Dynamic poster generation method and device, electronic equipment and storage medium

Abstract

The invention relates to a dynamic poster generation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a target video, and carrying out the frame splitting of the target video, so as to obtain a first image frame sequence corresponding to the target video; determining a key image frame from the first image frame sequence as a target image frame; according to the target image frame, a second image frame sequence is determined from the first image frame sequence, the second image frame sequence comprises the target image frame and a plurality of image frames, the plurality of image frames and the target image frame are continuous in time, and all image frames in the second image frame sequence are similar to the target image frame; and synthesizing all image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video. The target dynamic poster which can attract people is automatically generated, and the generation efficiency of the target dynamic poster is improved.

Description

Technical Field

[0001] The present application relates to the field of video processing technology, and in particular to a method, device, electronic device and storage medium for generating a dynamic poster. Background Art

[0002] Some video websites need to display posters of TV series or movies. In addition to static posters, dynamic posters are often needed. By generating dynamic posters, users' attention can be more effectively attracted through movement and change. Compared with static posters, dynamic posters can better catch the audience's sight, thereby increasing the viewers' attention to the content. In addition, by generating dynamic posters, the climax of the plot or the characteristics of the characters can be shown to the audience, which helps to increase the audience's interest and expectations for the work. However, at present, the generation efficiency of dynamic posters is low, and the dynamic effect of the generated dynamic posters is not attractive enough. Summary of the invention

[0003] In view of this, in order to solve the above-mentioned technical problems or part of the technical problems, the embodiments of the present application provide a method, device, electronic device and storage medium for generating a dynamic poster.

[0004] In a first aspect, the present application provides a method for generating a dynamic poster, comprising:

[0005] Acquire a target video, and perform frame splitting processing on the target video to obtain a first image frame sequence corresponding to the target video;

[0006] Determining a key image frame from the first image frame sequence as a target image frame;

[0007] According to the target image frame, determining a second image frame sequence from the first image frame sequence, the second image frame sequence comprising the target image frame and a plurality of image frames, the plurality of image frames being temporally continuous with the target image frame and all the image frames in the second image frame sequence being similar to the target image frame;

[0008] All the image frames in the second image frame sequence are synthesized with the target image frame to generate a target dynamic poster corresponding to the target video.

[0009] In an optional implementation, determining a key image frame from the first image frame sequence as a target image frame includes:

[0010] For each of the image frames in the first image frame sequence, performing an image aesthetic evaluation on the image frame to obtain a first evaluation value corresponding to the image frame, and performing an image quality evaluation on the image frame to obtain a second evaluation value corresponding to the image frame;

[0011] determining a target evaluation value corresponding to the image frame according to the first evaluation value and the second evaluation value corresponding to the image frame;

[0012] According to the target evaluation values ​​corresponding to all the image frames in the first image frame sequence, a key image frame is determined from the first image frame sequence to serve as a target image frame.

[0013] In an optional implementation, determining a target evaluation value corresponding to the image frame according to the first evaluation value and the second evaluation value corresponding to the image frame includes:

[0014] Determine a first weight corresponding to the first evaluation value and a second weight corresponding to the second evaluation value;

[0015] Determining a weighted sum of the first evaluation value, the first weight, the second evaluation value, and the second weight to obtain a target evaluation value corresponding to the image frame;

[0016] The step of determining a key image frame from the first image frame sequence as a target image frame according to the target evaluation values ​​corresponding to all the image frames in the first image frame sequence includes:

[0017] According to the target evaluation values ​​corresponding to all the image frames in the first image frame sequence, determining a key image frame that meets a first preset condition from the first image frame sequence, wherein the first preset condition includes that the target evaluation value corresponding to the key image frame is the largest among all the obtained target evaluation values;

[0018] The key image frame is determined as a target image frame.

[0019] In an optional implementation, determining a target evaluation value corresponding to the image frame according to the first evaluation value and the second evaluation value corresponding to the image frame includes:

[0020] Determine a first weight corresponding to the first evaluation value and a second weight corresponding to the second evaluation value;

[0021] Determining a weighted sum of the first evaluation value, the first weight, the second evaluation value, and the second weight to obtain a target evaluation value corresponding to the image frame;

[0022] The step of determining a key image frame from the first image frame sequence as a target image frame according to the target evaluation values ​​corresponding to all the image frames in the first image frame sequence includes:

[0023] According to the target evaluation values ​​corresponding to all the image frames in the first image frame sequence, determining a key image frame that meets a first preset condition from the first image frame sequence, wherein the first preset condition includes that the target evaluation value corresponding to the key image frame is the largest among all the obtained target evaluation values;

[0024] The key image frame is determined as a target image frame.

