Video generation method, device, equipment, and storage medium

Abstract

The present disclosure provides a video generating method, device, equipment, and storage medium. The method includes: when a client receives an identification operation triggered for a shooting screen on a shooting page, obtaining a target identification image based on the shooting screen on the shooting page and sending it to a server side, the server side is used to determine a target effect resource for the target object after identifying the target object from the target identification image. The client receives the target effect resource from the server side and applies it to the target object in the shooting screen, and generates a target video based on the shooting screen corresponding to the target object to which the target effect resource is applied.

Description

[Technical Field]

[0001] The present disclosure relates to the field of data processing, and in particular to video generation methods, devices, apparatus, and storage media.

[0002] CROSS-REFERENCE TO RELATED APPLICATIONS This disclosure claims priority to an application proposed on October 22, 2021, entitled "Video Generation Method, Apparatus, Device, and Storage Medium," and bearing Chinese Patent Application Number "202111234267.3," the entire contents of which are incorporated herein by reference. [Background technology]

[0003] With the popularity of multimedia shot video, people are becoming more and more interested in taking pictures or videos, and the functions of the shooting page are becoming more and more. How to enrich the functions of video shooting and thereby improve people's video creation experience is currently a technical problem that needs to be solved urgently. Summary of the Invention [Problem to be solved by the invention]

[0004] In order to solve or at least partially solve the above technical problems, an embodiment of the present disclosure provides a video generation method that automatically applies corresponding target effect resources to target objects in a shooting screen, enriches the functions of video shooting, and thereby enhances the user's creative experience. [Means for solving the problem]

[0005] According to a first aspect, the present disclosure provides a video generation method for client application, the method comprising: When receiving an identification operation triggered on a photographing screen on a photographing page, acquiring a target identification image based on the photographing screen on the photographing page; sending the target-identifying image to a server side for identifying a target object from the target-identifying image and then determining a target effect resource for the target object; receiving the target effect resource from the server side and applying the target effect resource to the target object on the shooting screen; generating a target video based on a shooting scene corresponding to the target object to which the target effect resource is applied.

[0006] According to a second aspect, the present disclosure provides a video generation method applied on a server side, the method comprising: receiving a target identification image from the client, the target identification image being acquired based on a photography screen on the photography page of the client; determining whether the target identification image includes any one of the preset objects; When it is determined that the target identification image includes any one of the preset targets, determining the preset target as a target target and determining a target effect resource corresponding to the target target; and returning the target effects resource to the client for generating a target video at the client.

[0007] According to a third aspect, the present disclosure further provides a video generation system including a client and a server side. When the client receives an identification operation triggered on the photographing screen on the photographing page, the client acquires a target identification image based on the photographing screen on the photographing page, and transmits the target identification image to the server side; The server side receives a target identification image from a client, determines whether the target identification image includes any one of the preset targets, and if it determines that the target identification image includes any one of the preset targets, determines the preset target as a target target, determines a target effect resource corresponding to the target target, and returns the target effect resource to the client; The client is further used to receive the target effect resource from the server side, apply the target effect resource to the target object in the shooting screen, and generate a target video based on the shooting screen corresponding to the target object to which the target effect resource is applied.

[0008] According to a fourth aspect, the present disclosure provides a video generation device for client application, the device comprising: an acquisition module for acquiring a target identification image based on the photographing screen on the photographing page when receiving an identification operation triggered on the photographing screen on the photographing page; a transmitting module for transmitting the target-identifying image to a server side for determining target effect resources for the target object after identifying the target object from the target-identifying image; an application module for receiving the target effect resource from the server side and applying the target effect resource to the target object on the shooting screen; a generating module for generating a target video based on a shooting scene corresponding to the target object to which the target effect resource is applied.

[0009] According to a fifth aspect, the present disclosure provides a video generation device for use on a reading side, said device comprising: a first receiving module for receiving a target identification image from the client, the target identification image being acquired based on a photographing screen on the photographing page of the client; a first determination module for determining whether the target identification image includes any one preset object; a second determination module for determining, when determining that the target identification image includes any one preset target, the preset target as a target target and determining a target effect resource corresponding to the target target; a return module for returning the target effect resource to the client for generating a target video at the client.

[0010] According to a sixth aspect, the present disclosure provides a computer-readable storage medium having stored thereon instructions that, when executed on a terminal device, cause the terminal device to implement the above method.

[0011] According to a seventh aspect, the present disclosure provides an apparatus including a memory, a processor, and a computer program stored in the memory and executable by the processor, the computer program, when executed by the processor, implementing the method described above.

[0012] According to an eighth aspect, the present disclosure provides a computer program product, the computer program product including computer programs / instructions that, when executed by a processor, implement the above method. [Effects of the Invention]

[0013] The technical solution according to the embodiments of the present disclosure has the following advantages over the prior art:

[0014] An embodiment of the present disclosure provides a video generation method. First, when a client receives an identification operation triggered on a shooting screen on a shooting page, the client obtains a target identification image based on the shooting screen on the shooting page and sends the target identification image to a server side. The server side identifies a target object from the target identification image and then determines a target effect resource for the target object. The client then receives the target effect resource from the server side, applies the target effect resource to the target object on the shooting screen, and generates a target video based on the shooting screen corresponding to the target object to which the target effect resource is applied. In an embodiment of the present disclosure, during the video shooting process, a target effect resource matching the target object on the shooting screen can be automatically applied to generate a target video. As can be seen, the embodiment of the present disclosure enriches the functionality of video shooting, thereby enhancing the user's creative experience. [Brief explanation of the drawings]

[0015] The drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification serve to explain the principles of the present disclosure.

