Video processing method, apparatus and device, and storage medium

Abstract

The present disclosure provides a video processing method, apparatus and device, and a storage medium. The method specifically comprises: acquiring a first video draft, and determining an initial highlight interval corresponding to the first video draft; on the basis of the initial highlight interval, determining a processed highlight interval corresponding to the first video draft; and generating a second video draft on the basis of the processed highlight interval corresponding to the first video draft and the first video draft. In embodiments of the present disclosure, by automatically determining a processed highlight interval corresponding to a first video draft, the first video draft is edited, and then a second video draft composed of a highlight clip (a second video clip) corresponding to the processed highlight interval is generated.

Description

A video processing method, apparatus, device, and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese Patent Application No. 202410498432.3, filed on April 24, 2024, entitled “A Video Processing Method, Apparatus, Device and Storage Medium”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to the field of data processing, and more particularly to a video processing method, apparatus, device, and storage medium. Background Technology

[0004] Traditional video editing techniques typically require users to manually locate highlight segments in video footage and then perform video editing based on these highlights. This method no longer meets users' needs for video editing. Summary of the Invention

[0005] To address the aforementioned technical problems, this disclosure provides a video processing method, apparatus, device, and storage medium.

[0006] In a first aspect, this disclosure provides a video processing method, the method comprising:

[0007] Obtain a first video draft and determine the initial highlight interval corresponding to the first video draft; wherein, the first video draft consists of one or more first video segments, and the initial highlight interval is used to characterize the display time interval of the highlight segment in the first video draft;

[0008] Based on the initial highlight range, the processed highlight range corresponding to the first video draft is determined; wherein, the processed highlight range has a one-to-one or many-to-one correspondence with the first video segment;

[0009] Based on the processed highlight region corresponding to the first video draft and the first video draft, a second video draft is generated; wherein, the second video draft consists of one or more second video segments, the second video segments are obtained from the first video draft based on the processed highlight region, the second video segments in the second video draft have a corresponding relationship with the first video segments in the first video draft, and the second video draft is used to generate the target video.

[0010] In one optional implementation, determining the processed highlight region corresponding to the first video draft based on the initial highlight region includes:

[0011] Determine whether the first initial highlight interval in the initial highlight interval corresponding to the first video draft is within the display time interval of multiple first video segments;

[0012] If it is determined that the first initial highlight interval is within the display time interval of multiple first video segments, then the first initial highlight interval is split into multiple highlight intervals, which are used as the processed highlight intervals corresponding to the first initial highlight interval; wherein, the multiple highlight intervals are respectively within the display time intervals of different first video segments, and each of the multiple highlight intervals is within the display time interval of one first video segment.

[0013] In an optional implementation, before generating the second video draft based on the processed highlight region corresponding to the first video draft and the first video draft, the method further includes:

[0014] Receive a range editing operation for a first processed highlight range within the processed highlight range corresponding to the first video draft; wherein the range editing operation is used to edit at least one of the range length, range start time point, and range end time point of the first processed highlight range;

[0015] Based on the interval editing operation, the edited highlight interval corresponding to the first processed highlight interval is determined;

[0016] Accordingly, generating a second video draft based on the processed highlight region corresponding to the first video draft and the first video draft includes:

[0017] A second video draft is generated based on the processed highlight region corresponding to the first video draft, the edited highlight region corresponding to the first processed highlight region, and the first video draft; wherein, the second video segment in the second video draft is obtained from the first video draft based on the processed highlight region and / or the edited highlight region.

[0018] In an optional implementation, before receiving the interval editing operation for the first processed highlight interval in the processed highlight interval corresponding to the first video draft, the method further includes:

[0019] Create a highlight range adjustment view component for the first processed highlight range, and display the highlight range adjustment view component;

[0020] Accordingly, receiving the interval editing operation for the first processed highlight interval in the processed highlight interval corresponding to the first video draft includes:

[0021] Based on the highlight range adjustment view component, a range editing operation is received for the first processed highlight range.

[0022] In one optional implementation, generating a second video draft based on the processed highlight region corresponding to the first video draft and the first video draft includes:

[0023] Cut out the video segment corresponding to the processed highlight area from the first video draft;

[0024] If it is determined that different processed highlight regions are within the same display time interval of the first video segment, then the video segments corresponding to the different processed highlight regions are all determined as the second video segments corresponding to the first video segment.

[0025] A second video draft is generated based on the second video segment.

