Vehicle-mounted video production method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a vehicle-mounted video production method and device, electronic equipment and a storage medium. The method comprises the following steps: identifying a highlight moment picture from video frames shot by cameras with different visual angles inside and outside a vehicle according to a preset period; determining a target camera according to the camera where the highlight moment picture is located, and recording a video by using the target camera to obtain a video material; fusing the video picture tag corresponding to the video material and the vehicle state tag according to a timestamp to obtain a vehicle end tag file; and performing video editing on the video material at least based on the vehicle end label file to generate a target video. Therefore, according to the scheme, automatic recording and video production of the vehicle-mounted video can be realized by identifying the highlight picture, and the generation efficiency and quality of the vehicle-mounted video are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of vehicle-mounted video technology, and in particular to a vehicle-mounted video production method, device, electronic device and storage medium. Background Art

[0002] Existing in-vehicle video shooting mainly relies on simple DVR (Digital Video Recorder) recording, or manual shooting through large screen, voice, etc. This is not only inconvenient to operate during driving, but also difficult to capture the wonderful moments inside and outside the car in time. It is also impossible to instantly preview the captured material images and edit them to form high-quality film output and share them. Summary of the invention

[0003] In view of this, embodiments of the present application provide a method, device, electronic device and storage medium for producing an in-vehicle video to at least partially solve the above-mentioned problems.

[0004] According to the first aspect of an embodiment of the present application, a method for producing in-vehicle videos is provided, including: identifying highlight moment images from video frames taken by cameras from different perspectives inside and outside a vehicle according to a preset period; determining a target camera according to the camera where the highlight moment images are located, and recording a video using the target camera to obtain video material; fusing the video image label and the vehicle status label corresponding to the video material according to a timestamp to obtain a vehicle-side label file; and performing video editing on the video material at least based on the vehicle-side label file to generate a target video.

[0005] According to the second aspect of an embodiment of the present application, a vehicle-mounted video production device is provided, including: an identification module, used to identify highlight moment images from video frames taken by cameras from different perspectives inside and outside the vehicle according to a preset period; a recording module, used to determine a target camera according to the camera where the highlight moment image is located, and use the target camera to record video to obtain video material; a fusion module, used to fuse the video image label and the vehicle status label corresponding to the video material according to the timestamp to obtain a vehicle-side label file; and an editing module, used to edit the video material at least based on the vehicle-side label file to generate a target video.

[0006] According to the third aspect of an embodiment of the present application, an electronic device is provided, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform an operation corresponding to any one of the above-mentioned in-vehicle video production methods.

[0007] According to a fourth aspect of an embodiment of the present application, a computer storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, any of the above-mentioned in-vehicle video production methods is implemented.

[0008] According to the in-vehicle video production solution provided by each embodiment of the present application, highlight moment images are identified from video frames shot by cameras at different perspectives inside and outside the vehicle through a preset period, and then the target camera for recording the video is determined based on the highlight moment image identified each time. This ensures that the best perspective is selected from multiple perspectives for recording, thereby ensuring the recording quality of the video material; at the same time, the video picture label and the vehicle status label corresponding to the video material are fused according to the timestamp, which ensures that the obtained vehicle-side label file combines the picture information and vehicle information in the video frame; and the target video is obtained by performing video editing at least according to the vehicle-side label file, which ensures the quality of the target video. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0010] Figure 1 is a flow chart of a method for producing an in-vehicle video according to an embodiment of the present application;

[0011] Figure 2 is a structural diagram of a vehicle-mounted video production system according to an embodiment of the present application;

[0012] Figure 3 is a schematic diagram of a vehicle-mounted video production device according to an embodiment of the present application;

[0013] Figure 4 It is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0014] In-car video production method

[0015] An embodiment of the present application provides a method for producing in-vehicle videos, by which the highlight images corresponding to the wonderful moments during driving can be automatically shot and edited.

[0016] Figure 1 It is a flow chart of a method for producing an in-vehicle video according to an embodiment of the present application.

[0017] like Figure 1 As shown, the vehicle-mounted video production method in this embodiment includes the following steps:

[0018] Step 101: Identify highlight moment images from video frames captured by cameras at different viewing angles inside and outside the vehicle according to a preset period.

[0019] In some embodiments, at least one candidate video frame may be randomly extracted from video frames of each camera with different viewing angles outside and inside the vehicle at every preset period. The camera may include a periscopic camera and a surround camera. The preset period may be set according to actual needs, such as once per second.

