10, namely, the vertex at the upper right corner of the video is used as the origin (0,0) of the two-dimensional coordinate system. After the two-dimensional coordinate system is established, the X axis is the length direction of the video, and the Y axis is the width direction of the video, namely the positive direction of the horizontal axis, the negative direction of the horizontal axis, the positive direction of the vertical axis and the negative direction of the vertical axis of the two-dimensional coordinate system can be determined. In fig. 9 and 10, the intersection of the picture golden section points is shown with the positive directions of the horizontal axis and the vertical axis, with point (X2, 0) being a picture golden section point on the X axis and point (0, Y2) being a picture golden section point on the Y axis; point C (X2, Y2) is the intersection of a picture golden section point of the X axis and the Y axis; here, a point C (X2, Y2) determined by the orientation of the positive abscissa direction and the positive ordinate direction is close to the lower left corner vertex of the video. In addition, when the intersection point C of the golden section point of the picture is determined according to the directions of the horizontal axis negative direction and the vertical axis negative direction, the determined point C is close to the top right corner vertex of the video; when the intersection point C of the golden section point of the picture is determined in the positive direction of the horizontal axis and the negative direction of the vertical axis, the determined point C is close to the top point of the upper left corner of the video; when the intersection point C of the golden section point of the picture is determined according to the directions of the negative direction of the horizontal axis and the positive direction of the vertical axis, the determined point C is close to the vertex of the lower right corner of the video.
After determining each intersection point of the golden section point of the picture, acquiring a starting frame and an ending frame from a plurality of key frames to be processed, wherein the starting frame corresponds to the picture of the point A in the pictures in the figures 9 and 10, the ending frame corresponds to the picture of the point B in the figures 9 and 10, then connecting a target character contained in the starting frame with a target character contained in the ending frame to obtain a connecting line segment, the connecting line segment is AB, and the point A and the point B are respectively a certain part of the target character in the starting frame and the ending frame.
And drawing a circle tangent to the AB by taking the intersection point (such as C) as a center, representing the tangent point of the circle and the AB as D, and selecting the video frame at each tangent point as a golden section point frame after the tangent point is determined. Then, calculating the lengths of the AB, the distances DA between the D and the target person contained in the initial frame, and calculating and determining a first frame number P of each golden section point frame according to the lengths of the AB, the distances DA, the frame numbers N (number) of all key frames to be processed and a third frame number (frame number of the initial frame) of the initial frame; the calculation formula is as follows: p ═ N (DA/AB) a frame number of the start frame. The golden section point frame is a frame of a golden section point, and the golden section point frame is a frame of a video frame.
Furthermore, based on each connecting line segment, the frame number interval between the third frame number of each starting frame and the fourth frame number (frame number of ending frame) corresponding to the ending frame, that is, the maximum value of the frame number interval is the fourth frame number, and the minimum value is the third frame number of the starting frame, and then each frame number interval is associated with the corresponding first frame number to obtain a plurality of association relations. The third frame number is Fs, the fourth frame number is Fe, the first frame number is Fg, the relationship is (Fs, Fe, Fg), and then the relationships are stored together to generate the golden section frame set. For example, a total of 4 correlations are obtained, and the correlation 1 is (Fs1, Fe1, Fg1), the correlation 2 is (Fs2, Fe2, Fg2), the correlation 3 is (Fs3, Fe3, Fg3), and the correlation 4 is (Fs4, Fe4, Fg4), that is, the golden section frame set includes the correlations 1 to 4.
Further, as shown in fig. 11, according to the first embodiment, the selecting a video cover of the video from each of the to-be-processed key frames according to the action score and the position score includes the following steps:
step S244: drawing n line segments corresponding to the n kinds of dimensionality scores so as to enable one ends of the n line segments to be intersected at a central point;
step S245: according to the n dimensionality scores of the target person in the key frame to be processed, correspondingly increasing each line segment along the direction far away from the central point;
step S246: sequentially connecting one end of each increased line segment, which is far away from the central point, to obtain a scoring polygon corresponding to each key frame to be processed;
step S247: and selecting a video cover of the video from each key frame to be processed according to the area of each scoring polygon.