[0016] In order to more clearly describe the technical solutions in the embodiments or prior art of the present disclosure, the following briefly introduces the drawings that need to be used in the embodiments or prior art description. Obviously, those skilled in the art can obtain other drawings based on these drawings without any creative effort. [Figure 1] 1 is a flowchart of a video generation method according to an embodiment of the present disclosure. [Figure 2] 10 is a flowchart of another video generation method according to an embodiment of the present disclosure. [Figure 3] FIG. 2 is a schematic diagram of data interaction in a video generation method according to an embodiment of the present disclosure. [Figure 4]1 is a structural schematic diagram of a video generation system according to an embodiment of the present disclosure. [Figure 5] 1 is a structural schematic diagram of a video generation device according to an embodiment of the present disclosure; [Figure 6] FIG. 2 is a structural schematic diagram of another video generating device according to an embodiment of the present disclosure. [Figure 7] 1 is a structural schematic diagram of a video production device according to an embodiment of the present disclosure; DETAILED DESCRIPTION OF THE INVENTION

[0017] In order to make the above-mentioned objects, features, and advantages of the present disclosure more clearly understood, the present disclosure will be further described below. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0018] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure; however, the present disclosure may be implemented in ways different from those described herein. Obviously, the embodiments in the specification are merely some embodiments of the present disclosure, but not all embodiments.

[0019] To enrich the functionality of video shooting and thereby enhance users' video creation experiences, an embodiment of the present disclosure proposes a video creation method. First, when a client receives an identification operation triggered on a shooting screen on a shooting page, the client obtains a target identification image based on the shooting screen on the shooting page and sends the target identification image to a server side. The server side identifies a target object from the target identification image and then determines a target effect resource for the target object. The client then receives the target effect resource from the server side, applies the target effect resource to the target object on the shooting screen, and generates a target video based on the shooting screen corresponding to the target object to which the target effect resource is applied. In an embodiment of the present disclosure, during the video shooting process, a target effect resource matching the target object on the shooting screen can be automatically applied to generate a target video. As can be seen, the embodiment of the present disclosure enriches the functionality of video shooting and thereby enhances users' creation experiences.

[0020] Based on this, an embodiment of the present disclosure provides a video generation method. Referring to Figure 1, there is shown a flowchart of a video generation method according to an embodiment of the present disclosure, where the method is applied to a client, as shown in Figure 1. The method includes:

[0021] S101: Upon receiving an identification operation triggered on a photographing screen on a photographing page, obtain a target identification image based on the photographing screen on the photographing page.

[0022] In the embodiment of the present disclosure, there may be multiple ways of triggering the identification operation on the shooting screen of the shooting page. For example, Method 1 is a long press trigger operation on the shooting screen of the shooting page, where the long press trigger operation is performed on any position on the shooting screen. Method 2 is a trigger operation on an identification control set on the shooting page, where the identification control may be set at any position on the shooting page (for example, a position on the right side or bottom of the shooting page).

[0023] In an embodiment of the present disclosure, when an identification operation is triggered for the captured image on the capture page, the target identification image acquired based on the captured image on the capture page may be a single frame image captured by the current camera or any single frame image extracted from a series of consecutive multi-frame images. Here, the series of consecutive multi-frame images includes consecutive multi-frame images whose end frame is the current image corresponding to the captured image. For example, the second frame image is extracted as the target identification image from five consecutive frames captured by the current camera and whose end frame is the current image corresponding to the captured image.

[0024] It should be noted that the continuous multi-frame images including the continuous multi-frame images and having the current image corresponding to the captured screen as the end frame may be continuous 5-frame images, continuous 7-frame images, etc., and the second frame image from the continuous multi-frame images may be extracted as the target identification image, or the third frame image may be extracted as the target identification image, etc. The embodiments of the present disclosure are not limited to the specific number of frames in the continuous multi-frame images and the number of frames among them that are extracted as the target identification image.

[0025] The target identification image acquired based on the above embodiment may have issues such as blurring or dark colors, and therefore an invalid target identification image may be sent to the server for identification later. Therefore, it is possible to determine whether the image resolution of the target identification image acquired based on the shooting screen on the shooting page satisfies the preset resolution conditions, which is advantageous in reducing the occurrence of invalid input.

[0026] In some embodiments, target-identifying images whose image resolution meets preset resolution requirements can be determined based on steps A1-A3 as follows:

[0027] Step A1: Upon receiving an identification operation triggered for a photographing screen on a photographing page, obtain the current image corresponding to the photographing screen as the image whose resolution should be identified.

[0028] In an embodiment of the present disclosure, when an identification operation is received triggered for a photographed screen on a photographing page, a current image corresponding to the photographed screen is acquired, and the current image corresponding to the photographed screen may be a single frame image, for example, image 1, or may be any single frame image extracted from a series of consecutive multi-frame images with the current image corresponding to the photographed screen as the final frame. Furthermore, the acquired current image is the image whose resolution should be identified.

[0029] Step A2: Determine whether the image resolution of the image for which the resolution is to be identified satisfies the preset resolution condition.

[0030] In some embodiments, determining whether the image resolution of the image for which a resolution is to be identified satisfies the preset resolution condition includes processing the image for which a resolution is to be identified based on a predetermined fuzzy filter model to obtain an image resolution point value of the image for which a resolution is to be identified; determining that the image resolution of the image for which a resolution is to be identified satisfies the preset resolution condition if the image resolution point value of the image for which a resolution is to be identified is greater than or equal to a point value threshold corresponding to satisfying the preset resolution condition; and determining that the image resolution of the image for which a resolution is to be identified does not satisfy the preset resolution condition if the image resolution point value of the image for which a resolution is to be identified is less than the point value threshold corresponding to satisfying the preset resolution condition.

[0031] In an embodiment of the present disclosure, the method for determining whether the image resolution of an image whose resolution is to be identified satisfies a preset resolution condition includes multiple methods. For example, in method 1, the image resolution of the image whose resolution is to be identified is compared with an image resolution that satisfies a preset resolution condition and is pre-stored in the client, thereby determining whether the image resolution of the image whose resolution is to be identified satisfies the preset resolution condition. In method 2, a fuzzy filter model is pre-set in the client. Here, the fuzzy filter model may be obtained by training based on image samples of different resolutions. After processing the image whose resolution is to be identified through the fuzzy filter model, an image resolution score value of the image whose resolution is to be identified can be output. For example, if the score value threshold corresponding to satisfying the preset resolution condition is set to 80 points, an image that satisfies the preset resolution condition means that the image resolution score value corresponding to this image is 80 points or more.

[0032] It should be noted that the set point value threshold corresponding to satisfying the preset resolution condition may be used to determine whether the image resolution of the image satisfies the preset resolution condition, and the point value threshold may be set to 80 points, 82 points, 85 points, etc. according to needs. The embodiments of the present disclosure are not limited to a specific value of the set point value threshold corresponding to satisfying the preset resolution condition.

