Optimization processing method and system for short video shooting of unmanned aerial vehicle

Abstract

The invention provides an optimization processing method and system for short video shooting of an unmanned aerial vehicle. The method comprises the following steps: acquiring video files shot by the unmanned aerial vehicle in the same scenic spot and shooting parameters corresponding to each video file; encoding the shooting parameters to obtain video file metadata; evaluating each video file by using the multi-dimensional evaluation index to obtain evaluation results of each video file in different dimensions; according to the specific short video shooting themes and the evaluation results, clustering processing is carried out on the video file metadata corresponding to each video file, and target metadata combinations corresponding to different specific short video shooting themes are obtained. Subsequent analysis processing is carried out based on the metadata integrated in the video file, selection of shooting lines, shooting parameters and parameters of later video rendering is achieved, various use scenes are optimized, and finally the short video effect and quality are improved.

Description

Technical Field

[0001] This article belongs to the field of computer technology, and specifically relates to an optimization processing method and system for drone short video shooting. Background Art

[0002] With the promotion and application of the fifth generation mobile communication technology (5G) and artificial intelligence (AI) in China, the real-time shooting, editing and processing of short videos has become a fast-growing highlight and has been implemented in many industries such as culture, tourism, and sports. Among them, short video services in scenic spots are gradually becoming a basic service for scenic spot operators to attract tourists.

[0003] The existing short video shooting in scenic spots is mainly operated by trained professionals, and there are different shooting techniques for different scenic spots, such as: personnel positions, human postures and movements, shooting angles and shooting routes, etc. Therefore, the experience of the shooting personnel will have a great impact on the final effect of the short video. In addition, the external conditions such as the shooting environment, time, weather, etc. on the scene also have a great impact on the shooting techniques, and professional shooting personnel generally have corresponding countermeasures. These experiences and measures are greatly affected by the training level and operational proficiency of the shooting personnel, and it is difficult to reach a unified standard. In addition, since this type of video is shot outdoors, it is difficult to record the above-mentioned influencing factors during the shooting process, and it is impossible to subsequently improve and optimize the quality of the video shooting process.

[0004] Therefore, the prior art urgently needs a technical solution that can achieve rapid optimization processing of short videos. Summary of the invention

[0005] In view of the above problems in the prior art, the purpose of this article is to provide an optimization processing method and system for drone short video shooting to improve the efficiency of short video optimization processing.

[0006] In order to solve the above technical problems, the specific technical solutions of this article are as follows:

[0007] On the one hand, this article provides an optimization processing method for drone short video shooting, the method comprising:

[0008] Obtain video files shot by a drone in the same scenic spot, and shooting parameters corresponding to each video file, wherein the shooting parameters at least include drone shooting parameters, environmental parameters, shooting equipment parameters, and video file parameters;

[0009] Encoding the shooting parameters to obtain video file metadata bound to the video file;

[0010] Use multi-dimensional evaluation indicators to evaluate each video file and obtain evaluation results of each video file in different dimensions;

[0011] According to the specific short video shooting theme and combined with the evaluation results of each video file in different dimensions, the video file metadata corresponding to each video file is clustered to obtain the target metadata combinations corresponding to different specific short video shooting themes.

[0012] Furthermore, the drone shooting parameters include at least: longitude, latitude, altitude, speed, and nose direction;

[0013] The environmental parameters include at least: weather, temperature, humidity, wind speed, wind direction, air quality, light intensity, and ultraviolet intensity;

[0014] The parameters of the shooting equipment shall at least include: the manufacturer, brand, model, and serial number of the shooting equipment; as well as the aperture, ISO value, white balance, exposure compensation, color space, color depth, contrast, saturation, sharpness, focal length, flash, shooting mode, metering mode, focus mode, shooting time, latitude, longitude, and altitude of the shooting point, and latitude, longitude, and altitude reference;

[0015] The video file parameters include at least: video encoding format, bit rate, frame rate, video duration, video resolution, thumbnail size and thumbnail, file size, file type, file MIME type, and file MD5 value.