Specifically, the n kinds of dimension scores include an action score and a position score, n is greater than or equal to 2, that is, when n is 2, the n kinds of dimension scores include an action score and a position score; when n >2, the n-dimension scores include both the action score and the position score, and may include other scores, such as an expression score, an attention score, and the like of the target person.
Drawing a plurality of line segments, wherein one ends of the plurality of line segments are intersected at a central point O, the length of each line segment is 1, the line segments can be understood as a unit circle with the central point O as the center and the radius of 1, then selecting n radii from the unit circle, wherein the n radii correspond to the n line segments, and the n radii respectively represent the initial values of the action score, the position score and other scores, namely the initial values are 1. The n radii divide the unit circle into a plurality of sectors, and the included angle of each sector can be the same or different.
Assuming that when n is 2, the n kinds of dimensional scores include a motion score and a position score, after a unit circle is drawn, 2 radii are selected from the unit circle, the included angle of the 2 radii is one of a right angle, an obtuse angle and an acute angle, and the lengths of the 2 radii are initial values of the motion score and the position score, respectively, and the included angles of the 2 radii may be preset and are known included angles. Then according to the action score and the position score, the 2 radiuses are correspondingly increased outwards along the radial direction of the unit circle, and the ends, far away from the center of the unit circle, of the 2 increased radiuses are sequentially connected to form a scoring polygon, wherein the formed scoring polygon is a scoring triangle; wherein, since the key frame to be processed has multiple frames, the scoring triangle has multiple numbers. Then, the area of the scoring triangle is calculated through a triangle area formula, and then the comprehensive score of the key frame to be processed is represented by the area of the scoring triangle.
As shown in fig. 12, assuming that when n is 3, the n-dimensional scores include a motion score, a position score, and other scores, and the other scores are expression scores, after drawing a unit circle, 3 radii are selected from the unit circle. The 3 radii represent initial values of the motion score, the position score, and the expression score, and are each 1, that is, OA, OB, and OC are all 1. The included angle between two radiuses in the three radiuses is equal, namely, equal to. AA 'represents the motion score, BB' represents the expression score, and CC 'represents the position score, and the final motion score, expression score, and position score, i.e., OA', OB ', and OC', are obtained by increasing the radii in the direction away from the center point O according to the motion score, position score, and expression score corresponding to each target person. And connecting the A ', the B' and the C 'in sequence to form a scoring polygon, wherein the formed scoring polygon is a scoring triangle, namely a triangle A' B 'C'. Wherein, since the key frame to be processed has multiple frames, the scoring triangle has multiple numbers. And further calculating the area S of each scoring triangle, wherein the area S is calculated according to the following formula:
S＝1/2*OA′OB′sin120°A1/2*OA′OC′sin120°A1/2*OC′OB′sin120°。
in addition, when n >3, the drawn line segment has 4 or more, that is, one end of the line segment of 4 or more intersects the center point O. Furthermore, the number of sides of the score polygon to be drawn is 4 or more, and the score polygon includes, for example, a score quadrangle, a score pentagon, a score hexagon, and the like, based on the n-dimensional score corresponding to each target person. Wherein, since the key frame to be processed has multiple frames, the scoring polygon has multiple. And then, the comprehensive score of each key frame to be processed is determined by calculating the area of the scoring polygon, and the video cover of the video is selected according to the comprehensive score of each key frame to be processed, so that the accuracy and the quality of video cover selection are improved.
Furthermore, the comprehensive score of the key frame to be processed is represented by the area of the scoring polygon, so that the n kinds of dimension scores are closely related to the comprehensive score of the key frame to be processed, the score of the comprehensive score can be influenced by any one of the n kinds of dimension scores when changing, the accuracy and the quality of video cover selection can be improved by determining the comprehensive score based on the area of the scoring polygon, and the selected video cover can better meet the requirements of users.