[0033] Step A3: If it is determined that the image resolution of the image for which resolution is to be identified satisfies the preset resolution condition, the image for which resolution is to be identified is determined as a target identification image.

[0034] In the embodiment of the present disclosure, if it is determined based on step A2 above that the image resolution of the image (image 1) whose resolution is to be identified satisfies the preset resolution condition, image 1 is determined as the target identification image.

[0035] For example, in the above step A2, a fuzzy filter model is preset in the client, for example, the point value threshold corresponding to meeting the preset resolution condition is set to 80 points. When receiving an identification operation triggered for the shooting screen on the shooting page, the current image (image 1) corresponding to the shooting screen is obtained, and image 1 is input into the fuzzy filter model. Based on the processing of the fuzzy filter model, the image resolution point value of this image 1 (for example, point value is 90 points) is obtained and compared with the preset threshold (for example, 80 points). Based on the comparison, it is determined that the image resolution of image 1 meets the preset resolution condition (for example, 90 points is greater than the threshold 80 points), and image 1 is determined as the target identification image.

[0036] In some embodiments, after step A2 of the above example, if it is determined that the image resolution of the image whose resolution is to be identified does not satisfy the preset resolution condition, an image is acquired from the shooting screen on the shooting page based on the preset frame extraction condition, and this image is used to update the image whose resolution is to be identified.Furthermore, the step of determining whether the image resolution of the image whose resolution is to be identified satisfies the preset resolution condition is continued until it is determined that the preset resolution identification end condition is reached.

[0037] In some embodiments, acquiring an image from the shooting screen on the shooting page based on the preset frame extraction conditions includes extracting one frame of image from the image corresponding to the shooting screen every preset time, or extracting one frame of image from the image corresponding to the shooting screen every preset number of frames.

[0038] In an embodiment of the present disclosure, the preset frame extraction condition may include extracting one frame of image from an image corresponding to the captured screen every preset time, or extracting one frame of image from an image corresponding to the captured screen every preset number of frames, etc. Here, the preset time to be left may be 20 milliseconds, 30 milliseconds, etc., and the number of preset frames to be left may be 20 frames, 30 frames, etc., and the embodiment of the present disclosure is not limited to specific values ​​for the preset time to be left and the preset number of frames to be left.

[0039] In some embodiments, determining that a preset resolution identification termination condition has been reached includes terminating the image resolution identification when it is determined that the number of image frames extracted from an image corresponding to the captured screen reaches a preset number of image extractions, and terminating the image resolution identification when it is determined that the image resolution point value of the image for which the resolution is to be identified is less than the preset minimum point value.

[0040] In an embodiment of the present disclosure, the preset resolution identification termination condition may include terminating image resolution identification when the number of extracted image frames reaches a preset number of image extractions, or terminating image resolution identification when the image resolution point value of the image whose resolution is to be identified is smaller than a preset minimum point value, etc. Here, the preset number of image extractions may be 3, 5, 7, etc., and the embodiment of the present disclosure is not limited to a specific value for the preset number of image extractions.

[0041] For example, a fuzzy filter model is preset in the client, and the point value threshold corresponding to meeting the preset resolution condition is 80 points. The preset number of image extractions for the preset resolution identification termination condition is 5. If it is determined that the image resolution of the image (Image 1) for which resolution is to be identified does not meet the preset resolution condition, one frame of image (Image 2) is extracted from the image corresponding to the captured screen every preset time (e.g., 30 milliseconds), and Image 2 is used to update the image for which resolution is to be identified. That is, Image 2 becomes the new image for which resolution is to be identified. It continues to determine whether the image resolution of Image 2 meets the preset resolution condition, and Image 2 is input into the fuzzy filter model. It is determined that the image resolution point value of Image 2 is less than the preset threshold (e.g., 80 points), and the image resolution page of Image 2 does not meet the preset resolution condition. Furthermore, it determines whether the acquired image 2 meets the preset resolution identification end condition, and if not, continues to acquire an image (image 3) from the shooting screen on the shooting page based on the preset frame extraction condition, and based on this, when acquiring image 5 from the shooting screen on the shooting page, it determines whether the image resolution of image 5 meets the preset resolution condition, and if so, determines image 5 as the target identification image. If it does not meet the condition and it is determined that the acquired image 5 has already met the preset resolution identification end condition (for example, the number of extracted image frames reaches 5), it ends image resolution identification and prompts the user that this identification has failed.

[0042] As can be seen, in the embodiments of the present disclosure, the client can determine a target identification image whose image resolution meets the preset resolution conditions before sending it to the server side, thereby reducing the occurrence of invalid input, thereby reducing the number of invalid identifications on the server side and reducing the waste of network resources between the client and the server side.

[0043] S102: The target identification image is transmitted to the server side.

[0044] Here, the server side is used to determine target effect resources for the target object after identifying the target object from the target identification image.

[0045] In the embodiment of the present disclosure, the target identification image acquired in S101 is sent to the server side, and the server side can perform an identification process on the target identification image. After identifying the target object corresponding to the target identification image, the server side determines the corresponding target effect resource for the target object. Here, the target object may include any category of object whose corresponding feature information can be collected, such as pictures, three-dimensional objects, landmark buildings, etc., and may also include categories of objects such as a T-shirt pattern, a can, a high-rise building, etc. A specific implementation method for determining the target effect resource for the target object after the server side identifies the target object from the target identification image will be introduced in subsequent embodiments and will not be further described here.

[0046] S103: Receive a target effect resource from the server side, and apply the target effect resource to a target object on the shooting screen.

[0047] In an embodiment of the present disclosure, when the server identifies a target object from the target identification image based on S102, it determines a target effect resource for the target object and sends the target effect resource to the client. The client then receives the target effect resource and applies the target effect resource to the target object on the shooting screen. Specifically, a software development kit (SDK) analyzes the target effect resource and obtains the configuration of tools, templates, etc. included in the target effect resource. After initializing the SDK, rendering is enabled on the client's shooting page, allowing the user to preview the configuration on the preview screen of the shooting page.