[0016] Furthermore, the shooting parameters are encoded to obtain video file metadata bound to the video file, including:

[0017] Acquire a shooting data structure of a shooting device, where the shooting data structure at least includes video file parameters obtained by shooting;

[0018] The shooting data structure is expanded, and the drone shooting parameters, the environmental parameters and the shooting equipment parameters are stored in the expanded data structure to obtain video file metadata.

[0019] Furthermore, the method further comprises:

[0020] A set of header data is added to the header of the video file metadata to indicate the version number of the video file metadata.

[0021] Furthermore, the method further comprises:

[0022] A digital signature is added at the end of the metadata of the video file, and the digital signature is obtained by encrypting the metadata of the video file through a digest algorithm.

[0023] Furthermore, different specific short video shooting themes correspond to different multi-dimensional evaluation indicators.

[0024] Furthermore, the specific short video shooting themes include at least the following themes: recommendation of shooting routes for specific attractions, recommendation of shooting routes for specific seasons, recommendation of shooting parameters for specific lighting, recommendation of video shooting parameters for specific weather, recommendation of video background rendering parameters for specific lighting, and recommendation of video background rendering parameters for specific weather conditions.

[0025] Furthermore, according to the specific short video shooting theme, combined with the evaluation results of each video file in different dimensions, the video file metadata corresponding to each video file is clustered to obtain target metadata combinations corresponding to different specific short video shooting themes, including:

[0026] Determine specific short video shooting themes and their corresponding multi-dimensional evaluation indicators;

[0027] Acquire a collection of historical video files associated with the specific short video shooting theme;

[0028] Based on the multi-dimensional evaluation index, each historical video file in the historical video file set is analyzed using big data to obtain an evaluation result of each historical video file on each evaluation index, wherein the evaluation index represents the contribution degree of the evaluation index to the historical video file;

[0029] Based on a preset clustering algorithm, a cluster analysis is performed on all evaluation results in the historical video file set to determine a target metadata combination that satisfies a preset contribution degree to the characteristic short video shooting theme.

[0030] On the other hand, this article also provides an optimization processing device for drone short video shooting, the device comprising:

[0031] An acquisition module is used to acquire video files shot by drones in the same scenic spot, and shooting parameters corresponding to each video file, wherein the shooting parameters at least include drone shooting parameters, environmental parameters, shooting equipment parameters and video file parameters;

[0032] An encoding module, used for encoding the shooting parameters to obtain video file metadata bound to the video file;

[0033] An evaluation module is used to evaluate each video file using multi-dimensional evaluation indicators to obtain evaluation results of each video file in different dimensions;

[0034] The clustering module is used to cluster the video file metadata corresponding to each video file according to the specific short video shooting theme and the evaluation results of each video file in different dimensions to obtain the target metadata combination corresponding to different specific short video shooting themes.

[0035] Finally, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described above when executing the computer program.

[0036] By adopting the above technical scheme, an optimization processing method and system for drone short video shooting described in this paper obtains video files shot by drones in the same scenic spot, and shooting parameters corresponding to each video file, wherein the shooting parameters at least include drone shooting parameters, environmental parameters, shooting equipment parameters and video file parameters; the shooting parameters are encoded to obtain video file metadata bound to the video file; each video file is evaluated using multi-dimensional evaluation indicators to obtain evaluation results of each video file in different dimensions; according to a specific short video shooting theme, combined with the evaluation results of each video file in different dimensions, the video file metadata corresponding to each video file is clustered to obtain target metadata combinations corresponding to different specific short video shooting themes. By recording the data collected during drone video shooting into video files, this paper can not only be used for data collection in various drone video shooting processes, but also can be used for subsequent analysis and processing based on the metadata integrated in the video files, including but not limited to optimization and recommendation of shooting routes, automatic selection and optimization of shooting parameters, parameter selection and optimization of post-video rendering, verification of video shooting data, verification of video files and other usage scenarios, based on the comprehensive application of different shooting scenarios, and ultimately achieve the improvement of short video effect and quality.