As shown in fig. 13, the information obtaining module of the video cover selecting apparatus according to the present invention includes:
the information acquisition module 310 is configured to acquire a to-be-processed key frame in a video, and determine an angle of a target person in the to-be-processed key frame, where the to-be-processed key frame has multiple frames;
the action recognition module 320 is configured to recognize a first gesture action of the target person, and acquire a preset picture matched with the first gesture action;
the score calculating module 330 is configured to correct each action angle of the second gesture action of the reference character in the preset picture according to the facing angle, and determine an action score of the first gesture action according to the facing angle and each corrected action angle;
and the cover selecting module 340 is configured to determine a position score of the target person in the to-be-processed key frame, and select a video cover of the video from each to-be-processed key frame according to the action score and the position score.
It should be noted that the video cover selecting device may further include other optional functional modules, so that it may perform other steps involved in the above embodiments. The specific implementation of the video cover selection device of the present invention is substantially the same as that of the above-mentioned video cover selection method, and is not described herein again.
In addition, to achieve the above object, the present invention also provides a terminal device, including: the video cover selection method comprises a memory, a processor and a video cover selection program which is stored on the memory and can run on the processor, wherein the video cover selection program realizes the steps of the video cover selection method when being executed by the processor.
In addition, to achieve the above object, the present invention further provides a storage medium having a video cover selection program stored thereon, wherein the video cover selection program, when executed by a processor, implements the steps of the video cover selection method described above.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A video cover selecting method is characterized by comprising the following steps:
acquiring a key frame to be processed in a video, and determining the facing angle of a target character in the key frame to be processed, wherein the key frame to be processed has multiple frames;
identifying a first posture action of the target person, and acquiring a preset picture matched with the first posture action;
correcting each action angle of the second posture action of the reference character in the preset picture according to the facing angle, and determining the action score of the first posture action according to the facing angle and each corrected action angle;
and determining the position score of the target person in the key frames to be processed, and selecting a video cover of the video from each key frame to be processed according to the action score and the position score.
2. The method according to claim 1, wherein the step of correcting each motion angle of the second gesture motion of the reference character in the preset picture according to the facing angle comprises:
extracting a first action frame point line graph of the second posture action, wherein the first action frame point line graph is formed by connecting lines of all joint points of the reference person;
rotating the first action frame point diagram according to a preset direction, the central axis of the first action frame point diagram and the facing angle to obtain a second action frame point diagram, wherein the central axis is a connecting line of midpoints between a neck joint and a hip joint;
acquiring an included angle between each joint point and the central axis in the second action frame point diagram;
and taking the included angle between each joint point and the central axis as each corrected action angle.
3. The method of claim 1, wherein the step of determining a motion score for the first gesture motion based on the facing angle and the modified respective motion angle comprises:
acquiring a maximum facing angle in facing angles of a target person in each to-be-processed key frame, a maximum action angle in each action angle after correction and a preset weight value corresponding to each action angle after correction;
determining an angle score of each corrected action angle according to the facing angle, the maximum action angle, each corrected action angle and the preset weight value;
determining a comparison score of the first posture action and the corrected second posture action of the target person in each key frame to be processed according to each angle score;
and determining the action score of the first gesture action according to each comparison score.
4. The method of claim 1, wherein the step of determining the target person's position score in the pending keyframe comprises:
determining intersection points of picture golden section points in the video, wherein the number of the intersection points is at least two;
determining golden section point scores of the region where the target character is located in the key frame to be processed relative to the intersection points;
and determining the position score according to the golden section point score of the area where the target person is located relative to each intersection point.
5. The method of claim 4, wherein said step of determining a golden section point score for the region of said target person in said keyframe to be processed with respect to each of said intersection points comprises:
constructing a golden section point frame set, wherein the golden section point frame set comprises first frame numbers of a plurality of golden section point frames and frame number intervals related to the first frame numbers;
when the second frame number of the key frame to be processed is within the frame number interval, determining a plurality of picture scores of the key frame to be processed according to the first frame number, each second frame number, and the maximum value and the minimum value of each frame number interval;
determining the golden section point score from a plurality of the picture scores.
