Driving video automatic editing method, electronic equipment and storage medium

Abstract

The invention discloses a driving video automatic editing method, electronic equipment and a storage medium. The method comprises the following steps: automatically obtaining driving video clips meeting preset conditions in a driving video; marking an emotion label of a moment corresponding to the driving video clip; and processing the driving video clip at least according to the emotion tag to obtain a target edited video. According to the driving video automatic editing method, after the driving video clip meeting the preset condition is automatically identified and intercepted, the emotion tag at the current moment is obtained in real time, the target edited video is generated in combination with the emotion tag and the driving video clip, manual editing by a user is not needed, and when the user reviews the target edited video, the user experience is improved. And the current emotional state can be recalled according to the target edited video, so that the driving journey recording modes are enriched, and the user emotional resonance and recording efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of video editing technology, and more particularly to an automatic video editing method for driving, an electronic device, and a storage medium. Background Technology

[0002] Existing technology allows for the recording and storage of driving videos via in-vehicle cameras, which users can then review later. However, traditional video recording methods are no longer sufficient to meet users' recording needs, as they often need to edit the videos. For example, after a journey, a user might select highlight clips from the video footage to edit and share. This process requires manual operation, especially for long trips where users must sift through lengthy videos to find and edit highlights, resulting in low efficiency. Furthermore, the recording process doesn't capture the user's emotional state in real time, meaning that even if the user eventually obtains the edited video, they cannot recall their feelings at the time when reviewing it. Summary of the Invention

[0003] This application provides a method for automatic editing of driving videos, an electronic device, and a storage medium to at least solve one of the above-mentioned technical problems.

[0004] In a first aspect, embodiments of this application provide a method for automatic editing of driving videos, including: Automatically acquire driving video clips that meet preset conditions from driving videos; Label the emotional tags for the corresponding moments in the driving video clips; The target edited video is obtained by processing the driving video clips based on at least the emotion tags.

[0005] In some embodiments, automatically acquiring driving video segments that meet preset conditions from driving videos includes: using a pre-trained model to identify and extract driving video segments that meet preset conditions from driving videos, and / or, identifying and extracting driving video segments that meet preset conditions from driving videos based on the shooting address of the driving video.

[0006] In some embodiments, labeling the driving video clip with an emotion tag corresponding to a specific moment includes: Acquire driving scene data at the time corresponding to the driving video clip, wherein the driving scene data includes at least one of the following: facial images of people inside the vehicle, music played inside the vehicle, audio of people inside the vehicle, and vehicle driving data; Emotional tags for the corresponding moments in the driving video segments are obtained by performing emotion recognition processing based on the driving scene data.

[0007] In some embodiments, the emotion tag includes an emotion type, and the step of obtaining the emotion tag for the corresponding moment of the driving video segment by performing emotion recognition processing based on the driving scene data includes: The emotion type of the driving video segment at the corresponding moment is obtained by performing emotion recognition processing based on at least one of the following: facial images of people inside the vehicle, music played inside the vehicle, audio of people inside the vehicle, and vehicle driving data.

[0008] In some embodiments, the emotion tag includes an emotion score, and the step of obtaining the emotion tag for the corresponding moment of the driving video segment by performing emotion recognition processing based on the driving scene data includes: A first emotion score is obtained by scoring the emotions of the occupants based on their facial images; and / or a second emotion score is obtained by scoring the emotions of the occupants based on the music played in the vehicle; and / or a third emotion score is obtained by scoring the emotions of the occupants based on their audio recordings; and / or a fourth emotion score is obtained by scoring the emotions of the occupants based on their vehicle driving data. The emotional score of the occupants in the vehicle is determined based on at least one of the first to fourth emotional scores.

[0009] In some embodiments, the driving video clip is processed at least according to the emotion tag to obtain the target edited video, including: An emotion score curve is generated based on multiple emotion scores corresponding to multiple driving video clips at multiple times. The emotion score curve is used to characterize the correspondence between emotion scores and time. Multiple driving video clips are processed according to the emotion score curve to obtain a target edited video; wherein, the target edited video includes the driving video clips corresponding to the peaks in the emotion score curve.