[0037] In order to make the above and other purposes, features and advantages of this article more obvious and easy to understand, the following specifically cites preferred embodiments and describes them in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of this article or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of this article. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 A schematic diagram showing the steps of the optimization processing method for drone short video shooting provided in the embodiments of this article is shown;

[0040] Figure 2 A schematic diagram showing shooting parameters in the embodiments of this article is shown;

[0041] Figure 3 A schematic diagram of a framework of an optimization processing device for drone short video shooting provided in an embodiment of this invention is shown;

[0042] Figure 4 A schematic diagram of the framework of a computer device provided in the embodiments of this document is shown.

[0043] Description of the accompanying symbols:

[0044] 310, acquisition module; 320, encoding module; 330, evaluation module; 340, clustering module. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of this article to clearly and completely describe the technical solutions in the embodiments of this article. Obviously, the described embodiments are only part of the embodiments of this article, not all of the embodiments. Based on the embodiments of this article, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this article.

[0046] It should be noted that the terms "first", "second", etc. in the specification and claims of this article and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of this article described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0047] First, the technical terms that appear in the article are explained as follows:

[0048] Exchangeable image file format (EXIF) is a format specially designed for photos taken with digital cameras. It can record the attribute information and shooting data of digital photos.

[0049] Matroska Multimedia Container is an open standard free container and file format. It is a multimedia encapsulation format that supports video encoding and audio encoding in any format and can accommodate an unlimited number of video, audio, picture or subtitle tracks in one file.

[0050] In the prior art, short video shooting in scenic spots is mainly operated by trained professionals, and there are different shooting techniques for different scenic spots, such as: personnel positions, human postures and movements, shooting angles and shooting routes, etc. Therefore, the experience of the shooting personnel will have a great impact on the final short video effect. In addition, the external conditions such as the shooting environment time and weather on site also have a great impact on the shooting techniques, and professional shooting personnel generally have corresponding countermeasures. These experiences and measures are greatly affected by the training level and operational proficiency of the shooting personnel, and it is difficult to reach a unified standard. In addition, since this type of video is shot outdoors, it is difficult to record the above-mentioned influencing factors during the shooting process, and it is impossible to subsequently improve and optimize the quality of the video shooting process.

[0051] In order to solve the above problems, the embodiments of this article provide an optimization processing method for drone short video shooting, which can improve the effect and quality of short videos. Figure 1 It is a schematic diagram of the steps of an optimization processing method for drone short video shooting provided in the embodiments of this article. This specification provides the method operation steps described in the embodiments or flow charts, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiments is only one way of executing the steps among many orders, and does not represent the only order of execution. When the actual system or device product is executed, it can be executed in the order of the methods shown in the embodiments or drawings or in parallel. Specifically, Figure 1 As shown, the method may include:

[0052] S101: Obtain video files shot by a drone in the same scenic spot and shooting parameters corresponding to each video file, wherein the shooting parameters at least include drone shooting parameters, environment parameters, shooting equipment parameters and video file parameters;

[0053] S102: Encoding the shooting parameters to obtain video file metadata bound to the video file;

[0054] S103: Evaluate each video file using multi-dimensional evaluation indicators to obtain evaluation results of each video file in different dimensions;

[0055] S104: According to the specific short video shooting theme and in combination with the evaluation results of each video file in different dimensions, the video file metadata corresponding to each video file is clustered to obtain target metadata combinations corresponding to different specific short video shooting themes.

