WO2023071920A1 - 文字特效展示方法、装置、电子设备及存储介质 - Google Patents

文字特效展示方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2023071920A1
WO2023071920A1 PCT/CN2022/126579 CN2022126579W WO2023071920A1 WO 2023071920 A1 WO2023071920 A1 WO 2023071920A1 CN 2022126579 W CN2022126579 W CN 2022126579W WO 2023071920 A1 WO2023071920 A1 WO 2023071920A1
Authority
WO
WIPO (PCT)
Prior art keywords
text
key
displayed
video image
points
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.)
Ceased
Application number
PCT/CN2022/126579
Other languages
English (en)
French (fr)
Inventor
许坚聪
丁明旭
刘翔
唐雯静
李应鹏
齐立洋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing ByteDance Network Technology Co Ltd
Original Assignee
Beijing ByteDance Network Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing ByteDance Network Technology Co Ltd filed Critical Beijing ByteDance Network Technology Co Ltd
Priority to US18/291,753 priority Critical patent/US20240357210A1/en
Publication of WO2023071920A1 publication Critical patent/WO2023071920A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

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
    • H04N21/47—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
    • 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
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
    • 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
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
    • H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
    • H04N21/4316—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations for displaying supplemental content in a region of the screen, e.g. an advertisement in a separate window
    • 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
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
    • H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
    • 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
    • H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
    • 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
    • H04N21/488—Data services, e.g. news ticker
    • 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]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • 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
    • H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
    • 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
    • H04N21/488—Data services, e.g. news ticker
    • H04N21/4884—Data services, e.g. news ticker for displaying subtitles

