Panoramic video automatic editing method and device, computer equipment and storage medium
By analyzing the picture characteristics of the panoramic video clips and adjusting the order of the template video clips, automatic editing of panoramic videos is realized, solving the trouble of manually typing and moving mirrors in the existing technology, and improving editing efficiency.
Patent Information
- Application Number
- CN202411519915.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-29
- Publication Date
- 2025-03-04
AI Technical Summary
The existing technology lacks automatic editing methods for panoramic videos, and users need to manually apply the mirror, which is troublesome and time-consuming.
By obtaining the panoramic video to be edited, extracting the video clips and analyzing their picture characteristics, adjusting the order of the template video clips, and realizing automatic video editing.
Without the need for manual user touching, the edited target video is automatically generated, which simplifies the panoramic video editing process and improves efficiency.
Smart Images
Figure CN119562129A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of video editing technology, and specifically to a method, apparatus, computer equipment and storage medium for automatic editing of panoramic videos. Background Art
[0002] Panoramic videos are becoming more and more popular among users due to their 360° all-round vision. More and more users like to use panoramic videos to record their lives. However, since panoramic videos contain too much content, users need to edit them in order to obtain better visual viewing effects. This requires users to have a certain level of video editing skills and a certain amount of video editing time. Some video editing applications provide users with video editing templates, but they are usually only applicable to flat videos. For panoramic videos, there is currently no good method for users to quickly complete panoramic video editing. Summary of the invention
[0003] The embodiments of the present application provide a method, apparatus, computer device and storage medium for automatic editing of panoramic videos. The technical problem to be solved is that, in view of the defects of the prior art, there is no automatic editing method for panoramic video templates in the existing video editing template solutions. Users mainly need to rely on manual dot-and-move camera movements to edit panoramic videos, which is cumbersome and time-consuming and labor-intensive to operate.
[0004] In order to solve the above technical problems, a technical solution adopted by the present application is to provide a panoramic video automatic editing method, device, computer equipment and storage medium, wherein the panoramic video automatic editing method comprises:
[0005] Obtain a panoramic video to be edited, and extract n video segments to be edited from the panoramic video to be edited, where n is a positive integer;
[0006] Obtain a template video, and extract m template video segments from the template video, where m is a positive integer;
[0007] Analyzing the video clips to be edited, and obtaining the picture features of each of the video clips to be edited according to the analysis results;
[0008] According to the picture features, adjusting the sequence of the m template video clips to obtain an adjusted template video;
[0009] The n video clips to be edited are edited according to the adjusted template video to obtain an edited target video.
[0010] In a specific implementation, the analyzing the video clip to be edited includes:
[0011] Performing target analysis on the video clip to be edited to obtain a target object, analyzing motion features of the target object to obtain motion features of the target object, and analyzing scenes of the target object to obtain scene features of the target object.
[0012] In a specific implementation, obtaining the picture features of each of the video segments to be edited according to the analysis results includes:
[0013] According to the motion characteristics of the target object and the scene characteristics of the target object, the picture characteristics of each of the video clips to be edited are analyzed, the picture characteristics include picture motion characteristics and picture scene characteristics, the picture motion characteristics include picture change amounts, and the picture scene characteristics include any one of cycling scene characteristics, skiing scene characteristics, sky scene characteristics, indoor scene characteristics, and water scene characteristics.
[0014] In a specific implementation, adjusting the sequence of the m template video clips according to the picture features to obtain an adjusted template video includes:
[0015] Each of the template video clips corresponds to a key frame camera movement template. According to the picture features of the video clips to be edited, the target camera movement effect of each of the video clips to be edited is determined. According to the target camera movement effect of the video clips to be edited, the sequence of the m template video clips is adjusted so that the sequence of the key frame camera movement templates corresponding to the adjusted template video clips corresponds to the sequence of the target camera movement effects of the video clips to be edited, thereby obtaining the adjusted template video.