[0056] It can be understood that this article can improve the efficiency of data collection and preservation of the drone video shooting process by integrating and encoding the relevant parameters corresponding to the short video files obtained by shooting in the same scenic spot and binding them to the video files. At the same time, subsequent analysis and processing are performed based on the metadata integrated in the video files, including but not limited to the optimization and recommendation of shooting routes, automatic selection and optimization of shooting parameters, parameter selection and optimization of post-video rendering, verification of video shooting data, verification of video files and other usage scenarios. In this way, when shooting for a specific shooting theme, the success rate of short video shooting can be improved by determining the metadata combination in advance for shooting, reducing the time and difficulty of subsequent processing.

[0057] In the embodiments of this specification, Figure 2 As shown, the drone shooting parameters include at least: longitude, latitude, altitude, speed, and nose direction;

[0058] The environmental parameters include at least: weather, temperature, humidity, wind speed, wind direction, air quality, light intensity, and ultraviolet intensity;

[0059] The parameters of the shooting equipment shall at least include: the manufacturer, brand, model, and serial number of the shooting equipment; as well as the aperture, ISO value, white balance, exposure compensation, color space, color depth, contrast, saturation, sharpness, focal length, flash, shooting mode, metering mode, focus mode, shooting time, latitude, longitude, and altitude of the shooting point, and latitude, longitude, and altitude reference;

[0060] The video file parameters include at least: video encoding format, bit rate, frame rate, video duration, video resolution, thumbnail size and thumbnail, file size, file type, file MIME type, and file MD5 value.

[0061] In other words, by taking into account the factors that affect the quality of short videos produced by drone shooting, the parameter combination corresponding to the better short video quality can be fully determined, thereby improving the quality and efficiency of subsequent short video production.

[0062] Of course, shooting parameters can also include optimization parameters for short video rendering or processing by later users, such as video background music, color saturation, film effect, playback speed and other factors. In this way, all parameters involved in the entire process from the generation of short videos to subsequent video processing and playback or uploading to the Internet can be recorded and saved, so as to screen out the best parameter combination for a specific theme and recommend it to subsequent users. Furthermore, in order to avoid the homogenization of short videos, multiple sub-themes can be divided in a specific shooting theme. For example, multiple parameter combinations can be adapted according to user age, gender and user preferences, so as to achieve targeted parameter combination recommendations and improve the user experience.

[0063] In the embodiment of the present specification, the shooting parameters are encoded to obtain video file metadata bound to the video file, including:

[0064] Acquire a shooting data structure of a shooting device, where the shooting data structure at least includes video file parameters obtained by shooting;

[0065] The shooting data structure is expanded, and the drone shooting parameters, the environmental parameters and the shooting equipment parameters are stored in the expanded data structure to obtain video file metadata.

[0066] For example, if the shooting device is a digital camera, the video file format is the Exchangeable Image File Format (EXIF), which is specially set for photos of digital cameras and can record the attribute information and shooting data of digital photos. By expanding the basic data recorded by the original EXIF, defining an extensible data structure, recording various index parameters such as shooting environment, location, route, etc. into the video file, and supporting video file formats such as MP4 and MKV, the auxiliary information such as the on-site situation of the video shooting process is integrated into the video file as a set of extensible standard data sets, which is not only convenient for subsequent optimization of the shooting video, but also improves the film effect and quality.

[0067] In a specific implementation, the above data may be stored in a SimpleTag array object in a video file. The specific implementation method may be:

[0068] TagName field: used to store the key value name (Key Name) of the above data. The default name is Chinese, but you can use English name and save it in UTF-8 encoding;

[0069] TagLanguage field: used to save the language of the key value name. It can be named in three uppercase and lowercase English letters, for example: eng for English, enu for American English, chs for Simplified Chinese, cht for Traditional Chinese, etc. It is saved in UTF-8 encoding.

[0070] TagString field: used to store the value of the above data, which is a UTF-8 encoded string.

[0071] In the embodiment of the present specification, a set of header data is added to the header of the video file metadata to indicate the version number of the video file metadata.

[0072] That is to say, by adding a version number to the metadata of each video file, it is convenient to expand and identify the above information data in the future. At the same time, the corresponding data can be quickly identified according to the version number, thereby improving the reliability and accuracy of data extraction.