Definitions

  • Embodiments of the present disclosure relate to the field of computer technology, for example, to a text special effect display method, device, electronic equipment, and storage medium.
  • the user can enter text in the interactive information input field of the viewing interface to interact with the host, or conduct comments and analysis on the watched video.
  • the interactive text entered by the user will appear on the video viewing interface in the form of a barrage. As more interactive text is displayed, the text content entered earlier will be removed from the current viewing interface and will not be displayed or displayed in a loop. Users cannot personalize the display effect of text special effects, which lacks interest.
  • Embodiments of the present disclosure provide a text special effect display method, device, electronic equipment, and storage medium, which can provide an editable text special effect display method, so that users can control the text special effect display effect when sending text interactive information.
  • Personalized settings increase the fun of text special effects display.
  • the embodiment of the present disclosure provides a text special effect display method, including:
  • the text information to be displayed is dynamically displayed according to the display path.
  • the embodiment of the present disclosure also provides a text special effect display device, including:
  • the text special effect display data acquisition module is configured to obtain a video image displaying the text information to be displayed in response to determining that the text information to be displayed and the text display parameters have been obtained;
  • the text special effect display path determination module is configured to identify the key position points of the target object in the video image, and confirm the display path of the text to be displayed based on the key position points;
  • the text special effect display module is configured to dynamically display the text information to be displayed according to the display path according to the text display parameters.
  • an embodiment of the present disclosure further provides an electronic device, and the electronic device includes:
  • processors one or more processors
  • storage means configured to store one or more programs
  • the one or more processors When the one or more programs are executed by the one or more processors, the one or more processors are made to implement the method for displaying special text effects as described in any one of the embodiments of the present disclosure.
  • the embodiments of the present disclosure also provide a storage medium containing computer-executable instructions, which are configured to execute the text special effects described in any one of the embodiments of the present disclosure when executed by a computer processor. Show method.
  • FIG. 1 is a schematic flowchart of a text special effect display method provided by an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram of a target object and multiple location points provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic flowchart of a text special effect display method provided by another embodiment of the present disclosure.
  • FIG. 4 is a schematic flowchart of a text special effect display method provided by another embodiment of the present disclosure.
  • FIG. 5 is a schematic flowchart of a text special effect display method provided by another embodiment of the present disclosure.
  • Fig. 6 is a schematic diagram of the overall necessary key positions of a standard portrait model provided by an embodiment of the present disclosure
  • Fig. 7 is a schematic diagram of necessary key positions of the upper body of a human body image provided by an embodiment of the present disclosure
  • Fig. 8 is a schematic diagram of key points of contour expansion provided by an embodiment of the present disclosure.
  • Fig. 9 is a schematic diagram of key points of contour expansion after supplementation provided by an embodiment of the present disclosure.
  • FIG. 10 is a schematic diagram of a fitting curve of a display path provided by an embodiment of the present disclosure.
  • FIG. 11 is a schematic flow chart of calculating a feature position using a Newton iterative algorithm provided by an embodiment of the present disclosure
  • Fig. 12 is a schematic structural diagram of a text special effect display device provided by an embodiment of the present disclosure.
  • FIG. 13 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • the term “comprise” and its variations are open-ended, ie “including but not limited to”.
  • the term “based on” is “based at least in part on”.
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one further embodiment”; the term “some embodiments” means “at least some embodiments.” Relevant definitions of other terms will be given in the description below.
  • FIG. 1 is a schematic flowchart of a method for displaying special text effects provided by an embodiment of the present disclosure.
  • the embodiment of the present disclosure is applicable to displaying special text effects in video images.
  • the method can be executed by a text special effect display device, which can be implemented in the form of software and/or hardware, and which can be configured in electronic equipment, such as a mobile terminal or server equipment.
  • the text special effect display method provided in this embodiment includes:
  • the live viewers or the anchor himself want to interact with the live broadcast through some text, they can enter the text information to be displayed and the parameters of the text display in the text interaction window of the live broadcast client. Or when the user wishes to interact with the plot content when watching short videos, long videos and other variety shows or film and television series, he can also input the text information to be displayed and the text display parameters in the text interaction window of the video client interface.
  • the text information to be displayed is a text object to be rendered with special effects.
  • the parameters of the text display are the personalized settings of the rules for special effect rendering of the text to be displayed, for example, the number of words, font, font size, color, interval between multiple texts, text life cycle (special effect display time), etc. parameter.
  • the text life cycle refers to the time from appearance to disappearance of a word in text effects, which determines the speed of text movement.
  • the live broadcast or video application client When the live broadcast or video application client receives the text information to be displayed and the text display parameters, it indicates that the client needs to perform text rendering, and the client will obtain the video image displaying the text information to be displayed, including the live broadcast screen that is being broadcast Or the video image screen that is being played.
  • the video images are consecutive frames of video images within the duration corresponding to the life cycle of the text to be displayed.
  • image processing will be performed frame by frame to determine the position information of the text to be displayed in each frame of video image.
  • the target object may be a person, an animal or other objects in the video image.
  • the key position points of the target object are the key position points on the target object and corresponding to the morphological features of the target object and the feature points of the target object. For example, the connection points of different joints or parts of the target object.
  • the feature points may be the facial features of the person or animal.
  • information comparison or artificial intelligence image recognition methods can be used to identify target objects in video images.
  • a certain type of object can be preset as the target object, and the determined target object can be selected from the multiple identified target objects. For example, in the live broadcast scene, the default setting of people is target.
  • the user specifies a target object when inputting text information to be displayed, and then only recognizes the target object specified by the user in the video image when performing video image recognition, and continues to perform image processing operations if recognized; If the target object specified by the user is not recognized in the , the text special effect rendering operation process will be stopped. After the target object is recognized, the key position point of the target object will be identified, so as to obtain the key position point information, that is, the coordinate information of the key position point on the display screen of the client.
  • the display path of the text to be displayed is determined according to some key position points.
  • curve fitting is required.
  • the number of key position points at least including all necessary key point.
  • the necessary key position points are the key position points that have a great influence on the fitting results when performing curve fitting.
  • the contour expansion key points corresponding to the key position points can be determined according to the position information of the key position points and the preset contour expansion parameters; thereby performing contour curve fitting based on the contour expansion key points , and use the fitted target contour expansion curve as the final text display path.
  • the contour key point corresponding to the key position point according to the position information of the key position point and the preset contour expansion parameters
  • the contour key point corresponding to the key position point on the contour line of the target object can be determined first; then, On the basis of the position information of the contour key points, the contour expansion distance determined based on the preset contour expansion parameters is superimposed to obtain the position information of the contour expansion key points.
  • the outline expansion key points match the appropriate curve type for fitting, and obtain the target outline expansion curve, which is used as the display path of the text to be displayed when the text special effect is displayed.
  • FIG. 2 is a target object recognized in a video image, and the target object is a table.
  • the solid line rectangle represents the table top, and the two ovals represent the table legs.
  • the black dots marked from 1001-1011 in the solid line area represent all necessary key position points of the target object, and the dots filled with small black dots on the solid line are key position points on the contour line of the target object (necessary key position points ) corresponding to the contour key points, and the dots filled with black dots on the dotted line are the contour expansion key points, and the dotted line is the fitting curve obtained by curve fitting according to the contour expansion key points.
  • the contour key point is based on the positional relationship of the key position points, and the contour key point of the target object is determined according to the aspect ratio of the preset table model and the distance ratio between the key position point and the edge of the table contour. Then, on the position of the contour key point, the contour expansion length in the specified direction is superimposed, and the contour expansion key point can be determined.
  • the contour expansion length in the specified direction can be multiplied by the vector cross product result between the preset contour expansion length and the contour tangent direction vector and the vertical screen-facing vector to obtain the target result.
  • the preset contour expansion length indicates the distance between the expanded contour lines and the contour lines. For example, it is also possible to establish a mapping relationship between the key position points and expansion parameters of the target object and the target object model, and directly generate the corresponding contour expansion key points.
  • the text to be displayed is displayed according to parameters such as font, font size, color, interval between multiple texts, text lifetime (special effect display duration) and other parameters required by text display parameters.
  • the effect of the text special effect display is to move along the display path until the end of the text life cycle.
  • the moving speed of the text can also be determined according to the length of the display path and the duration of the text life cycle.
  • the technical solution of the embodiment of the present disclosure can obtain the text information to be displayed and the text display parameters when a user issues a text special effect display command, and then obtain the video image displaying the text information to be displayed; and identify the target in the video image
  • the technical solution of the embodiment of the present disclosure avoids the situation that the text special effect in the video screen cannot be personalized, and realizes an editable text special effect display mode, so that the user can display the text special effect when sending text interactive information Make personalized settings to increase the fun of text special effect display.
  • Embodiments of the present disclosure may be combined with multiple exemplary solutions in the text special effect display method provided in the above embodiments.
  • the text special effect display method provided in this embodiment describes the process of supplementing key position points.
  • FIG. 3 is a schematic flowchart of a text special effect display method provided by another embodiment of the present disclosure. As shown in Figure 3, the text special effect display method provided in this embodiment includes:
  • the live viewers or the anchor himself want to interact with the live broadcast through some text, they can enter the text information to be displayed and the parameters of the text display in the text interaction window of the live broadcast client. Or when the user wishes to interact with the plot content when watching short videos, long videos and other variety shows or film and television series, he can also input the text information to be displayed and the text display parameters in the text interaction window of the video client interface.
  • the text information to be displayed is a text object to be rendered with special effects.
  • the parameters of the text display are the personalized settings of the rules for special effect rendering of the text to be displayed, for example, the number of words, font, font size, color, interval between multiple texts, text life cycle (special effect display time), etc. parameter.
  • the text life cycle refers to the time from appearance to disappearance of a word in text effects, which determines the speed of text movement.
  • the live broadcast or video application client When the live broadcast or video application client receives the text information to be displayed and the text display parameters, it indicates that the client needs to perform text rendering, and the client will obtain the video image displaying the text information to be displayed, including the live broadcast screen that is being broadcast Or the video image screen that is being played.
  • the video images are consecutive frames of video images within the duration corresponding to the life cycle of the text to be displayed.
  • image processing will be performed frame by frame to determine the position information of the text to be displayed in each frame of video image.
  • the integrity of the key position points will be checked to check whether the identified key position points contain all the necessary key position points.
  • the necessary key position points are the key position points that have a great influence on the fitting results when performing curve fitting.
  • the key point for determining whether the unrecognized necessary key position points can be supplemented is whether all the preset reference key position points are included in the identified key position points.
  • the preset datum key position point is a part of the necessary key position point, and it is the key point that the non-datum key position point can refer to for setting.
  • anti-shake processing is performed on the identified key points before determining the contour expansion key points corresponding to the key points.
  • the anti-shake operation can be performed by means of median filtering or mean filtering. Taking the median filter as an example, the median value of the position information of the key position points in the continuous number (such as three frames) of video images can be respectively taken as the position information of the key position points in the current video image to filter out noise and jitter.
  • the key position points include all preset reference key position points, according to the position information of the preset reference key position points in the key position points and the size ratio of the standard reference model of the target object, supplement Necessary key position points not included in the key position points.
  • the contour line of the target object can be determined first according to the preset model ratio of the target object.
  • Contour key points corresponding to the key position points are superimposed to obtain the position information of the contour expansion key points.
  • the outline expansion key points match the appropriate curve type for fitting, and obtain the target outline expansion curve, which is used as the display path of the text to be displayed when the text special effect is displayed.
  • the fitting curve is smooth at the first contour expansion key point at the start and the last contour expansion key point at the end point.
  • This requires a certain linear relationship between the added contour expansion key point and its adjacent two contour expansion key points, that is, keep the added contour expansion key point and its adjacent two contour expansion key points on the same straight line.
  • the correlation coefficient of the linear relationship can be set according to the characteristics of the fitting curve, or set in a random number manner. Then, contour curve fitting is performed based on the supplemented contour expansion key points, and the target contour expansion curve is obtained as a display path.
  • the display path of the text to be displayed is confirmed based on the key position points after completion; finally, according to the text display parameters, the text information to be displayed is dynamically displayed according to the display path, forming a dynamic display of the text to be displayed around the outline of the target object text effects.
  • the technical solution of the embodiment of the present disclosure avoids the situation that the special effects of text in the video screen cannot be personalized, and the problem that the necessary key points are missing during the processing of special effects of text, and realizes an editable display method of special effects of text, so that When users send text interactive information, they can personalize the display effect of text special effects to increase the interest of text special effect display. Even under the condition of incomplete identification of key positions, text special effects can still be processed.
  • Embodiments of the present disclosure may be combined with multiple exemplary solutions in the text special effect display method provided in the above embodiments.
  • the method for displaying text with special effects provided in this embodiment describes the process of displaying text according to a display path.
  • FIG. 4 is a schematic flowchart of a text special effect display method provided by another embodiment of the present disclosure. As shown in Figure 4, the text special effect display method provided in this embodiment includes:
  • the target object may move in different frames of video images, for example, in consecutive video image frames, the target object is getting closer to the lens, then the target object will become larger, and the curve showing the path will also become longer . Therefore, the moving process of the text to be displayed on the display path is uneven.
  • the text feature position information can be transmitted in two adjacent frames of video images. Since the target object in the video is constantly changing, the position of the text in the human eye is generally set with reference to a certain feature point, and the position of the feature point in the current video image can be kept visually consistent with the position in the previous frame of video image. position invariance. Therefore, a concept of feature location is introduced here.
  • the feature position represents the position of each text on the curve segment between two silhouette expansion keys that lie on the display path.
  • the path position represents the length of the curved path that each character moves on the display path.
  • the characteristic position of the text on the screen can be represented by CN(n, t), which means that the position of the Nth character is located on the curve segment of the contour expansion key point P(n) and the contour expansion key point P(n+1), t
  • the value range of t is 0-1, indicating the degree to which the position of the nth character is close to the outline expansion key point P(n) or the outline expansion key point P(n+1).
  • the path position indicates the length of the curved path that the Nth character travels from the starting point P1 in the outline expansion key point, which can be represented by LN.
  • the path position is introduced to ensure the visual speed invariance of text movement.
  • LN(n, t) can be used to represent the curve length corresponding to the movement of the Nth word from the feature position CN(n, 0) to CN(n, t);
  • L(n, m) can represent the curve length of Pn-m , that is, the length of the curve between the key point n of contour expansion and the key point m of contour expansion;
  • L(n) represents L(n, n+1), which is the curve between the key point n of contour expansion and the key point n+1 of contour expansion length.
  • the moving speed of the text to be displayed is determined according to the text life cycle in the text display parameters and the curve length of the display path.
  • the curve length is the length from the first contour expansion key point to the last contour expansion key point. Divide the length of the curve by the text lifetime to determine the speed of the text.
  • the feature position of the first character in the text to be displayed in the previous frame of video image when the previous frame is not empty, directly obtain the feature position; if the current video image is the first frame of video image, then the previous frame If the frame is empty, the feature position of the first character in the text to be displayed in the previous frame of the video image is recorded as CN(1, 0), indicating that the first character is at the position of the key point of the first outline expansion , which is equivalent to the starting point of the dynamic display of text effects. Then, the path position of the first character in the current video image can be calculated according to the characteristic position of the first character among the characters to be displayed in the previous frame of video image.
  • the preset curve integration method can be used first to perform integral calculation on the fitting curve of the display path based on the characteristic position of the first character in the previous frame of video image, and determine the corresponding position of the first character in the current video image.
  • the integral method using the preset curve can be the Gauss-Legend integral algorithm. This method is a numerical algorithm commonly used in computers to solve integrals. Point calculation result.
  • the text display interval between each text in the text to be displayed and the first text can be superimposed on the basis of the path position of the first text in the current video image, and the distance between each text in the text to be displayed is determined in the current video image. path location.
  • S340 Calculate the characteristic position of each character in the current video image according to the path position of each character in the to-be-displayed characters in the current video image.
  • the characteristic position is equivalent to a point on the display path curve, so the path position of each character in the current video image can be determined by solving the solution of the curve.
  • a Newton iteration algorithm may be used to calculate the feature position of each character. Newton's iterative method is a common method for finding approximate roots of equations. Compared with finding exact roots, Newton's iterative method has the advantages of reasonable calculation amount and satisfactory solution accuracy.
  • the number of Newton iterations is usually set to 3. Firstly, according to the path position of each character in the current video image, it is determined which two contour expansion key points on the display path curve the path position is in. Then, bring the curve parameters of the display path into the Newton iteration function, and iteratively solve according to the preset number of Newton iterations, and finally obtain the characteristic position of each character in the current video image.
  • S350 Determine the screen position of each character according to the characteristic position of each character in the current video image.
  • contour expansion curve fitting is carried out according to the screen position of each contour expansion key point, then the output of the fitting curve is the screen position.
  • the position information of t, the contour expansion key point P(n) and one or more adjacent contour expansion key points into the display path curve to obtain The screen position of the Nth text.
  • the position information of the contour expansion key point P(n) and one or more adjacent contour expansion key points input to the display path curve is consistent with the conditions when the display path curve is fitted.
  • the position information input into the display path curve is P(n-1), The position information of four contour expansion key points P(n), P(n+1) and P(n+2).
  • the text to be displayed can be rendered at the screen position of each text according to the text font and font size in the text display parameters; then, the rendering effect of each text is superimposed on the corresponding video image for display.
  • the video image is rendered before the text is rendered.
  • the technical solution of the embodiment of the present disclosure introduces the characteristic position and path position of the characters in the video image, and when determining the movement process of the characters to be displayed, according to the position of each character in the previous frame of the video image
  • the feature position determines its path position in the current video image, and then converts the path position into a feature position in the current video image, and then determines the screen position of each character. It can avoid the uneven change of the text rendering dynamic effect caused by the change of the target object in different frames of video images, and optimize the rendering effect of the text to be displayed.
  • a dynamic display text effect is formed in which the text to be displayed moves at a constant speed around the outline of the target object.
  • the technical solution of the embodiment of the present disclosure avoids the situation that the text special effect in the video screen cannot be personalized, and the problem that the target object changes in different video frames, and realizes an editable text special effect display mode, which enables the user to send text When interacting with information, it is possible to personalize the display effect of text special effects to increase the interest of text special effect display.
  • Embodiments of the present disclosure may be combined with multiple exemplary solutions in the text special effect display method provided in the above embodiments.
  • the method for displaying text with special effects provided in this embodiment describes the process of displaying text according to the contour curve path of the portrait when the target object is a portrait.
  • FIG. 5 is a schematic flowchart of a text special effect display method provided by another embodiment of the present disclosure. As shown in Figure 5, the text special effect display method provided in this embodiment includes:
  • the target object is a person image
  • the process of dynamically displaying the text to be displayed above the outline of the human body can be realized. It can be applied to user interaction in live broadcast scenarios, or other video interaction scenarios.
  • FIG. 6 shows a two-dimensional human skeleton key point model, including 0-17 key points in the model.
  • a three-dimensional human skeleton key point model can also be used.
  • the reason for using a two-dimensional human skeleton key point model rather than a three-dimensional human skeleton key point model is because the accuracy of the three-dimensional human skeleton key point model and The stability is not as good as the two-dimensional human skeleton key point model, and the two-dimensional human skeleton key point model already meets the requirements of special effects.
  • the process of determining all necessary key position points of the person image is described.
  • the set of necessary key position points is: [0, 1, 2, 5, 14, 15, 16, 17]. Because some of the characters in the video image are sometimes outside the video image, the necessary key points identified by the image algorithm are incomplete. Therefore, it is necessary to check whether the acquired necessary key points are missing. If they are missing, you need to follow the preset strategy. make up. For example, some preset reference key position points near the faces are selected, and the default positions of other necessary key position points are calculated based on the ratio of the standard portrait.
  • the preset reference key position point in this embodiment is [0, 1, 14, 15], point 0 is taken as the coordinate origin, the direction from point 0-1 is the direction of the vertical axis, and the direction from point 14-15 is the direction of the horizontal axis
  • the specific calculation formula of the a-th key point is as follows (the value range of a is the serial number of the necessary key position point in the set of necessary key position points):
  • B(a) represents the screen position of the key point of the ath person, that is, the position information obtained when the key point is identified
  • x(a) and y(a) are respectively the abscissa of point a in the reference coordinate system axis and ordinate coordinates.
  • x(a) and y(a) can be pre-calculated based on the position information of the known key position points and the proportion of the key point model of the human skeleton.
  • the coordinate calculation results of the necessary key position points in the reference coordinate system are as follows:
  • bringing the coordinate values in the above table into the key point screen position calculation formula can determine the supplementary screen position information of the necessary key position points.
  • a simple median filter can be used to take the median of the key point position components of three consecutive frames as the position component of the current frame to filter out noise and jitter.
  • other filtering methods may also be used.
  • the contour expansion key points generally select several key position points corresponding to the necessary key position points, usually the position points reflecting the overall contour and characteristics of the person image.