[0026] In one optional implementation, before generating the second video draft based on the second video segment, the method further includes:

[0027] If it is determined that the end time point of the second processed highlight interval and the start time point of the third processed highlight interval are the same in the processed highlight interval corresponding to the first video draft, and the second processed highlight interval and the third processed highlight interval are in the same display time interval of the first video segment, then the video segments corresponding to the second processed highlight interval and the third processed highlight interval are merged to obtain the second video segment corresponding to the first video segment.

[0028] In one optional implementation, determining the initial highlight region corresponding to the first video draft includes:

[0029] The first video draft is analyzed using a highlight region recognition model to obtain the initial highlight region corresponding to the first video draft.

[0030] Secondly, this disclosure also provides a video processing apparatus, the apparatus comprising:

[0031] The first determining module is used to obtain a first video draft and determine the initial highlight interval corresponding to the first video draft; wherein, the first video draft is composed of one or more first video segments, and the initial highlight interval is used to characterize the display time interval of the highlight segment in the first video draft.

[0032] The second determining module is used to determine the processed highlight region corresponding to the first video draft based on the initial highlight region; wherein the processed highlight region has a one-to-one or many-to-one correspondence with the first video segment;

[0033] A first generation module is used to generate a second video draft based on the processed highlight region corresponding to the first video draft and the first video draft; wherein, the second video draft consists of one or more second video segments, the second video segments are obtained from the first video draft based on the processed highlight region, the second video segments in the second video draft have a corresponding relationship with the first video segments in the first video draft, and the second video draft is used to generate a target video.

[0034] Thirdly, this disclosure provides a computer-readable storage medium storing instructions that, when executed on a terminal device, cause the terminal device to implement the above-described method.

[0035] Fourthly, this disclosure provides a video processing device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the above-described method.

[0036] Fifthly, this disclosure provides a computer program product comprising a computer program / instruction that, when executed by a processor, implements the method described above.

[0037] The technical solution provided in this disclosure has at least the following advantages compared with the prior art:

[0038] This disclosure provides a video processing method. Specifically, a first video draft is obtained, and an initial highlight interval corresponding to the first video draft is determined. The first video draft consists of one or more first video segments, and the initial highlight interval is used to characterize the display time interval of the highlight segments in the first video draft. Then, a processed highlight interval corresponding to the first video draft is determined based on the initial highlight interval. The processed highlight interval has a one-to-one or many-to-one correspondence with the first video segments. Furthermore, a second video draft is generated based on the processed highlight interval corresponding to the first video draft and the first video draft. The second video draft consists of one or more second video segments, which are obtained from the first video draft based on the processed highlight interval. The second video segments in the second video draft have a correspondence with the first video segments in the first video draft. The second video draft is used to generate a target video. Attached Figure Description

[0039] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0040] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 is a flowchart of a video processing method provided in an embodiment of this disclosure;

[0042] Figure 2 is a schematic diagram showing the relationship between a first video segment, an initial highlight region, and a processed highlight region provided in an embodiment of this disclosure.

[0043] Figure 3 is a schematic diagram of a processed highlight region provided in an embodiment of this disclosure;

[0044] Figure 4 is a schematic diagram of a highlight range adjustment view component provided in an embodiment of this disclosure;

[0045] Figure 5 is a flowchart of a video processing method provided in an embodiment of this disclosure;

[0046] Figure 6 is a schematic diagram of a video processing device provided in an embodiment of this disclosure;

[0047] Figure 7 is a schematic diagram of the structure of a video processing device provided in an embodiment of this disclosure. Detailed Implementation

[0048] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0049] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0050] Traditional video editing techniques typically require users to manually locate highlight segments in video footage and then perform video editing based on these segments. This method no longer meets users' needs for video editing. Therefore, enriching video editing methods to satisfy users' demands is a pressing technical problem that needs to be solved.

[0051] To this end, this disclosure provides a video processing method. Specifically, a first video draft is obtained, and an initial highlight interval corresponding to the first video draft is determined. The first video draft consists of one or more first video segments, and the initial highlight interval is used to characterize the display time interval of the highlight segments in the first video draft. Then, a processed highlight interval corresponding to the first video draft is determined based on the initial highlight interval. The processed highlight interval has a one-to-one or many-to-one correspondence with the first video segments. Furthermore, a second video draft is generated based on the processed highlight interval corresponding to the first video draft and the first video draft. The second video draft consists of one or more second video segments, which are obtained from the first video draft based on the processed highlight interval. The second video segments in the second video draft have a correspondence with the first video segments in the first video draft. The second video draft is used to generate a target video.