[0048] Furthermore, since the client can apply the target effect resource to the target object on the shooting screen, when the client receives the target effect resource from the server side, the client can later receive the position information of the target object on the shooting screen that is notified from the server side so that the client can apply the target effect resource to the target object on the shooting screen.

[0049] In some embodiments, the location information of the target object on the shooting screen is received from the server side, and the target effect resource is applied to the target object on the shooting screen based on the location information.

[0050] In an embodiment of the present disclosure, the client can receive the target effect resource from the server side and can also receive the position information of the target object on the shooting screen from the server side, so that the client can apply the target effect resource to the target object on the shooting screen based on the position information, where the position information of the target object on the shooting screen can be expressed by coordinate information, etc.

[0051] S104: Generate a target video based on the shooting scene corresponding to the target object to which the target effect resource is applied.

[0052] In an embodiment of the present disclosure, the target effect resource may include tools, effects, templates, etc. recommended based on the corresponding target object, such as at least one of a virtual overlay effect, a shielding effect, a magnification effect, and a special effect processing effect. A video recording operation can be triggered based on the captured image corresponding to the target object to which the target effect resource is applied, thereby generating a target video. The target video may include any one or a variety of effects from the target effect resource corresponding to the target object, enriching the video effect and thereby enhancing the user's creative experience.

[0053] For example, taking the target object as a can, based on the above embodiment, the client receives a target effect resource corresponding to the can determined by the server side. If the target effect resource includes a virtual superimposition effect, after applying the target effect resource to the target object on the shooting screen, an effect of integrating the virtual world information content and the target object can be generated on the preview screen of the shooting page. If the target effect resource includes an occlusion effect, after applying the target effect resource to the target object on the shooting screen, an effect of a video resource partially occluding the target object can be generated on the preview screen of the shooting page. If the target effect resource includes a magnification effect, after applying the target effect resource to the target object on the shooting screen, an effect of fully or partially magnifying the target object can be generated on the preview screen of the shooting page. If the target effect resource includes a special effect processing effect, after applying the target effect resource to the target object on the shooting screen, an effect of a text resource rotating around the target object can be generated on the preview screen of the shooting page.

[0054] An embodiment of the present disclosure provides a video generation method. First, when a client receives an identification operation triggered on a shooting screen on a shooting page, the client obtains a target identification image based on the shooting screen on the shooting page and sends the target identification image to a server side. The server side identifies a target object from the target identification image and then determines a target effect resource for the target object. The client then receives the target effect resource from the server side, applies the target effect resource to the target object on the shooting screen, and generates a target video based on the shooting screen corresponding to the target object to which the target effect resource is applied. In an embodiment of the present disclosure, during the video shooting process, a target effect resource matching the target object on the shooting screen can be automatically applied to generate a target video. As can be seen, the embodiment of the present disclosure enriches the functionality of video shooting, thereby enhancing the user's creative experience.

[0055] Based on the above video generation system, an embodiment of the present disclosure provides another video generation method. Referring to Figure 4, there is shown a flowchart of another video generation method according to an embodiment of the present disclosure. As shown in Figure 4, the method is applied on the server side. The method includes:

[0056] S201: Receive a target identification image from a client.

[0057] Here, the target identification image is acquired based on the photographed screen on the client's photographing page.

[0058] In some embodiments of the present disclosure, the server side receives a target identification image from the client side, where the target identification image is a frame image acquired based on the capture screen on the capture page when the client receives an identification operation triggered on the capture screen on the capture page. In some embodiments, the target identification image whose image resolution determined by the client satisfies the preset resolution condition can be the target identification image received by the server side.

[0059] S202: Determine whether the target identification image includes any one of the preset objects.

[0060] In an embodiment of the present disclosure, the preset object may include any category of object for which corresponding feature information can be collected, such as objects in categories such as pictures, three-dimensional objects, and landmark buildings, as well as objects such as a T-shirt pattern, a can, and a high-rise building. Based on the target identification image acquired in S201, it is determined whether the target identification image includes any preset object. For example, if the image capture page shows a table with a can placed on it, the preset object included in the target identification image may be a can; if the image capture page shows multiple high-rise buildings, the preset object included in the target identification image may be a high-rise building.

[0061] In some embodiments, when determining whether a target-identifying image contains any one of the preset objects, image features of the target-identifying image are first extracted, and then the image features are matched with feature information corresponding to the preset object.

[0062] In an embodiment of the present disclosure, the correspondence between the preset target and the feature information corresponding to the preset target is set in advance on the server side, and after receiving a target identification image from a client, the feature information of the target identification image is extracted and matched with the feature information corresponding to a specific preset target.

[0063] For example, an information comparison model may be configured on the server side, where the information comparison model may be obtained by training based on a sample cell of correspondence relationships between different preset objects and corresponding feature information of the preset objects. The server side inputs the extracted feature information of the target identification image into the information comparison model, and obtains a matching result corresponding to the feature information of the target identification image.

[0064] In an embodiment of the present disclosure, if the image features of the target identification image are successfully matched with the feature information corresponding to one of the preset targets based on the matching results in the above embodiment, this preset target is determined as the target target.

[0065] For example, take an example in which an information comparison model is configured on the server side. Here, the sample data of the information comparison model includes the correspondence between cans and feature information of the cans (e.g., length, width, and height data X of the can), and the feature information of the extracted target identification image includes this length, width, and height data X. The feature information of this target identification image is input into the information comparison model, and a successful match is obtained between this feature information (e.g., this length, width, and height data X) and feature information corresponding to a preset object (e.g., a can), and this preset object (e.g., a can) is determined as the target object, and the target object identified from this target identification image is a can.

[0066] S203: If it is determined that the target identification image includes any one of the preset targets, the preset target is determined as the target target, and a target effect resource corresponding to the target target is determined.

[0067] In the embodiment of the present disclosure, based on the above S202, it is determined whether the target identification image includes any one of the preset objects, and if it is determined that the target identification image includes any one of the preset objects, the preset object is determined as the target object, and a target effect resource corresponding to the target object is determined, where the target effect resource may include a tool, effect, template, etc. recommended based on the corresponding target object.

[0068] In an embodiment of the present disclosure, if it is determined that the target identification image does not include any one of the preset targets, it is considered that the identification has failed, and the server side can determine a general-purpose effect resource for the client.