  • the selection of key points for contour expansion of the task image can refer to key points P1-P9 of contour expansion shown in FIG. 8 .
  • the position calculation of dilated keypoints in each round relies on the contour keypoints on the contour line of the human body image.
  • P(n) is the position information of the nth contour expansion key point, that is, the screen coordinate position
  • O(a) is the position information of each necessary key position point on the contour line of the human body, which can be calculated according to the position information of the necessary key position point
  • the distance between the location information and the necessary key location points, and the ratio of the standard portrait to determine the specific value, or the calculation rules can be pre-set based on the characteristics of the portrait.
  • the calculation rules only need to meet the visual effect that fits the outline of the human body, and the preferred choice is simple.
  • length is the length of the contour expansion, which indicates the distance between the contour expansion curve and the human body
  • cross() is the vector cross product function
  • T(n) is the tangential direction of the contour line
  • forward is the vector facing inwards vertically on the screen, here is (0, 0, 1).
  • the values of O(a) and T(n) determine the shape of the contour expansion curve, and the length determines the contour size.
  • the numerical calculation of O(a) corresponding to each contour key point follows the calculation rules in the following table:
  • distance() represents the distance function between two points.
  • P0 and P10 must conform to a certain linear relationship with the key points of the original contour, so that the fitting curve can be smoothed at the initial P1 and the end point P9, that is, keep P2-3-0 and P8-9-10 on the same straight line superior.
  • the specific calculation relationship between P0 and P10 can be calculated as follows:
  • the above calculation relationship can be determined by setting multiple sets of linear relationship parameters in advance, respectively obtaining multiple sets of linear fitting results, and determining the final calculation relationship according to the effect of curve fitting. For example, in this embodiment, after determining the final key point of contour expansion after supplementation, CatmullRom spline curve is used for linear fitting.
  • the calculation code is as follows, where p0, p1, p2 and p3 are respectively Corresponding to 4 input points, t ranges from 0-1, a, b and c are known curve fitting parameters, so the return value is the screen position.
  • the finally obtained fitting curve is shown by the dotted line in FIG. 10 , wherein the curve segment P1-P9 is a dynamic display path of the text to be displayed.
  • the target object may move in different frames of video images, for example, in consecutive video image frames, the target object is getting closer to the lens, then the target object will become larger, and the curve showing the path will also become longer . Therefore, the moving process of the text to be displayed on the display path is uneven.
  • the text feature position information can be transmitted in two adjacent frames of video images. Since the target object in the video is constantly changing, the position of the text in the human eye is generally set with reference to a certain feature point, and the position of the feature point in the current video image can be kept visually consistent with the position in the previous frame of video image. position invariance. Therefore, a concept of feature location is introduced here.
  • the feature position represents the position of each text on the curve segment between two silhouette expansion keys that lie on the display path.
  • the path position represents the length of the curved path that each character moves on the display path.
  • the characteristic position of the text on the screen can be represented by CN(n, t), which means that the position of the Nth character is located on the curve segment of the contour expansion key point P(n) and the contour expansion key point P(n+1), t
  • the value range of t is 0-1, indicating the degree to which the position of the nth character is close to the outline expansion key point P(n) or the outline expansion key point P(n+1).
  • the path position indicates the length of the curved path that the Nth character travels from the starting point P1 in the outline expansion key point, which can be represented by LN.
  • the path position is introduced to ensure the visual speed invariance of text movement.
  • LN(n, t) can be used to represent the curve length corresponding to the movement of the Nth word from the feature position CN(n, 0) to CN(n, t);
  • L(n, m) can represent the curve length of Pn-m , that is, the length of the curve between the key point n of contour expansion and the key point m of contour expansion;
  • L(n) represents L(n, n+1), which is the curve between the key point n of contour expansion and the key point n+1 of contour expansion length.
  • the moving speed of the text to be displayed is determined according to the text life cycle in the text display parameters and the curve length of the display path.
  • the curve length is the length from the first contour expansion key point to the last contour expansion key point. Divide the length of the curve by the text lifetime to determine the speed of the text.
  • the characteristic position of the first character in the text to be displayed in the previous frame of video image obtains the characteristic position.
  • the previous frame is not empty, directly obtain the characteristic position. If the current video image is the first frame of video image, then If the frame is empty, the feature position of the first character in the text to be displayed in the previous frame of the video image is recorded as CN(1, 0), indicating that the first character is at the position of the key point of the first outline expansion , which is equivalent to the starting point of the dynamic display of text effects. Then, the path position of the first character in the current video image can be calculated according to the characteristic position of the first character among the characters to be displayed in the previous frame of video image.
  • the preset curve integration method can be used first to perform integral calculation on the fitting curve of the display path based on the characteristic position of the first character in the previous frame of video image, and determine the corresponding position of the first character in the current video image.
  • the initial path location for .
  • the character feature position points can be expressed as
  • the parameters corresponding to ⁇ i and xi Gaussler handicap integrals can be selected according to the following table.
  • the path location can be expressed as
  • the moving distance of the first character is determined according to the time interval between the current video image and the previous frame of video image and the moving speed of the text to be displayed; The moving distance is superimposed on the basis of the initial path position in the video image to obtain the path position of the first character in the text to be displayed in the current video image.
  • the text display interval between each text in the text to be displayed and the first text can be superimposed on the basis of the path position of the first text in the current video image, and the distance between each text in the text to be displayed is determined in the current video image. path location.
  • the feature position is equivalent to a point on the display path curve
  • the feature position point corresponding to the path position of each character in the current video image in the current video image can be determined by solving the solution of the curve.
  • a Newton iteration algorithm may be used to calculate the feature position of each character. Newton's iterative method is a common method for finding approximate roots of equations. Compared with finding exact roots, Newton's iterative method has the advantages of reasonable calculation amount and satisfactory solution accuracy.
  • the number of Newton iterations is usually set to 3. Firstly, according to the path position of each character in the current video image, it is determined which two contour expansion key points on the display path curve the path position is in. Then, bring the curve parameters of the display path into the Newton iteration function, and iteratively solve according to the preset number of Newton iterations, and finally obtain the characteristic position of each character in the current video image.
  • the process of calculating the feature position may refer to the flow chart shown in FIG. 11 . Assign the path position of the Nth word to len, and then start from P1 to determine which two contour expansion key points the Nth word falls in.
  • the curve fitting is carried out according to the screen position of the contour expansion key point, then the output of the fitting curve is the screen position.
  • the feature position CN(n, t) of the Nth character input the position information of t, the contour expansion key point P(n) and one or more adjacent contour expansion key points into the display path curve to obtain The screen position of the Nth text.
  • SN (x, y) is the screen position of the Nth word.
  • the text to be displayed can be rendered at the screen position of each text according to the text font and font size in the text display parameters; then, the rendering effect of each text is superimposed on the corresponding video image for display.
  • the video image is rendered before the text is rendered.
  • the text special effect display method is applied to the scene where the target object is a human body image, firstly identify the necessary key points in the video image, and supplement the unrecognized necessary points. Key position points, and then gradually fit the text display path curve, and then according to the curve fitting results, introduce the characteristic position and path position of the text in the video image, when determining the movement process of the text to be displayed, according to the position of each text.
  • the characteristic position of the previous frame video image determines its path position in the current video image, and then converts the path position into the characteristic position in the current video image, and then determines the screen position of each character.
  • a dynamic display text effect is formed in which the text to be displayed moves at a constant speed around the outline of the portrait.
  • the technical solution of the embodiment of the present disclosure avoids the situation that the text special effect in the video screen cannot be personalized, and the problem that the target object changes in different video frames, and realizes an editable text special effect display mode, which enables the user to send text When interacting with information, it is possible to personalize the display effect of text special effects to increase the interest of text special effect display.
  • Fig. 12 is a schematic structural diagram of a text special effect display device provided by an embodiment of the present disclosure.
  • the text special effect display device provided in this embodiment is suitable for displaying text special effects in video images.
  • the text special effect display device includes: a text special effect display data acquisition module 510 , a text special effect display path determination module 520 and a text special effect display module 530 .
  • the text special effect display data acquisition module 510 is configured to obtain and display the video image of the text information to be displayed when the text information to be displayed and text display parameters are obtained;
  • the text special effect display path determination module 520 is configured to identify the text information to be displayed.
  • the text special effect display module 530 is set to display the text information according to the text display parameter The display path is dynamically displayed.
  • the technical solution of the embodiment of the present disclosure avoids the situation that the text special effect in the video screen cannot be personalized, and realizes an editable text special effect display mode, so that the user can display the text special effect when sending text interactive information Make personalized settings to increase the fun of text special effect display.
  • the character special effect display path determination module 520 includes a contour expansion key point determination submodule and a path curve fitting submodule; wherein,
  • the contour expansion key point determination submodule is configured to determine the contour expansion corresponding to the key position point according to the position information of the key position point and the preset contour expansion parameters when the key position point includes all necessary key position points key points; a path curve fitting submodule, configured to perform contour curve fitting based on the contour expansion key points, and use the fitted target contour expansion curve as the display path.
  • the text special effect display path determination module 520 also includes a key position point supplement submodule, which is set to:
  • the key position points include all the preset benchmark key position points, according to the position information of the preset benchmark key position points in the key position points and the size ratio of the standard reference model of the target object, supplement the Necessary key position points not included in key position points;
  • contour expansion key point determination submodule is set to:
  • the position information of the key points of contour expansion is obtained by superimposing the contour expansion distance determined based on the preset contour expansion parameters on the basis of the position information of the contour key points.
  • the path curve fitting submodule is set to:
  • Contour curve fitting is performed based on the supplemented contour dilation keypoints.
  • the text special effect display device also includes a key position point information correction module, which is configured to obtain the position information of the key position point in consecutive multiple frames of video images before determining the contour expansion key point corresponding to the key position point The median value in is used as the position information of the key position point.
  • a key position point information correction module configured to obtain the position information of the key position point in consecutive multiple frames of video images before determining the contour expansion key point corresponding to the key position point The median value in is used as the position information of the key position point.
  • the text special effect display module 530 includes: a text path position determination submodule, a text feature position determination submodule, a text screen position determination submodule and a text rendering display submodule; wherein, the text path position determination submodule is set to The text display parameters, the curve of the display path and the characteristic position of the first text in the text to be displayed in the previous frame video image, determine the path position of each text in the current video image in the displayed text, wherein, the feature position represents the position of each character on the curve segment between two outline expansion key points on the display path, and the path position represents the distance of each character moving on the display path.
  • the character position determination submodule is set to calculate the feature position of each character in the current video image according to the path position of each character in the text to be displayed in the current video image;
  • the character screen position determination submodule It is set to determine the screen position of each character according to the characteristic position of each character in the current video image;
  • the character rendering display submodule is set to place the character to be displayed in the video image based on the screen position of each character Perform a rendering display.
  • literal path location determination submodule is set to:
  • literal path location determination submodule is set to:
  • the moving distance is superimposed on the basis of the initial path position to determine the path position of the first character in the current video image.
  • the text rendering display submodule is set to:
  • the rendering effect of each character is superimposed on the video image for display.
  • the target object includes a person image in a video image.
  • the text special effect display device provided in the embodiments of the present disclosure can execute the text special effect display method provided in any embodiment of the present disclosure, and has corresponding functional modules and beneficial effects for executing the method.
  • FIG. 13 it shows a schematic structural diagram of an electronic device (such as a terminal device or a server in FIG. 13 ) 600 suitable for implementing an embodiment of the present disclosure.
  • the terminal equipment in the embodiment of the present disclosure may include but not limited to such as mobile phone, notebook computer, digital broadcast receiver, PDA (personal digital assistant), PAD (tablet computer), PMP (portable multimedia player), vehicle terminal (such as mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers and the like.
  • the electronic device shown in FIG. 13 is only an example, and should not limit the functions and scope of use of the embodiments of the present disclosure.
  • the electronic device 600 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 606 is loaded into the program in the random access memory (Random Access Memory, RAM) 603 to execute various appropriate actions and processes.
  • a processing device such as a central processing unit, a graphics processing unit, etc.
  • RAM Random Access Memory
  • various programs and data necessary for the operation of the electronic device 600 are also stored.
  • the processing device 601, ROM 602, and RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O) interface 605 is also connected to the bus 604 .
  • the following devices can be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speaker, vibration an output device 607 such as a computer; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609.
  • the communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While FIG. 13 shows electronic device 600 having various means, it is to be understood that implementing or possessing all of the means shown is not a requirement. More or fewer means may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer readable medium, where the computer program includes program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from a network via communication means 609 , or from storage means 606 , or from ROM 602 .
  • the processing device 601 the above-mentioned functions defined in the text special effect display method of the embodiment of the present disclosure are executed.
  • the electronic device provided by the embodiment of the present disclosure belongs to the same disclosed concept as the text special effect display method provided by the above embodiment.
  • the above embodiment please refer to the above embodiment, and this embodiment has the same features as the above embodiment. beneficial effect.
  • An embodiment of the present disclosure provides a computer storage medium, on which a computer program is stored.
  • the program is executed by a processor, the method for displaying text with special effects provided in the above embodiments is implemented.
  • the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two.
  • a computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof.
  • Computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM) or flash memory (FLASH), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted by any appropriate medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
  • the client and the server can communicate using any currently known or future-developed network protocols such as HTTP (Hyper Text Transfer Protocol, Hypertext Transfer Protocol), and can communicate with any form or medium of digital Data communication (eg, communication network) interconnections.
  • HTTP Hyper Text Transfer Protocol
  • Examples of communication networks include local area networks ("LANs”), wide area networks ("WANs”), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device, or may exist independently without being incorporated into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device:
  • the text information to be displayed is dynamically displayed according to the display path.
  • Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, or combinations thereof, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and Includes conventional procedural programming languages - such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through an Internet service provider). Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider such as AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions for implementing specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments described in the present disclosure may be implemented by software or by hardware. Wherein, the names of the units and modules do not constitute limitations on the units and modules themselves under certain circumstances, for example, the data generating module may also be described as a "video data generating module".
  • exemplary types of hardware logic components include: Field Programmable Gate Arrays (Field Programmable Gate Arrays, FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (Application Specific Standard Parts, ASSP), System on Chip (System on Chip, SOC), Complex Programmable Logic Device (CPLD), etc.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • Example 1 provides a text special effect display method, the method includes:
  • the text information to be displayed is dynamically displayed according to the display path.
  • Example 2 provides a text special effect display method, which also includes:
  • confirming the display path of the text to be displayed based on the key position point includes:
  • the contour expansion key points corresponding to the key position points according to the position information of the key position points and preset contour expansion parameters
  • Contour curve fitting is performed based on the contour expansion key points, and the fitted target contour expansion curve is used as the display path.
  • Example 3 provides a text special effect display method, which also includes:
  • the method further includes:
  • the key position points include all the preset benchmark key position points, according to the position information of the preset benchmark key position points in the key position points and the size ratio of the standard reference model of the target object, supplement the Necessary key position points not included in key position points;
  • Example 4 provides a text special effect display method, which also includes:
  • determining the contour expansion key point corresponding to the key position point according to the position information of the key position point and the preset contour expansion parameters includes:
  • the position information of the key points of contour expansion is obtained by superimposing the contour expansion distance determined based on the preset contour expansion parameters on the basis of the position information of the contour key points.
  • Example 5 provides a text special effect display method, which also includes:
  • the contour curve fitting based on the contour expansion key points includes:
  • Contour curve fitting is performed based on the supplemented contour dilation keypoints.
  • Example 6 provides a text special effect display method, which also includes:
  • the method before determining the contour expansion key point corresponding to the key position point, the method further includes:
  • Example 7 provides a text special effect display method, which also includes:
  • the text information to be displayed is dynamically displayed according to the display path, and the method further includes:
  • the curve of the display path and the characteristic position of the first text in the text to be displayed in the previous frame video image determine the path of each text in the displayed text in the current video image position, wherein the feature position represents the position of each character on the curve segment between two outline expansion key points on the display path, and the path position represents the position of each character on the display path the length of the moved curve path;
  • the text to be displayed is rendered and displayed in the video image based on the screen position of each text.
  • Example 8 provides a text special effect display method, which also includes:
  • each character in the displayed characters is at the current The path location of the video image, including:
  • Example 9 provides a text special effect display method, which also includes:
  • determining the path position of the first text in the current video image includes:
  • the moving distance is superimposed on the basis of the initial path position to determine the path position of the first character in the current video image.
  • Example 10 provides a text special effect display method, which also includes:
  • rendering and displaying the text to be displayed in a video image based on the screen position of each text includes:
  • the rendering effect of each character is superimposed on the video image for display.
  • Example 11 provides a text special effect display method, which also includes:
  • the target object includes a person image in a video image.
  • Example 12 provides a text special effect display device, including:
  • the text special effect display data acquisition module is configured to obtain and display the video image of the text information to be displayed when the text information to be displayed and the text display parameters are obtained;
  • the text special effect display path determination module is configured to identify the key position points of the target object in the video image, and confirm the display path of the text to be displayed based on the key position points;
  • the text special effect display module is configured to dynamically display the text information to be displayed according to the display path according to the text display parameters.
  • Example 13 provides a text special effect display device, further comprising:
  • the text special effect display path determination module specifically includes a contour expansion key point determination sub-module and a path curve fitting sub-module; wherein,
  • the contour expansion key point determination submodule is configured to determine the contour expansion corresponding to the key position point according to the position information of the key position point and the preset contour expansion parameters when the key position point includes all necessary key position points key points; a path curve fitting submodule, configured to perform contour curve fitting based on the contour expansion key points, and use the fitted target contour expansion curve as the display path.
  • Example Fourteen provides a text special effect display device, further comprising:
  • the text special effect display path determination module also includes a key position point supplementary sub-module, which is set as:
  • the key position points include all the preset benchmark key position points, according to the position information of the preset benchmark key position points in the key position points and the size ratio of the standard reference model of the target object, supplement the Necessary key position points not included in key position points;
  • Example 15 provides a text special effect display device, further comprising:
  • contour expansion key point determination submodule is set to:
  • the position information of the key points of contour expansion is obtained by superimposing the contour expansion distance determined based on the preset contour expansion parameters on the basis of the position information of the contour key points.
  • Example 16 provides a text special effect display device, further comprising:
  • the path curve fitting submodule is set to:
  • Contour curve fitting is performed based on the supplemented contour dilation keypoints.
  • Example 17 provides a text special effect display device, further comprising:
  • the text special effect display device also includes a key position point information correction module, which is configured to obtain the position information of the key position point in consecutive multiple frames of video images before determining the contour expansion key point corresponding to the key position point The median value in is used as the position information of the key position point.
  • a key position point information correction module configured to obtain the position information of the key position point in consecutive multiple frames of video images before determining the contour expansion key point corresponding to the key position point The median value in is used as the position information of the key position point.
  • Example Eighteen provides a text special effect display device, further comprising:
  • the text special effect display module includes: a text path position determination submodule, a text feature position determination submodule, a text screen position determination submodule and a text rendering display submodule; wherein, the text path position determination submodule is set to Display parameters, the curve of the display path and the characteristic position of the first character in the text to be displayed in the previous frame video image, determine the path position of each character in the current video image in the displayed text, wherein, The feature position represents the position of each character on the curve segment between the two outline expansion key points on the display path, and the path position represents the curved path that each character moves on the display path Length; character feature position determination submodule is set to calculate the feature position of each character in the current video image according to the path position of each character in the current video image in the text to be displayed; the character screen position determination submodule is set to Determine the screen position of each character according to the characteristic position of each character in the current video image; the character rendering and display submodule is configured to render the character to be displayed in the video image
  • Example 19 provides a text special effect display device, further comprising:
  • literal path location determination submodule is set to:
  • Example 20 provides a text special effect display device, further comprising:
  • literal path location determination submodule is set to:
  • the moving distance is superimposed on the basis of the initial path position to determine the path position of the first character in the current video image.
  • Example 21 provides a text special effect display device, further comprising:
  • the text rendering display submodule is set to:
  • the rendering effect of each character is superimposed on the video image for display.
  • Example 22 provides a text special effect display device, further comprising:
  • the target object includes a person image in a video image.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Human Computer Interaction (AREA)
  • Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Controls And Circuits For Display Device (AREA)