[0016] In a specific implementation, adjusting the sequence of the m template video clips according to the target camera effect of each of the video clips to be edited includes:
[0017] According to the target camera movement effect of each video clip to be edited, a target template video clip is selected from the m template video clips, the key frame camera movement template corresponding to the target template video clip has the same camera movement effect as the target camera movement effect, and the target template video clips are arranged in chronological order of the video clips to be edited to obtain n target template video clips.
[0018] In a specific implementation, determining the target camera effect of each of the video segments to be edited according to the picture features of the video segments to be edited includes:
[0019] When the picture change amount of the video clip to be edited is greater than the set change amplitude, and the picture scene has a cycling scene feature or a skiing scene feature, determining that the target camera movement effect of the video clip to be edited is a surround camera effect or a follow camera movement effect;
[0020] When the picture change amount of the video segment to be edited is less than the set change amplitude, the picture scene is any one of the sky scene characteristics, indoor scene characteristics or water scene characteristics, and it is determined that the target camera movement effect of the video segment to be edited is a push-pull camera movement effect.
[0021] In a specific implementation, the extracting n video segments to be edited from the panoramic video to be edited includes:
[0022] The beginning and the end of the panoramic video to be edited are removed, and the middle part of the panoramic video to be edited is divided into a video segment at set intervals to obtain n video segments to be edited.
[0023] In a specific embodiment, a panoramic video automatic editing device is also provided, and the panoramic video automatic editing device includes:
[0024] A first extraction module, the first extraction module is used to obtain a panoramic video to be edited, analyze the video segments to be edited, and extract n video segments to be edited from the panoramic video to be edited, where n is a positive integer;
[0025] A second extraction module, the second extraction module is used to obtain a template video, and extract m template video segments from the template video, where m is a positive integer;
[0026] An analysis module, the analysis module is used to analyze the video segments to be edited, and obtain the picture features of each video segment to be edited according to the analysis results;
[0027] An adjustment module, the adjustment module being used to adjust the sequence of the m template video clips according to the picture features to obtain an adjusted template video;
[0028] A video editing module is used to perform video editing on the n video clips to be edited according to the adjusted template video to obtain an edited target video.
[0029] In a specific embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the panoramic video automatic editing method described in any of the above specific embodiments are implemented.
[0030] In a specific embodiment, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the panoramic video automatic editing method described in any of the above specific embodiments are implemented.
[0031] The beneficial effect of the present application is that, different from the prior art, the present application provides a panoramic video automatic editing method, device, computer equipment and storage medium, and the panoramic video automatic editing method includes:
[0032] Obtain a panoramic video to be edited, and extract n video segments to be edited from the panoramic video to be edited, where n is a positive integer;
[0033] Obtain a template video, and extract m template video segments from the template video, where m is a positive integer;
[0034] Analyzing the video clips to be edited, and obtaining the picture features of each of the video clips to be edited according to the analysis results;
[0035] According to the picture features, adjusting the sequence of the m template video clips to obtain an adjusted template video;
[0036] The n video clips to be edited are edited according to the adjusted template video to obtain an edited target video.
[0037] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:
[0038] The method divides the panoramic video to be edited into n video segments to be edited and divides the template video into m template video segments, analyzes the video segments to be edited, obtains the picture features of each video segment to be edited according to the analysis results, and adjusts the sequence of the m template video segments according to the picture features of the video segments to be edited, so that each video segment to be edited has a corresponding template video segment to match it, thereby automatically editing the n video segments to be edited according to the adjusted template video, and automatically generates the edited target video without the need for the user to manually mark and move the camera, which is convenient for users to share quickly. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] In order to more clearly illustrate the technical solutions in the implementation modes of the present application, the drawings required for use in the description of the implementation modes will be briefly introduced below. Obviously, the drawings described below are only some implementation modes of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0040] Figure 1This is a schematic diagram of the implementation process of a panoramic video automatic editing method provided in Example 1 of the present application;
[0041] Figure 2 This is a schematic diagram of the module composition of a panoramic video automatic editing device provided in Example 2 of the present application;
[0042] Figure 3 It is a schematic diagram of the internal structure of a computer device provided in Example 3 of the present application. DETAILED DESCRIPTION
[0043] The present application is further described in detail below in conjunction with the accompanying drawings and implementation methods. It is particularly noted that the following implementation methods are only used to illustrate the present application, but do not limit the scope of the present application. Similarly, the following implementation methods are only some implementation methods of the present application rather than all implementation methods. All other implementation methods obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0044] The terms "including" and "having" and any variations thereof in this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or modules is not limited to the listed steps or modules, but may optionally include steps or modules not listed, or may optionally include other steps or modules inherent to these processes, methods, products or devices.