[0069] S204: Return the target effect resource to the client.

[0070] Here, the target effect resource is used by the client to generate the target video.

[0071] In some embodiments, after determining the preset object as the target object, the method further includes returning position information of the target object on the shooting screen to the client, so that the client applies the target effect resource to the target object on the shooting screen based on the position information.

[0072] In an embodiment of the present disclosure, based on the target effect resource corresponding to the target object determined in S203 above, the server side returns this target effect resource to the client, and the server side further returns the position information of this target object on the shooting screen to the client, so that the client generates a target video based on the target effect resource and the position information of the target object on the shooting screen.

[0073] In a video generation method according to an embodiment of the present disclosure, the server first receives a target-identifying image from a client. The target-identifying image is obtained based on the shooting screen on the client's shooting page. The server then determines whether the target-identifying image includes any preset object. If the server determines that the target-identifying image includes any preset object, the server determines the preset object as the target object and a target effect resource corresponding to the target object. The server then returns the target effect resource to the client for the client to generate a target video. In an embodiment of the present disclosure, during the video shooting process, the server can automatically apply a target effect resource corresponding to the target object in the shooting screen to generate a target video. As can be seen, the embodiment of the present disclosure enriches the functionality of video shooting, thereby enhancing the user's creative experience.

[0074] Based on the above video generation method, the disclosed embodiment further provides a video generation method. Referring to Figure 3, there is shown a data interaction schematic diagram of the video generation method according to the embodiment of the present disclosure. As shown in Figure 3, the method includes:

[0075] In S301, when the client receives an identification operation triggered for the shooting screen on the shooting page, the client acquires the current image corresponding to the shooting screen as the image whose resolution should be identified.

[0076] In an embodiment of the present disclosure, when a client receives a trigger operation on an identification control set on the photography page, the client obtains a current image of one frame corresponding to the photography screen, for example, image 1, and sets image 1 as the image whose resolution should be identified.

[0077] In S302, the client determines whether the image resolution of the image for which the resolution is to be identified satisfies the preset resolution condition.

[0078] In an embodiment of the present disclosure, image 1 is input to a preset fuzzy filter model in a client, where a score threshold corresponding to satisfying a preset resolution condition corresponding to this preset fuzzy filter model is set to 80 points, and a score value (e.g., 90 points) of image 1 is output based on the processing of the fuzzy filter model.

[0079] In S303, if it is determined that the image resolution of the image for which resolution is to be identified satisfies the preset resolution condition, the image for which resolution is to be identified is determined as a target identification image.

[0080] In an embodiment of the present disclosure, the point value of image 1 output in S302 above is compared with a preset threshold (e.g., 80 points), and it is determined that the image resolution of image 1 meets the preset resolution condition (e.g., 90 points is greater than the threshold of 80 points), and image 1 is determined as the target identification image.

[0081] In S304, the client transmits the target identification image to the server side.

[0082] In the embodiment of the present disclosure, the client sends the target identification image (image 1) determined in the above S303 to the server side.

[0083] In S305, the server side extracts image features of the target identification image.

[0084] In the embodiment of the present disclosure, an information comparison model is set in advance on the server side, and the target identification image (image 1) is input into the information comparison model, and the image features of image 1 are extracted.

[0085] In S306, the server side matches the image feature with the feature information corresponding to the preset target, and determines whether the matching of the image feature with the feature information corresponding to any one of the preset targets is successful. If successful, execute S307; if not successful, execute S310.

[0086] In the embodiment of the present disclosure, the information comparison model on the server side may be trained and obtained based on the correspondence sample cells between different preset objects and the feature information corresponding to the preset objects. Image 1 is input into the information comparison model, and the image features of Image 1 are matched with the feature information corresponding to the preset objects to obtain a matching result corresponding to the feature information of Image 1.

[0087] In S307, if the image features of the target identification image are successfully matched with the feature information corresponding to any one of the preset targets, the successfully matched preset target is determined as the target target, and the target effect resource corresponding to the target target is determined.

[0088] In an embodiment of the present disclosure, if the image features (e.g., length, width, and height data X) of image 1 are successfully matched with feature information corresponding to one of the preset objects (e.g., length, width, and height data Y of a can) based on the matching result of S306, the preset object (e.g., the can) is determined as a target object, and a target effect resource corresponding to the target object is determined. Here, the target effect resource may include tools, effects, templates, etc. recommended based on the corresponding target object, and may include at least one of a virtual superimposition effect, an occlusion effect, an enlargement effect, and a special effect processing effect.

[0089] In S308, the server side transmits the target effect resource and the position information of the target object on the shooting screen to the client.

[0090] In an embodiment of the present disclosure, when the server side determines a preset target as a target target, the server side can not only determine a target effect resource corresponding to the target target, but also determine the position information of the target target on the shooting screen, and the server side sends the target effect resource and the position information of the target target on the shooting screen to the client, so that later, the client applies the target effect resource to the target target on the shooting screen based on this position information.

[0091] In S309, the client applies the target effect resource to the target object in the shooting screen according to the position information to generate a target video.

[0092] In an embodiment of the present disclosure, after receiving the target effect resource and the position information of the target object on the shooting screen, the client analyzes the target effect resource to obtain the configuration of tools, templates, etc. contained in the target effect resource, and after initializing the SDK, rendering is enabled on the client's shooting page, allowing the user to preview it on the preview screen of the shooting page.

[0093] In the embodiment of the present disclosure, when the server side receives a recording trigger operation, it records based on the preview screen to which the target effect resource is applied, and then generates a target video.

[0094] In S310, if the image features of the target identification image are not matched with the feature information corresponding to any one of the preset objects, the server side determines a general effect resource for the client.

[0095] In the embodiment of the present disclosure, if the image features (e.g., length, width, height data X) of image 1 are not successfully matched with the feature information corresponding to any one of the preset objects based on the matching result of S306 above, it is considered that the identification target object has failed, and the server side can determine a general-purpose effect resource for the client.

[0096] In S311, the server side transmits a general-purpose effect resource to the client.

[0097] In S312, the client applies the general-purpose effect resource to the target object on the shooting screen to generate a target video.