Abstract

本公开实施例公开了一种文字特效展示方法、装置、电子设备及存储介质，其中，方法包括：响应于确定获取到待显示文字信息和文字显示参数，获取显示所述待显示文字信息的视频图像；识别所述视频图像中目标对象的关键位置点，并基于所述关键位置点确认所述待显示文字的显示路径；根据所述文字显示参数，将所述待显示文字信息按照所述显示路径进行动态展示。

Description

文字特效展示方法、装置、电子设备及存储介质
本申请要求在2021年10月26日提交中国专利局、申请号为202111250376.4的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本公开实施例涉及计算机技术领域，例如涉及一种文字特效展示方法、装置、电子设备及存储介质。
背景技术
通常，在用户在观看直播或者视频的过程中，可以在观看界面的互动信息输入栏中输入文字与主播进行互动，或者是对观看的视频进行评论分析等互动。用户输入的互动文字会以弹幕的形式出现在视频观看界面上，随着更多互动文字的展示，较先输入的文字内容就会在当前的观看界面上移出不再展示或者循环展示。用户不能个性化的设置文字特效的展示效果，缺乏趣味性。
发明内容
本公开实施例提供了一种文字特效展示方法、装置、电子设备及存储介质，能够提供一种可编辑的文字特效展示方式，使用户在发送文字互动信息时，能够对文字特效的展示效果进行个性化的设置，增加文字特效展示的趣味性。
第一方面，本公开实施例提供了一种文字特效展示方法，包括：
响应于确定获取到待显示文字信息和文字显示参数，获取显示所述待显示文字信息的视频图像；
识别所述视频图像中目标对象的关键位置点，并基于所述关键位置点确认所述待显示文字的显示路径；
根据所述文字显示参数，将所述待显示文字信息按照所述显示路径进行动态展示。
第二方面，本公开实施例还提供了一种文字特效展示装置，包括：
文字特效展示数据获取模块，设置为响应于确定获取到待显示文字信息和文字显示参数，获取显示所述待显示文字信息的视频图像；
文字特效展示路径确定模块，设置为识别所述视频图像中目标对象的关键位置点，并基于所述关键位置点确认所述待显示文字的显示路径；
文字特效展示模块，设置为根据所述文字显示参数，将所述待显示文字信息按照所述显示路径进行动态展示。
第三方面，本公开实施例还提供了一种电子设备，所述电子设备包括：
一个或多个处理器；
存储装置，设置为存储一个或多个程序，
当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如本公开实施例任一所述的文字特效展示方法。
第四方面，本公开实施例还提供了一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时设置为执行如本公开实施例任一所述的文字特效展示方法。
附图说明
贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，原件和元素不一定按照比例绘制。
图1为本公开一实施例所提供的一种文字特效展示方法的流程示意图；
图2为本公开一实施例所提供的一种目标对象与多个位置点的是示意图；
图3为本公开另一实施例所提供的一种文字特效展示方法的流程示意图；
图4为本公开另一实施例所提供的一种文字特效展示方法的流程示意图；
图5为本公开另一实施例所提供的一种文字特效展示方法的流程示意图；
图6为本公开一实施例所提供的一种标准人像模型的整体必要关键位置点示意图；
图7为本公开一实施例所提供的一种人体图像上半身必要关键位置点示意图；
图8为本公开一实施例所提供的一种轮廓扩张关键点示意图；
图9为本公开一实施例所提供的一种补充后轮廓扩张关键点示意图；
图10为本公开一实施例所提供的一种显示路径的拟合曲线示意图；
图11为本公开一实施例所提供的一种采用牛顿迭代算法计算特征位置的流程示意图；
图12为本公开一实施例所提供的一种文字特效展示装置结构示意图；
图13为本公开一实施例所提供的一种电子设备结构示意图。
具体实施方式
应当理解，本公开的方法实施方式中记载的多个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。
本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
图1为本公开一实施例所提供的一种文字特效展示方法流程示意图，本公开实施例适用于在视频图像中展示文字特效的情形。该方法可以由文字特效展示装置来执行，该装置可以通过软件和/或硬件的形式实现，该装置可配置于电子设备中，例如配置于移动终端或服务器设备中。
如图1所示，本实施例提供的文字特效展示方法，包括：
S110、当获取到待显示文字信息和文字显示参数时，获取显示所述待显示文字信息的视频图像。
在直播场景下，当直播观众或者主播本人希望通过一些文字进行直播互动时，可以在直播客户端的文字交互窗口中输入待显示文字信息和文字显示的参数。或者用户在观看短视频、长视频等综艺节目或影视剧集时，希望能与剧情内容产生互动，也可以通过视频客户端界面的文字交互窗口中输入待显示文字信息和文字显示的参数。
其中，待显示文字信息即是要进行特效渲染的文字对象。文字显示的参数即是对待显示文字进行特效渲染的规则的个性化设置，例如，待显示文字的字数、字体、字号、颜色、多个文字之间的间隔、文字生存周期(特效展示时长)等参数。例如，文字生存周期是指在文字特效中，一个字从出现到消失的时间，决定了文字移动的速度感受。
当直播或视频应用客户端，接收到待显示文字信息和文字显示参数时，则表明客户端需要进行文字特效渲染了，客户端会获取显示待显示文字信息的视频图像，包括正在直播的直播画面或者是正在播放的视频图像画面。视频图像是待显示文字的生存周期对应的时长内的连续的每一帧视频图像。接下来便会逐帧进行图像处理，确定待显示文字在每帧视频图像中的位置信息。
S120、识别所述视频图像中目标对象的关键位置点，并基于所述关键位置点确认所述待显示文字的显示路径。
其中，目标对象可以是视频图像中的人、动物或者其他物体。目标对象的关键位置点是在目标对象上，且与目标对象的形态特征相对应的关键位置点以及目标对象的特征点。例如，目标对象不同关节或部位的连接点。当目标对象为人或动物时，特征点可以是人或动物的五官位置点。在进行视频图像内容的识别时，可以采用信息比对或者人工智能的图像识别方法，从而识别视频图像中的目标对象。当视频图像中包含多个目标对象时，可以预先设定某一类对象为目标对象，在识别出的多个目标对象中选择确定的目标对象，例如，在直播场景下，默认将人设置为目标对象。或者，用户在输入待显示文字信息时，指定一个目标对象，然后在进行视频图像识别时，仅在视频图像中识别用户指定的目标对象，如果识别到了便继续进行图像处理操作；如果在视频图像中未识别到用户指定的目标对象，便会停止文字特效渲染操作过程。在识别到目标对象之后，会识别目标对象的关键位置点，从而获取关键位置点信息，即关键位置点在客户端显示屏幕的坐标信息。
例如，由于根据一些关键位置点确定待显示文字的显示路径，需要进行曲线拟合，为了保证曲线拟合结果的准确度，对关键位置点的数量会有一定的要求，至少要包含全部的必要关键位置点。必要关键位置点即是在进行曲线拟合时，对拟合结果影响较大的关键位置点。
当关键位置点包括全部必要关键位置点时，便可以根据关键位置点的位置信息和预设轮廓扩张参数确定与关键位置点对应的轮廓扩张关键点；从而基于轮廓扩张关键点进行轮廓曲线拟合，并将拟合得到的目标轮廓扩张曲线作为最终的文字显示路径。例如，在根据关键位置点的位置信息和预设轮廓扩张参数确定与关键位置点对应的轮廓扩张关键点时，可以先确定目标对象的轮廓线上与关键位置点对应的轮廓关键点；然后，在轮廓关键点的位置信息基础上叠加基于预设轮廓扩张参数确定的轮廓扩张距离，得到所述轮廓扩 张关键点的位置信息。最终，可以根据轮廓扩张关键点，匹配适合的曲线类型进行拟合，得到目标轮廓扩张曲线，作为文字特效展示时待显示文字的显示路径。
示例性的，图2为视频图像中识别到的目标对象，该目标对象为一个桌子。实线矩形表示桌面，两个椭圆形表示桌腿。实线区域内标号从1001-1011的黑色圆点表示该目标对象的全部必要关键位置点，实线上黑色小点填充的圆点为目标对象的轮廓线上与关键位置点(必要关键位置点)对应的轮廓关键点，而虚线上的上黑色小点填充的圆点即为轮廓扩张关键点，该虚线即为根据轮廓扩张关键点进行曲线拟合得到的拟合曲线。
其中，轮廓关键点是基于关键位置点的位置关系，根据预设桌子模型的长宽比例以及关键位置点与桌子轮廓边缘的距离比例确定目标对象的轮廓关键点。然后在轮廓关键点的位置上，叠加在指定方向上的轮廓扩张长度，即可确定轮廓扩张关键点。其中，在本实施例中，指定方向上的轮廓扩张长度可以用预设轮廓扩张长度与轮廓切线方向向量和垂直屏幕朝里的向量间的向量叉乘结果进行数乘，得到目标结果。预设轮廓扩张长度表示扩张轮廓线和轮廓线间的距离大小。例如，还可以建立目标对象的关键位置点及扩展参数，与目标对象模型的映射关系，直接生成相应的轮廓扩张关键点。
S130、根据所述文字显示参数，将所述待显示文字信息按照所述显示路径进行动态展示。
在确定了待显示文字的显示路径值之后，便将待显示文字按照文字显示参数要求的字体、字号、颜色、多个文字之间的间隔、文字生存周期(特效展示时长)等参数进行显示。在连续多帧的视频图像切换过程中，文字特效展示的效果就是沿着显示路径进行移动，直到文字生存周期结束。还可以根据显示路径的长度以及文字生存周期的时长，确定文字的移动速度。本实施例方案可以应用在视频字幕或弹幕显示中的文字特效的个性化设置与展示。
本公开实施例的技术方案，可以通过在有用户发出文字特效显示指令时，获取到待显示文字信息和文字显示参数时，然后获取显示待显示文字信息的视频图像；并的识别视频图像中目标对象的关键位置点，当识别到的关键位置点包含全部必要关键位置点时，确认待显示文字的显示路径；最终根据文字显示参数，将待显示文字信息按照显示路径进行动态展示，形成一种待显示文字围绕目标对象的轮廓进行动态显示的文字特效。本公开实施例的技术方案避免了视频画面中文字特效效果不能个性化设置的情况，实现了一种可编辑的文字特效展示方式，使用户在发送文字互动信息时，能够对文字特效的展示效果进行个性化的设置，增加文字特效展示的趣味性。
本公开实施例与上述实施例中所提供的文字特效展示方法中多个示例方案可以结合。本实施例所提供的文字特效展示方法，描述了对关键位置点进行补充的过程。
图3为本公开另一实施例所提供的一种文字特效展示方法的流程示意图。如图3所示，本实施例提供的文字特效展示方法，包括：
S210、当获取到待显示文字信息和文字显示参数时，获取显示所述待显示文字信息的视频图像。
在直播场景下，当直播观众或者主播本人希望通过一些文字进行直播互动时，可以在直播客户端的文字交互窗口中输入待显示文字信息和文字显示的参数。或者用户在观看短视频、长视频等综艺节目或影视剧集时，希望能与剧情内容产生互动，也可以通过视频客户端界面的文字交互窗口中输入待显示文字信息和文字显示的参数。
其中，待显示文字信息即是要进行特效渲染的文字对象。文字显示的参数即是对待显示文字进行特效渲染的规则的个性化设置，例如，待显示文字的字数、字体、字号、颜色、多个文字之间的间隔、文字生存周期(特效展示时长)等参数。例如，文字生存周期是指在文字特效中，一个字从出现到消失的时间，决定了文字移动的速度感受。
当直播或视频应用客户端，接收到待显示文字信息和文字显示参数时，则表明客户端需要进行文字特效渲染了，客户端会获取显示待显示文字信息的视频图像，包括正在直播的直播画面或者是正在播放的视频图像画面。视频图像是待显示文字的生存周期对应的时长内的连续的每一帧视频图像。接下来便会逐帧进行图像处理，确定待显示文字在每帧视频图像中的位置信息。
S220、识别所述视频图像中目标对象的关键位置点，当所述关键位置点中未包含全部所述必要关键位置点时，确定所述关键位置点中是否包含全部预设基准关键位置点。
为了保证曲线拟合结果的准确度，会对关键位置点的完整性进行检查，查看识别到的关键位置点是否包含全部的必要关键位置点。必要关键位置点即是在进行曲线拟合时，对拟合结果影响较大的关键位置点。当关键位置点中未包含全部必要关键位置点时，需要确定是否可以将未识别到的必要关键位置点进行补充，如果不可以的话，则需要停止文字特效处理过程。
确定是否可以将未识别到的必要关键位置点进行补充的关键点在于，识别到的关键位置点中是否包含全部预设基准关键位置点。预设基准关键位置点是必要关键位置点的一部分，是非基准关键位置点可参考 进行设置的关键点。
例如，为了减少视频或图像算法原因引起文字特效的抖动，在确定与关键位置点对应的轮廓扩张关键点之前，对识别到的关键位置点进行防抖处理。可以采用中值滤波或均值滤波等方式进行防抖操作。以中值滤波为例，可以分别取连续数量(如三帧)视频图像中关键位置点的位置信息的中值作为关键位置点在当前视频图像中的位置信息，过滤掉噪声抖动。
S230、当所述关键位置点中包含全部预设基准关键位置点时，根据所述关键位置点中的预设基准关键位置点的位置信息和所述目标对象的标准参考模型的尺寸比例，补充所述关键位置点中未包含的必要关键位置点。
示例性的，在图2中，在识别到目标对象时，识别出了其中的全部预设基准关键点1001、1003、1004、1008、1009和1011。那么，可以的将必要关键位置点补齐。
例如，可以基于基准关键点中在同一条水平直线上的点和在同一条竖直直线上的点建立一个坐标系，并确定多个基准关键点在该坐标系下的坐标，和多个基准关键点之间的距离。再参考目标对象的预设模型中多个必要关键位置点之间的位置关系，将缺失的必要关键位置点补齐。
S240、根据补充后的关键位置点的位置信息和预设轮廓扩张参数确定与所述关键位置点对应的轮廓扩张关键点。
例如，在根据补充后的关键位置点的位置信息和预设轮廓扩张参数确定与关键位置点对应的轮廓扩张关键点时，可以先依据目标对象的预设模型比例，确定目标对象的轮廓线上与关键位置点对应的轮廓关键点；然后，在轮廓关键点的位置信息基础上叠加基于预设轮廓扩张参数确定的轮廓扩张距离，得到所述轮廓扩张关键点的位置信息。最终，可以根据轮廓扩张关键点，匹配适合的曲线类型进行拟合，得到目标轮廓扩张曲线，作为文字特效展示时待显示文字的显示路径。