[0025] In an optional implementation, determining the second image frame sequence from the first image frame sequence according to the target image frame includes:

[0026] For each of the image frames in the first image frame sequence, extracting facial features from the image frame to obtain facial features corresponding to the image frame;

[0027] For each of the image frames except the target image frame in the first image frame sequence, determining a similarity between the facial features corresponding to the image frame and the facial features corresponding to the target image frame;

[0028] Determine from the first image frame sequence all the image frames that are temporally continuous with the target image frame and whose similarity is greater than a preset similarity threshold;

[0029] All the obtained image frames are determined as a second image frame sequence.

[0030] In an optional implementation, before performing the step of synthesizing all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video, the method further includes:

[0031] Determine the sum of the number of frames between the target image frame and a plurality of the image frames in the second image frame sequence to obtain a target number of frames;

[0032] When the target frame number is greater than a preset frame number threshold, the step of synthesizing all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video is performed.

[0033] In an optional implementation, when the target frame number is greater than a preset frame number threshold, performing the step of synthesizing all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video includes:

[0034] When the target frame number is greater than a preset frame number threshold, performing image quality evaluation on the target image frame to obtain a third evaluation value corresponding to the target image frame;

[0035] performing image quality evaluation on each of the image frames in the second image frame sequence to obtain a fourth evaluation value corresponding to each of the image frames in the second image frame sequence;

[0036] Determine the average value between the third evaluation value and all the fourth evaluation values ​​obtained to obtain a target evaluation average value;

[0037] When the target evaluation mean is greater than a preset evaluation threshold, the step of synthesizing all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video is performed.

[0038] In a second aspect, the present application provides a device for generating a dynamic poster, comprising:

[0039] A processing module, used for acquiring a target video and performing frame splitting processing on the target video to obtain a first image frame sequence corresponding to the target video;

[0040] A determination module, used to determine a key image frame from the first image frame sequence as a target image frame;

[0041] The determining module is further configured to determine a second image frame sequence from the first image frame sequence according to the target image frame, wherein the second image frame sequence includes the target image frame and a plurality of image frames, the plurality of image frames are temporally continuous with the target image frame, and all the image frames in the second image frame sequence are similar to the target image frame;

[0042] A generation module is used to synthesize all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video.

[0043] In a third aspect, the present application provides an electronic device, comprising: a processor and a memory, wherein the processor is used to execute a dynamic poster generation program stored in the memory to implement the dynamic poster generation method as described above.

[0044] In a fourth aspect, the present application also provides a storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method for generating a dynamic poster as described above.

[0045] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art. The method provided by the embodiment of the present application includes: obtaining a target video, and performing frame splitting processing on the target video to obtain a first image frame sequence corresponding to the target video; determining a key image frame from the first image frame sequence as the target image frame; according to the target image frame, determining a second image frame sequence from the first image frame, the second image frame sequence including a target image frame and a plurality of image frames, the plurality of image frames are temporally continuous with the target image frame and all image frames in the second image frame sequence are similar to the target image frame; synthesizing all image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video. In the above manner, the embodiment of the present application determines the key image frame from the first image frame sequence corresponding to the target video, and then synthesizes all image frames obtained with the key image frame according to the key image frame from all image frames in the first image frame sequence that are temporally continuous with the key image frame and similar to the key image frame, so as to automatically generate an attractive target dynamic poster, and improve the generation efficiency of the target dynamic poster. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0048] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0049] Figure 1 A schematic diagram of a flow chart of a method for generating a dynamic poster provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of a flow chart of another method for generating a dynamic poster provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of the structure of a dynamic poster generation device provided in an embodiment of the present application;

[0052] Figure 4A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0053] In the above attached figure:

[0054] 10. Processing module; 20. Determination module; 30. Generation module;

[0055] 400, electronic device; 401, processor; 402, memory; 4021, operating system; 4022, application; 403, user interface; 404, network interface; 405, bus system. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0057] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0058] refer to Figure 1 , Figure 1 A schematic diagram of a flow chart of a method for generating a dynamic poster provided in an embodiment of the present application. A method for generating a dynamic poster provided in the present application comprises the following steps:

[0059] S101: Acquire a target video, and perform frame splitting processing on the target video to obtain a first image frame sequence corresponding to the target video.

[0060] In this embodiment, performing frame splitting processing on the target video can be understood as performing frame splitting processing on the target video according to the time sequence to obtain a first image frame sequence corresponding to the target video, and the first image frame sequence includes multiple image frames according to the time sequence. The target video can be understood as a video for which a dynamic poster needs to be generated. The target video can be selected according to actual needs, and the target video is not described in detail in this embodiment.

[0061] S102: Determine a key image frame from the first image frame sequence to serve as a target image frame.