[0010] In some embodiments, processing multiple driving video clips according to the emotion score curve to obtain a target edited video includes: Based on the peak of the emotion score curve, obtain the music clip that matches the driving video clip; and / or determine the transition method between different driving video clips based on the changing trend of the emotion score curves corresponding to multiple driving video clips. Multiple driving video clips are processed according to the music clips and / or transition methods to obtain the target edited video.

[0011] In some embodiments, the method further includes: configuring matching emoji icons for the target clip video, and pushing the target clip video and emoji icons to a display terminal for display.

[0012] In some embodiments, the method further includes displaying multiple target video clips on the display terminal according to date.

[0013] In a second aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform any of the above-described automatic video editing methods of this application.

[0014] Thirdly, embodiments of this application provide a storage medium storing one or more programs including execution instructions, which can be read and executed by electronic devices (including but not limited to computers, servers, or network devices, etc.) to perform any of the above-described automatic video editing methods for driving in this application.

[0015] Fourthly, embodiments of this application also provide a computer program product, the computer program product including a computer program stored on a storage medium, the computer program including program instructions, which, when executed by a computer, cause the computer to perform any of the above-described automatic video editing methods.

[0016] The automatic video editing method of this application automatically identifies and extracts video clips that meet preset conditions, obtains the current mood tag in real time, and combines the mood tag with the video clip to generate the target edited video. No manual editing is required from the user. When the user reviews the target edited video, they can also recall their emotional state at that time based on the target edited video, which enriches the way of recording driving journeys and improves the user's emotional resonance and recording efficiency. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of an embodiment of the automatic video editing method of this application; Figure 2 A flowchart of another embodiment of the automatic video editing method of this application; Figure 3 A flowchart of another embodiment of the automatic video editing method of this application; Figure 4A flowchart of another embodiment of the automatic video editing method of this application; Figure 5 A flowchart of another embodiment of the automatic video editing method of this application; Figure 6 This is a schematic diagram illustrating the loading of the emotion easter egg in the HMI interface of this application; Figure 7 This is a schematic diagram of the HMI interface - emotion easter egg pop-up in this application; Figure 8 This is a schematic diagram of the HMI interface for playing finished videos in this application; Figure 9 This is a schematic diagram of the HMI interface - mood calendar in this application; Figure 10 This is a schematic diagram of the HMI interface in this application - viewed by month; Figure 11 This is a schematic diagram of the HMI interface in this application - viewed by day; Figure 12 This is a schematic diagram of the structure of an embodiment of the electronic device of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other.

[0020] It should also be noted that, in this document, the terms "comprising" or "including" include not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0021] This application provides a method for automatically editing driving videos. This method can be executed by an electronic device installed in a vehicle. The electronic device can be a vehicle infotainment system, a processor installed in the vehicle, or other hardware devices. This application does not limit the specific form of the electronic device. For example, the electronic device is connected to the vehicle's in-vehicle camera and a display device. The electronic device acquires driving videos from the in-vehicle camera, automatically edits the driving videos, and then pushes the edited target video to the display device.

[0022] like Figure 1 As shown, an embodiment of this application provides a method for automatic editing of driving videos, including: S10. Automatically acquire driving video clips that meet preset conditions from the driving video.

[0023] For example, a pre-trained model is used to identify and extract video clips that meet preset conditions from driving videos. These preset conditions can be reflected in the network structure and internal parameters of the pre-trained model (learned through training on a large number of training samples). The pre-trained model can be a neural network model from the prior art that can automatically identify highlight moments in videos; this application does not limit this approach.

[0024] During vehicle operation, onboard cameras record driving video in real time. The vehicle's electronic equipment uses a pre-trained model to automatically identify driving video clips that meet preset conditions. These clips are then extracted and stored.

[0025] For example, video clips that meet preset conditions can also be identified and extracted from driving videos based on the shooting location of the video. For instance, if the vehicle camera detects that the current shooting location (e.g., the driving position obtained by the vehicle positioning device) is a preset shooting location (e.g., near certain scenic spots, landmarks, or special buildings) during the shooting process, then this video clip is considered a highlight video clip, that is, a scene or journey worth recording, and is a video clip that meets the preset conditions.