[0045] The above terms are only for the convenience of description and should not be construed as limitations on the present technical solution.
[0046] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0047] The specific implementation of the present application is described in detail below in conjunction with specific embodiments.
[0048] Embodiment 1.
[0049] Figure 1 The implementation process of a panoramic video automatic editing method provided in Example 1 of the present application is shown. For the sake of convenience of explanation, only the part related to the embodiment of the present application is shown, which is described in detail as follows.
[0050] A panoramic video to be edited is obtained, and n video segments to be edited are extracted from the panoramic video to be edited, where n is a positive integer.
[0051] It should be noted that the panoramic video to be edited is a panoramic video that needs to be automatically edited. It can be a panoramic video with a certain length shot by a user through a panoramic device such as a panoramic camera. The length can range from a few seconds to more than ten minutes. It can be one panoramic video or multiple panoramic videos.
[0052] Extract n video segments to be edited from the panoramic video to be edited, extract n video segments to be edited by dividing a complete or multiple complete panoramic videos according to a certain rule, and then analyze each video segment to be edited. By performing video editing processing on each of the video segments to be edited, the video editing processing of the panoramic video to be edited can be completed more efficiently.
[0053] One specific implementation manner is that extracting n video segments to be edited from the panoramic video to be edited includes:
[0054] The beginning and the end of the panoramic video to be edited are removed, and the middle part of the panoramic video to be edited is divided into a video segment at set intervals to obtain n video segments to be edited.
[0055] It should be noted that usually the beginning and ending parts of the panoramic video shot by the user have certain empty shots. Therefore, the empty shots can be removed to obtain a better video editing effect. One specific implementation method is that the removed beginning and ending parts can be automatically supplemented with set beginning templates and ending templates to form a complete visual effect.
[0056] After removing the beginning and ending parts of the panoramic video to be edited, the remaining middle part is divided into a video segment every set time. The set time is determined according to the length of the panoramic video to be edited. It can usually be selected to split every 10s-30s to obtain n video segments to be edited, and n is usually selected as 3-6.
[0057] If the panoramic video to be edited is a plurality of panoramic videos, then after removing the beginning and the end of each panoramic video, the panoramic video is divided into a video segment at set time intervals according to the duration of each panoramic video. For the panoramic video with a long duration, the set time can be longer, and for the panoramic video with a short duration, the set time can be shorter.
[0058] A template video is obtained, and m template video segments are extracted from the template video, where m is a positive integer.
[0059] It should be noted that the template video is a template video with multiple camera movement effects. A video clip is extracted according to each camera movement effect to obtain m template video clips, and each template video clip corresponds to a camera movement effect.
[0060] The video segments to be edited are analyzed, and according to the analysis results, the picture features of each of the video segments to be edited are obtained.
[0061] It should be noted that, by analyzing each of the video clips to be edited, the picture features of the video clips to be edited are obtained. The picture features reflect the picture characteristics of the video clips to be edited and can describe the video clips to be edited to a certain extent. They can be used as a reference to determine what kind of camera movement effects should be selected for the video clips to be edited, so as to achieve a better video browsing effect.
[0062] One specific implementation method is that the analyzing the video clip to be edited includes:
[0063] Performing target analysis on the video clip to be edited to obtain a target object, analyzing motion features of the target object to obtain motion features of the target object, and analyzing scenes of the target object to obtain scene features of the target object.