[0062] In this embodiment, the key image frame can be understood as a key shot in the target video. In order to make the target dynamic poster corresponding to the generated target video attractive, based on the determined key image frame, each image frame related to the key image frame is determined from the first image frame sequence, so as to obtain the target dynamic poster corresponding to the target video according to the determined image frames and the key image frame.

[0063] Among them, the key image frame can be determined according to the image aesthetics of each image frame in the first image frame sequence, and the key image can also be determined according to the image quality of each image frame in the first image frame sequence. Of course, the key image frame can also be comprehensively determined according to the image aesthetics and image quality of each image frame in the first image frame sequence. The method for determining the key image frame will be described in detail below and will not be repeated in this embodiment.

[0064] S103: Determine a second image frame sequence from the first image frame sequence according to the target image frame.

[0065] In this embodiment, the second image frame sequence includes a target image frame and a plurality of image frames, the plurality of image frames and the target image frame are temporally continuous, and all image frames in the second image frame sequence are similar to the target image frame.

[0066] Among them, after obtaining the target image frame, the target time point corresponding to the target image frame can be determined, and multiple image frames are determined from the first image frame sequence according to the target time point under the conditions of time continuity and image similarity, so that the multiple image frames and the target image frame are used as the second image frame sequence, and the multiple image frames and the target image frames in the second image frame sequence are arranged in a time series.

[0067] S104: Synthesize all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video.

[0068] In this embodiment, after obtaining the second image frame sequence, all image frames in the second image frame sequence can be synthesized with the target image frame to generate a target dynamic poster corresponding to the target video. When synthesizing all image frames in the second image frame sequence with the target image frame, the synthesis of the image can be achieved through operations such as image superposition and mixing, thereby obtaining a target dynamic poster corresponding to the target video. Since the target image frame is a key shot in the target video, the second image frame sequence determined based on the target image frame is attractive and improves the efficiency of generating the target dynamic poster.

[0069] The present embodiment provides a method for generating a dynamic poster, which determines a key image frame from a first image frame sequence corresponding to a target video, and then uses all image frames obtained from the first image frame sequence that are temporally continuous with the key image frame and similar to the key image frame to synthesize the key image frame to automatically generate an attractive target dynamic poster, thereby improving the generation efficiency of the target dynamic poster.

[0070] refer to Figure 2 , Figure 2 A flow chart of another method for generating a dynamic poster provided in an embodiment of the present application. A method for generating a dynamic poster provided in the present application comprises the following steps:

[0071] S201: Acquire a target video, and perform frame splitting processing on the target video to obtain a first image frame sequence corresponding to the target video.

[0072] In this embodiment, step S201 is consistent with the above-mentioned step S101. For details, please refer to the above-mentioned step S101, and this embodiment will not be described in detail here.

[0073] S202: For each image frame in the first image frame sequence, perform image aesthetic evaluation on the image frame to obtain a first evaluation value corresponding to the image frame, and perform image quality evaluation on the image frame to obtain a second evaluation value corresponding to the image frame.

[0074] S203: Determine a target evaluation value corresponding to the image frame according to the first evaluation value and the second evaluation value corresponding to the image frame.

[0075] S204: Determine a key image frame from the first image frame sequence according to the target evaluation values ​​corresponding to all the image frames in the first image frame sequence to serve as a target image frame.

[0076] With respect to the above-mentioned steps S202 to S204, since the key image frame is a key shot in the target video, in order to determine the key image frame, the image aesthetics of each image frame in the first image frame sequence may be evaluated to obtain a first evaluation value corresponding to each image frame, and the image quality corresponding to each image frame in the first image frame sequence may be evaluated to obtain a second evaluation value corresponding to each image frame. After obtaining the first evaluation value and the second evaluation value corresponding to each image frame, the target evaluation value corresponding to each image frame is obtained, and thus the key image frame is determined from the first image frame sequence as the final target image frame by using the target evaluation values ​​corresponding to all image frames in the first image frame sequence.

[0077] In this embodiment, determining the target evaluation value corresponding to the image frame according to the first evaluation value and the second evaluation value corresponding to the image frame in step S203 includes:

[0078] Determine a first weight corresponding to the first evaluation value and a second weight corresponding to the second evaluation value;

[0079] A weighted sum of the first evaluation value, the first weight, the second evaluation value, and the second weight is determined to obtain a target evaluation value corresponding to the image frame.