[0073] For example, for the same short video file, the user can render different types of short videos according to different application scenarios. Therefore, the corresponding version number can be added to the header of the video file metadata to ensure that each output video can match the corresponding video file metadata.

[0074] In the embodiment of this specification, the method further includes:

[0075] A digital signature is added at the end of the metadata of the video file, and the digital signature is obtained by encrypting the metadata of the video file through a digest algorithm.

[0076] In other words, by adding a digital signature to the metadata of a video file, the authenticity of the data can be guaranteed and data tampering can be prevented. For example, for the verification of shooting parameters, all data parameters can be read from the SimpleTag array object in the video file, and the corresponding numerical values ​​calculated by the digest algorithm (MD5 / SHA-1 / SHA-2 / SM3, etc.) can be compared with the value of the digital signature field. If they are consistent, it means that the parameters have not been modified; otherwise, it means that the parameters have been changed; for the verification of video files (i.e. short videos), the MD5 value calculated by the digest algorithm for the entire video file data can be compared with the MD5 value read from the SimpleTag array object in the video file. If they are consistent, it means that the file has not been modified; otherwise, it means that the file is not the original file.

[0077] In an embodiment of the present specification, the specific short video shooting theme includes at least the following themes: recommendation of shooting routes for specific scenic spots, recommendation of shooting routes for specific seasons, recommendation of shooting parameters for specific lighting, recommendation of video shooting parameters for specific weather conditions, recommendation of video background rendering parameters for specific lighting conditions, and recommendation of video background rendering parameters for specific weather conditions. Furthermore, different specific short video shooting themes correspond to different multi-dimensional evaluation indicators. It can be understood that the evaluation indicators can be the shooting parameters mentioned above, that is, the contribution degree of different shooting parameters in different short video shooting themes is different. For example, when recommending shooting routes, more attention will be paid to the flight path of the drone, such as longitude, latitude, altitude, speed, nose direction, etc. Therefore, according to different specific short video shooting themes, the corresponding evaluation indicator set can be set in advance, so that when evaluating short videos, targeted evaluation can be carried out, and the parameter set corresponding to the corresponding theme can be quickly obtained.

[0078] Furthermore, according to the specific short video shooting theme, combined with the evaluation results of each video file in different dimensions, the video file metadata corresponding to each video file is clustered to obtain target metadata combinations corresponding to different specific short video shooting themes, including:

[0079] Determine specific short video shooting themes and their corresponding multi-dimensional evaluation indicators;

[0080] Acquire a collection of historical video files associated with the specific short video shooting theme;

[0081] Based on the multi-dimensional evaluation index, each historical video file in the historical video file set is analyzed using big data to obtain an evaluation result of each historical video file on each evaluation index, wherein the evaluation index represents the contribution degree of the evaluation index to the historical video file;

[0082] Based on a preset clustering algorithm, a cluster analysis is performed on all evaluation results in the historical video file set to determine a target metadata combination that satisfies a preset contribution degree to the characteristic short video shooting theme.

[0083] Among them, when evaluating video files, different evaluation weights can also be set according to different user age groups, so as to improve the reliability of the evaluation of each video file. Furthermore, different evaluation weights can be set according to the user's network traces to ensure that the evaluation of each video file meets the network evaluation standards, where the network traces can be the user's network browsing time, the frequency or number of short videos posted online, etc.

[0084] The present invention records the data collected during the drone video shooting process into a video file, which can not only be used for data collection in various drone video shooting processes, but also can perform subsequent analysis and processing based on the metadata integrated in the video file, including but not limited to optimization and recommendation of shooting routes, automatic selection and optimization of shooting parameters, parameter selection and optimization of post-video rendering, verification of video shooting data, verification of video files and other usage scenarios.

[0085] Based on the comprehensive application of the above scenarios, the final goal is to improve the film effect and quality, and also to trace the copyright and production process of the video files.