[0052] This embodiment of the disclosure automatically determines the processed highlight regions corresponding to the first video draft, thereby enabling the editing of the first video draft and generating a second video draft composed of highlight segments (second video segments) corresponding to the processed highlight regions. It is evident that this embodiment of the disclosure enriches the video editing methods and enhances the user's video editing experience by determining the highlight regions.

[0053] Specifically, this disclosure provides a video processing method. Referring to Figure 1, which is a flowchart of a video processing method provided in this disclosure, the method specifically includes:

[0054] S101: Obtain the first video draft and determine the initial highlight range corresponding to the first video draft.

[0055] The first video draft consists of one or more first video segments, and the initial highlight range is used to characterize the display time range of the highlight segments in the first video draft.

[0056] The video processing method provided in this disclosure can be applied to a client, which can be deployed on terminals such as smartphones, tablets, laptops, and desktop computers.

[0057] In this embodiment of the disclosure, the first video draft can be any video imported by the user. The first video draft consists of one or more video segments, each of which can be referred to as a first video segment. For example, the first video segment can be video material corresponding to a shot in the first video draft. Each first video segment has duration information, etc.

[0058] In this embodiment of the disclosure, after obtaining the first video draft, the initial highlight interval corresponding to the first video draft is determined. The first video draft may include one or more initial highlight intervals. Each initial highlight interval may be within the display time interval of one first video segment in the first video draft, or it may occupy the display time intervals of multiple adjacent first video segments. That is, one initial highlight interval corresponds to one or more first video segments. In the relationship diagram shown in Figure 2, initial highlight segment A corresponds to first video segment 1, and initial highlight segment B corresponds to both first video segment 1 and first video segment 2.

[0059] Each initial highlight interval records the display time information of the highlight segment corresponding to that initial highlight interval in the first video draft. The highlight segment can be a video segment with high video content and video quality in the first video draft. The display time information of the highlight segment can specifically include the display time interval of the highlight segment in the first video draft. For example, if the display time interval of the first video draft is 0-17s, that is, the total duration is 17s, and assuming that the display time interval of a highlight segment in the first video draft is 1-4s, then the initial highlight interval corresponding to that highlight segment is 1-4s.

[0060] In practical applications, each initial highlight interval can also record the time information of the first video segment corresponding to that initial highlight interval in the first video draft, i.e., the display time interval of the first video segment. By recording the display time interval of the first video segment, it can be determined whether the initial highlight interval identified from the first video draft is accurate. In other words, the initial highlight interval identified from the first video segment cannot exceed the display time interval of the first video segment. For example, if the display time interval of the first video segment is 0-10s, then the minimum time point of the display time interval of the initial highlight interval identified from the first video segment cannot be less than 0s, and the maximum time point cannot be greater than 10s. If the initial highlight interval identified from the first video segment is 7-20s, since it exceeds the display time interval of 0-10s, it can be determined that the identified initial highlight interval has an accuracy problem. The initial highlight interval can be determined to be 7-10s by extracting the effective portion.

[0061] The method for determining the initial highlight region corresponding to the first video draft can include: using a highlight region recognition model to perform content analysis on the first video draft to obtain the initial highlight region corresponding to the first video draft. Specifically, the first video draft is input into the highlight region recognition model, and the highlight region recognition model identifies each highlight region in the first video draft, which is then output as the initial highlight region corresponding to the first video draft.

[0062] It is worth noting that the embodiments disclosed herein do not limit other methods for determining the initial highlight region corresponding to the first video draft.

[0063] S102: Determine the processed highlight range corresponding to the first video draft based on the initial highlight range.

[0064] The processed highlight region has a one-to-one or many-to-one correspondence with the first video segment.

[0065] In this embodiment of the disclosure, the processed highlight area and the first video segment in the first video draft can have a one-to-one relationship, that is, one processed highlight area is in the display time interval of one first video segment; the processed highlight area and the first video segment in the first video draft can have a many-to-one relationship, that is, multiple processed highlight areas can belong to the display time interval of the same first video segment.

[0066] In one optional implementation, determining the processed highlight region corresponding to the first video draft based on the initial highlight region may include:

[0067] For any initial highlight interval in the initial highlight interval corresponding to the first video draft, hereinafter referred to as the first initial highlight interval, we first determine whether the first initial highlight interval is within the display time interval of multiple first video segments, that is, whether the first initial highlight interval occupies the display time interval of multiple adjacent first video segments.