[0080] Among them, the first weight corresponding to the image aesthetic evaluation and the second weight corresponding to the image quality evaluation can be pre-set. After obtaining the first evaluation value and the second evaluation value, the first weight corresponding to the image aesthetic evaluation can be used as the first weight corresponding to the first evaluation value, and the second weight corresponding to the image quality evaluation can be used as the second weight corresponding to the second evaluation value, so as to determine the first product between the first evaluation value and the first weight and the second product between the second evaluation value and the second weight value, and the sum of the first product and the second product is used as the weighted sum of the first evaluation value, the first weight, the second evaluation value and the second weight, so as to obtain the target evaluation value corresponding to the image frame. It should be noted that the specific values ​​of the first weight and the second weight can be set according to actual needs, and the specific values ​​of the first weight and the second weight are not limited in this embodiment.

[0081] In this embodiment, in step S204, according to the target evaluation values ​​corresponding to all the image frames in the first image frame sequence, a key image frame is determined from the first image frame sequence as a target image frame, including:

[0082] According to the target evaluation values ​​corresponding to all the image frames in the first image frame sequence, a key image frame satisfying a first preset condition is determined from the first image frame sequence, wherein the first preset condition includes that the target evaluation value corresponding to the key image frame is the largest among all the obtained target evaluation values;

[0083] A key image frame is determined as a target image frame.

[0084] Among them, since the target evaluation value corresponding to the key image frame is the largest among all the obtained target evaluation values, the determined key image frame has high attractiveness, so that the second image frame sequence determined from the first image frame sequence based on the key image frame is also attractive. It should be noted that, for example, the first image frame sequence includes image frame A, image frame B and image frame C, the target evaluation value corresponding to image frame A is E1, the target evaluation value corresponding to image frame B is E2, and the target evaluation value corresponding to image frame C is E3, the target evaluation value E1 is less than the target evaluation value E2, and the target evaluation value E2 is less than the target evaluation value E3, then image frame C is the key image frame in the first image frame series.

[0085] Specifically, after obtaining the target evaluation value corresponding to each image frame in the first image frame sequence, a plurality of image frames satisfying a second preset condition are determined from the first image frame sequence, wherein the second preset condition includes that the target evaluation value corresponding to the image frame is greater than a preset evaluation threshold;

[0086] For each image frame that meets the second preset condition, determining a target story line to which the image frame belongs;

[0087] Determine, from all the obtained image frames satisfying the second preset condition, all the image frames whose target story line is a preset story line;

[0088] When all the obtained image frames are one, the image frame is determined as a key image frame in the first image frame sequence, and the key image frame is used as a target image frame;

[0089] When there are at least two image frames obtained, determining a key image frame satisfying a third preset condition from all the image frames obtained, wherein the third preset condition includes that a target evaluation value corresponding to the key image frame is the largest among the target evaluation values ​​corresponding to all the image frames obtained;

[0090] The key image frame is used as the target image frame.

[0091] More specifically, the correspondence between each image frame and the story line in the target video can be preset. In order to make the target dynamic poster generated in the end more attractive, the preset story line to which the generated target dynamic poster belongs can be pre-selected to generate the target dynamic poster corresponding to the final target video according to the preset story line. When the target dynamic poster needs to be generated, multiple image frames whose target evaluation values ​​are greater than the preset evaluation threshold can be determined from the first image frame sequence, so that according to the multiple determined image frames, the target story line to which the image frame belongs is determined to be the image frame of the preset story line, so that when the determined image frame is one, the image frame is used as the final target image frame, and the final target dynamic poster is generated according to the target image frame. When the determined image frame is at least two, the image frame corresponding to the maximum target evaluation value is determined from all the obtained image frames, and then the image frame is used as the final target image frame, and the final target dynamic poster is generated according to the target image frame. The specific value of the preset evaluation threshold can be set according to actual needs, and the specific value of the preset evaluation threshold is not limited in this embodiment.

[0092] It should be noted that when determining the key image frame based on the image aesthetics of each image frame in the first image frame sequence, the image aesthetics of each image frame in the first image frame sequence may be evaluated separately to determine the image frame corresponding to the maximum image aesthetics evaluation value from the first image frame sequence, and the image frame is used as the key image frame; when determining the key image frame based on the image quality of each image frame in the first image frame sequence, the image quality of each image frame in the first image frame sequence may be evaluated separately to determine the image frame corresponding to the maximum image quality evaluation value from the first image frame sequence, and the image frame is used as the key image frame.

[0093] S205: Determine a second image frame sequence from the first image frame sequence according to the target image frame.

[0094] In this embodiment, determining the second image frame sequence from the first image frame sequence according to the target image frame in step S205 includes:

[0095] For each image frame in the first image frame sequence, extracting facial features of the image frame to obtain facial features corresponding to the image frame;

[0096] For each image frame except the target image frame in the first image frame sequence, determining the similarity between the facial features corresponding to the image frame and the facial features corresponding to the target image frame;

[0097] Determine from the first image frame sequence all image frames that are temporally continuous with the target image frame and whose similarity is greater than a preset similarity threshold;

[0098] All obtained image frames are determined as a second image frame sequence.