6. The method of claim 5, wherein said step of constructing a golden section frame set comprises:
constructing a two-dimensional coordinate system in the video, selecting at least two of a positive direction of a transverse axis, a negative direction of the transverse axis, a positive direction of a longitudinal axis and a negative direction of the longitudinal axis of the two-dimensional coordinate system as target directions, and marking an intersection point of a golden section point of a picture in the two-dimensional coordinate system according to the target directions;
acquiring a starting frame and an ending frame from each key frame to be processed, and constructing a connecting line segment between the target person contained in the starting frame and the target person contained in the ending frame in the two-dimensional coordinate system;
determining the tangent point of each intersection point and the connecting line segment by taking each intersection point as the circle center, and selecting the video frame positioned at each tangent point as a golden section point frame;
determining a first frame number of each golden section point frame according to the length of each connecting line segment, the distance between each tangent point and the target figure contained in the initial frame, the number of frames of the key frame to be processed and a third frame number of the initial frame;
establishing a frame number interval of a third frame number of the initial frame and a fourth frame number corresponding to the ending frame based on each connecting line segment, and associating each frame number interval with the corresponding first frame number to obtain a plurality of association relations;
and generating the golden section point frame set according to a plurality of incidence relations.
7. The method of claim 1, wherein the step of selecting a video cover of the video from each of the to-be-processed key frames according to the motion score and the position score comprises:
drawing n line segments corresponding to the n kinds of dimensionality scores so as to enable one ends of the n line segments to be intersected at a central point; wherein the n kinds of dimensionality scores comprise the action score and the position score, and n is more than or equal to 2;
according to the n dimensionality scores of the target person in the key frame to be processed, correspondingly increasing each line segment along the direction far away from the central point;
sequentially connecting one end of each increased line segment, which is far away from the central point, to obtain a scoring polygon corresponding to each key frame to be processed;
and selecting a video cover of the video from each key frame to be processed according to the area of each scoring polygon.
8. The utility model provides a device is selected to video cover which characterized in that, device is selected to video cover includes:
the information acquisition module is used for acquiring a key frame to be processed in a video and determining the facing angle of a target person in the key frame to be processed, wherein the key frame to be processed has multiple frames;
the action recognition module is used for recognizing a first posture action of the target person and acquiring a preset picture matched with the first posture action;
the score calculation module is used for correcting each action angle of the second gesture action of the reference character in the preset picture according to the facing angle and determining the action score of the first gesture action according to the facing angle and each corrected action angle;
and the cover selecting module is used for determining the position score of the target character in the key frames to be processed and selecting the video cover of the video from each key frame to be processed according to the action score and the position score.
9. A terminal device, characterized in that the terminal device comprises: a memory, a processor, and a video cover selection program stored on the memory and executable on the processor, the video cover selection program when executed by the processor implementing the steps of the video cover selection method of any one of claims 1-7.