[0086] The embodiment of this specification also provides an optimization processing method for drone short video shooting, which expands the basic data recorded by the original EXIF, defines an extensible data structure, records various index parameters such as shooting environment, location, route, etc. into the video file, and supports video file formats including MP4, MKV, etc., which is convenient for subsequent optimization of video shooting, and can also trace the source and manage copyright of video files. The subsequent possible application scenarios are relatively wide: including but not limited to:

[0087] 1. Can be used for short video shooting and editing in tourist attractions:

[0088] 1.1. Can be used to optimize and recommend shooting routes

[0089] 1.2. Can be used for automatic selection and optimization of shooting parameters;

[0090] 1.3. Parameter selection and optimization for later video rendering;

[0091] 1.4. Can be used to verify video shooting data;

[0092] 1.5. Can be used for video file verification;

[0093] 2. It can also be used for editing and producing short videos of cultural tourism, sports events, etc.:

[0094] 3. It can also be used to verify whether the video file is an unprocessed original file.

[0095] 4. It can also be used to protect the copyright of video files.

[0096] Furthermore, the specific implementation method of the embodiment of this specification is as follows: the platform collects and records the following data including but not limited to the following during the short video shooting and editing process, and associates and integrates the following data with the short video file after the shooting and editing is completed into the video file data stream:

[0097] Data of multiple track points in the drone route: longitude, latitude, altitude, speed, nose direction, etc.

[0098] Weather data of the external environment of the scenic spot: weather, temperature, humidity, wind speed, wind direction, air quality, light intensity, ultraviolet intensity, etc.

[0099] Data related to the camera equipment: camera equipment manufacturer, brand, model, equipment serial number, etc.

[0100] Video shooting related data: aperture, ISO value, white balance, exposure compensation, color space, color depth, contrast, saturation, sharpness, focal length, flash, shooting mode, metering mode, focus mode, shooting time, latitude, longitude and altitude of the shooting point, latitude, longitude and altitude reference, etc.;

[0101] Video encoding related data: video encoding format, bit rate, frame rate, video duration, video resolution, thumbnail size and thumbnail, file size, file type, file MIME type, file MD5 value, etc.;

[0102] User copyright-related data: author, editing software, editing time, user comments, etc.

[0103] The above data is stored in the SimpleTag array object in the video file; a set of header data is added to the head of these arrays to mark the version number of the data, etc., to facilitate the expansion and identification of the above information data in the future; and a digital signature and verification of the above data according to the digest algorithm (MD5 / SHA-1 / SHA-2 / SM3, etc.) is added to the tail of the array to prevent the above data from being modified;

[0104] TagName field: used to store the key value name (Key Name) of the above data. The default name is Chinese, but you can use English name and save it in UTF-8 encoding;

[0105] TagLanguage field: used to save the language of the key value name. It can be named in three uppercase and lowercase English letters, for example: eng for English, enu for American English, chs for Simplified Chinese, cht for Traditional Chinese, etc. It is saved in UTF-8 encoding.

[0106] TagString field: used to store the value of the above data, which is a UTF-8 encoded string.

[0107] When evaluating the objective scoring of the video's filming quality or the subjective scoring of tourists' satisfaction, the above metadata can be directly read from the data stream integrated into the video file, and the short video shooting parameters can be analyzed by big data in combination with these data. Using cluster analysis tools, the top five major influencing factors can be obtained according to the size of the impact, and the platform's video shooting or subsequent optimization processing can be gradually optimized, such as: route design and recommendation for short video shooting at specific attractions and specific seasons, selection of specific lighting and weather conditions and video shooting parameters, and optimization of video background rendering parameters, etc. Including but not limited to one or more of the following combinations:

[0108] Design and recommend shooting routes for specific scenic spots: Use clustering algorithms to analyze the correlation between different shooting routes and reviews of short videos of the same scenic spot, and obtain the best shooting route for the scenic spot;