[0099] Among them, in order to make the target dynamic poster finally generated, after determining the target image frame from the first image frame sequence, the facial feature correlation between the target image frame and each image frame in the first image frame sequence can be used to determine all image frames similar to the target image frame from the first image frame sequence, and then use all image frames similar to the target image frame and the target image frame to obtain the second image frame sequence. For example, the time interval between every two image frames in the first image frame sequence is d1, and the target image frame img 目 The corresponding target time point is t1, all the image frames included in the second image frame sequence are img1, img2, img3 and img4, and the relationship between the target image frame and all the image frames in the second image frame sequence in time sequence is: img1, img2, img3, img4. 目 , img4, then img1, img2, img3 and img4 are all the same as img 目Similarly, the time interval between img2 and img1 is d1, the time interval between img3 and img2 is d1, and the time interval between img 目 The time interval between img4 and img3 is d1, and the time interval between img4 and img 目 The time interval between them is d1.

[0100] Specifically, in order to determine the second image frame sequence, we can first select all continuous image frames of a first preset number n1 before the target time point and all continuous image frames of a second preset number n2 after the target time point in the first image frame sequence according to the target time point corresponding to the target image frame. When determining all image frames that are temporally continuous and similar to the target image frame, we determine them from all the image frames obtained above, thereby obtaining the second image frame sequence.

[0101] In this embodiment, after the step of determining the second image frame sequence from the first image frame sequence according to the target image frame is performed, a method for generating a dynamic poster provided by this embodiment includes the following steps:

[0102] Determine the sum of the number of frames between the target image frame and the plurality of image frames in the second image frame sequence to obtain the target number of frames;

[0103] When the target frame number is greater than the preset frame number threshold, the following step S206 is executed.

[0104] Among them, the specific value of the preset frame number threshold can be set according to actual needs, and the specific value of the preset frame number threshold is not limited in this embodiment. In order to ensure the dynamic effect of the target dynamic poster finally generated, the sum of the frame numbers between the target image frame and multiple image frames in the second image frame sequence is determined to obtain the target frame number. Only when the target frame number is greater than the preset frame number threshold can the dynamic effect of the target dynamic poster finally generated be guaranteed. Therefore, when the target frame number is greater than the preset frame number threshold, the following S206 step can be executed to generate the final target dynamic poster.

[0105] In this embodiment, when the target frame number is greater than a preset frame number threshold, all image frames in the second image frame sequence are synthesized with the target image frame to generate a target dynamic poster corresponding to the target video, including:

[0106] When the target frame number is greater than a preset frame number threshold, performing image quality evaluation on the target image frame to obtain a third evaluation value corresponding to the target image frame;

[0107] Performing image quality evaluation on each image frame in the second image frame sequence to obtain a fourth evaluation value corresponding to each image frame in the second image frame sequence;

[0108] Determine the average between the third evaluation value and all the obtained fourth evaluation values ​​to obtain a target evaluation average;

[0109] When the target evaluation mean is greater than a preset evaluation threshold, a step of synthesizing all image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video is performed.

[0110] Among them, the specific value of the preset evaluation threshold can be set according to actual needs, and the specific value of the preset evaluation threshold is not limited in this embodiment. In order to further improve the visual effect of the generated target dynamic poster, when the target frame number between the target image frame in the second image frame sequence and all image frames is greater than the preset frame number threshold, the average between the image quality evaluation value of the target image frame in the second image frame sequence and the image quality evaluation value of all image frames can be determined to obtain the target evaluation mean. When the target evaluation mean is greater than the preset evaluation threshold, the following S206 step is executed to generate the final target dynamic poster.

[0111] In this embodiment, when there are multiple target image frames, each target image frame corresponds to a second image frame sequence. In order to ensure the target dynamic poster that is finally generated, the target frame number corresponding to each second image frame sequence is determined in the above manner, so as to determine all second image frame sequences whose target frame number is greater than the preset frame number threshold from the multiple second image frame sequences. For each determined second image frame sequence, the target evaluation mean corresponding to the second image frame sequence is determined, and the second image frame sequence corresponding to the largest target evaluation mean is determined from all the determined second image frame sequences, and the second image frame sequence corresponding to the largest target evaluation mean is used to perform step S206.

[0112] S206: Synthesize all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video.