[0098] In the embodiment of the present disclosure, after receiving the general effect resource, the client analyzes the general effect resource to obtain the configuration of the tools, templates, etc. contained in the general effect resource, and after initializing the SDK, rendering is enabled on the client's photography page, allowing the user to preview on the preview screen of the photography page. When the server receives a recording trigger operation, it records according to the preview screen to which the general effect resource is applied, and then generates a target video.

[0099] In an embodiment of the present disclosure, the server side can determine a target effect resource based on the identified target object in the shooting screen, so that the client can apply the target effect resource determined by the server side to the target object in the shooting screen to generate a video, enriching the functions of video shooting and thereby improving the user's creative experience.

[0100] Based on the above video generation method, an embodiment of the present disclosure provides a video generation system. Referring to Figure 4, there is shown a structural schematic diagram of a video generation system according to an embodiment of the present disclosure. As shown in Figure 4, the video generation system may include a client 41 and a server side 42. The client 41 is communicatively connected to the server side 42.

[0101] When the client 41 receives an identification operation triggered for the photographing screen on the photographing page, the client 41 is used to obtain a target identification image based on the photographing screen on the photographing page and transmit the target identification image to the server side 42.

[0102] The server side 42 receives 41 target identification images from the client, determines whether the target identification image includes any one of the preset targets, and if it determines that the target identification image includes any one of the preset targets, determines the preset target as the target target, determines a target effect resource corresponding to the target target, and uses the target effect resource to return to the client 41.

[0103] The client 41 is further used to receive target effect resources from the server side 42, apply the target effect resources to a target object in a shooting screen, and generate a target video based on the shooting screen corresponding to the target object to which the target effect resources are applied.

[0104] In some embodiments, when the client 41 receives an identification operation triggered for the shooting screen on the shooting page, it further obtains the current image corresponding to the shooting screen as an image whose resolution should be identified, determines whether the image resolution of the image whose resolution should be identified satisfies the preset resolution condition, and if it determines that the image resolution of the image whose resolution should be identified satisfies the preset resolution condition, it is used to determine the image whose resolution should be identified as a target identification image.

[0105] In some embodiments, when the client 41 determines that the image resolution of the image whose resolution is to be identified does not satisfy the preset resolution condition, the client 41 is further used to obtain an image from the shooting screen on the shooting page based on the preset frame extraction condition, update the image whose resolution is to be identified using the image, and continue executing the step of determining whether the image resolution of the image whose resolution is to be identified satisfies the preset resolution condition until it determines that the preset resolution identification termination condition is reached.

[0106] In some embodiments, the client 41 is further used to process the image whose resolution is to be identified based on a predetermined fuzzy filter model, obtain an image resolution point value of the image whose resolution is to be identified, and determine that the image resolution of the image whose resolution is to be identified satisfies the preset resolution condition if the image resolution point value of the image whose resolution is to be identified is equal to or greater than a point value threshold corresponding to satisfying the preset resolution condition, and determine that the image resolution of the image whose resolution is to be identified does not satisfy the preset resolution condition if the image resolution point value of the image whose resolution is to be identified is less than the point value threshold corresponding to satisfying the preset resolution condition.

[0107] In some embodiments, the client 41 is further used to extract a frame of image from the image corresponding to the captured screen every preset time, or extract a frame of image from the image corresponding to the captured screen every preset number of frames.

[0108] In some embodiments, the client 41 is further used to terminate the image resolution identification when it determines that the number of image frames extracted from the image corresponding to the captured screen reaches a preset number of image extractions, or to terminate the image resolution identification when it determines that the image resolution point value of the image for which the resolution is to be identified is less than a preset minimum point value.

[0109] In some embodiments, the client 41 is further used to receive position information of the target object on the shooting screen from the server side 42, and apply the target effect resource to the target object on the shooting screen based on the position information.

[0110] In some embodiments, the server side 42 is further used to extract image features of the target-identifying image, match the image features with feature information corresponding to the preset targets, and determine the preset target as the target target if the image features of the target-identifying image are successfully matched with feature information corresponding to any one of the n preset targets.

[0111] In some embodiments, the server side 42 is further used to apply target effect resources to the target object on the shooting screen based on the client position information by returning the position information of the target object on the shooting screen to the client.

[0112] In the video generation system according to an embodiment of the present disclosure, the server side 42 can determine target effect resources based on the identified target object in the shooting screen, so that the client 41 can apply the target effect resources determined by the server side 42 to the target object in the shooting screen to generate a video and enrich the functions of video shooting, thereby enhancing the user's creation experience.

[0113] Based on the above method embodiment, the present disclosure further provides a video generation device. Referring to Figure 5, there is shown a structural schematic diagram of a video generation device according to an embodiment of the present disclosure. The device is applied to a client, and the video generation device 500 includes: an acquisition module 501 for acquiring a target identification image according to the photographing screen on the photographing page when receiving an identification operation triggered for the photographing screen on the photographing page; a sending module 502 for, after identifying a target object from the target-identifying image, sending the target-identifying image to a server side for determining target effect resources for the target object; an application module 503 for receiving the target effect resource from the server side and applying the target effect resource to the target object in the shooting screen; a generating module 504 for generating a target video based on a shooting scene corresponding to the target object to which the target effect resource is applied.

[0114] In some embodiments, the acquisition module 501: an acquisition submodule for acquiring a current image corresponding to the shooting screen as an image whose resolution should be identified when receiving an identification operation triggered for the shooting screen on the shooting page; a first determination sub-module for determining whether the image resolution of the image to be identified satisfies a preset resolution condition; and a second determination sub-module for determining, when determining that the image resolution of the image to be identified satisfies the preset resolution condition, the image to be identified as a target identification image.

[0115] In some embodiments, the device comprises: an update module for acquiring an image from a photographing screen on the photographing page based on a preset frame extraction condition when it is determined that the image resolution of the image to be identified does not satisfy the preset resolution condition, and updating the image to be identified by using the acquired image; and an identification module for continuing to perform the step of determining whether the image resolution of the image for which resolution is to be identified satisfies a preset resolution condition until determining that a preset resolution identification termination condition is reached.