[0026] For example, during the recording process, the in-vehicle camera can identify images in the video in real time. When a preset scene is identified (e.g., certain scenic spots, landmarks, or special buildings), the video clip is considered a highlight video clip, which is a scene or journey worth recording and meets the preset conditions.

[0027] S20. Mark the emotion tag for the corresponding moment of the driving video segment.

[0028] For example, after obtaining a driving video clip that meets the preset conditions, the current mood tag inside the car is obtained in real time, and the driving video clip is marked with the tag. The mood tag and the corresponding driving video clip are then stored together.

[0029] S30. Process the driving video clip at least according to the emotion tag to obtain a target edited video. For example, the driving video clip is processed into a target edited video that matches the emotion tag. For instance, a matching music clip can be obtained based on the emotion tag, and this music clip can be used as the background music for the driving video clip to form the target edited video.

[0030] The automatic driving video editing method in this embodiment automatically identifies and extracts driving video clips that meet preset conditions, obtains the current moment's emotion tag in real time, and combines the emotion tag with the driving video clip to generate the target edited video. No manual editing is required from the user. Furthermore, when the user reviews the target edited video, the target edited video can also be associated with the user's emotional state at a historical moment. This enables the automated creation of personalized driving journey vlogs, enriches the ways of recording driving journeys, and improves the user's emotional resonance and recording efficiency.

[0031] like Figure 2 The diagram shows a flowchart of another embodiment of the automatic video editing method of this application. In this embodiment, step S20 includes: S21. Obtain driving scene data corresponding to the driving video clip at the specified time. The driving scene data includes at least one of the following: facial images of occupants inside the vehicle, music playing inside the vehicle, audio of occupants inside the vehicle, and vehicle driving data. Occupants inside the vehicle include, but are not limited to, the driver, front-seat passengers, and rear-seat passengers. For example, after obtaining a driving video clip that meets preset conditions, the driving scene data for the current time is obtained in real time.

[0032] For example, facial images of occupants in the vehicle can be captured by an in-vehicle camera and transmitted to the vehicle's electronic equipment, which may be equipped with a driver monitoring system (DMS) and an occupant monitoring system (OMS) for recognition processing of facial images of occupants in the vehicle and for emotion recognition.

[0033] For example, the music playing inside the vehicle and the audio of the occupants can be collected by microphones inside the vehicle and transmitted to the vehicle's electronic equipment. This electronic equipment can be configured with an audio recognition model for emotion recognition based on the music playing inside the vehicle and the audio of the occupants. The audio of the occupants can include laughter, voice, etc. The audio recognition model can be a mature model from the prior art, capable of performing emotion recognition and classification based on the audio of the occupants; this application does not impose any limitations on this.

[0034] For example, vehicle driving data includes, but is not limited to, rapid acceleration and sudden braking. Rapid acceleration can correspond to feelings of excitement, while sudden braking can correspond to feelings of tension.

[0035] S22. Based on the driving scene data, perform emotion recognition processing to obtain the emotion tag for the corresponding moment of the driving video segment.

[0036] For example, the emotion tag includes an emotion type. Step S22 includes: performing emotion recognition processing based on at least one of the facial images of the occupants in the vehicle, the music playing in the vehicle, the audio of the occupants in the vehicle, and the vehicle driving data to obtain the emotion type of the driving video segment at the corresponding moment. The emotion type includes, but is not limited to, at least one of excitement, exhilaration, happiness, pleasure, calmness, tension, sadness, grief, anger, and surprise.

[0037] In this embodiment, emotion recognition is performed using data from various driving scenarios, which can accurately determine the user's emotional state when recording driving video clips, making it easier to assign accurate emotion labels to the driving video clips.

[0038] like Figure 3 The diagram shows a flowchart of another embodiment of the automatic video editing method of this application. In this embodiment, the emotion label includes an emotion score, and step S22 includes: S221. Score the emotions of the occupants based on their facial images to obtain a first emotion score; and / or score the emotions of the occupants based on the music played in the vehicle to obtain a second emotion score; and / or score the emotions of the occupants based on their audio recordings to obtain a third emotion score; and / or score the emotions of the occupants based on their vehicle driving data to obtain a fourth emotion score.