[0113] In this embodiment, in step S206, all the image frames in the second image frame sequence are synthesized with the target image frame to generate a target dynamic poster corresponding to the target video, including:

[0114] Determine a face frame and a subtitle frame in a target image frame in a second image frame sequence, and determine a face frame and a subtitle frame in each image frame in the second image frame sequence;

[0115] Determine the largest face frame from all the obtained face frames and determine the largest subtitle frame from all the obtained subtitle frames;

[0116] Cropping each image frame in the second image frame sequence according to the largest face frame and the largest subtitle frame to obtain a cropped image segment corresponding to each image frame in the second image frame sequence;

[0117] All the obtained cropped image segments are synthesized with the target image frame to generate a target dynamic poster corresponding to the target video.

[0118] Among them, in order to ensure the visual effect of the generated target dynamic poster, the face frames and subtitle frames of all image frames and the target image frames in the second image frame sequence are determined, so as to determine the largest face frame and the largest subtitle frame from all the obtained face frames, and then use the largest face frame and the largest subtitle frame to crop the faces and subtitles in the image frames to crop out suitable image segments, and then synthesize all the cropped image segments and the target image frames according to the time series to generate the target dynamic poster corresponding to the target video.

[0119] The present embodiment provides a method for generating a dynamic poster, which determines a key image frame from a first image frame sequence corresponding to a target video, and then uses all image frames obtained from the first image frame sequence that are temporally continuous with the key image frame and similar to the key image frame to synthesize the key image frame to automatically generate an attractive target dynamic poster, thereby improving the generation efficiency of the target dynamic poster.

[0120] refer to Figure 3 , Figure 3 A schematic diagram of the structure of a dynamic poster generation device provided in an embodiment of the present application. A dynamic poster generation device provided in an embodiment of the present application includes: a processing module 10, a determination module 20 and a generation module 30. The processing module 10 is used to obtain a target video and perform frame decomposition processing on the target video to obtain a first image frame sequence corresponding to the target video; the determination module 20 is used to determine a key image frame from the first image frame sequence as a target image frame; the determination module 20 is also used to determine a second image frame sequence from the first image frame sequence according to the target image frame, the second image frame sequence includes the target image frame and multiple image frames, the multiple image frames are temporally continuous with the target image frame and all the image frames in the second image frame sequence are similar to the target image frame; the generation module 30 is used to synthesize all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video.

[0121] In this embodiment, the determination module 20 is further configured to:

[0122] For each of the image frames in the first image frame sequence, performing an image aesthetic evaluation on the image frame to obtain a first evaluation value corresponding to the image frame, and performing an image quality evaluation on the image frame to obtain a second evaluation value corresponding to the image frame;

[0123] determining a target evaluation value corresponding to the image frame according to the first evaluation value and the second evaluation value corresponding to the image frame;

[0124] According to the target evaluation values ​​corresponding to all the image frames in the first image frame sequence, a key image frame is determined from the first image frame sequence to serve as a target image frame.

[0125] In this embodiment, the determination module 20 is further configured to:

[0126] Determine a first weight corresponding to the first evaluation value and a second weight corresponding to the second evaluation value;

[0127] A weighted sum of the first evaluation value, the first weight, the second evaluation value, and the second weight is determined to obtain a target evaluation value corresponding to the image frame.

[0128] In this embodiment, the determination module 20 is further configured to:

[0129] According to the target evaluation values ​​corresponding to all the image frames in the first image frame sequence, determining a key image frame that meets a first preset condition from the first image frame sequence, wherein the first preset condition includes that the target evaluation value corresponding to the key image frame is the largest among all the obtained target evaluation values;

[0130] The key image frame is determined as a target image frame.

[0131] In this embodiment, the generating module 30 is further used for:

[0132] Determine a face frame and a subtitle frame in the target image frame in the second image frame sequence, and determine a face frame and a subtitle frame in each of the image frames in the second image frame sequence;

[0133] Determine the largest face frame from all the obtained face frames, and determine the largest subtitle frame from all the obtained subtitle frames;

[0134] Cropping each of the image frames in the second image frame sequence according to the largest face frame and the largest subtitle frame to obtain a cropped image segment corresponding to each of the image frames in the second image frame sequence;

[0135] All the obtained cropped image segments are synthesized with the target image frame to generate a target dynamic poster corresponding to the target video.

[0136] In this embodiment, the determination module 20 is further configured to:

[0137] For each of the image frames in the first image frame sequence, extracting facial features from the image frame to obtain facial features corresponding to the image frame;

[0138] For each of the image frames except the target image frame in the first image frame sequence, determining a similarity between the facial features corresponding to the image frame and the facial features corresponding to the target image frame;

[0139] Determine from the first image frame sequence all the image frames that are temporally continuous with the target image frame and whose similarity is greater than a preset similarity threshold;

[0140] All the obtained image frames are determined as a second image frame sequence.