S250、基于所述轮廓扩张关键点进行轮廓曲线拟合，并将拟合得到的目标轮廓扩张曲线作为所述显示路径。
为确保拟合曲线在起始的第一个轮廓扩张关键点及终点的最后一个轮廓扩张关键点处是平滑，要在拟合曲线的两端分别增加一个轮廓扩张关键点。这就需要添加的轮廓扩张关键点与其临近的两个轮廓扩张关键点之间符合一定的线性关系，即保持添加的轮廓扩张关键点与其临近的两个轮廓扩张关键点分别在同一直线上。其中，线性关系的相关的系数可以根据拟合曲线的特征进行设置，或者采用随机数的方式进行设置。然后，再基于补充后的轮廓扩张关键点进行轮廓曲线拟合，得到目标轮廓扩张曲线，作为显示路径。
S260、根据所述文字显示参数，将所述待显示文字信息按照所述显示路径进行动态展示。
本公开实施例的技术方案，在上述实施例的基础上，通过在有用户发出文字特效显示指令时，获取到待显示文字信息和文字显示参数时，然后获取显示待显示文字信息的视频图像；并识别视频图像中目标对象的关键位置点，当识别到的关键位置点未包含全部必要关键位置点时，确认识别到的关键位置点是否包含全部预设基准关键位置点，若识别到的关键位置点包含全部预设基准关键位置点，则根据全部预设基准关键点将未识别到的必要关键位置点进行补齐。然后，基于补齐之后的关键位置点确认待显示文字的显示路径；最终根据文字显示参数，将待显示文字信息按照显示路径进行动态展示，形成一种待显示文字围绕目标对象的轮廓进行动态显示的文字特效。本公开实施例的技术方案避免了视频画面中文字特效效果不能个性化设置的情况，以及文字特效处理过程中，必要关键位置点缺失的问题，实现了一种可编辑的文字特效展示方式，使用户在发送文字互动信息时，能够对文字特效的展示效果进行个性化的设置，增加文字特效展示的趣味性，即便在关键位置点识别不全面的条件下，仍然能够进行文字特效处理。
本公开实施例与上述实施例中所提供的文字特效展示方法中多个示例方案可以结合。本实施例所提供的文字特效展示方法，描述了将文字按照显示路径进行展示的过程。
图4为本公开另一实施例所提供的一种文字特效展示方法的流程示意图。如图4所示，本实施例提供的文字特效展示方法，包括：
S310、当获取到待显示文字信息和文字显示参数时，获取显示所述待显示文字信息的视频图像。
S320、识别所述视频图像中目标对象的关键位置点，并基于所述关键位置点确认所述待显示文字的显示路径。
S310-S320具体内容可参照前述实施例内容，在本实施例中不再赘述。
S330、根据所述文字显示参数、所述显示路径的曲线和所述待显示文字中的第一个文字在前一帧视频图像的特征位置，确定所述显示文字中每个文字在当前视频图像的路径位置。
由于在不同帧视频图像中，目标对象可能会发生移动，例如，在连续的视频图像帧中，目标对象是越来越靠近镜头的，那么目标对象会变大，显示路径的曲线也会变长。因此，待显示文字在显示路径上的移动过程是不均匀的。为了使文字特效展示时，文字动态移动的过程更加的稳定和均匀，可以在相邻的两帧 视频图像中进行文字特征位置信息的传递。由于视频中的目标对象会不断变化，人眼中的文字位置一般会参照某个特征点进行设置，特征点位置可以在当前视频图像中的位置保持与前一帧视频图像中的位置在视觉上的位置不变性。因此，在这里引入了一个特征位置的概念。特征位置表示每个文字在显示路径上所处的两个轮廓扩张关键点之间的曲线段上的位置。所述路径位置表示每个文字在所述显示路径上移动的曲线路径长度。文字在屏幕上的特征位置，可由CN(n，t)表示，表示第N个字的位置位于轮廓扩张关键点P(n)和轮廓扩张关键点P(n+1)的曲线段上，t为显示路径曲线的参数，t的取值范围为0-1，表示第n个字的位置靠近轮廓扩张关键点P(n)或轮廓扩张关键点P(n+1)的程度。路径位置表示第N个字从轮廓扩张关键点中起点P1开始走过的曲线路径长度，可由LN表示。引入路径位置是为了确保文字移动在视觉上的速度不变性。另外，可由LN(n，t)表示第N个字从特征位置CN(n，0)移动到CN(n，t)对应的曲线长度；由L(n，m)表示Pn-m的曲线长度，即轮廓扩张关键点n与轮廓扩张关键点m间的曲线长度；由L(n)表示L(n，n+1)，即轮廓扩张关键点n与轮廓扩张关键点n+1间的曲线长度。
例如，在显示文字中每个文字在当前视频图像的路径位置的过程如下：
首先，在当前视频图像中，根据文字显示参数中的文字生存周期和显示路径的曲线长度，确定所述待显示文字的移动速度。其中，曲线长度是是第一个轮廓扩张关键点到最后一个轮廓扩张关键点的长度。用曲线长度除以文字生存周期即可确定文字的速度。
然后，获取待显示文字中的第一个文字在前一帧视频图像的特征位置，当前一帧非空时，直接获取特征位置即可；如果当前视频图像为第一帧视频图像，则前一帧是空的，则将待显示文字中的第一个文字在前一帧视频图像的特征位置记为CN(1，0)，表示第一个文字在第一个轮廓扩张关键点的位置处，相当于在文字特效动态展示的起点。那么，便可以根据待显示文字中的第一个文字在前一帧视频图像的特征位置计算该第一个文字在当前视频图像中的路径位置。例如，可以先可以采用预设曲线积分法，基于第一个文字在前一帧视频图像的特征位置对显示路径的拟合曲线进行积分计算，确定该第一个文字在当前视频图像中的对应的初始路径位置。采用预设曲线积分法可以是高斯勒让得积分算法，该方法是一种计算机中常用的积分求解的数值算法，优点是用相对较少的求值计算次数，得到精度很高且数值稳定的积分计算结果。然后，根据当前视频图像和前一帧视频图像之间的时间间隔和待显示文字的移动速度确定第一个文字的移动距离；进而，在第一个文字在前一帧视频图像中的初始路径位置的基础上叠加移动距离，得到待显示文字中第一个文字在当前视频图像的路径位置。
例如，可以在第一个文字在当前视频图像的路径位置的基础上叠加待显示文字中每个文字与第一个文字的文字显示间隔，确定所述待显示文字中每个文字在当前视频图像的路径位置。
S340、根据所述待显示文字中每个文字在当前视频图像的路径位置计算出每个文字在当前视频图像的特征位置。
特征位置相当于显示路径曲线上的一个点，那么可以通过求解曲线的解的方式确定每个文字在当前视频图像的路径位置在当前视频图像中对应的特征位置点。示例性的，可以采用牛顿迭代算法计算每文字的特征位置。牛顿迭代法是求方程近似根的常用方法，比起求精确根具有计算量合理，求解精度满足要求的优点。
在采用牛顿迭代算法进行求解的过程中，牛顿迭代次数通常设置为3。首先，根据每个文字在当前视频图像的路径位置，确定该路径位置在显示路径曲线上的哪两个轮廓扩张关键点间的曲线段内。然后，将显示路径的曲线参数带入到牛顿迭代的函数中，按照预设的牛顿迭代次数进行迭代求解，最终得到每个文字在当前视频图像的特征位置。
S350、根据所述每个文字在当前视频图像的特征位置确定每个文字的屏幕位置。
在轮廓扩张曲线拟合的过程中，就是根据每个轮廓扩张关键点的屏幕位置进行曲线拟合的，那么该拟合曲线的输出即屏幕位置。对于第N个文字的特征位置CN(n，t)，将t及轮廓扩张关键点P(n)及相邻的一个或多个轮廓扩张关键点的位置信息输入到显示路径曲线中便可以得到第N个文字的屏幕位置。其中，具体输入到显示路径曲线的轮廓扩张关键点P(n)及相邻的一个或多个轮廓扩张关键点的位置信息是根据显示路径曲线在进行拟合时的条件一致。例如，在进行曲线拟合时，采用相邻的四个轮廓扩张关键点进行样条曲线拟合，那么在确定屏幕位置时，输入到显示路径曲线中的位置信息就是P(n-1)、P(n)、P(n+1)和P(n+2)四个轮廓扩张关键点的位置信息。
S360、基于所述每个文字的屏幕位置将所述待显示文字在视频图像中进行渲染展示。
在该步骤中，可以按照文字显示参数中的文字字体和字号在每个文字的屏幕位置对待显示文字进行渲染；然后，将每个文字的渲染效果叠加在对应的视频图像中进行展示。其中，视频图像时在文字渲染之前进行渲染的。
本公开实施例的技术方案，在上述实施例的基础上，引入文字在视频图像中的特征位置和路径位置， 在确定待显示文字的移动过程时，依据每个文字在前一帧视频图像的特征位置确定其在当前视频图像的路径位置，再将路径位置转换为在当前视频图像的特征位置，然后确定每个文字的屏幕位置。可以避免不同帧视频图像中目标对象变化导致文字渲染动态效果变化不均匀的情况，优化待显示文字的渲染效果。最终形成一种待显示文字围绕目标对象的轮廓匀速移动的动态显示文字特效。本公开实施例的技术方案避免了视频画面中文字特效效果不能个性化设置的情况，以及不同视频帧目标对象发生变化的问题，实现了一种可编辑的文字特效展示方式，使用户在发送文字互动信息时，能够对文字特效的展示效果进行个性化的设置，增加文字特效展示的趣味性。
本公开实施例与上述实施例中所提供的文字特效展示方法中多个示例方案可以结合。本实施例所提供的文字特效展示方法，描述了当目标对象为人像时，使文字依据人像轮廓曲线路径进行展示的过程。
图5为本公开另一实施例所提供的一种文字特效展示方法的流程示意图。如图5所示，本实施例提供的文字特效展示方法，包括：
S410、当获取到待显示文字信息和文字显示参数时，获取显示所述待显示文字信息的视频图像。
S420、识别所述视频图像中人物图像的关键位置点，当所述关键位置点中未包含全部所述必要关键位置点，但是包含全部预设基准关键位置点时，根据所述关键位置点中的预设基准关键位置点的位置信息和所述目标对象的标准参考模型的尺寸比例，补充所述关键位置点中未包含的必要关键位置点。
在本实施例中，目标对象为人物图像，通过本实施例的技术方案，可以实现待显示文字在人体轮廓上方进行动态显示的过程。可适用于直播场景下的用户互动，或其他的视频互动场景。
在识别人物图像的关键位置点时，是参照预设的人体骨骼关键点模型，模型中多个关键点的位置可如图6所示。图6中展示了二维的人体骨骼关键点模型，在模型中包括0-17个关键点。当然，也可以采用三维的人体骨骼关键点模型，在本实施例中使用二维的人体骨骼关键点模型而不是三维的人体骨骼关键点模型的原因，是因为三维的人体骨骼关键点模型精度和稳定性不如二维的人体骨骼关键点模型，而且二维的人体骨骼关键点模型已经满足特效的要求。
现以人体骨骼关键点模型的上半身的关键位置点(如图7)为例，说明确定人物图像的全部必要关键位置点的过程。在人体上半身部分中，必要关键位置点集合是：[0，1，2，5，14，15，16，17]。由于视频图像中的人物有时会有部分在视频图像之外，导致图像算法识别出来的必要关键位置点不全，所以需要检查获取到的必要关键位置点是否有丢失，如果丢失需要按预设的策略补齐。例如，选中一些人脸附近中间的预设基准关键位置点，基于标准人像的比例计算其出他必要关键位置点的默认位置。例如，本实施例中的预设基准关键位置点是[0，1，14，15]，取0点为坐标原点，0-1点方向为纵轴方向，14-15点方向为横轴方向建立参考坐标系，第a个关键点的具体计算公式如下(a的取值范围是必要关键位置点集合中的必要关键位置点的序号)：
B(a)＝B(0)+x(a)*[B(15)-B(14)]+y(a)*[B(1)-B(0)]。
其中，B(a)表示第a个人体关键点的屏幕位置，即关键位置点识别时获取到的位置信息，x(a)和y(a)分别是a点在该参考坐标系下的横轴和纵轴坐标。x(a)和y(a)可以根据已知关键位置点的位置信息和人体骨骼关键点模型的比例预先计算出来，待补充必要关键位置点在参考坐标系的坐标计算结果如下表：
a x(a) y(a)
2 -2.0 1.5
5 2.0 1.5
16 -0.9 -0.3
17 0.9 -0.3
例如，将上表中的坐标值带入到关键点屏幕位置计算公式中便可以确定补充的必要关键位置点的屏幕位置信息。
例如，为了减少视频或图像算法原因引起文字特效的抖动，对识别到的关键位置点进行防抖处理。可以采用简单的中值滤波，分别取连续三帧关键点位置分量的中值作为当前帧的位置分量，过滤掉噪声抖动。或者，还可以采用其他的滤波方式。
S430、根据补充后的关键位置点的位置信息和预设轮廓扩张参数确定与所述关键位置点对应的轮廓扩张关键点。
轮廓扩张关键点一般选取几个与必要关键位置点相对应的关键位置点，通常是反映人物图像整体轮廓和特征的位置点。针对任务图像的轮廓扩张关键点的选取可参考图8所示的轮廓扩张关键点P1-P9。每轮扩张关键点的位置计算依赖于人体图像轮廓线上的轮廓关键点。这里第n个外轮廓关键点的位置计算可采用如下计算公式：P(n)＝O(a)+length*cross(T(n),forward)。
其中，P(n)是第n个轮廓扩张关键点的位置信息，即屏幕坐标位置；O(a)是每个必要关键位置点在人 体轮廓线上的位置信息，可以根据必要关键位置点的位置信息和必要关键位置点间的距离，与标准人像的比例确定具体的数值，或者可以基于人像的特点预先设定计算规则，计算规则满足与人体轮廓契合的视觉效果即可，且优先选择简单的计算规则；length是轮廓扩张长度，表示轮廓扩张曲线和人体的距离大小，cross()是向量叉乘函数，T(n)是轮廓线切向方向，forward是垂直屏幕朝里的向量，这里是(0，0，1)。O(a)和T(n)的数值决定了轮廓扩张曲线的形状，length决定轮廓大小。在本实施例中，为了使计算关系尽量简化，每个轮廓关键点对应的O(a)的数值计算遵从下表中的计算规则：
Figure PCTCN2022126579-appb-000001
其中，distance()表示两个点之间的距离函数。
S440、基于所述轮廓扩张关键点进行轮廓曲线拟合，并将拟合得到的目标轮廓扩张曲线作为所述显示路径。
首先，为确保拟合曲线在起始的P1及终点的P9处平滑，需要在轮廓扩张关键点的起始点和终止点处补充轮廓扩张关键点，如图9中的P0和P10。P0和P10与原先的轮廓关键点需要符合一定线性关系，才能够使拟合曲线在起始的P1及终点的P9处平滑，即保持P2-3-0和P8-9-10分别在同一直线上。在本实施例中，可计算得出P0和P10的具体计算关系如下：
P(0)＝P(1)*2-P(2)，P(10)＝P(9)*2-P(8)。