[0109] Design and recommend shooting routes for specific seasons: Use clustering algorithms to conduct correlation analysis on different shooting routes and evaluations of short videos of the same scenic spot in a specific season, and obtain the best shooting route for the scenic spot;

[0110] Selection of video shooting parameters for specific lighting conditions: Use clustering algorithms to conduct correlation analysis on short videos of the same scenic spot with lighting conditions at different times, video shooting parameters, and evaluations, and obtain the recommended shooting parameter combinations corresponding to different lighting conditions;

[0111] Selection of video shooting parameters for specific weather conditions: Use clustering algorithms to conduct correlation analysis on short videos of the same scenic spot for different weather conditions, video shooting parameters and evaluations, and obtain the recommended shooting parameter combinations for different weather conditions;

[0112] Optimization of video background rendering parameters for specific lighting conditions: Use clustering algorithms to conduct correlation analysis on the lighting conditions at different times and the background rendering parameter combinations and evaluations of short videos of the same scenic spot, and obtain the recommended background rendering optimization parameter combinations corresponding to different lighting conditions;

[0113] Optimization of video background rendering parameters for specific weather conditions: Use clustering algorithms to conduct correlation analysis on short videos of the same scenic spot for different weather conditions and background rendering parameter combinations and evaluations, and obtain the recommended background rendering optimization parameter combinations for different weather conditions;

[0114] Combined with the various metadata integrated into the video file data stream, the copyright and production process of the video file can also be traced. At the same time, it can also verify whether the video file is original:

[0115] Data verification for video recording: read all data parameters from the SimpleTag array object in the video file, calculate the corresponding value through the digest algorithm (MD5 / SHA-1 / SHA-2 / SM3, etc.) and compare it with the value of the digital signature field. If they are consistent, it means that the parameters have not been modified; otherwise, it means that the parameters have been changed.

[0116] Verification of video files: Calculate the MD5 value of the entire video file data using the digest algorithm and compare it with the MD5 value read from the SimpleTag array object in the video file. If they are consistent, it means that the file has not been modified; otherwise, it means that the file is not the original file.

[0117] Based on the above-mentioned method, the embodiment of this specification also provides an optimization processing device for drone short video shooting, such as Figure 3 As shown, the device comprises:

[0118] An acquisition module 310 is used to acquire video files shot by drones in the same scenic spot, and shooting parameters corresponding to each video file, wherein the shooting parameters at least include drone shooting parameters, environmental parameters, shooting equipment parameters, and video file parameters;

[0119] The encoding module 320 is used to encode the shooting parameters to obtain video file metadata bound to the video file;

[0120] An evaluation module 330 is used to evaluate each video file using multi-dimensional evaluation indicators to obtain evaluation results of each video file in different dimensions;

[0121] The clustering module 340 is used to cluster the video file metadata corresponding to each video file according to the specific short video shooting theme and the evaluation results of each video file in different dimensions to obtain the target metadata combination corresponding to different specific short video shooting themes.

[0122] The friendship effect obtained by the above-mentioned device is consistent with the above-mentioned method, and will not be described in detail in the embodiments of this specification.

[0123] This embodiment provides a computer device, whose internal structure diagram can be shown as follows: Figure 4 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection.

[0124] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0125] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0126] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0127] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0128] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0129] It should also be understood that in the embodiments of this article, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0130] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this article.

[0131] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0132] In the several embodiments provided herein, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.

[0133] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of this article.

[0134] Specific embodiments are used in this article to illustrate the principles and implementation methods of this article. The description of the above embodiments is only used to help understand the methods and core ideas of this article. At the same time, for general technicians in this field, according to the ideas of this article, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on this article.