[0141] In this embodiment, the generating module 30 is further used for:

[0142] Determine the sum of the number of frames between the target image frame and a plurality of the image frames in the second image frame sequence to obtain a target number of frames;

[0143] When the target frame number is greater than a preset frame number threshold, all the image frames in the second image frame sequence are synthesized with the target image frame to generate a target dynamic poster corresponding to the target video.

[0144] In this embodiment, the generating module 30 is further used for:

[0145] When the target frame number is greater than a preset frame number threshold, performing image quality evaluation on the target image frame to obtain a third evaluation value corresponding to the target image frame;

[0146] performing image quality evaluation on each of the image frames in the second image frame sequence to obtain a fourth evaluation value corresponding to each of the image frames in the second image frame sequence;

[0147] Determine the average value between the third evaluation value and all the fourth evaluation values ​​obtained to obtain a target evaluation average value;

[0148] When the target evaluation mean is greater than a preset evaluation threshold, all the image frames in the second image frame sequence are synthesized with the target image frame to generate a target dynamic poster corresponding to the target video.

[0149] The present embodiment provides a device for generating a dynamic poster, which determines a key image frame from a first image frame sequence corresponding to a target video, and then synthesizes all image frames obtained with the key image frame from the first image frame sequence that are temporally continuous with the key image frame and similar to the key image frame, so as to automatically generate an attractive target dynamic poster, thereby improving the generation efficiency of the target dynamic poster.

[0150] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4 The electronic device 400 shown includes: at least one processor 401, a memory 402, at least one network interface 404 and other user interfaces 403. The various components in the electronic device 400 are coupled together via a bus system 405. It is understood that the bus system 405 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 405 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 405 is not shown in FIG. Figure 4 Various buses are labeled as bus system 405 .

[0151] The user interface 403 may include a display, a keyboard, or a pointing device (eg, a mouse, a trackball, a touch pad, or a touch screen).

[0152] It can be understood that the memory 402 in the embodiment of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 402 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0153] In some implementations, the memory 402 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system 4021 and application programs 4022 .

[0154] Among them, the operating system 4021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 4022 includes various application programs, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. The program for implementing the method of the embodiment of the present application can be included in the application 4022.

[0155] In the embodiment of the present application, by calling the program or instructions stored in the memory 402, specifically, the program or instructions stored in the application 4022, the processor 401 is used to execute the method steps provided by each method embodiment.

[0156] The method disclosed in the above embodiment of the present application can be applied to the processor 401, or implemented by the processor 401. The processor 401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 401 or the instruction in the form of software. The above processor 401 can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software units in the decoding processor can be executed. The software unit can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 402, and the processor 401 reads the information in the memory 402 and completes the steps of the above method in combination with its hardware.

[0157] It is understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPDevice, DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in the present application, or a combination thereof.

[0158] For software implementation, the technology described herein can be implemented by a unit that performs the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.

[0159] The electronic device provided in this embodiment may be Figure 4 The electronic device shown in FIG. 1 may perform the following steps: Figure 1 and Figure 2 All steps of the method for generating dynamic posters in Figure 1 and Figure 2 For details on the technical effects of the method for generating dynamic posters shown, please refer to Figure 1 and Figure 2 For the sake of brevity, the relevant description is not repeated here.

[0160] The embodiment of the present application also provides a storage medium (computer-readable storage medium). The storage medium here stores one or more programs. The storage medium may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk or a solid-state drive; the memory may also include a combination of the above-mentioned types of memory.

[0161] When one or more programs in the storage medium can be executed by one or more processors, the dynamic poster generation method executed on the dynamic poster generation device side can be implemented.

[0162] The processor is used to execute the dynamic poster generation program stored in the memory to implement the following steps of the dynamic poster generation method performed on the dynamic poster generation device side.

[0163] The professionals should further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0164] It should be noted that the phrases "one implementation", "an embodiment", "an exemplary embodiment", "some embodiments", etc. mentioned in the specification indicate that the described embodiments may include certain features, structures or characteristics, but not every embodiment may include the certain features, structures or characteristics. In addition, such phrases do not necessarily refer to the same embodiment. In addition, when describing certain features, structures or characteristics in conjunction with an embodiment, it is within the knowledge of those skilled in the art to implement such features, structures or characteristics in conjunction with other embodiments, whether explicitly or not explicitly described.

[0165] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0166] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for generating a dynamic poster, characterized in that: include: Acquire a target video, and perform frame splitting processing on the target video to obtain a first image frame sequence corresponding to the target video; Determining a key image frame from the first image frame sequence as a target image frame; According to the target image frame, determining a second image frame sequence from the first image frame sequence, the second image frame sequence comprising the target image frame and a plurality of image frames, the plurality of image frames being temporally continuous with the target image frame and all the image frames in the second image frame sequence being similar to the target image frame; All the image frames in the second image frame sequence are synthesized with the target image frame to generate a target dynamic poster corresponding to the target video.