[0064] It should be noted that the target analysis is performed on the video clip to be edited, and the target object is obtained through target detection and tracking. The target object can be a person, an animal or a building, etc. Here, it is preferred to perform target detection and tracking on the person, and analyze the motion characteristics of the target object to obtain the motion characteristics of the target object, such as analyzing whether the target object is moving, what kind of movement it is doing, such as skiing, cycling, walking, playing ball, etc. The scene of the target object is analyzed to obtain the scene characteristics of the target object, such as analyzing the current scene of the target object, such as outdoor cycling, snow skiing, sky wing flying or indoor scene.
[0065] One specific implementation method is that, according to the analysis result, the picture feature of each video segment to be edited is obtained, including:
[0066] According to the motion characteristics of the target object and the scene characteristics of the target object, the picture characteristics of each of the video clips to be edited are analyzed, the picture characteristics include picture motion characteristics and picture scene characteristics, the picture motion characteristics include picture change amounts, and the picture scene characteristics include any one of cycling scene characteristics, skiing scene characteristics, sky scene characteristics, indoor scene characteristics, and water scene characteristics.
[0067] It should be noted that the picture features of the video clips to be edited are obtained by analyzing the target object in the video clips to be edited. The picture features of each of the video clips to be edited are analyzed according to the motion features of the target object and the scene features of the target object. Specifically, one feasible implementation method is to use the motion features of the target object, such as the movement speed of the target object, as the picture change amount of the video clips to be edited. The faster the movement speed, the greater the picture change amount of the video clips to be edited; and use the scene features of the target object as the picture scene features of the video clips to be edited, that is, the target object is riding outdoors, skiing on the snow, flying in the sky, indoor scenes, and playing on the water. The picture scene features of the video clips to be edited are riding scene features, skiing scene features, sky scene features, indoor scene features, and water scene features.
[0068] According to the picture features, the sequence of the m template video clips is adjusted to obtain an adjusted template video.
[0069] It should be noted that the video clips to be edited with different picture features need to correspond to different template video clips. Therefore, the order of the template video clips is adjusted according to the picture content of the video clips to be edited, so that the video clips to be edited can match the corresponding template video clips to obtain an edited video with better camera movement visual effects.
[0070] One specific implementation method is that adjusting the sequence of the m template video clips according to the picture features to obtain an adjusted template video includes:
[0071] Each of the template video clips corresponds to a key frame camera movement template. According to the picture features of the video clips to be edited, the target camera movement effect of each of the video clips to be edited is determined. According to the target camera movement effect of the video clips to be edited, the sequence of the m template video clips is adjusted so that the sequence of the key frame camera movement templates corresponding to the adjusted template video clips corresponds to the sequence of the target camera movement effects of the video clips to be edited, thereby obtaining the adjusted template video.
[0072] It should be noted that after determining the target camera movement effect of each video clip to be edited, the order of the template video clips is adjusted according to the target camera movement effect of the video clip to be edited, each template video clip corresponds to a video clip to be edited, and the key frame camera movement template of the template video clip is the same as or similar to the target camera movement effect of the video clip to be edited.
[0073] One specific implementation method is that adjusting the sequence of the m template video clips according to the target camera effect of each video clip to be edited includes:
[0074] According to the target camera movement effect of each video clip to be edited, a target template video clip is selected from the m template video clips, the key frame camera movement template corresponding to the target template video clip has the same camera movement effect as the target camera movement effect, and the target template video clips are arranged in chronological order of the video clips to be edited to obtain n target template video clips.
[0075] It should be noted that the key frame camera movement template corresponding to the target template video clip has the same or similar camera movement effect as the target camera movement effect, such as camera movement effects including push shot, pull shot, pan shot, moving shot, follow shot, etc. Push shot is used to move the camera from far to near, approaching the object, and highlighting the subject through changes in scene scale (far, full, medium, close, special). Camera movement techniques are used to enhance the user's sense of immersion, focus the audience's attention, magnify the expression of a character or an object, and create a sense of visual impact. The corresponding key frame camera movement template can be a push-then-pull or slow push shot.
[0076] Select n target template video segments from the m template video segments, so that the n target template video segments correspond one-to-one to the n video segments to be edited, wherein m can be greater than or equal to n, or less than n, and there can be repeated target template video segments between the n target template video segments.