Claims

1. An optimization processing method for drone short video shooting, characterized in that: The method comprises: Obtain video files shot by a drone in the same scenic spot, and shooting parameters corresponding to each video file, wherein the shooting parameters at least include drone shooting parameters, environmental parameters, shooting equipment parameters, and video file parameters; Encoding the shooting parameters to obtain video file metadata bound to the video file; Use multi-dimensional evaluation indicators to evaluate each video file and obtain evaluation results of each video file in different dimensions; According to the specific short video shooting theme and combined with the evaluation results of each video file in different dimensions, the video file metadata corresponding to each video file is clustered to obtain the target metadata combinations corresponding to different specific short video shooting themes.

2. The method according to claim 1, characterized in that The drone shooting parameters include at least: longitude, latitude, altitude, speed, and nose direction; The environmental parameters include at least: weather, temperature, humidity, wind speed, wind direction, air quality, light intensity, and ultraviolet intensity; The parameters of the shooting equipment shall at least include: the manufacturer, brand, model, and serial number of the shooting equipment; as well as the aperture, ISO value, white balance, exposure compensation, color space, color depth, contrast, saturation, sharpness, focal length, flash, shooting mode, metering mode, focus mode, shooting time, latitude, longitude, and altitude of the shooting point, and latitude, longitude, and altitude reference; The video file parameters include at least: video encoding format, bit rate, frame rate, video duration, video resolution, thumbnail size and thumbnail, file size, file type, file MIME type, and file MD5 value.

3. The method according to claim 1, characterized in that The shooting parameters are encoded to obtain video file metadata bound to the video file, including: Acquire a shooting data structure of a shooting device, where the shooting data structure at least includes video file parameters obtained by shooting; The shooting data structure is expanded, and the drone shooting parameters, the environmental parameters and the shooting equipment parameters are stored in the expanded data structure to obtain video file metadata.

4. The method according to claim 3, characterized in that The method further comprises: A set of header data is added to the header of the video file metadata to indicate the version number of the video file metadata.

5. The method according to claim 4, characterized in that The method further comprises: A digital signature is added at the end of the metadata of the video file, and the digital signature is obtained by encrypting the metadata of the video file through a digest algorithm.

6. The method according to claim 1, characterized in that The multi-dimensional evaluation indicators corresponding to different specific short video shooting themes are different.

7. The method according to claim 1, characterized in that The specific short video shooting themes include at least the following themes: recommendation of shooting routes for specific attractions, recommendation of shooting routes for specific seasons, recommendation of shooting parameters for specific lighting, recommendation of video shooting parameters for specific weather, recommendation of video background rendering parameters for specific lighting, and recommendation of video background rendering parameters for specific weather conditions.

8. The method according to claim 1, characterized in that: According to the specific short video shooting theme, combined with the evaluation results of each video file in different dimensions, the video file metadata corresponding to each video file is clustered to obtain the target metadata combinations corresponding to different specific short video shooting themes, including: Determine specific short video shooting themes and their corresponding multi-dimensional evaluation indicators; Acquire a collection of historical video files associated with the specific short video shooting theme; Based on the multi-dimensional evaluation index, each historical video file in the historical video file set is analyzed using big data to obtain an evaluation result of each historical video file on each evaluation index, wherein the evaluation index represents the contribution degree of the evaluation index to the historical video file; Based on a preset clustering algorithm, a cluster analysis is performed on all evaluation results in the historical video file set to determine a target metadata combination that satisfies a preset contribution degree to the characteristic short video shooting theme.

9. An optimization processing device for drone short video shooting, characterized in that: The device comprises: An acquisition module is used to acquire video files shot by drones in the same scenic spot, and shooting parameters corresponding to each video file, wherein the shooting parameters at least include drone shooting parameters, environmental parameters, shooting equipment parameters and video file parameters; An encoding module, used for encoding the shooting parameters to obtain video file metadata bound to the video file; An evaluation module is used to evaluate each video file using multi-dimensional evaluation indicators to obtain evaluation results of each video file in different dimensions; The clustering module is used to cluster the video file metadata corresponding to each video file according to the specific short video shooting theme and the evaluation results of each video file in different dimensions to obtain the target metadata combination corresponding to different specific short video shooting themes.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

Images