2. The method according to claim 1, characterized in that The step of determining a key image frame from the first image frame sequence as a target image frame includes: For each of the image frames in the first image frame sequence, performing an image aesthetic evaluation on the image frame to obtain a first evaluation value corresponding to the image frame, and performing an image quality evaluation on the image frame to obtain a second evaluation value corresponding to the image frame; determining a target evaluation value corresponding to the image frame according to the first evaluation value and the second evaluation value corresponding to the image frame; According to the target evaluation values ​​corresponding to all the image frames in the first image frame sequence, a key image frame is determined from the first image frame sequence to serve as a target image frame.

3. The method according to claim 2, characterized in that Determining a target evaluation value corresponding to the image frame according to the first evaluation value and the second evaluation value corresponding to the image frame includes: Determine a first weight corresponding to the first evaluation value and a second weight corresponding to the second evaluation value; Determining a weighted sum of the first evaluation value, the first weight, the second evaluation value, and the second weight to obtain a target evaluation value corresponding to the image frame; The step of determining a key image frame from the first image frame sequence as a target image frame according to the target evaluation values ​​corresponding to all the image frames in the first image frame sequence includes: According to the target evaluation values ​​corresponding to all the image frames in the first image frame sequence, determining a key image frame that meets a first preset condition from the first image frame sequence, wherein the first preset condition includes that the target evaluation value corresponding to the key image frame is the largest among all the obtained target evaluation values; The key image frame is determined as a target image frame.

4. The method according to claim 1, characterized in that: The synthesizing all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video includes: Determine a face frame and a subtitle frame in the target image frame in the second image frame sequence, and determine a face frame and a subtitle frame in each of the image frames in the second image frame sequence; Determine the largest face frame from all the obtained face frames, and determine the largest subtitle frame from all the obtained subtitle frames; Cropping each of the image frames in the second image frame sequence according to the largest face frame and the largest subtitle frame to obtain a cropped image segment corresponding to each of the image frames in the second image frame sequence; All the obtained cropped image segments are synthesized with the target image frame to generate a target dynamic poster corresponding to the target video.

5. The method according to claim 1, characterized in that The step of determining a second image frame sequence from the first image frame sequence according to the target image frame comprises: For each of the image frames in the first image frame sequence, extracting facial features from the image frame to obtain facial features corresponding to the image frame; For each of the image frames except the target image frame in the first image frame sequence, determining a similarity between the facial features corresponding to the image frame and the facial features corresponding to the target image frame; Determine from the first image frame sequence all the image frames that are temporally continuous with the target image frame and whose similarity is greater than a preset similarity threshold; All the obtained image frames are determined as a second image frame sequence.

6. The method according to claim 5, characterized in that Before performing the step of synthesizing all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video, the method further includes: Determine the sum of the number of frames between the target image frame and a plurality of the image frames in the second image frame sequence to obtain a target number of frames; When the target frame number is greater than a preset frame number threshold, the step of synthesizing all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video is performed.

7. The method according to claim 6, characterized in that When the target frame number is greater than a preset frame number threshold, performing the step of synthesizing all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video includes: When the target frame number is greater than a preset frame number threshold, performing image quality evaluation on the target image frame to obtain a third evaluation value corresponding to the target image frame; performing image quality evaluation on each of the image frames in the second image frame sequence to obtain a fourth evaluation value corresponding to each of the image frames in the second image frame sequence; Determine the average value between the third evaluation value and all the fourth evaluation values ​​obtained to obtain a target evaluation average value; When the target evaluation mean is greater than a preset evaluation threshold, the step of synthesizing all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video is performed.

8. A device for generating a dynamic poster, characterized in that: include: A processing module, used for acquiring a target video and performing frame splitting processing on the target video to obtain a first image frame sequence corresponding to the target video; A determination module, used to determine a key image frame from the first image frame sequence as a target image frame; The determining module is further configured to determine a second image frame sequence from the first image frame sequence according to the target image frame, wherein the second image frame sequence includes the target image frame and a plurality of image frames, the plurality of image frames are temporally continuous with the target image frame, and all the image frames in the second image frame sequence are similar to the target image frame; A generation module is used to synthesize all the image frames in the second image frame sequence with the target image frame to generate a target dynamic poster corresponding to the target video.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the processor is used to execute a dynamic poster generation program stored in the memory to implement the dynamic poster generation method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method for generating a dynamic poster according to any one of claims 1 to 7.

Images