[0068] Figure 2 illustrates the relationship between a first video segment, an initial highlight region, and a processed highlight region, according to an embodiment of this disclosure. The first video draft contains two first video segments: the display time of first video segment 1 is 0-8.5 seconds, and the display time of first video segment 2 is 8.5-17 seconds. The first initial highlight region B identified from the first video draft is 6-9 seconds. Therefore, the first initial highlight region B is within the display time range of first video segment 1 and first video segment 2, meaning it falls within the display time range of multiple first video segments.

[0069] If it is determined that the first initial highlight region falls within the display time interval of multiple first video segments, then the first initial highlight region is split into multiple highlight regions, and these multiple split highlight regions are used as the processed highlight regions corresponding to the first initial highlight region. It is worth noting that the first initial highlight region occupying the display time interval of multiple first video segments can be split according to the display time interval of different first video segments. The resulting multiple highlight regions each fall within the display time interval of a different first video segment, and each of these multiple split highlight regions falls within the display time interval of one first video segment; that is, each processed highlight region corresponds to only one first video segment.

[0070] As shown in Figure 2 above, the first initial highlight region B falls within the display time interval of the first video segment 1 and the first video segment 2. Therefore, the first initial highlight region B is divided into highlight region B1 (6-8.5s) and highlight region B2 (8.5-9s). Highlight region B1 falls within the display time interval of the first video segment 1, and highlight region B2 falls within the display time interval of the first video segment 2. Highlight regions B1 and B2 are both processed highlight regions corresponding to the first initial highlight region B.

[0071] In one optional implementation, a corresponding highlight data model can be established for each processed highlight interval, and the highlight data model can be used to store the time information of the corresponding processed highlight interval, specifically including the time range corresponding to the processed highlight interval, the start time point and end time point of the first video segment in which the processed highlight interval is located, etc.

[0072] As shown in Figure 2 above, the processed highlight interval B1 (6-8.5s) obtained by splitting the first initial highlight interval B is within the display time interval of the first video segment 1. A corresponding highlight data model is created for the processed highlight interval B1 (6-8.5s). The minimum time point is stored as 0s, the maximum time point is 8.5s, and the time range is 6-8.5s.

[0073] If it is determined that the first initial highlight region is within the display time interval of a first video segment, then there is no need to split the first initial highlight region. The first initial highlight region can be directly used as the processed highlight region. A highlight data model can also be created for the processed highlight region to store the time information of the processed highlight region.

[0074] S103: Generate a second video draft based on the processed highlight region corresponding to the first video draft and the first video draft.

[0075] The second video draft consists of one or more second video segments, which are obtained from the first video draft based on the processed highlight range. The second video segments in the second video draft correspond to the first video segments in the first video draft. The second video draft is used to generate the target video.

[0076] In one optional implementation, after determining the processed highlight interval corresponding to the first video draft, it is determined whether different processed highlight intervals are within the same display time interval of the first video segment. If it is determined that different processed highlight intervals are within the same first video segment, then the video segments corresponding to the different processed highlight intervals in the first video draft are all determined as the second video segments corresponding to the first video segment.

[0077] In another optional implementation, if it is determined that different processed highlight regions are within the same first video segment, then it is further determined whether the video segments corresponding to the different processed highlight regions in the first video draft are adjacent, that is, whether the playback end time of the previous video segment is consistent with the playback start time of the next video segment. If they are consistent, then the video segment obtained by merging the video segments corresponding to the different processed highlight regions is determined as the second video segment corresponding to the first video segment.

[0078] Specifically, if it is determined that the end time point of the second processed highlight interval and the start time point of the third processed highlight interval are the same within the processed highlight interval corresponding to the first video draft, and the second and third processed highlight intervals are within the same display time interval of the first video segment, then the video segments corresponding to the second and third processed highlight intervals are merged to obtain the second video segment corresponding to the first video segment. A second video draft is then generated based on the merged video segment. The second and third processed highlight intervals are two adjacent processed highlight intervals within the same first video segment.

[0079] In other words, for two different processed highlight regions within the same first video segment, if the two different processed highlight regions are consecutive, then the video segments corresponding to the two different processed highlight regions are merged into a second video segment.

[0080] Figure 3 shows a schematic diagram of a processed highlight region provided in an embodiment of this disclosure. Assuming a first video segment corresponds to a processed highlight region, the video segment corresponding to this processed highlight region is cropped from the first video draft as the second video segment of the first video segment. This is illustrated in Case 1 of Figure 3.