上述计算关系的确定可以预先设定多组线性关系参数，分别得到多组线性拟合结果，根据曲线拟合的效果确定最终的计算关系。例如，本实施例，在确定了最终的补充后的轮廓扩张关键点之后，采用CatmullRom样条曲线进行线性拟合，对于任意两个轮廓扩张关键点间的曲线段P(n)-P(n+1)，需要P(n-1)、P(n)、P(n+1)和P(n+2)4个点作为输入，计算代码如下，其中，p0、p1、p2和p3分别对应4个输入的点，t范围从0-1，a、b和c是已知曲线拟合参数，从而返回值即为屏幕位置。
Figure PCTCN2022126579-appb-000002
最终得出的拟合曲线如图10中虚线所示，其中，P1-P9的曲线段是待显示文字的动态显示路径。
S450、根据所述文字显示参数、所述显示路径的曲线和所述待显示文字中的第一个文字在前一帧视频图像的特征位置，确定所述显示文字中每个文字在当前视频图像的路径位置。
由于在不同帧视频图像中，目标对象可能会发生移动，例如，在连续的视频图像帧中，目标对象是越来越靠近镜头的，那么目标对象会变大，显示路径的曲线也会变长。因此，待显示文字在显示路径上的移 动过程是不均匀的。为了使文字特效展示时，文字动态移动的过程更加的稳定和均匀，可以在相邻的两帧视频图像中进行文字特征位置信息的传递。由于视频中的目标对象会不断变化，人眼中的文字位置一般会参照某个特征点进行设置，特征点位置可以在当前视频图像中的位置保持与前一帧视频图像中的位置在视觉上的位置不变性。因此，在这里引入了一个特征位置的概念。特征位置表示每个文字在显示路径上所处的两个轮廓扩张关键点之间的曲线段上的位置。所述路径位置表示每个文字在所述显示路径上移动的曲线路径长度。文字在屏幕上的特征位置，可由CN(n，t)表示，表示第N个字的位置位于轮廓扩张关键点P(n)和轮廓扩张关键点P(n+1)的曲线段上，t为显示路径曲线的参数，t的取值范围为0-1，表示第n个字的位置靠近轮廓扩张关键点P(n)或轮廓扩张关键点P(n+1)的程度。路径位置表示第N个字从轮廓扩张关键点中起点P1开始走过的曲线路径长度，可由LN表示。引入路径位置是为了确保文字移动在视觉上的速度不变性。另外，可由LN(n，t)表示第N个字从特征位置CN(n，0)移动到CN(n，t)对应的曲线长度；由L(n，m)表示Pn-m的曲线长度，即轮廓扩张关键点n与轮廓扩张关键点m间的曲线长度；由L(n)表示L(n，n+1)，即轮廓扩张关键点n与轮廓扩张关键点n+1间的曲线长度。
例如，在显示文字中每个文字在当前视频图像的路径位置的具体过程如下：
首先，在当前视频图像中，根据文字显示参数中的文字生存周期和显示路径的曲线长度，确定所述待显示文字的移动速度。其中，曲线长度是是第一个轮廓扩张关键点到最后一个轮廓扩张关键点的长度。用曲线长度除以文字生存周期即可确定文字的速度。
然后，获取待显示文字中的第一个文字在前一帧视频图像的特征位置，当前一帧非空时，直接获取特征位置即可，如果当前视频图像为第一帧视频图像，则前一帧是空的，则将待显示文字中的第一个文字在前一帧视频图像的特征位置记为CN(1，0)，表示第一个文字在第一个轮廓扩张关键点的位置处，相当于在文字特效动态展示的起点。那么，便可以根据待显示文字中的第一个文字在前一帧视频图像的特征位置计算该第一个文字在当前视频图像中的路径位置。例如，可以先可以采用预设曲线积分法，基于第一个文字在前一帧视频图像的特征位置对显示路径的拟合曲线进行积分计算，确定该第一个文字在当前视频图像中的对应的初始路径位置。
在本实施例中，基于曲线拟合函数，文字特征位置点可表示为
Q(n，t)＝CatmullRomPoint[t,P(n-1),P(n),P(n+1),P(n+2)]；在为多项式时可得到：Q(n，t)＝a+bt+ct 2+dt 3；多项式的导数表示为：Q′(n,t)＝b+2ct+3dt 2；导数对应的向量长度为：
Figure PCTCN2022126579-appb-000003
然后，根据高斯勒让得积分可以算出曲线长度LN(n，t)，
Figure PCTCN2022126579-appb-000004
Figure PCTCN2022126579-appb-000005
其中，k＝5。ω i和x i高斯勒让得积分对应的参数，取值可按照如下表格进行取值。
Figure PCTCN2022126579-appb-000006
路径位置可以表示为
Figure PCTCN2022126579-appb-000007
在计算出路径位置之后，便根据当前视频图像和前一帧视频图像之间的时间间隔和待显示文字的移动速度确定第一个文字的移动距离；进而，在第一个文字在前一帧视频图像中的初始路径位置的基础上叠加移动距离，得到待显示文字中第一个文字在当前视频图像的路径位置。
例如，可以在第一个文字在当前视频图像的路径位置的基础上叠加待显示文字中每个文字与第一个文字的文字显示间隔，确定所述待显示文字中每个文字在当前视频图像的路径位置。
S460、根据所述待显示文字中每个文字在当前视频图像的路径位置计算出每个文字在当前视频图像的 特征位置。
其中，特征位置相当于显示路径曲线上的一个点，那么可以通过求解曲线的解的方式确定每个文字在当前视频图像的路径位置在当前视频图像中对应的特征位置点。示例性的，可以采用牛顿迭代算法计算每个文字的特征位置。牛顿迭代法是求方程近似根的常用方法，比起求精确根具有计算量合理，求解精度满足要求的优点。
在采用牛顿迭代算法进行求解的过程中，牛顿迭代次数通常设置为3。首先，根据每个文字在当前视频图像的路径位置，确定该路径位置在显示路径曲线上的哪两个轮廓扩张关键点间的曲线段内。然后，将显示路径的曲线参数带入到牛顿迭代的函数中，按照预设的牛顿迭代次数进行迭代求解，最终得到每个文字在当前视频图像的特征位置。在本实施例中，进行特征位置计算的过程可参考图11所示的流程图。将第N个字的路径位置赋值给len，然后从P1开始，确定第N个字落在哪两个轮廓扩张关键点的区间内，当len大于P1与P2之间的长度时，将len的数值减去P1与P2之间的长度，根据新的len数值，判断第N个字的特征位置是否在P2和P3点之间的位置，直到len小于L(n)，确定第N个字所在的曲线段内，然后利用牛顿迭代算法求解参数t，确定第N个字的特征位置。其中，
Figure PCTCN2022126579-appb-000008
S470、根据所述每个文字在当前视频图像的特征位置确定每个文字的屏幕位置。
在轮廓扩张曲线拟合的过程中，就是根据轮廓扩张关键点的屏幕位置进行曲线拟合的，那么该拟合曲线的输出即屏幕位置。对于第N个文字的特征位置CN(n，t)，将t及轮廓扩张关键点P(n)及相邻的一个或多个轮廓扩张关键点的位置信息输入到显示路径曲线中便可以得到第N个文字的屏幕位置。可表示为：SN(x,y)＝Q(n,t)＝CatmullRomPoint[t,P(n-1),P(n),P(n+1),P(n+2)]，SN(x,y)即为第N个字的屏幕位置。
S480、基于所述每个文字的屏幕位置将所述待显示文字在视频图像中进行渲染展示。
在该步骤中，可以按照文字显示参数中的文字字体和字号在每个文字的屏幕位置对待显示文字进行渲染；然后，将每个文字的渲染效果叠加在对应的视频图像中进行展示。其中，视频图像时在文字渲染之前进行渲染的。
本公开实施例的技术方案，在上述实施例的基础上，将文字特效展示方法应用于目标对象为人体图像的场景下，首先识别视频图像中的必要关键位置点，并补充未识别到的必要关键位置点，然后逐步进行文字显示路径曲线的拟合，进而根据曲线拟合结果，引入文字在视频图像中的特征位置和路径位置，在确定待显示文字的移动过程时，依据每个文字在前一帧视频图像的特征位置确定其在当前视频图像的路径位置，再将路径位置转换为在当前视频图像的特征位置，然后确定每个文字的屏幕位置。最终形成一种待显示文字围绕人像的轮廓匀速移动的动态显示文字特效。本公开实施例的技术方案避免了视频画面中文字特效效果不能个性化设置的情况，以及不同视频帧目标对象发生变化的问题，实现了一种可编辑的文字特效展示方式，使用户在发送文字互动信息时，能够对文字特效的展示效果进行个性化的设置，增加文字特效展示的趣味性。
图12为本公开实施例所提供的一种文字特效展示装置结构示意图。本实施例提供的文字特效展示装置适用于在视频图像中展示文字特效的情形。
如图12所示，文字特效展示装置包括：文字特效展示数据获取模块510、文字特效展示路径确定模块520和文字特效展示模块530。
其中，文字特效展示数据获取模块510，设置为当获取到待显示文字信息和文字显示参数时，获取显示所述待显示文字信息的视频图像；文字特效展示路径确定模块520，设置为识别所述视频图像中目标对象的关键位置点，并基于所述关键位置点确认所述待显示文字的显示路径；文字特效展示模块530，设置为根据所述文字显示参数，将所述待显示文字信息按照所述显示路径进行动态展示。
本公开实施例的技术方案，通过在有用户发出文字特效显示指令时，获取到待显示文字信息和文字显示参数时，然后获取显示待显示文字信息的视频图像；并识别视频图像中目标对象的关键位置点，确认待显示文字的显示路径；最终根据文字显示参数，将待显示文字信息按照显示路径进行动态展示，形成一种待显示文字围绕目标对象的轮廓进行动态显示的文字特效。本公开实施例的技术方案避免了视频画面中文字特效效果不能个性化设置的情况，实现了一种可编辑的文字特效展示方式，使用户在发送文字互动信息时，能够对文字特效的展示效果进行个性化的设置，增加文字特效展示的趣味性。
例如，文字特效展示路径确定模块520包括轮廓扩张关键点确定子模块和路径曲线拟合子模块；其中，
轮廓扩张关键点确定子模块，设置为当所述关键位置点包括全部必要关键位置点时，根据所述关键位置点的位置信息和预设轮廓扩张参数确定与所述关键位置点对应的轮廓扩张关键点；路径曲线拟合子模块，设置为基于所述轮廓扩张关键点进行轮廓曲线拟合，并将拟合得到的目标轮廓扩张曲线作为所述显示路径。
例如，文字特效展示路径确定模块520还包括关键位置点补充子模块，设置为：
确定所述关键位置点中是否包含全部预设基准关键位置点；
当所述关键位置点中包含全部预设基准关键位置点时，根据所述关键位置点中的预设基准关键位置点的位置信息和所述目标对象的标准参考模型的尺寸比例，补充所述关键位置点中未包含的必要关键位置点；
当所述关键位置点中未包含全部预设基准关键位置点时，停止当前文字特效展示处理过程。
例如，轮廓扩张关键点确定子模块设置为：
确定所述目标对象的轮廓线上与所述关键位置点对应的轮廓关键点；
在所述轮廓关键点的位置信息基础上叠加基于所述预设轮廓扩张参数确定的轮廓扩张距离，得到所述轮廓扩张关键点的位置信息。
例如，路径曲线拟合子模块，设置为：
根据预设轮廓扩张关键点位置关系补充轮廓扩张关键点；
基于补充后的轮廓扩张关键点进行轮廓曲线拟合。
例如，文字特效展示装置还包括关键位置点信息修正模块，设置为在确定与所述关键位置点对应的轮廓扩张关键点之前，取所述关键位置点在连续多帧的视频图像中的位置信息中的中值，作为所述关键位置点的位置信息。
例如，文字特效展示模块530，包括：文字路径位置确定子模块、文字特征位置确定子模块、文字屏幕位置确定子模块和文字渲染展示子模块；其中，文字路径位置确定子模块，设置为根据所述文字显示参数、所述显示路径的曲线和所述待显示文字中的第一个文字在前一帧视频图像的特征位置，确定所述显示文字中每个文字在当前视频图像的路径位置，其中，所述特征位置表示每个文字在所述显示路径上所处的两个轮廓扩张关键点之间的曲线段上的位置，所述路径位置表示每个文字在所述显示路径上移动的曲线路径长度；文字特征位置确定子模块，设置为根据所述待显示文字中每个文字在当前视频图像的路径位置计算出每个文字在当前视频图像的特征位置；文字屏幕位置确定子模块，设置为根据所述每个文字在当前视频图像的特征位置确定每个文字的屏幕位置；文字渲染展示子模块，设置为基于所述每个文字的屏幕位置将所述待显示文字在视频图像中进行渲染展示。
例如，文字路径位置确定子模块设置为：
根据所述文字显示参数中的文字生存周期和所述显示路径的曲线长度，确定所述待显示文字的移动速度；
基于所述显示文字的移动速度和所述待显示文字中的第一个文字在前一帧视频图像的特征位置，确定所述第一个文字在当前视频图像的路径位置；
根据所述第一个文字在当前视频图像的路径位置和所述根据所述文字显示参数中文字显示间隔，确定所述待显示文字中每个文字在当前视频图像的路径位置。
例如，文字路径位置确定子模块设置为：
采用预设曲线积分算法对所述第一个文字在前一帧视频图像的特征位置进行积分，确定所述第一个文字在前一帧视频图像中特征位置在当前视频图像中对应的初始路径位置；
根据所述当前视频图像和所述前一帧视频图像之间的时间间隔和所述待显示文字的移动速度确定所述第一个文字的移动距离；
在所述初始路径位置的基础上叠加所述移动距离，确定所述第一个文字在当前视频图像的路径位置。
例如，所述文字渲染展示子模块，设置为：
按照所述文字显示参数中的文字字体和字号在所述每个文字的屏幕位置对待显示文字进行渲染；
将所述每个文字的渲染效果叠加在所述视频图像中进行显示。
例如，所述目标对象包括视频图像中的人物图像。
本公开实施例所提供的文字特效展示装置，可执行本公开任意实施例所提供的文字特效展示方法，具备执行方法相应的功能模块和有益效果。
值得注意的是，上述装置所包括的多个单元和模块只是按照功能逻辑进行划分的，但并不局限于上述的划分，只要能够实现相应的功能即可；另外，多个功能单元的具体名称也只是为了便于相互区分，并不用于限制本公开实施例的保护范围。
下面参考图13，其示出了适于用来实现本公开实施例的电子设备(例如图13中的终端设备或服务器)600的结构示意图。本公开实施例中的终端设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图13示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图13所示，电子设备600可以包括处理装置(例如中央处理器、图形处理器等)601，其可以根据存储在只读存储器(Read-Only Memory，ROM)602中的程序或者从存储装置606加载到随机访问存储器(Random Access Memory，RAM)603中的程序而执行多种适当的动作和处理。在RAM 603中，还存储有电子设备600操作所需的多种程序和数据。处理装置601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