[0116] In some embodiments, the first determination sub-module specifically: The image whose resolution is to be identified is processed based on a predetermined fuzzy filter model to obtain an image resolution point value of the image whose resolution is to be identified, and if the image resolution point value of the image whose resolution is to be identified is equal to or greater than a point value threshold corresponding to satisfying a preset resolution condition, the image resolution of the image whose resolution is to be identified is determined to satisfy the preset resolution condition, and if the image resolution point value of the image whose resolution is to be identified is smaller than the point value threshold corresponding to satisfying the preset resolution condition, the image resolution of the image whose resolution is to be identified is used to determine that the image resolution of the image whose resolution is to be identified does not satisfy the preset resolution condition.

[0117] In some embodiments, the update module specifically: It is used to extract one frame of image from the image corresponding to the photographed screen every preset time, or to extract one frame of image from the image corresponding to the photographed screen every preset number of frames.

[0118] In some embodiments, the identification module specifically: It is used to terminate image resolution identification when it is determined that the number of image frames extracted from the image corresponding to the photographed screen reaches the preset number of image extractions, or to terminate image resolution identification when it is determined that the image resolution point value of the image for which the resolution is to be identified is smaller than the preset minimum point value.

[0119] In some embodiments, the device comprises: Further, a second receiving module is provided for receiving position information of the target object on the photographing screen from the server side; In response, the application module 503: and an application sub-module for applying the target effect resource to the target object in the shooting screen based on the position information.

[0120] In a video generating device according to an embodiment of the present disclosure, first, when a client receives an identification operation triggered on a shooting screen on a shooting page, the client obtains a target identification image based on the shooting screen on the shooting page and sends the target identification image to the server side. The server side identifies a target object from the target identification image and then determines a target effect resource for the target object. The client then receives the target effect resource from the server side, applies the target effect resource to the target object on the shooting screen, and generates a target video based on the shooting screen corresponding to the target object to which the target effect resource is applied. In an embodiment of the present disclosure, during the video shooting process, a target effect resource matching the target object on the shooting screen can be automatically applied to generate a target video. As can be seen, the embodiment of the present disclosure enriches the functionality of video shooting, thereby enhancing the user's creative experience.

[0121] Based on the above method embodiment, the present disclosure further provides a video generation device. Referring to Figure 6, there is shown a structural schematic diagram of another video generation device according to an embodiment of the present disclosure. The device is applied to a server side, and the video generation device 600 includes: a first receiving module 601 for receiving a target identification image from the client, the target identification image being acquired based on the photographing screen of the client's photographing page; a first determination module 602 for determining whether the target identification image includes any one of the preset objects; a second determination module 603 for determining, when determining that the target identification image includes any one preset target, the preset target as a target target and determining a target effect resource corresponding to the target target; a return module 604 for returning the target effect resource to the client for generating a target video at the client.

[0122] In some embodiments, the first determination module 602: an extraction sub-module for extracting image features of the target-identification image; a matching sub-module for matching the image features with feature information corresponding to a preset object; In response, the second determination module 603: The third determination sub-module is configured to determine the preset object as a target object when the image features of the target identification image are successfully matched with feature information corresponding to any one of the preset objects.

[0123] In some embodiments, the return module 604 further comprises: By returning the position information of the target object on the shooting screen to the client, the client can apply the target effect resource to the target object on the shooting screen based on the position information.

[0124] In a video generating device according to an embodiment of the present disclosure, the server side first receives a target-identifying image from a client. Here, the target-identifying image is obtained based on the shooting screen on the client's shooting page, and then determines whether the target-identifying image includes any preset target. If it is determined that the target-identifying image includes any preset target, the server side determines the preset target as the target target and a target effect resource corresponding to the target target. The server side then returns the target effect resource to the client for the client to generate a target video. In an embodiment of the present disclosure, during the video shooting process, the server side can automatically apply a target effect resource matching the target target on the shooting screen to generate a target video.

[0125] As can be seen, embodiments of the present disclosure enrich the functionality of video capture, thereby enhancing the user's creative experience.

[0126] In addition to the above method and apparatus, an embodiment of the present disclosure further provides a computer-readable storage medium having instructions stored thereon, the instructions, when executed by a terminal device, causing the terminal device to implement a video generation method according to an embodiment of the present disclosure.

[0127] An embodiment of the present disclosure further provides a computer program product, which includes computer programs / instructions that, when executed by a processor, implement the video generation method according to the embodiment of the present disclosure.

[0128] Moreover, an embodiment of the present disclosure further provides a video generation device 700. Referring to FIG. The video generation device may include a processor 701, a memory 702, an input device 703, and an output device 704. The number of processors 701 in the video generation device may be one or more, and one processor is shown in Figure 7 as an example. In some embodiments of the present disclosure, the processor 701, the memory 702, the input device 703, and the output device 704 may be connected by a bus or other method, and Figure 7 shows them connected by a bus as an example.

[0129] The memory 702 may be used to store software programs and modules, and the processor 701 executes the software programs and modules stored in the memory 702 to perform various functional applications and data processing of the video production device. The memory 702 may primarily include a program storage area and a data storage area. The program storage area may store an operating system, an application program required for at least one function, etc. The memory 702 may include high-speed random access memory or non-volatile memory, such as at least one magnetic disk memory device, flash memory device, or other volatile solid-state memory device. The input device 703 may be used to receive input numeric or character information and to input signals related to user settings and function control of the video production device.

[0130] Specifically, in this embodiment, the processor 701 loads executable files corresponding to the progress of one or more application programs into the memory 702 according to the following instructions, and the processor 701 executes the application programs stored in the memory 702, thereby realizing various functions of the above-mentioned video generation device:

[0131] It should be explained that, in this specification, relational terms such as "first" and "second" are used solely to distinguish one entity or operation from another, without necessarily requiring or implying any such actual relationship or order between those entities or operations. Furthermore, the terms "comprise," "include," "includes," or any other variation thereof are intended to cover a non-exclusive "comprise," whereby a process, method, article, or apparatus that includes a set of elements not only includes those elements, but also other elements not expressly listed, or elements inherent in such process, method, article, or apparatus. In the absence of further limitations, an element qualified by the phrase "comprises a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0132] The foregoing description is of only specific embodiments of the present disclosure, and as will be appreciated by those skilled in the art, various modifications of these embodiments will be apparent to those skilled in the art. The general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not intended 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. 1. A video generation method applied to a client, comprising: When receiving an identification operation triggered on a photographing screen on a photographing page, acquiring a target identification image based on the photographing screen on the photographing page; sending the target-identifying image to a server side for identifying a target object from the target-identifying image and then determining a target effect resource for the target object; receiving the target effect resource from the server side and position information of the target object on the shooting screen, and applying the target effect resource to the target object on the shooting screen based on the position information; generating a target video based on a shooting scene corresponding to the target object to which the target effect resource is applied; method.