[0081] Suppose a first video segment corresponds to two processed highlight regions. Then, the video segments corresponding to these two processed highlight regions are cropped from the first video draft and each is identified as the second video segment corresponding to the first video segment. This is illustrated in Case 2 of Figure 3. Note that the two processed highlight regions are not contiguous.

[0082] Suppose that a certain first video segment corresponds to two processed highlight regions, and these two processed highlight regions are contiguous. Then, the video segments corresponding to these two processed highlight regions are merged to obtain the second video segment corresponding to the first video segment. As shown in Case 3 of Figure 3.

[0083] In practical applications, if a certain first video segment does not have a corresponding processed highlight area, in one optional implementation, the first video segment can be deleted.

[0084] In another optional implementation, if a certain first video segment does not have a corresponding processed highlight area, a prompt message can also be displayed to prompt the user to manually find the highlight area.

[0085] In practical applications, after determining the processed highlight regions corresponding to the first video draft, video segments corresponding to each processed highlight region are extracted from the first video draft to obtain second video segments with a sequential relationship. Then, a second video draft is generated based on this sequential relationship and each second video segment. Each second video segment constituting the second video draft can be a highlight segment extracted from the first video draft.

[0086] In the video processing method provided in this embodiment, firstly, a first video draft is obtained, and an initial highlight interval corresponding to the first video draft is determined. The first video draft consists of one or more first video segments, and the initial highlight interval is used to characterize the display time interval of the highlight segments in the first video draft. Based on the initial highlight interval, a processed highlight interval corresponding to the first video draft is determined. The processed highlight interval and the first video segments have a one-to-one or many-to-one correspondence. Based on the processed highlight interval corresponding to the first video draft and the first video draft, a second video draft is generated. The second video draft consists of one or more second video segments, which are obtained from the first video draft based on the processed highlight interval. The second video segments in the second video draft have a correspondence with the first video segments in the first video draft. The second video draft is used to generate a target video.

[0087] This embodiment of the disclosure automatically determines the processed highlight regions corresponding to the first video draft, thereby enabling the editing of the first video draft and generating a second video draft composed of highlight segments (second video segments) corresponding to the processed highlight regions. It is evident that this embodiment of the disclosure enriches the video editing methods and enhances the user's video editing experience by determining the highlight regions.

[0088] In practical applications, to support editing operations on the processed highlight regions corresponding to the first video draft, this embodiment of the disclosure can also perform interval editing operations on the processed highlight regions corresponding to the first video draft before generating the second video draft. Specifically, the interval editing operation is used to edit at least one of the interval length, interval start time point, and interval end time point of the processed highlight region.

[0089] Specifically, after determining the processed highlight regions corresponding to the first video draft, each processed highlight region is displayed. If an edit operation is received targeting any one of the processed highlight regions (hereinafter referred to as the first processed highlight region) in the first video draft, the edited highlight region corresponding to the first processed highlight region is determined based on the edit operation. Then, based on the processed highlight region corresponding to the first video draft, the edited highlight region corresponding to the first processed highlight region, and the first video draft, a second video draft is generated.

[0090] The second video segment in the second video draft can be obtained from the first video draft based on the processed highlight range, or it can be obtained from the first video draft based on the edited highlight range, or it can be obtained from the first video draft based on both the processed highlight range and the edited highlight range.

[0091] In practical applications, to support users in editing the processed highlight regions, this embodiment of the present disclosure, after determining the processed highlight regions corresponding to the first video draft, creates highlight region adjustment view components for each processed highlight region, so as to display the highlight regions to the user and facilitate the user's editing of the corresponding processed highlight regions.

[0092] In one optional implementation, before receiving a range editing operation for a first processed highlight range within the processed highlight range corresponding to the first video draft, a highlight range adjustment view component can be created for the first processed highlight range and displayed. Then, based on the highlight range adjustment view component, a range editing operation for the first processed highlight range is received.

[0093] In practical applications, this highlight range adjustment view component can include a preview area, adjustment controls, and a shadow area. The preview area displays the corresponding processed highlight range, showing the user its specific location in the first video draft and the corresponding video frame. The adjustment controls allow users to adjust the length, start time, and end time of the processed highlight range. By triggering the adjustment controls, users can adjust these parameters as needed. The shadow area covers the non-highlight range, helping users distinguish between the processed highlight and non-highlight areas.