通常，以下装置可以连接至I/O接口605：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置606；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置607；包括例如磁带、硬盘等的存储装置608；以及通信装置609。通信装置609可以允许电子设备600与其他设备进行无线或有线通信以交换数据。虽然图13示出了具有多种装置的电子设备600，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置609从网络上被下载和安装，或者从存储装置606被安装，或者从ROM602被安装。在该计算机程序被处理装置601执行时，执行本公开实施例的文字特效展示方法中限定的上述功能。
本公开实施例提供的电子设备与上述实施例提供的文字特效展示方法属于同一公开构思，未在本实施例中详尽描述的技术细节可参见上述实施例，并且本实施例与上述实施例具有相同的有益效果。
本公开实施例提供了一种计算机存储介质，其上存储有计算机程序，该程序被处理器执行时实现上述实施例所提供的文字特效展示方法。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(Erasable Programmable Read-Only Memory，EPROM)或闪存(FLASH)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(Hyper Text Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：
当获取到待显示文字信息和文字显示参数时，获取显示所述待显示文字信息的视频图像；
识别所述视频图像中目标对象的关键位置点，并基于所述关键位置点确认所述待显示文字的显示路径；
根据所述文字显示参数，将所述待显示文字信息按照所述显示路径进行动态展示。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开多种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一 部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，单元、模块的名称在某种情况下并不构成对该单元、模块本身的限定，例如，数据生成模块还可以被描述为“视频数据生成模块”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(Field Programmable Gate Array，FPGA)、专用集成电路(Application Specific Integrated Circuit，ASIC)、专用标准产品(Application Specific Standard Parts，ASSP)、片上系统(System on Chip，SOC)、复杂可编程逻辑设备(CPLD)等等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
根据本公开的一个或多个实施例，【示例一】提供了一种文字特效展示方法，该方法包括：
当获取到待显示文字信息和文字显示参数时，获取显示所述待显示文字信息的视频图像；
识别所述视频图像中目标对象的关键位置点，并基于所述关键位置点确认所述待显示文字的显示路径；
根据所述文字显示参数，将所述待显示文字信息按照所述显示路径进行动态展示。
根据本公开的一个或多个实施例，【示例二】提供了一种文字特效展示方法，还包括：
例如，基于所述关键位置点确认所述待显示文字的显示路径，包括：
当所述关键位置点包括全部必要关键位置点时，根据所述关键位置点的位置信息和预设轮廓扩张参数确定与所述关键位置点对应的轮廓扩张关键点；
基于所述轮廓扩张关键点进行轮廓曲线拟合，并将拟合得到的目标轮廓扩张曲线作为所述显示路径。
根据本公开的一个或多个实施例，【示例三】提供了一种文字特效展示方法，还包括：
例如，响应于确定所述关键位置点中未包含全部所述必要关键位置点，所述方法还包括：
确定所述关键位置点中是否包含全部预设基准关键位置点；
当所述关键位置点中包含全部预设基准关键位置点时，根据所述关键位置点中的预设基准关键位置点的位置信息和所述目标对象的标准参考模型的尺寸比例，补充所述关键位置点中未包含的必要关键位置点；
当所述关键位置点中未包含全部预设基准关键位置点时，停止当前文字特效展示处理过程。
根据本公开的一个或多个实施例，【示例四】提供了一种文字特效展示方法，还包括：
例如，根据所述关键位置点的位置信息和预设轮廓扩张参数确定与所述关键位置点对应的轮廓扩张关键点，包括：
确定所述目标对象的轮廓线上与所述关键位置点对应的轮廓关键点；
在所述轮廓关键点的位置信息基础上叠加基于所述预设轮廓扩张参数确定的轮廓扩张距离，得到所述轮廓扩张关键点的位置信息。
根据本公开的一个或多个实施例，【示例五】提供了一种文字特效展示方法，还包括：
例如，所述基于所述轮廓扩张关键点进行轮廓曲线拟合，包括：
根据预设轮廓扩张关键点位置关系补充轮廓扩张关键点；
基于补充后的轮廓扩张关键点进行轮廓曲线拟合。
根据本公开的一个或多个实施例，【示例六】提供了一种文字特效展示方法，还包括：
例如，在确定与所述关键位置点对应的轮廓扩张关键点之前，所述方法还包括：
取所述关键位置点在连续多帧的视频图像中的位置信息中的中值，作为所述关键位置点的位置信息。
根据本公开的一个或多个实施例，【示例七】提供了一种文字特效展示方法，还包括：
例如，根据所述文字显示参数，将所述待显示文字信息按照所述显示路径进行动态展示，所述方法还包括：
根据所述文字显示参数、所述显示路径的曲线和所述待显示文字中的第一个文字在前一帧视频图像的 特征位置，确定所述显示文字中每个文字在当前视频图像的路径位置，其中，所述特征位置表示每个文字在所述显示路径上所处的两个轮廓扩张关键点之间的曲线段上的位置，所述路径位置表示每个文字在所述显示路径上移动的曲线路径长度；
根据所述待显示文字中每个文字在当前视频图像的路径位置计算出每个文字在当前视频图像的特征位置；
根据所述每个文字在当前视频图像的特征位置确定每个文字的屏幕位置；
基于所述每个文字的屏幕位置将所述待显示文字在视频图像中进行渲染展示。
根据本公开的一个或多个实施例，【示例八】提供了一种文字特效展示方法，还包括：
例如，所述根据所述文字显示参数、所述显示路径的曲线和所述待显示文字中的第一个文字在前一帧视频图像的特征位置，确定所述显示文字中每个文字在当前视频图像的路径位置，包括：
根据所述文字显示参数中的文字生存周期和所述显示路径的曲线长度，确定所述待显示文字的移动速度；
基于所述显示文字的移动速度和所述待显示文字中的第一个文字在前一帧视频图像的特征位置，确定所述第一个文字在当前视频图像的路径位置；
根据所述第一个文字在当前视频图像的路径位置和所述根据所述文字显示参数中文字显示间隔，确定所述待显示文字中每个文字在当前视频图像的路径位置。
根据本公开的一个或多个实施例，【示例九】提供了一种文字特效展示方法，还包括：
例如，基于所述显示文字的移动速度和所述待显示文字中的第一个文字在前一帧视频图像的特征位置，确定所述第一个文字在当前视频图像的路径位置，包括：
采用预设曲线积分算法对所述第一个文字在前一帧视频图像的特征位置进行积分，确定所述第一个文字在前一帧视频图像中特征位置在当前视频图像中对应的初始路径位置；
根据所述当前视频图像和所述前一帧视频图像之间的时间间隔和所述待显示文字的移动速度确定所述第一个文字的移动距离；
在所述初始路径位置的基础上叠加所述移动距离，确定所述第一个文字在当前视频图像的路径位置。
根据本公开的一个或多个实施例，【示例十】提供了一种文字特效展示方法，还包括：
例如，所述基于所述每个文字的屏幕位置将所述待显示文字在视频图像中进行渲染展示，包括：
按照所述文字显示参数中的文字字体和字号在所述每个文字的屏幕位置对待显示文字进行渲染；
将所述每个文字的渲染效果叠加在所述视频图像中进行显示。
根据本公开的一个或多个实施例，【示例十一】提供了一种文字特效展示方法，还包括：
例如，所述目标对象包括视频图像中的人物图像。
根据本公开的一个或多个实施例，【示例十二】提供了一种文字特效展示装置，包括：
文字特效展示数据获取模块，设置为当获取到待显示文字信息和文字显示参数时，获取显示所述待显示文字信息的视频图像；
文字特效展示路径确定模块，设置为识别所述视频图像中目标对象的关键位置点，并基于所述关键位置点确认所述待显示文字的显示路径；
文字特效展示模块，设置为根据所述文字显示参数，将所述待显示文字信息按照所述显示路径进行动态展示。
根据本公开的一个或多个实施例，【示例十三】提供了一种文字特效展示装置，还包括：
例如，文字特效展示路径确定模块具体包括轮廓扩张关键点确定子模块和路径曲线拟合子模块；其中，
轮廓扩张关键点确定子模块，设置为当所述关键位置点包括全部必要关键位置点时，根据所述关键位置点的位置信息和预设轮廓扩张参数确定与所述关键位置点对应的轮廓扩张关键点；路径曲线拟合子模块，设置为基于所述轮廓扩张关键点进行轮廓曲线拟合，并将拟合得到的目标轮廓扩张曲线作为所述显示路径。
根据本公开的一个或多个实施例，【示例十四】提供了一种文字特效展示装置，还包括：
例如，文字特效展示路径确定模块还包括关键位置点补充子模块，设置为：
确定所述关键位置点中是否包含全部预设基准关键位置点；
当所述关键位置点中包含全部预设基准关键位置点时，根据所述关键位置点中的预设基准关键位置点的位置信息和所述目标对象的标准参考模型的尺寸比例，补充所述关键位置点中未包含的必要关键位置点；
当所述关键位置点中未包含全部预设基准关键位置点时，停止当前文字特效展示处理过程。
根据本公开的一个或多个实施例，【示例十五】提供了一种文字特效展示装置，还包括：
例如，轮廓扩张关键点确定子模块设置为：
确定所述目标对象的轮廓线上与所述关键位置点对应的轮廓关键点；
在所述轮廓关键点的位置信息基础上叠加基于所述预设轮廓扩张参数确定的轮廓扩张距离，得到所述轮廓扩张关键点的位置信息。
根据本公开的一个或多个实施例，【示例十六】提供了一种文字特效展示装置，还包括：
例如，路径曲线拟合子模块，设置为：
根据预设轮廓扩张关键点位置关系补充轮廓扩张关键点；
基于补充后的轮廓扩张关键点进行轮廓曲线拟合。
根据本公开的一个或多个实施例，【示例十七】提供了一种文字特效展示装置，还包括：
例如，文字特效展示装置还包括关键位置点信息修正模块，设置为在确定与所述关键位置点对应的轮廓扩张关键点之前，取所述关键位置点在连续多帧的视频图像中的位置信息中的中值，作为所述关键位置点的位置信息。
根据本公开的一个或多个实施例，【示例十八】提供了一种文字特效展示装置，还包括：
例如，文字特效展示模块包括：文字路径位置确定子模块、文字特征位置确定子模块、文字屏幕位置确定子模块和文字渲染展示子模块；其中，文字路径位置确定子模块，设置为根据所述文字显示参数、所述显示路径的曲线和所述待显示文字中的第一个文字在前一帧视频图像的特征位置，确定所述显示文字中每个文字在当前视频图像的路径位置，其中，所述特征位置表示每个文字在所述显示路径上所处的两个轮廓扩张关键点之间的曲线段上的位置，所述路径位置表示每个文字在所述显示路径上移动的曲线路径长度；文字特征位置确定子模块，设置为根据所述待显示文字中每个文字在当前视频图像的路径位置计算出每个文字在当前视频图像的特征位置；文字屏幕位置确定子模块，设置为根据所述每个文字在当前视频图像的特征位置确定每个文字的屏幕位置；文字渲染展示子模块，设置为基于所述每个文字的屏幕位置将所述待显示文字在视频图像中进行渲染展示。
根据本公开的一个或多个实施例，【示例十九】提供了一种文字特效展示装置，还包括：
例如，文字路径位置确定子模块设置为：
根据所述文字显示参数中的文字生存周期和所述显示路径的曲线长度，确定所述待显示文字的移动速度；
基于所述显示文字的移动速度和所述待显示文字中的第一个文字在前一帧视频图像的特征位置，确定所述第一个文字在当前视频图像的路径位置；
根据所述第一个文字在当前视频图像的路径位置和所述根据所述文字显示参数中文字显示间隔，确定所述待显示文字中每个文字在当前视频图像的路径位置。
根据本公开的一个或多个实施例，【示例二十】提供了一种文字特效展示装置，还包括：
例如，文字路径位置确定子模块设置为：
采用预设曲线积分算法对所述第一个文字在前一帧视频图像的特征位置进行积分，确定所述第一个文字在前一帧视频图像中特征位置在当前视频图像中对应的初始路径位置；
根据所述当前视频图像和所述前一帧视频图像之间的时间间隔和所述待显示文字的移动速度确定所述第一个文字的移动距离；
在所述初始路径位置的基础上叠加所述移动距离，确定所述第一个文字在当前视频图像的路径位置。
根据本公开的一个或多个实施例，【示例二十一】提供了一种文字特效展示装置，还包括：
例如，所述文字渲染展示子模块，设置为：
按照所述文字显示参数中的文字字体和字号在所述每个文字的屏幕位置对待显示文字进行渲染；
将所述每个文字的渲染效果叠加在所述视频图像中进行显示。
根据本公开的一个或多个实施例，【示例二十二】提供了一种文字特效展示装置，还包括：
例如，所述目标对象包括视频图像中的人物图像。
以上描述仅为本公开的示例实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
此外，虽然采用特定次序描绘了多种操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的多种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。