[0077] If the target template video segment is not found in the m template video segments, the template video segment having a similar camera movement effect to the target template video segment is selected as the target template video segment.
[0078] One specific implementation manner is that determining the target camera effect of each video segment to be edited according to the picture features of the video segment to be edited includes:
[0079] When the picture change amount of the video clip to be edited is greater than the set change amplitude, and the picture scene has a cycling scene feature or a skiing scene feature, determining that the target camera movement effect of the video clip to be edited is a surround camera effect or a follow camera movement effect;
[0080] When the picture change amount of the video segment to be edited is less than the set change amplitude, the picture scene is any one of the sky scene characteristics, indoor scene characteristics or water scene characteristics, and it is determined that the target camera movement effect of the video segment to be edited is a push-pull camera movement effect.
[0081] It should be noted that this specific implementation only provides a feasible reference implementation. The picture features of the video clip to be edited include picture motion features and picture scene features. The picture motion features include picture change amounts. The picture scene features include any one of cycling scene features, skiing scene features, sky scene features, indoor scene features, and water scene features. By analyzing the picture change amount of the video clip to be edited, that is, the speed of picture change, if it is detected that the target object is taking a leisurely walk, or riding, running, skiing, etc. at a fast speed, or sitting quietly in a place to watch the scenery, etc., then according to the picture scene features of the current video clip to be edited, such as cycling in the open outdoors, skiing outdoors, flying in the sky, watercraft, or in an indoor scene, it is determined which motion should be adopted. A mirror effect, wherein a feasible specific implementation method is that when the picture change amount of the video clip to be edited is greater than the set change amplitude, and the picture scene is a cycling scene feature or a skiing scene feature, it is detected that the target object is riding or skiing quickly outdoors. In order to highlight the movement and expression of the target object, the target mirror effect of the video clip to be edited is determined to be a surround lens effect or a follow-up mirror effect. When the picture change amount of the video clip to be edited is less than the set change amplitude, the picture scene is any one of a sky scene feature, an indoor scene feature or a water scene feature, that is, it is detected that the target object is leisurely marching in the sky, indoors or on the water. In order to highlight the environment around the target object, the target mirror effect of the video clip to be edited is determined to be a push-pull mirror effect.
[0082] The n video clips to be edited are edited according to the adjusted template video to obtain an edited target video.
[0083] It should be noted that the adjusted template video has n target template video clips, and the key frame camera movement template corresponding to each target template video clip has the same camera movement effect as the target camera movement effect of the video clip to be edited. The target template video clips and the video clips to be edited are matched one by one, and the video clips to be edited are automatically edited according to the key frame camera movement templates corresponding to the target template video clips to obtain the edited target video clips. Finally, the n edited target video clips are merged to obtain the edited target video.
[0084] Embodiment 2.
[0085] Figure 2 A schematic diagram of the module composition of a panoramic video automatic editing device provided in the second embodiment of the present application is shown. For the sake of ease of explanation, only the parts related to the embodiment of the present application are shown.
[0086] An automatic panoramic video editing device according to an embodiment of the present application includes:
[0087] A first extraction module, the first extraction module is used to obtain a panoramic video to be edited, analyze the video segments to be edited, and extract n video segments to be edited from the panoramic video to be edited, where n is a positive integer;
[0088] A second extraction module, the second extraction module is used to obtain a template video, and extract m template video segments from the template video, where m is a positive integer;
[0089] An analysis module, the analysis module is used to analyze the video segments to be edited, and obtain the picture features of each video segment to be edited according to the analysis results;
[0090] An adjustment module, the adjustment module being used to adjust the sequence of the m template video clips according to the picture features to obtain an adjusted template video;
[0091] A video editing module is used to perform video editing on the n video clips to be edited according to the adjusted template video to obtain an edited target video.