10. A storage medium having stored thereon a video cover selection program, the video cover selection program when executed by a processor implementing the steps of the video cover selection method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210411941.9A CN114827730B (en) | 2022-04-19 | 2022-04-19 | Video cover selection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210411941.9A CN114827730B (en) | 2022-04-19 | 2022-04-19 | Video cover selection method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114827730A true CN114827730A (en) | 2022-07-29 |
| CN114827730B CN114827730B (en) | 2024-05-31 |
Family
ID=82505431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210411941.9A Active CN114827730B (en) | 2022-04-19 | 2022-04-19 | Video cover selection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114827730B (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105809653A (en) * | 2014-12-29 | 2016-07-27 | 深圳Tcl数字技术有限公司 | Image processing method and device |
| CN106658141A (en) * | 2016-11-29 | 2017-05-10 | 维沃移动通信有限公司 | Video processing method and mobile terminal |
| CN109621332A (en) * | 2018-12-29 | 2019-04-16 | 北京卡路里信息技术有限公司 | A kind of attribute determining method, device, equipment and the storage medium of body-building movement |
| CN110245623A (en) * | 2019-06-18 | 2019-09-17 | 重庆大学 | A kind of real time human movement posture correcting method and system |
| CN110446063A (en) * | 2019-07-26 | 2019-11-12 | 腾讯科技（深圳）有限公司 | Generation method, device and the electronic equipment of video cover |
| CN110796077A (en) * | 2019-10-29 | 2020-02-14 | 湖北民族大学 | Attitude motion real-time detection and correction method |
| US20200097729A1 (en) * | 2017-06-16 | 2020-03-26 | Beijing Jingdong Shangke Information Technology Co., Ltd. | Method and apparatus for determining target rotation direction, computer readable medium and electronic device |
| CN110933452A (en) * | 2019-12-02 | 2020-03-27 | 广州酷狗计算机科技有限公司 | Method and device for displaying lovely face gift and storage medium |
| CN111080589A (en) * | 2019-12-05 | 2020-04-28 | 广州极泽科技有限公司 | Target object matching method, system, device and machine readable medium |
| CN111247389A (en) * | 2019-03-29 | 2020-06-05 | 深圳市大疆创新科技有限公司 | Data processing method and device for shooting equipment and image processing equipment |
| JP2020140283A (en) * | 2019-02-27 | 2020-09-03 | 国立大学法人東海国立大学機構 | Information processing device, information processing method, and computer program |
| CN111859022A (en) * | 2020-07-07 | 2020-10-30 | 咪咕文化科技有限公司 | Cover generation method, electronic device and computer-readable storage medium |
| CN112383830A (en) * | 2020-11-06 | 2021-02-19 | 北京小米移动软件有限公司 | Video cover determining method and device and storage medium |
| WO2021129064A1 (en) * | 2019-12-24 | 2021-07-01 | 腾讯科技（深圳）有限公司 | Posture acquisition method and device, and key point coordinate positioning model training method and device |
| KR20210091076A (en) * | 2020-12-17 | 2021-07-21 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Method and apparatus for processing video, electronic device, medium and computer program |
| KR20210091955A (en) * | 2020-01-15 | 2021-07-23 | 금오공과대학교 산학협력단 | Exercise posture correction program |
| CN113327267A (en) * | 2021-07-15 | 2021-08-31 | 东南大学 | Action evaluation method based on monocular RGB video |
| US20220080260A1 (en) * | 2020-09-16 | 2022-03-17 | NEX Team Inc. | Pose comparison systems and methods using mobile computing devices |
-
2022
- 2022-04-19 CN CN202210411941.9A patent/CN114827730B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105809653A (en) * | 2014-12-29 | 2016-07-27 | 深圳Tcl数字技术有限公司 | Image processing method and device |
| CN106658141A (en) * | 2016-11-29 | 2017-05-10 | 维沃移动通信有限公司 | Video processing method and mobile terminal |
| US20200097729A1 (en) * | 2017-06-16 | 2020-03-26 | Beijing Jingdong Shangke Information Technology Co., Ltd. | Method and apparatus for determining target rotation direction, computer readable medium and electronic device |
| CN109621332A (en) * | 2018-12-29 | 2019-04-16 | 北京卡路里信息技术有限公司 | A kind of attribute determining method, device, equipment and the storage medium of body-building movement |
| JP2020140283A (en) * | 2019-02-27 | 2020-09-03 | 国立大学法人東海国立大学機構 | Information processing device, information processing method, and computer program |
| CN111247389A (en) * | 2019-03-29 | 2020-06-05 | 深圳市大疆创新科技有限公司 | Data processing method and device for shooting equipment and image processing equipment |