Claims (14)

  1. 一种文字特效展示方法，包括：
    响应于确定获取到待显示文字信息和文字显示参数，获取显示所述待显示文字信息的视频图像；
    识别所述视频图像中目标对象的关键位置点，并基于所述关键位置点确认所述待显示文字的显示路径；
    根据所述文字显示参数，将所述待显示文字信息按照所述显示路径进行动态展示。
  2. 根据权利要求1所述的方法，其中，所述基于所述关键位置点确认所述待显示文字的显示路径，包括：
    响应于确定所述关键位置点包括全部必要关键位置点，根据所述关键位置点的位置信息和预设轮廓扩张参数确定与所述关键位置点对应的轮廓扩张关键点；
    基于所述轮廓扩张关键点进行轮廓曲线拟合，并将拟合得到的目标轮廓扩张曲线作为所述显示路径。
  3. 根据权利要求2所述的方法，其中，响应于确定所述关键位置点中未包含全部所述必要关键位置点，所述方法还包括：
    确定所述关键位置点中是否包含全部预设基准关键位置点；
    响应于确定所述关键位置点中包含全部预设基准关键位置点，根据所述关键位置点中的预设基准关键位置点的位置信息和所述目标对象的标准参考模型的尺寸比例，补充所述关键位置点中未包含的必要关键位置点；
    响应于确定所述关键位置点中未包含全部预设基准关键位置点，停止当前文字特效展示处理过程。
  4. 根据权利要求2所述的方法，其中，所述根据所述关键位置点的位置信息和预设轮廓扩张参数确定与所述关键位置点对应的轮廓扩张关键点，包括：
    确定所述目标对象的轮廓线上与所述关键位置点对应的轮廓关键点；
    在所述轮廓关键点的位置信息基础上叠加基于所述预设轮廓扩张参数确定的轮廓扩张距离，得到所述轮廓扩张关键点的位置信息。
  5. 根据权利要求4所述的方法，其中，所述基于所述轮廓扩张关键点进行轮廓曲线拟合，包括：
    根据预设轮廓扩张关键点位置关系补充轮廓扩张关键点；
    基于补充后的轮廓扩张关键点进行轮廓曲线拟合。
  6. 根据权利要求2所述的方法，在所述确定与所述关键位置点对应的轮廓扩张关键点之前，所述方法还包括：
    取所述关键位置点在连续多帧的视频图像中的位置信息中的中值，作为所述关键位置点的位置信息。
  7. 根据权利要求2所述的方法，其中，所述待显示文字包括多个文字，所述根据所述文字显示参数，将所述待显示文字信息按照所述显示路径进行动态展示，包括：
    根据所述文字显示参数、所述显示路径的曲线和所述待显示文字中的第一个文字在前一帧视频图像的特征位置，确定所述显示文字中每个文字在当前视频图像的路径位置，其中，所述特征位置表示所述每个文字在所述显示路径上所处的两个轮廓扩张关键点之间的曲线段上的位置，所述路径位置表示所述每个文字在所述显示路径上移动的曲线路径长度；
    根据所述待显示文字中所述每个文字在当前视频图像的路径位置计算出所述每个文字在当前视频图像的特征位置；
    根据所述每个文字在当前视频图像的特征位置确定所述每个文字的屏幕位置；
    基于所述每个文字的屏幕位置将所述待显示文字在视频图像中进行渲染展示。
  8. 根据权利要求7所述的方法，其中，所述根据所述文字显示参数、所述显示路径的曲线和所述待显示文字中的第一个文字在前一帧视频图像的特征位置，确定所述显示文字中每个文字在当前视频图像的路径位置，包括：
    根据所述文字显示参数中的文字生存周期和所述显示路径的曲线长度，确定所述待显示文字的移动速度；
    基于所述显示文字的移动速度和所述待显示文字中的第一个文字在前一帧视频图像的特征位置，确定所述第一个文字在当前视频图像的路径位置；
    根据所述第一个文字在当前视频图像的路径位置和所述根据所述文字显示参数中文字显示间隔，确定所述待显示文字中每个文字在当前视频图像的路径位置。
  9. 根据权利要求8所述的方法，其中，所述基于所述显示文字的移动速度和所述待显示文字中的第一个文字在前一帧视频图像的特征位置，确定所述第一个文字在当前视频图像的路径位置，包括：
    采用预设曲线积分算法对所述第一个文字在前一帧视频图像的特征位置进行积分，确定所述第一个文字在前一帧视频图像中的特征位置在当前视频图像中对应的初始路径位置；
    根据所述当前视频图像和所述前一帧视频图像之间的时间间隔和所述待显示文字的移动速度确定所述第一个文字的移动距离；
    在所述初始路径位置的基础上叠加所述移动距离，确定所述第一个文字在当前视频图像的路径位置。
  10. 根据权利要求7所述的方法，其中，所述基于所述每个文字的屏幕位置将所述待显示文字在视频图像中进行渲染展示，包括：
    按照所述文字显示参数中的文字字体和字号在所述每个文字的屏幕位置对待显示文字进行渲染；
    将所述每个文字的渲染效果叠加在所述视频图像中进行展示。
  11. 根据权利要求1-10中任一所述的方法，其中，所述目标对象包括所述视频图像中的人物图像。
  12. 一种文字特效展示装置，包括：
    文字特效展示数据获取模块，设置为响应于确定获取到待显示文字信息和文字显示参数，获取显示所述待显示文字信息的视频图像；
    文字特效展示路径确定模块，设置为识别所述视频图像中目标对象的关键位置点，并基于所述关键位置点确认所述待显示文字的显示路径；
    文字特效展示模块，设置为根据所述文字显示参数，将所述待显示文字信息按照所述显示路径进行动态展示。
  13. 一种电子设备，包括：
    一个或多个处理器；
    存储装置，设置为存储一个或多个程序，
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-11中任一所述的文字特效展示方法。
  14. 一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时设置为执行如权利要求1-11中任一所述的文字特效展示方法。
PCT/CN2022/126579 2021-10-26 2022-10-21 文字特效展示方法、装置、电子设备及存储介质 Ceased WO2023071920A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US18/291,753 US20240357210A1 (en) 2021-10-26 2022-10-21 Method, apparatus, electronic device and storage medium for displaying a text effect

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111250376.4A CN116033201B (zh) 2021-10-26 2021-10-26 一种文字特效展示方法、装置、电子设备及存储介质
CN202111250376.4 2021-10-26

Publications (1)

Publication Number Publication Date
WO2023071920A1 true WO2023071920A1 (zh) 2023-05-04

Family

ID=86080193

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/126579 Ceased WO2023071920A1 (zh) 2021-10-26 2022-10-21 文字特效展示方法、装置、电子设备及存储介质

Country Status (3)

Country Link
US (1) US20240357210A1 (zh)
CN (1) CN116033201B (zh)
WO (1) WO2023071920A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117412100A (zh) * 2023-10-17 2024-01-16 北京字跳网络技术有限公司 视频处理方法及相关设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105100927A (zh) * 2015-08-07 2015-11-25 广州酷狗计算机科技有限公司 弹幕显示方法及装置
CN106101804A (zh) * 2016-06-16 2016-11-09 乐视控股（北京）有限公司 弹幕设定方法及装置
CN108495166A (zh) * 2018-01-29 2018-09-04 上海哔哩哔哩科技有限公司 弹幕播放控制方法、终端及弹幕播放控制系统
US20180332265A1 (en) * 2017-05-15 2018-11-15 Lg Electronics Inc. Method of transmitting 360-degree video, method of receiving 360-degree video, device for transmitting 360-degree video, and device for receiving 360-degree video
CN112328091A (zh) * 2020-11-27 2021-02-05 腾讯科技（深圳）有限公司 弹幕显示方法、装置、终端及存储介质

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8085982B1 (en) * 2008-06-20 2011-12-27 Google Inc. Object tracking in video with visual constraints
JP2013161205A (ja) * 2012-02-03 2013-08-19 Sony Corp 情報処理装置、情報処理方法、及びプログラム
US9240061B2 (en) * 2012-10-02 2016-01-19 International Business Machines Corporation Pattern representation images for business intelligence dashboard objects
CN105430471B (zh) * 2015-11-26 2018-07-24 无锡天脉聚源传媒科技有限公司 一种视频中弹幕的显示方法及装置
CN107147941A (zh) * 2017-05-27 2017-09-08 努比亚技术有限公司 视频播放的弹幕显示方法、装置及计算机可读存储介质
CN109391792B (zh) * 2017-08-03 2021-10-29 腾讯科技（深圳）有限公司 视频通信的方法、装置、终端及计算机可读存储介质
US10489918B1 (en) * 2018-05-09 2019-11-26 Figure Eight Technologies, Inc. Video object tracking
US11004249B2 (en) * 2019-03-18 2021-05-11 Apple Inc. Hand drawn animation motion paths
CN112347395B (zh) * 2019-08-07 2024-06-14 阿里巴巴集团控股有限公司 特效展示方法、装置、电子设备及计算机存储介质
US11887629B2 (en) * 2020-09-10 2024-01-30 Adobe Inc. Interacting with semantic video segments through interactive tiles
CN115733993A (zh) * 2021-08-27 2023-03-03 北京字节跳动网络技术有限公司 网络直播方法、装置、存储介质和电子设备
CN113891119A (zh) * 2021-09-28 2022-01-04 北京字跳网络技术有限公司 信息显示方法、装置、电子设备和存储介质
US20230401852A1 (en) * 2022-05-31 2023-12-14 Synamedia Limited Video Scene Change Detection

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105100927A (zh) * 2015-08-07 2015-11-25 广州酷狗计算机科技有限公司 弹幕显示方法及装置
CN106101804A (zh) * 2016-06-16 2016-11-09 乐视控股（北京）有限公司 弹幕设定方法及装置
US20180332265A1 (en) * 2017-05-15 2018-11-15 Lg Electronics Inc. Method of transmitting 360-degree video, method of receiving 360-degree video, device for transmitting 360-degree video, and device for receiving 360-degree video
CN108495166A (zh) * 2018-01-29 2018-09-04 上海哔哩哔哩科技有限公司 弹幕播放控制方法、终端及弹幕播放控制系统
CN112328091A (zh) * 2020-11-27 2021-02-05 腾讯科技（深圳）有限公司 弹幕显示方法、装置、终端及存储介质

Also Published As

Publication number Publication date
CN116033201B (zh) 2025-04-01
CN116033201A (zh) 2023-04-28
US20240357210A1 (en) 2024-10-24

Similar Documents

Publication Publication Date Title
CN111242881B (zh) 显示特效的方法、装置、存储介质及电子设备
CN111399729A (zh) 图像的绘制方法、装置、可读介质和电子设备
CN111669502B (zh) 目标对象显示方法、装置及电子设备
US11314965B2 (en) Method and apparatus for positioning face feature points
CN109816769A (zh) 基于深度相机的场景地图生成方法、装置及设备
CN112423021B (zh) 视频的处理方法、装置、可读介质和电子设备
WO2020220809A1 (zh) 目标对象的动作识别方法、装置和电子设备
US20220301184A1 (en) Accurate optical flow interpolation optimizing bi-directional consistency and temporal smoothness
CN110796664B (zh) 图像处理方法、装置、电子设备及计算机可读存储介质
CN112199016B (zh) 图像处理方法、装置、电子设备及计算机可读存储介质
US20250292444A1 (en) Video synthesis method, apparatus, device, medium and product
CN111833459A (zh) 一种图像处理方法、装置、电子设备及存储介质
WO2023138441A1 (zh) 视频生成方法、装置、设备及存储介质
CN114630057A (zh) 确定特效视频的方法、装置、电子设备及存储介质
KR20220110493A (ko) 비디오의 객체 표시 방법 및 장치, 전자 장치 및 컴퓨터 판독 가능 저장 매체
WO2023071920A1 (zh) 文字特效展示方法、装置、电子设备及存储介质
US12041374B2 (en) Segmentation-based video capturing method, apparatus, device and storage medium
CN112651909B (zh) 图像合成方法、装置、电子设备及计算机可读存储介质
US11810336B2 (en) Object display method and apparatus, electronic device, and computer readable storage medium
WO2023025181A1 (zh) 图像识别方法、装置和电子设备
CN117152385A (zh) 图像处理方法、装置、电子设备及存储介质
CN112085733A (zh) 图像处理方法、装置、电子设备和计算机可读介质
CN110288552A (zh) 视频美化方法、装置及电子设备
WO2023071631A1 (zh) 一种视频处理方法、装置及设备
CN113703704A (zh) 界面显示方法、头戴式显示设备和计算机可读介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22885797

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 18291753

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 06/08/2024)

122 Ep: pct application non-entry in european phase

Ref document number: 22885797

Country of ref document: EP

Kind code of ref document: A1