[0039] For example, an electronic device configured in the vehicle is used to perform step S221 above. This electronic device may be configured with one or more of a Driver Monitoring System (DMS), an Occupant Monitoring System (OMS), and an audio recognition model. Specifically, the Driver Monitoring System and the Occupant Monitoring System are used to identify and score the emotions of occupants based on facial images of them, obtaining a first emotion score. The audio recognition model is used to identify and score the emotions of occupants based on music played in the vehicle and / or audio of them, obtaining a second and / or a third emotion score. The electronic device can also obtain vehicle driving data (e.g., rapid acceleration, sudden braking, etc.) from the vehicle system and determine the emotion type corresponding to the vehicle driving data according to a preset correspondence, scoring it to obtain a fourth emotion score.

[0040] S222. Determine the emotional score of the occupant based on at least one of the first to fourth emotional scores. For example, after obtaining the first to fourth emotional scores in step S221, the emotional score of the occupant can be determined by a weighted sum.

[0041] This embodiment utilizes multimodal data, including facial images of occupants, music played inside the vehicle, audio recordings of occupants, and vehicle driving data, to perform emotion recognition and scoring across multiple data dimensions. Finally, the final emotion score is determined by comprehensively considering the scores from multiple dimensions. This improves the accuracy and objectivity of the emotion score.

[0042] like Figure 4 The diagram shows a flowchart of another embodiment of the automatic video editing method of this application. In this embodiment, step S30 includes: S31. Generate an emotion score curve based on multiple emotion scores corresponding to multiple driving video clips at multiple times. The emotion score curve is used to characterize the correspondence between emotion scores and time.

[0043] For example, a user records and captures multiple driving video clips at various times during a day's journey. Combining these with the emotion scores corresponding to each driving video clip calculated in the aforementioned embodiments, an emotion score curve can be generated with time as the horizontal axis and emotion score as the vertical axis. The horizontal axis of time can be specified to the date, time, and minute of each driving video clip's recording.

[0044] S32. Process multiple driving video clips according to the emotion score curve to obtain a target edited video; wherein, the target edited video includes the driving video clips corresponding to the peaks in the emotion score curve.

[0045] In this embodiment, the emotional score curve is used to present multiple driving video clips acquired over a period of time (e.g., a whole driving journey, a day, etc.) in a visual form, allowing users to intuitively view the distribution of multiple driving video clips recorded during this period over time.

[0046] like Figure 5 The diagram shows a flowchart of another embodiment of the automatic video editing method of this application. In this embodiment, step S32 includes: S321. Based on the peak of the emotion score curve, obtain a music segment that matches the driving video segment; and / or based on the changing trend of the emotion score curves corresponding to multiple driving video segments, determine the transition method between different driving video segments.

[0047] For example, based on the emotion score corresponding to the peak of the emotion score curve, a matching emotion type is determined, and then a suitable music segment for that emotion type is obtained (e.g., by determining a suitable music segment through a pre-built "emotion-music" mapping relationship, which can be pre-built by parsing the user's favorite songs or frequently played tracks in the in-vehicle music software); or, a matching music segment can be obtained directly based on the pre-built emotion score-music segment mapping relationship. For example, when the emotion type is calm, a gentle segment of a piano piece is matched as the audio segment.

[0048] For example, in multiple driving video clips, a fast transition is selected when the emotional score between the first and second video clips shows an increasing trend; a gradual transition is selected when the emotional score between the first and second video clips shows a decreasing trend. The fast transition involves a direct switch between shots without any transition effect, where the last frame of the previous shot is directly connected to the first frame of the next shot. The duration of a single shot is typically ≤0.5 seconds, creating a sense of rhythmic break and forming a strong contrast. The gradual transition involves a slow and natural transition between the previous and next shots using fade-in / fade-out (e.g., 0% to 100% transparency (fade-in)) or dissolve (synchronous change of the previous shot's transparency from 100% to 0% and the next shot's transparency from 0% to 100%).

[0049] S322. Process multiple driving video clips according to the music clips and / or transition methods to obtain the target edited video.