[0020] After the candidate video frame is obtained, the comprehensive score of the candidate video frame can be determined according to at least one of the scene dimension, composition dimension, color dimension and aesthetic dimension of the candidate video frame. As an example, at least one of the scene dimension score, composition dimension score, color dimension score and aesthetic dimension score of the candidate video frame can be obtained based on the high-score recognition algorithm, and the comprehensive score can be obtained based on the weighted sum of various scores. For the scene dimension, the scene type of the candidate video frame can be identified, such as city streets, grassland scenery, seaside scenery, etc., and the attractiveness and visual impact of the scene can be evaluated according to the scene range, scene complexity and other relevant characteristics of the candidate video frame, and the score of the scene dimension is obtained based on the attractiveness and visual impact of the scene; for the composition dimension, the composition elements of the candidate video frame can be determined, and the balance, harmony and attractiveness of the visual focus of the composition can be evaluated based on the composition rules of the composition elements, such as the rule of thirds, symmetry, guiding lines, etc., so as to determine the score of the composition dimension; for the color dimension, the color matching, saturation, etc. in the candidate video frame can be analyzed, and then the beauty of the color and visual comfort can be evaluated to obtain a score for the color dimension; for the aesthetic dimension, the light and shadow, clarity, etc. of the candidate video frame can be analyzed, and then the overall aesthetics of the candidate video frame can be evaluated to obtain a score for the aesthetic dimension.

[0021] If the comprehensive score is greater than or equal to the preset threshold, the candidate video frame is determined as the highlight moment picture.

[0022] Step 102: determine the target camera according to the camera where the highlight moment image is located, and use the target camera to record the video to obtain the video material.

[0023] In some embodiments, after obtaining the highlight moment picture, the camera corresponding to the highlight moment picture can be determined. If at least one candidate video frame extracted from the video frames shot by the camera is all a highlight moment picture, the camera is determined as the target camera.

[0024] In some embodiments, vehicle information of the vehicle at the current moment may be obtained, and the vehicle information may include at least one of vehicle speed information, vehicle location, battery power, memory capacity, driving mode, safety status, and user recording preference settings.

[0025] If the vehicle information meets the preset recording conditions, the target camera is used to record the video. As an example, the power threshold and memory threshold corresponding to the recording requirements can be determined based on the recording quality, such as the resolution and frame rate of the video, the recording format, such as MP4, AVI, etc., the single recording duration and other information. Among them, the recording quality, recording format, and single recording duration can be determined by the user's recording preference settings, or by the vehicle's preset recording information, or by the user's selected recording configuration. If the vehicle speed reaches the preset vehicle speed threshold, the vehicle position meets the recording area setting, the battery power is greater than the preset power threshold, the memory capacity is greater than the preset memory threshold, the driving mode is in the automatic driving mode or the sports mode, the safety state is in the normal and safe driving state, and no collision occurs, it is determined that the vehicle information meets the preset recording conditions, and the target camera is used to record the video.

[0026] Step 103: merge the video image label and vehicle status label corresponding to the video material according to the timestamp to obtain a vehicle-side label file.

[0027] In some embodiments, a video screen label corresponding to each frame of the video material may be obtained. The video screen label may include an in-car screen label and an out-car screen label. The in-car screen label may include at least one of the number of passengers in the car, in-car scene features, and character expression features. The out-car screen label may include at least one of the out-car scene features, out-car sky features, out-car weather features, out-car surrounding vehicle features, out-car character features, and out-car aesthetics scores. Among them, the scene features inside the car may include chatting, karaoke, resting, etc.; the character label features may include warm, tense, relaxed, cheerful, quiet, etc.; the scene features outside the car may include: coarse scene categories, subdivided scene categories and more subdivided scene categories. The large scene categories may be cities, grasslands, seaside, etc., and the subdivided scene categories may be city shopping, grassland scenery, seaside scenery, seaside scenery, etc. The more detailed scene categories may be seaside highways, ports, beaches, dams, etc.; the sky features outside the car may include coarse sky types, subdivided sky types and special sky types. The coarse sky types may be no sky, daytime, night, blue sky, cloudy sky, etc., and the subdivided sky types may be blue sky with few clouds, cloudy blue sky, moonlit night, moonless night, sunrise, sunset, etc., and the special sky types may be the moon, rainbow, fire clouds, airplane clouds, etc.; the vehicle features around the car may include the vehicle types around the car, the vehicle positions around the car, and the number of vehicles around the car, etc.; the aesthetic score outside the car may include a score for the beauty of the video screen. The video screen label corresponding to each frame image of the video material can be obtained in real time during the process of the target camera recording the video; or, the video screen label corresponding to each frame image of the video material can be obtained after the target camera completes the recording, which is not limited in this application.