[0094] Figure 4 shows a schematic diagram of a highlight range adjustment view component provided in an embodiment of this disclosure. The highlight range adjustment view component includes a preview area 401, an adjustment control 402, and a shadow area 403. When a user drags the adjustment control 402 to the left, the range length of the processed highlight area is increased, and the start time point of the processed highlight area is updated.

[0095] To facilitate understanding of the above embodiments, this disclosure will use a video editing client as an example to introduce the video processing method provided by the embodiments of this disclosure. Figure 5 shows a flowchart of a video processing method provided by an embodiment of this disclosure.

[0096] When a user triggers the smart editing function, the system checks whether a highlight recognition model is deployed in the local cache. If no highlight recognition model is found in the local cache, it downloads the highlight recognition model from the server; if a highlight recognition model is found in the local cache, it does not need to be downloaded.

[0097] Then, the highlight region recognition model is used to analyze the content of the first video draft imported by the user to obtain the initial highlight region corresponding to the first video draft. After determining the initial highlight region corresponding to the first video draft, the processing highlight region corresponding to the initial highlight region is determined.

[0098] In one application scenario, if it is determined that any initial highlight interval falls within the display time interval of multiple first video segments, then the initial highlight interval is split into multiple highlight intervals, which are used as the processed highlight intervals corresponding to the initial highlight interval.

[0099] Based on the above embodiments, in one application scenario, after obtaining the processed highlight intervals corresponding to the first video draft, a corresponding highlight data model is created for each processed highlight interval to record the time information of the corresponding processed highlight interval.

[0100] After determining the processed highlight range corresponding to the first video draft, create a highlight range adjustment view component for each processed highlight range and display the highlight range adjustment view component. Based on the highlight range adjustment view component, receive the user's range editing operation for each processed highlight range.

[0101] After determining the processed highlight range and the edited highlight range corresponding to the first video draft, a second video draft is generated based on the processed highlight range and the edited highlight range corresponding to the first video draft and the first video draft.

[0102] In one application scenario, video segments corresponding to the processed highlight regions and the edited highlight regions are cropped from the first video draft to generate the second video draft.

[0103] This disclosure not only supports the automatic identification of highlight regions from a first video draft, but also supports editing operations on the identified highlight regions, enabling the generation of a second video draft from highlight segments in the first video draft. Therefore, this disclosure enriches video editing functions, improves video editing efficiency, and thus enhances the user's video editing experience.

[0104] Based on the above method embodiments, this disclosure also provides a video processing apparatus. Referring to FIG6, which is a schematic diagram of the structure of a video processing apparatus provided in an embodiment of this disclosure, the apparatus includes:

[0105] The first determining module 601 is used to obtain a first video draft and determine the initial highlight interval corresponding to the first video draft; wherein, the first video draft is composed of one or more first video segments, and the initial highlight interval is used to characterize the display time interval of the highlight segment in the first video draft.

[0106] The second determining module 602 is used to determine the processed highlight interval corresponding to the first video draft based on the initial highlight interval; wherein the processed highlight interval has a one-to-one or many-to-one correspondence with the first video segment;

[0107] The first generation module 603 is used to generate a second video draft based on the processed highlight region corresponding to the first video draft and the first video draft; wherein, the second video draft consists of one or more second video segments, the second video segments are obtained from the first video draft based on the processed highlight region, the second video segments in the second video draft have a corresponding relationship with the first video segments in the first video draft, and the second video draft is used to generate a target video.

[0108] In one optional implementation, the second determining module includes:

[0109] The first determining submodule is used to determine whether the first initial highlight interval in the initial highlight interval corresponding to the first video draft is within the display time interval of multiple first video segments;

[0110] The first splitting submodule is used to split the first initial highlight interval into multiple highlight intervals when it is determined that the first initial highlight interval is in the display time interval of multiple first video segments, and these multiple highlight intervals are used as the processed highlight intervals corresponding to the first initial highlight interval; wherein, the multiple highlight intervals are respectively in the display time interval of different first video segments, and each of the multiple highlight intervals is in the display time interval of one first video segment.

[0111] In one optional embodiment, the apparatus further includes:

[0112] The first receiving module is configured to receive a range editing operation on the first processed highlight range corresponding to the first video draft; wherein the range editing operation is used to edit at least one of the range length, range start time point and range end time point of the first processed highlight range;

[0113] The third determining module is used to determine the edited highlight interval corresponding to the first processed highlight interval based on the interval editing operation;

[0114] Accordingly, the first generation module is specifically used for:

[0115] A second video draft is generated based on the processed highlight region corresponding to the first video draft, the edited highlight region corresponding to the first processed highlight region, and the first video draft; wherein, the second video segment in the second video draft is obtained from the first video draft based on the processed highlight region and / or the edited highlight region.