[0050] For example, each music clip is used as background music for the corresponding driving video clip, and then multiple driving video clips are spliced ​​into one video clip. The appropriate transition method is selected based on the changing trend of the emotion score curves corresponding to two adjacent driving video clips.

[0051] For example, splicing multiple driving video clips into one video clip includes: splicing multiple driving video clips into one video clip in chronological order; or sorting multiple driving video clips according to the emotional scores of the corresponding peaks in descending or ascending order, and then splicing multiple driving video clips into one video clip according to the sorting. The second splicing method provides a more flexible approach; furthermore, the difference in emotional scores between two adjacent driving video clips is more gradual in the second splicing method than in the first, avoiding the abruptness that can occur when directly splicing two driving video clips with significantly different emotional scores.

[0052] The automatic video editing method in this embodiment selects background music based on the emotion score curve (e.g., matching a piano piece with a gentle climax during calm periods) and dynamically adjusts the transition rhythm (e.g., using fast cuts during emotional rises and gradual transitions during emotional falls). This ensures that the background music of the resulting edited video matches each video segment, and the transition rhythm between adjacent video segments also matches the emotional type of those segments.

[0053] In some embodiments, the automatic video editing method further includes: determining location information of the vehicle's location when the video clip was captured; and storing the location information and the video clip in association. For example, while or after automatically acquiring video clips that meet preset conditions from the video footage, the method of this embodiment obtains the corresponding location information and stores it in association with the video clips.

[0054] This embodiment associates the location information of the driving video clips with the storage, so that the automatically edited target video not only has emotional state information, but also geographical location information. Users can use the automatically edited target video to immerse themselves in the wonderful moments of the journey, enriching the way driving journeys are recorded and enhancing the emotional resonance of users.

[0055] In some embodiments, the location information corresponding to each driving video clip can also be marked on the emotion score curve, so that users can intuitively see the distribution of various wonderful moments experienced on the journey in time and space.

[0056] In some embodiments, the method further includes: configuring matching emoji icons for the target clip video, and pushing the target clip video and emoji icons to a display terminal for display.

[0057] For example, the target video clips are displayed in a matrix on a display terminal, and emoji icons are labeled next to the corresponding target video clips.

[0058] In some embodiments, the method further includes displaying multiple target video clips on the display terminal according to date.

[0059] For example, the target video clips are displayed on a display terminal in chronological order of dates. For instance, they can be arranged in a matrix format. Alternatively, they can be arranged in a calendar format.

[0060] This application presents an automatic driving video editing method that integrates a driver monitoring system (DMS), an audio recognition model, music source preference analysis, and vehicle-side image data fusion to create a driving journey recording system. By assigning emotion tags to the recorded driving video content during the driving process, and combining the corresponding emotion types with emotion curves, multiple highlight segments (i.e., multiple driving video clips) are synthesized and edited. Through real-time emotion tag recognition, multi-source data fusion, and AI content generation technology, personalized driving journey vlogs are automatically created, enriching driving journey recording methods and improving user emotional resonance and recording efficiency.

[0061] In some embodiments, the automatic video editing method of this application includes the following steps: 1. Pre-trip settings: Analyze the user's favorite songs or frequently played tracks in the car's music software and establish an "emotion-music" mapping library (such as mapping fast-paced electronic music to excited emotions).

[0062] 2. Recording during the journey: The driver's emotional data is captured during the driving process through DSM and matched with labels such as pleasant / calm / excited. At the same time, the highlight video clips corresponding to the peak emotions are marked, and the song and lyrics currently playing on the vehicle's system are recorded simultaneously (if the vehicle's system is not playing music, the corresponding song and lyrics are matched according to the "emotion-music" mapping library pre-established in step 1 above).

[0063] 3. Post-trip generation: After the user switches to P gear, and the amount of highlight footage for the day is greater than or equal to the calibration value (for example, the amount of footage represents the total duration of highlight video clips for the day; taking a final cut of about 1-1.5 minutes as an example, the total duration of highlight video clips must be at least greater than this value to meet the requirements of editing the final cut), automatic background editing is performed; the editing mainly relies on automatically extracting highlight video clips (i.e., driving video clips) corresponding to the peak emotion score; background music is selected according to the emotion score curve (e.g., matching a gentle piano piece during calm periods) and the transition rhythm is dynamically adjusted (e.g., using fast cuts during the emotion rise and using fading during the emotion fall); the generated cut is pushed to the vehicle's infotainment system or the driver's mobile phone.