| CN110245623A (en) * | 2019-06-18 | 2019-09-17 | 重庆大学 | A kind of real time human movement posture correcting method and system |
| CN110446063A (en) * | 2019-07-26 | 2019-11-12 | 腾讯科技（深圳）有限公司 | Generation method, device and the electronic equipment of video cover |
| CN110796077A (en) * | 2019-10-29 | 2020-02-14 | 湖北民族大学 | Attitude motion real-time detection and correction method |
| CN110933452A (en) * | 2019-12-02 | 2020-03-27 | 广州酷狗计算机科技有限公司 | Method and device for displaying lovely face gift and storage medium |
| CN111080589A (en) * | 2019-12-05 | 2020-04-28 | 广州极泽科技有限公司 | Target object matching method, system, device and machine readable medium |
| WO2021129064A1 (en) * | 2019-12-24 | 2021-07-01 | 腾讯科技（深圳）有限公司 | Posture acquisition method and device, and key point coordinate positioning model training method and device |
| KR20210091955A (en) * | 2020-01-15 | 2021-07-23 | 금오공과대학교 산학협력단 | Exercise posture correction program |
| CN111859022A (en) * | 2020-07-07 | 2020-10-30 | 咪咕文化科技有限公司 | Cover generation method, electronic device and computer-readable storage medium |
| US20220080260A1 (en) * | 2020-09-16 | 2022-03-17 | NEX Team Inc. | Pose comparison systems and methods using mobile computing devices |
| CN112383830A (en) * | 2020-11-06 | 2021-02-19 | 北京小米移动软件有限公司 | Video cover determining method and device and storage medium |
| KR20210091076A (en) * | 2020-12-17 | 2021-07-21 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Method and apparatus for processing video, electronic device, medium and computer program |
| CN113327267A (en) * | 2021-07-15 | 2021-08-31 | 东南大学 | Action evaluation method based on monocular RGB video |
Non-Patent Citations (1)
| Title |
|---|
| 石念峰;侯小静;张平;孙西铭;: "姿态估计和跟踪结合的运动视频关键帧提取", 电视技术, no. 1 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114827730B (en) | 2024-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9968845B2 (en) | Image processing device and image processing method, and program | |
| Yang et al. | Faceness-net: Face detection through deep facial part responses | |
| US8126206B2 (en) | Image processing apparatus, image processing method, and program | |
| Lee et al. | Semantic line detection and its applications | |
| US8577099B2 (en) | Method, apparatus, and program for detecting facial characteristic points | |
| Xu et al. | A spine X-ray image retrieval system using partial shape matching | |
| US7369687B2 (en) | Method for extracting face position, program for causing computer to execute the method for extracting face position and apparatus for extracting face position | |
| US7027622B2 (en) | Method for locating face landmarks in an image | |
| US20060029276A1 (en) | Object image detecting apparatus, face image detecting program and face image detecting method | |
| US20150003740A1 (en) | Image processing device, method of controlling image processing device, and program for enabling computer to execute same method | |
| US20100296701A1 (en) | Person tracking method, person tracking apparatus, and person tracking program storage medium | |
| WO1994023390A1 (en) | Apparatus for identifying person | |
| JP2006524394A (en) | Delineation of human contours in images | |
| JPWO2009113231A1 (en) | Image processing apparatus and image processing method | |
| CN110532979A (en) | A kind of 3-D image face identification method and system | |
| WO2009147840A1 (en) | Image retrieval device and image retrieval computer program applied to the image retrieval device | |
| JP2001101429A (en) | Method and device for observing face, and recording medium for face observing processing | |
| KR20010080219A (en) | Image processing apparatus, image processing method, and recording medium | |
| JP2004185611A (en) | Method for extracting face position, program for making the face position extracting method executed by computer, and face position extracting apparatus | |
| JP2003346158A (en) | Face area tracking method by face image | |
| CN111488836A (en) | Face contour correction method, device, equipment and storage medium | |
| CN108876776B (en) | Classification model generation method, fundus image classification method and device | |
| Yan | Ear biometrics in human identification | |
| Kim et al. | Facial landmark extraction scheme based on semantic segmentation | |
| JP2003044853A (en) | Face detection device, face pose detection device, partial image extraction device and methods for the devices |
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 |