[0092] A panoramic video automatic editing device of an embodiment of the present application is used to implement a panoramic video automatic editing method provided by any specific implementation method of the first embodiment of the present application:
[0093] Obtain a panoramic video to be edited, and extract n video segments to be edited from the panoramic video to be edited, where n is a positive integer;
[0094] Obtain a template video, and extract m template video segments from the template video, where m is a positive integer;
[0095] Analyzing the video clips to be edited, and obtaining the picture features of each of the video clips to be edited according to the analysis results;
[0096] According to the picture features, adjusting the sequence of the m template video clips to obtain an adjusted template video;
[0097] The n video clips to be edited are edited according to the adjusted template video to obtain an edited target video.
[0098] It should be noted that each module in the above-mentioned panoramic video automatic editing device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.
[0099] It should be noted that for technical details that are not described in detail in this embodiment, reference can be made to the panoramic video automatic editing method provided in the above-mentioned embodiment 1, and will not be repeated here.
[0100] Embodiment three.
[0101] In an embodiment of the present application, a computer device is provided. Figure 3 A schematic diagram of the internal structure of a computer device.
[0102] The computer device includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the panoramic video automatic editing method in any specific implementation provided in the first embodiment of the present application, specifically including:
[0103] Obtain a panoramic video to be edited, and extract n video segments to be edited from the panoramic video to be edited, where n is a positive integer;
[0104] Obtain a template video, and extract m template video segments from the template video, where m is a positive integer;
[0105] Analyzing the video clips to be edited, and obtaining the picture features of each of the video clips to be edited according to the analysis results;
[0106] According to the picture features, adjusting the sequence of the m template video clips to obtain an adjusted template video;
[0107] The n video clips to be edited are edited according to the adjusted template video to obtain an edited target video.
[0108] It should be noted that the computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a video generation method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.
[0109] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0110] It should be noted that, for technical details not described in detail in this embodiment, reference can be made to the panoramic video automatic editing method provided in any specific implementation manner in the above-mentioned embodiment 1, and will not be repeated here.
[0111] Embodiment 4.
[0112] In an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for automatically editing a panoramic video in any specific implementation provided in the first embodiment of the present application is implemented, specifically including:
[0113] Obtain a panoramic video to be edited, and extract n video segments to be edited from the panoramic video to be edited, where n is a positive integer;
[0114] Obtain a template video, and extract m template video segments from the template video, where m is a positive integer;
[0115] Analyzing the video clips to be edited, and obtaining the picture features of each of the video clips to be edited according to the analysis results;
[0116] According to the picture features, adjusting the sequence of the m template video clips to obtain an adjusted template video;
[0117] The n video clips to be edited are edited according to the adjusted template video to obtain an edited target video.
[0118] It should be noted that, for technical details not described in detail in this embodiment, reference can be made to the panoramic video automatic editing method provided in any specific implementation manner in the above-mentioned embodiment 1, and will not be repeated here.
[0119] Different from the prior art, the embodiments of the present application provide a panoramic video automatic editing method, device, computer equipment and storage medium, and the panoramic video automatic editing method includes:
[0120] Obtain a panoramic video to be edited, and extract n video segments to be edited from the panoramic video to be edited, where n is a positive integer;
[0121] Obtain a template video, and extract m template video segments from the template video, where m is a positive integer;
[0122] Analyzing the video clips to be edited, and obtaining the picture features of each of the video clips to be edited according to the analysis results;
[0123] According to the picture features, adjusting the sequence of the m template video clips to obtain an adjusted template video;
[0124] The n video clips to be edited are edited according to the adjusted template video to obtain an edited target video.
[0125] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:
[0126] The method divides the panoramic video to be edited into n video segments to be edited and divides the template video into m template video segments, analyzes the video segments to be edited, obtains the picture features of each video segment to be edited according to the analysis results, and adjusts the sequence of the m template video segments according to the picture features of the video segments to be edited, so that each video segment to be edited has a corresponding template video segment to match it, thereby automatically editing the n video segments to be edited according to the adjusted template video, and automatically generates the edited target video without the need for the user to manually mark and move the camera, which is convenient for users to share quickly.
[0127] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0128] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.
[0129] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a terminal device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.