[0064] For example, after the current trip ends (the user shifts into Park), the final video editing and rendering begins. At this time, the interface displays the loading mood easter egg. After editing is completed, the current day's mood expression is displayed, and then the corresponding final video begins to play. In some embodiments, the final video editing and rendering can also be performed while driving.

[0065] like Figure 6 The image shown is a schematic diagram of the HMI interface loading the mood easter egg in this application. For example, it displays 7 emoji icons arranged in a circle, with the date displayed in the center, and a prompt message "Based on the DMS recognition result, today's mood has been matched" is displayed.

[0066] like Figure 7 The image shown is a schematic diagram of the HMI interface - Emotion Easter Egg pop-up in this application. It displays the finally matched emoji icon, accompanied by the text "It's late at night, I seem a little tired today, let's take a look at the scenery we passed together today...". Exemplarily, this text can be automatically generated using AI, and this application does not limit it to this.

[0067] like Figure 8 The diagram shown is an illustration of the HMI interface for playback of the final video clip in this application. The main interface plays the synthesized target video clip and simultaneously displays the corresponding date, mood icon, text, keywords, and music title.

[0068] 4. Mood Calendar Review: Automatically summarizes and visualizes daily journey videos based on mood tag types.

[0069] like Figure 9 The image shown is a schematic diagram of the HMI interface - Emotion Calendar in this application. This interface is the one displayed after selecting the "Highlight Memories" component. Next to the corresponding date with travel records on the calendar, the generated emotion icon for that day is displayed. Furthermore, this interface can also be displayed by week; selecting the "Week" component will redirect to... Figure 10 The interface shown.

[0070] like Figure 10 The image shown is a schematic diagram of the HMI interface in this application, viewed by month. It displays target edited videos recorded and generated during the past week's travels. Furthermore, when the "Recent Days" component in the image is selected, the interface will redirect to... Figure 11 The interface shown.

[0071] like Figure 11 The image shown is a schematic diagram of the HMI interface in this application, viewed by day. The main interface displays the target video clip corresponding to the selected date, along with address information and a mood icon. The right side of the main interface displays previews of target video clips for other dates, and users can click here to switch the content displayed on the main interface.

[0072] It should be noted that the above figures are merely examples and this application does not limit them.

[0073] In some embodiments, the mood calendar can also be shared with one click based on user actions. For example, the mood calendar can be transformed into a "driving mood postcard" based on user actions, which is to cut highlight clips from in-vehicle footage (e.g., target edited video) into live images and automatically add geographic tags. In some embodiments, based on nine highlight clips selected by the user at the same time, a nine-grid template for WeChat Moments can also be generated (different filters correspond to different emotions).

[0074] In some embodiments, services that match a user's current emotional state can also be recommended based on emotional data (e.g., emotional scores and / or emotional types and / or emotional icons). For example, when a user is anxious, coffee shops along the way can be recommended and navigation provided.

[0075] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of combined actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Secondly, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application. In the above embodiments, the descriptions of each embodiment have their own emphasis; for parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0076] In some embodiments, this application provides a non-volatile computer-readable storage medium storing one or more programs including execution instructions, which can be read and executed by electronic devices (including but not limited to computers, servers, or network devices) to perform any of the above-described automatic video editing methods of this application.

[0077] In some embodiments, this application also provides a computer program product, the computer program product including a computer program stored on a non-volatile computer-readable storage medium, the computer program including program instructions, which, when executed by a computer, cause the computer to perform any of the above-described automatic driving video editing methods.

[0078] In some embodiments, this application also provides an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform an automatic video editing method.

[0079] Figure 12This is a schematic diagram of the hardware structure of an electronic device for performing an automatic video editing method according to another embodiment of this application, as shown below. Figure 12 As shown, the device includes: One or more processors 1210 and memory 1220, Figure 12 Take the 1210 processor as an example.