2. When receiving an identification operation triggered on a photographing screen on a photographing page, acquiring a target identification image based on the photographing screen on the photographing page, When receiving an identification operation triggered for a photographing screen on a photographing page, acquiring a current image corresponding to the photographing screen as an image whose resolution should be identified; determining whether the image resolution of the image to be identified satisfies a preset resolution condition; determining, when it is determined that the image resolution of the image to be identified satisfies the preset resolution condition, the image to be identified as a target identification image; The method of claim 1 , comprising:

3. The method further comprises: After determining whether the image resolution of the image to be identified satisfies a preset resolution condition, When it is determined that the image resolution of the image whose resolution is to be identified does not satisfy the preset resolution condition, an image is acquired from the photographing screen on the photographing page based on the preset frame extraction condition, and the image whose resolution is to be identified is updated using the acquired image; continuing to execute the step of determining whether the image resolution of the image for which resolution is to be identified satisfies a preset resolution condition until determining that a preset resolution identification end condition is reached; The method of claim 2 , comprising:

4. Determining whether the image resolution of the image to be identified satisfies a preset resolution condition includes: processing the image to be identified based on a predetermined fuzzy filter model to obtain an image resolution point value for the image to be identified; determining that the image resolution of the image to be identified satisfies the preset resolution condition when the image resolution point value of the image to be identified is equal to or greater than a point value threshold corresponding to satisfying the preset resolution condition; determining that the image resolution of the image to be identified does not satisfy the preset resolution condition when the image resolution point value of the image to be identified is smaller than a point value threshold corresponding to satisfying the preset resolution condition; The method of claim 2 , comprising:

5. Acquiring an image from a photographing screen on the photographing page based on a preset frame extraction condition includes: Extracting one frame of image from the image corresponding to the photographed screen at preset time intervals; or extracting one frame of image from the image corresponding to the photographed screen every preset number of frames; The method of claim 3, comprising:

6. Determining that the preset resolution identification end condition is reached includes: When it is determined that the number of image frames extracted from the image corresponding to the photographed screen reaches a preset number of image extractions, the image resolution identification is terminated; or terminating the image resolution identification when it is determined that the image resolution point value of the image for which resolution is to be identified is smaller than the preset minimum point value; The method of claim 3, comprising:

7. A video generation method applied on a server side, comprising: receiving a target identification image from the client, the target identification image being acquired based on a photographing screen on the client's photographing page; determining whether the target identification image includes any one of the preset objects; When it is determined that the target identification image includes any one preset target, the preset target is determined as a target target, and a target effect resource corresponding to the target target and position information of the target target on the photographing screen are determined; Return the target effect resource for generating a target video at the client and the position information of the target object on the shooting screen to the client, so that the client applies the target effect resource to the target object on the shooting screen according to the position information; A method comprising:

8. Determining whether the target identification image includes any one preset object includes: extracting image features of the target-identification image; Matching the image features with feature information corresponding to preset objects; Including, Accordingly, when it is determined that any one of the preset objects is included in the target identification image, determining the preset object as a target object; If the image feature of the target identification image is successfully matched with feature information corresponding to any one of the preset objects, the preset object is determined to be the target object; The method of claim 7, comprising:

9. The method further comprises: After determining the preset object as a target object, returning position information of the target object on the shooting screen to the client, so that the client applies the target effect resource to the target object on the shooting screen based on the position information; The method of claim 7, comprising:

10. A video production system including a client and a server side, When the client receives an identification operation triggered on the photographing screen on the photographing page, the client acquires a target identification image based on the photographing screen on the photographing page, and transmits the target identification image to the server side; The server side receives a target identification image from the client, determines whether any one of the preset targets is included in the target identification image, and if it determines that any one of the preset targets is included in the target identification image, determines the preset target as a target target, determines a target effect resource corresponding to the target target and position information of the target target on the shooting screen, and returns the target effect resource and the position information of the target target on the shooting screen to the client; The client further receives the target effect resource from the server side and position information of the target object on the shooting screen, and applies the target effect resource to the target object on the shooting screen according to the position information, and generates a target video based on the shooting screen corresponding to the target object to which the target effect resource is applied. Video generation system.

11. an acquisition module for acquiring a target identification image based on the photographing screen on the photographing page when receiving an identification operation triggered on the photographing screen on the photographing page; a transmitting module for transmitting the target-identifying image to a server side for determining target effect resources for the target object after identifying the target object from the target-identifying image; an application module for receiving the target effect resource from the server side and position information of the target object on the shooting screen, and applying the target effect resource to the target object on the shooting screen based on the position information; a generating module for generating a target video according to a shooting scene corresponding to the target object to which the target effect resource is applied; a video generating device applied to a client, including:

12. a first receiving module for receiving a target identification image from the client, the target identification image being acquired based on a photographing screen on the photographing page of the client; a first determination module for determining whether the target identification image includes any one preset object; a second determination module for determining, when determining that the target identification image includes any one preset target, the preset target as a target target, and determining a target effect resource corresponding to the target target and position information of the target target on the photographing screen; a returning module for returning the target effect resource for generating a target video at the client and the position information of the target object on the shooting screen to the client, so that the client applies the target effect resource to the target object on the shooting screen according to the position information; A server-side applied video generation device, including:

13. - storing instructions which, when executed on a terminal device, cause the terminal device to implement the method of any one of claims 1 to 9; A computer-readable storage medium.

14. a memory; a processor; and a computer program stored in the memory and executable by the processor; 10. When the processor executes the computer program, it performs the method of any one of claims 1 to 9. device.

15. Comprising computer instructions which, when executed by a processor, cause the method of any one of claims 1 to 9 to be implemented. Computer program.

Images