[0116] In one optional embodiment, the apparatus further includes:

[0117] A creation module is used to create a highlight range adjustment view component for the first processed highlight range and to display the highlight range adjustment view component;

[0118] Accordingly, the first receiving module is specifically used for:

[0119] Based on the highlight range adjustment view component, a range editing operation is received for the first processed highlight range.

[0120] In one optional implementation, the first generation module includes:

[0121] The cropping submodule is used to crop out the video segment corresponding to the processed highlight area from the first video draft;

[0122] The second determining submodule is used to determine that when different processed highlight intervals are in the same display time interval of the first video segment, the video segments corresponding to the different processed highlight intervals are all determined as the second video segment corresponding to the first video segment.

[0123] The first generation submodule is used to generate a second video draft based on the second video segment.

[0124] In one optional embodiment, the apparatus further includes:

[0125] The merging module is used to determine that when the interval end time point of the second processed highlight interval and the interval start time point of the third processed highlight interval in the processed highlight interval corresponding to the first video draft are the same, and the second processed highlight interval and the third processed highlight interval are in the same display time interval of the first video segment, the video segments corresponding to the second processed highlight interval and the third processed highlight interval are merged to obtain the second video segment corresponding to the first video segment.

[0126] In one optional implementation, the first determining module is specifically used for:

[0127] The first video draft is analyzed using a highlight region recognition model to obtain the initial highlight region corresponding to the first video draft.

[0128] This disclosure provides a video processing apparatus. Specifically, it acquires a first video draft and determines an initial highlight region corresponding to the first video draft. The first video draft consists of one or more first video segments. The initial highlight region is used to characterize the display time interval of the highlight segments in the first video draft. Based on the initial highlight region, it determines a processed highlight region corresponding to the first video draft. The processed highlight region and the first video segments have a one-to-one or many-to-one correspondence. Based on the processed highlight region corresponding to the first video draft and the first video draft, it generates a second video draft. The second video draft consists of one or more second video segments. The second video segments are obtained from the first video draft based on the processed highlight regions. The second video segments in the second video draft have a correspondence with the first video segments in the first video draft. The second video draft is used to generate a target video.

[0129] This embodiment of the disclosure automatically determines the processed highlight regions corresponding to the first video draft, thereby enabling the editing of the first video draft and generating a second video draft composed of highlight segments (second video segments) corresponding to the processed highlight regions. It is evident that this embodiment of the disclosure enriches the video editing methods and enhances the user's video editing experience by determining the highlight regions.

[0130] In addition to the methods and apparatus described above, this disclosure also provides a computer-readable storage medium storing instructions that, when executed on a terminal device, cause the terminal device to implement the video processing method described in this disclosure.

[0131] This disclosure also provides a computer program product, which includes a computer program / instructions that, when executed by a processor, implement the video processing method described in this disclosure.

[0132] In addition, this disclosure also provides a video processing device, as shown in FIG7, which may include:

[0133] The video processing device includes a processor 701, a memory 702, an input device 703, and an output device 704. The number of processors 701 in the video processing device can be one or more; Figure 7 shows an example of one processor. In some embodiments of this disclosure, the processor 701, memory 702, input device 703, and output device 704 can be connected via a bus or other means; Figure 7 shows an example of connection via a bus.

[0134] The memory 702 can be used to store software programs and modules. The processor 701 executes various functional applications and data processing of the video processing device by running the software programs and modules stored in the memory 702. The memory 702 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc. In addition, the memory 702 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. The input device 703 can be used to receive input digital or character information, and to generate signal inputs related to user settings and function control of the video processing device.

[0135] Specifically in this embodiment, the processor 701 loads the executable files corresponding to the processes of one or more applications into the memory 702 according to the following instructions, and the processor 701 runs the applications stored in the memory 702, thereby realizing the various functions of the video processing device described above.