[0080] The device for performing the automatic video editing method may further include an input device 1230 and an output device 1240.

[0081] The processor 1210, memory 1220, input device 1230, and output device 1240 can be connected via a bus or other means. Figure 12 Taking the example of a connection between China and Israel via a bus.

[0082] The memory 1220, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the automatic driving video editing method in the embodiments of this application. The processor 1210 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions, and modules stored in the memory 1220, thereby implementing the automatic driving video editing method in the above-described method embodiments.

[0083] The memory 1220 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the automatic video editing device. Furthermore, the memory 1220 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 1220 may optionally include memory remotely located relative to the processor 1210, and these remote memories may be connected to the automatic video editing device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0084] Input device 1230 can receive input digital or character information, and generate signals related to user settings and function control of the vehicle video automatic editing device. Output device 1240 may include display devices such as a display screen.

[0085] The one or more modules are stored in the memory 1220, and when executed by the one or more processors 1210, the automatic video editing method for driving in any of the above method embodiments is executed.

[0086] The above-described product can perform the methods provided in the embodiments of this application, and has the corresponding functional modules and beneficial effects for performing the methods. Technical details not described in detail in this embodiment can be found in the methods provided in the embodiments of this application.

[0087] The embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0088] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for automatic editing of driving videos, comprising: Automatically acquire driving video clips that meet preset conditions from driving videos; Label the emotional tags for the corresponding moments in the driving video clips; The target edited video is obtained by processing the driving video clips based on at least the emotion tags.

2. The method according to claim 1, characterized in that, The automatic acquisition of driving video segments that meet preset conditions from driving videos includes: using a pre-trained model to identify and extract driving video segments that meet preset conditions from driving videos; and / or, identifying and extracting driving video segments that meet preset conditions from driving videos based on the shooting address of the driving video.

3. The method according to claim 1, characterized in that, The emotional tags that mark the corresponding moments in the driving video clips include: Acquire driving scene data at the time corresponding to the driving video clip, wherein the driving scene data includes at least one of the following: facial images of people inside the vehicle, music played inside the vehicle, audio of people inside the vehicle, and vehicle driving data; Emotional tags for the corresponding moments in the driving video segments are obtained by performing emotion recognition processing based on the driving scene data.

4. The method according to any one of claims 1-3, characterized in that, The emotion tag includes an emotion score. The process of obtaining the emotion tag for the corresponding moment of the driving video segment by performing emotion recognition processing based on the driving scene data includes: A first emotion score is obtained by scoring the emotions of the occupants based on their facial images; and / or a second emotion score is obtained by scoring the emotions of the occupants based on the music played in the vehicle; and / or a third emotion score is obtained by scoring the emotions of the occupants based on their audio recordings; and / or a fourth emotion score is obtained by scoring the emotions of the occupants based on their vehicle driving data. The emotional score of the occupants in the vehicle is determined based on at least one of the first to fourth emotional scores.

5. The method according to claim 4, characterized in that, The process of processing the driving video clips based at least on the emotion tags to obtain the target edited video includes: An emotion score curve is generated based on multiple emotion scores corresponding to multiple driving video clips at multiple times. The emotion score curve is used to characterize the correspondence between emotion scores and time. Multiple driving video clips are processed according to the emotion score curve to obtain a target edited video; wherein, the target edited video includes the driving video clips corresponding to the peaks in the emotion score curve.

6. The method according to claim 5, characterized in that, The process of processing multiple driving video clips based on the emotion score curve to obtain the target edited video includes: Based on the peak of the emotion score curve, obtain the music clip that matches the driving video clip; and / or determine the transition method between different driving video clips based on the changing trend of the emotion score curves corresponding to multiple driving video clips. Multiple driving video clips are processed according to the music clips and / or transition methods to obtain the target edited video.

7. The method according to any one of claims 1-3, characterized in that, Also includes: Configure matching emoji icons for the target video clip, and push the target video clip and emoji icons to the display terminal for display.

8. The method according to claim 7, characterized in that, Also includes: Multiple target video clips are displayed on the display terminal according to date.

9. An electronic device comprising: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method according to any one of claims 1-8.

10. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1-8.

Images