[0130] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. 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 make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A panoramic video automatic editing method, characterized in that: The panoramic video automatic editing method comprises: Obtain a panoramic video to be edited, and extract n video segments to be edited from the panoramic video to be edited, where n is a positive integer; Obtain a template video, and extract m template video segments from the template video, where m is a positive integer; Analyzing the video clips to be edited, and obtaining the picture features of each of the video clips to be edited according to the analysis results; According to the picture features, adjusting the sequence of the m template video clips to obtain an adjusted template video; The n video clips to be edited are edited according to the adjusted template video to obtain an edited target video.
2. A panoramic video automatic editing method according to claim 1, characterized in that: The analyzing the video clip to be edited includes: Performing target analysis on the video clip to be edited to obtain a target object, analyzing motion features of the target object to obtain motion features of the target object, and analyzing scenes of the target object to obtain scene features of the target object.
3. A panoramic video automatic editing method according to claim 2, characterized in that: The step of obtaining the picture features of each video segment to be edited according to the analysis result includes: According to the motion characteristics of the target object and the scene characteristics of the target object, the picture characteristics of each of the video clips to be edited are analyzed, the picture characteristics include picture motion characteristics and picture scene characteristics, the picture motion characteristics include picture change amounts, and the picture scene characteristics include any one of cycling scene characteristics, skiing scene characteristics, sky scene characteristics, indoor scene characteristics, and water scene characteristics.
4. A panoramic video automatic editing method according to claim 3, characterized in that: The step of adjusting the sequence of the m template video clips according to the picture features to obtain an adjusted template video includes: Each of the template video clips corresponds to a key frame camera movement template. According to the picture features of the video clips to be edited, the target camera movement effect of each of the video clips to be edited is determined. According to the target camera movement effect of the video clips to be edited, the sequence of the m template video clips is adjusted so that the sequence of the key frame camera movement templates corresponding to the adjusted template video clips corresponds to the sequence of the target camera movement effects of the video clips to be edited, thereby obtaining the adjusted template video.
5. A panoramic video automatic editing method according to claim 4, characterized in that: The step of adjusting the sequence of the m template video clips according to the target camera effect of each of the video clips to be edited comprises: According to the target camera movement effect of each video clip to be edited, a target template video clip is selected from the m template video clips, the key frame camera movement template corresponding to the target template video clip has the same camera movement effect as the target camera movement effect, and the target template video clips are arranged in chronological order of the video clips to be edited to obtain n target template video clips.
6. A panoramic video automatic editing method according to claim 5, characterized in that: The step of determining a target camera effect of each of the video segments to be edited according to the picture features of the video segments to be edited comprises: When the picture change amount of the video clip to be edited is greater than the set change amplitude, and the picture scene has cycling scene characteristics or skiing scene characteristics, determining that the target camera movement effect of the video clip to be edited is a surround camera effect or a follow camera movement effect; When the picture change amount of the video segment to be edited is less than the set change amplitude, the picture scene is any one of the sky scene characteristics, indoor scene characteristics or water scene characteristics, and it is determined that the target camera movement effect of the video segment to be edited is a push-pull camera movement effect.
7. The method for automatically editing a panoramic video according to any one of claims 1 to 6, wherein extracting n video segments to be edited from the panoramic video to be edited comprises: The beginning and the end of the panoramic video to be edited are removed, and the middle part of the panoramic video to be edited is divided into a video segment at set intervals to obtain n video segments to be edited.
8. A panoramic video automatic editing device, characterized in that: The panoramic video automatic editing device comprises: A first extraction module, the first extraction module is used to obtain a panoramic video to be edited, analyze the video segments to be edited, and extract n video segments to be edited from the panoramic video to be edited, where n is a positive integer; A second extraction module, the second extraction module is used to obtain a template video, and extract m template video segments from the template video, where m is a positive integer; An analysis module, the analysis module is used to analyze the video segments to be edited, and obtain the picture features of each video segment to be edited according to the analysis results; An adjustment module, the adjustment module being used to adjust the sequence of the m template video clips according to the picture features to obtain an adjusted template video; A video editing module is used to perform video editing on the n video clips to be edited according to the adjusted template video to obtain an edited target video.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the panoramic video automatic editing method described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the panoramic video automatic editing method described in any one of claims 1 to 7 are implemented.