[0136] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0137] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0138] As an optional but not limited implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0139] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0140] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0141] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A video processing method, comprising: Obtain a first video draft and determine the initial highlight interval corresponding to the first video draft; wherein, the first video draft consists of one or more first video segments, and the initial highlight interval is used to characterize the display time interval of the highlight segment in the first video draft; Based on the initial highlight range, the processed highlight range corresponding to the first video draft is determined; wherein, the processed highlight range has a one-to-one or many-to-one correspondence with the first video segment; Based on the processed highlight region corresponding to the first video draft and the first video draft, a second video draft is generated; wherein, the second video draft consists of one or more second video segments, the second video segments are obtained from the first video draft based on the processed highlight region, the second video segments in the second video draft have a corresponding relationship with the first video segments in the first video draft, and the second video draft is used to generate the target video.

2. The method according to claim 1, wherein determining the processed highlight region corresponding to the first video draft based on the initial highlight region includes: Determine whether the first initial highlight interval in the initial highlight interval corresponding to the first video draft is within the display time interval of multiple first video segments; If it is determined that the first initial highlight interval is within the display time interval of multiple first video segments, then the first initial highlight interval is split into multiple highlight intervals, which are used as the processed highlight intervals corresponding to the first initial highlight interval; wherein, the multiple highlight intervals are respectively within the display time intervals of different first video segments, and each of the multiple highlight intervals is within the display time interval of one first video segment.

3. The method according to claim 1 or 2, wherein before generating the second video draft based on the processed highlight region corresponding to the first video draft and the first video draft, the method further includes: Receive a range editing operation for a first processed highlight range within the processed highlight range corresponding to the first video draft; wherein the range editing operation is used to edit at least one of the range length, range start time point, and range end time point of the first processed highlight range; Based on the interval editing operation, the edited highlight interval corresponding to the first processed highlight interval is determined; Accordingly, generating a second video draft based on the processed highlight region corresponding to the first video draft and the first video draft includes: A second video draft is generated based on the processed highlight region corresponding to the first video draft, the edited highlight region corresponding to the first processed highlight region, and the first video draft; wherein, the second video segment in the second video draft is obtained from the first video draft based on the processed highlight region and / or the edited highlight region.

4. The method according to claim 3, wherein before receiving the interval editing operation on the first processed highlight interval corresponding to the first video draft, the method further comprises: Create a highlight range adjustment view component for the first processed highlight range, and display the highlight range adjustment view component; Accordingly, receiving the interval editing operation for the first processed highlight interval in the processed highlight interval corresponding to the first video draft includes: Based on the highlight range adjustment view component, a range editing operation is received for the first processed highlight range.

5. The method according to claim 1, wherein generating a second video draft based on the processed highlight region corresponding to the first video draft and the first video draft includes: Cut out the video segment corresponding to the processed highlight area from the first video draft; If it is determined that different processed highlight regions are within the same display time interval of the first video segment, then the video segments corresponding to the different processed highlight regions are all determined as the second video segments corresponding to the first video segment. A second video draft is generated based on the second video segment.

6. The method according to claim 5, wherein before generating the second video draft based on the second video segment, it further comprises: If it is determined that the end time point of the second processed highlight interval and the start time point of the third processed highlight interval are the same in the processed highlight interval corresponding to the first video draft, and the second processed highlight interval and the third processed highlight interval are in the same display time interval of the first video segment, then the video segments corresponding to the second processed highlight interval and the third processed highlight interval are merged to obtain the second video segment corresponding to the first video segment.

7. The method according to claim 1, wherein determining the initial highlight region corresponding to the first video draft includes: The first video draft is analyzed using a highlight region recognition model to obtain the initial highlight region corresponding to the first video draft.

8. A video processing apparatus, the apparatus comprising: The first determining module is used to obtain a first video draft and determine the initial highlight interval corresponding to the first video draft; wherein, the first video draft is composed of one or more first video segments, and the initial highlight interval is used to characterize the display time interval of the highlight segment in the first video draft. The second determining module is used to determine the processed highlight region corresponding to the first video draft based on the initial highlight region; wherein the processed highlight region has a one-to-one or many-to-one correspondence with the first video segment; A first generation module is used to generate a second video draft based on the processed highlight region corresponding to the first video draft and the first video draft; wherein, the second video draft consists of one or more second video segments, the second video segments are obtained from the first video draft based on the processed highlight region, the second video segments in the second video draft have a corresponding relationship with the first video segments in the first video draft, and the second video draft is used to generate a target video.

9. A computer-readable storage medium storing instructions that, when executed on a terminal device, cause the terminal device to perform the method as described in any one of claims 1-7.

10. A video processing apparatus, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as claimed in any one of claims 1-7.

11. A computer program product comprising a computer program / instructions that, when executed by a processor, implement the method as described in any one of claims 1-7.

Images