[0028] In some embodiments, the vehicle status tag of the vehicle can be obtained in real time, and the vehicle status tag includes at least one of: inertial measurement unit IMU information, throttle information, pedal information, in-vehicle temperature information, out-vehicle temperature information, and surrounding target information. Among them, IMU information can include the acceleration, angular velocity and magnetic field information of the vehicle, and the dynamic state of the vehicle, such as turning, accelerating or decelerating, can be determined through IMU information; throttle information includes throttle position information, and pedal information includes pedal position information, etc. It is very important to analyze the comfort of passengers in the vehicle and environmental factors that may affect the video viewing experience through this information; surrounding target information is the surrounding target information detected by the vehicle sensor, such as other vehicles, pedestrians, obstacles, etc. The vehicle status tag can be used to determine the driving state of the vehicle and the state of the surrounding environment.

[0029] In some embodiments, all in-car picture labels of the video material and all vehicle status labels of the video material during the recording process can be obtained, the in-car picture labels and vehicle status labels of the video material can be sequentially aligned based on timestamps, and the video picture labels and vehicle status labels corresponding to each timestamp can be fused to obtain a vehicle-side label file sorted based on timestamps.

[0030] Step 104: Edit the video material at least based on the vehicle-side tag file to generate a target video.

[0031] In some embodiments, after the video recording is completed, the recorded video can be desensitized to automatically identify and blur sensitive information such as license plate numbers, facial features, etc. in the video to protect user privacy.

[0032] In some embodiments, after desensitizing the video, the video material may be encoded and converted into a video material in a standard video format, such as MP4 format. The format-processed video material may be edited based on at least the vehicle-side tag file to generate a target video.

[0033] In some embodiments, the method of performing video editing on the video material based on at least the vehicle-side tag file to generate the target video may be:

[0034] The vehicle tracking information and user portrait information of the vehicle can be obtained. The vehicle tracking information is used to indicate the vehicle monitoring data at the preset monitoring points of the vehicle, and the user portrait information is used to indicate the basic information and behavioral preferences of the user. As an example, the vehicle monitoring data may include vehicle attribute information, such as color, model, etc., and vehicle behavior information, such as driver behavior during driving; the user's basic information may include the user's age, gender, occupation, geographic location, etc., and the behavioral preferences may include the user's commonly used template information for recording, etc.

[0035] The editing template can be determined based on the vehicle-side label file, vehicle tracking information, and user portrait information. As an example, the picture features of the video content corresponding to the video material can be determined through the vehicle-side label file, and the user's personalized features, such as the template type that the user likes, can be further determined through the user portrait information. Based on the picture features and personalized features, the editing template that is closest to the picture features and personalized features can be selected from the existing video template database based on the machine learning model or deep learning model.

[0036] The video material can be edited according to the editing template to generate a target video. As an example, the video material can be screened for segments, special effects and special scenes can be added, background music can be synthesized, etc. can be generated based on the editing template to generate the final target video.

[0037] In some embodiments, the method of performing video editing on the video material based on at least the vehicle-side tag file to generate the target video may also be:

[0038] The video frames corresponding to the preset scene information in the video material can be obtained according to the scene information corresponding to each timestamp in the vehicle-side tag file. As an example, the scene information may include road type, weather conditions, traffic conditions, etc., and the video frames with preset scene features can be automatically determined based on the scene information of each timestamp, such as all video frames of driving in rainy days can be obtained. The preset scene information can be determined based on the selection result for the scene information, or the scene information in the video with high popularity can be determined as the preset scene information in advance.

[0039] For a first video frame and a second video frame that are adjacent in playback order in a video frame, an element in the first video frame is identified, cross-frame information retention processing is performed on the element in the second video frame, and cross-frame information supplement processing is performed on the motion trajectory of the element in the second video frame to obtain a processed second video frame. The elements include objects, actions of objects, and scenes in which the actions are located, and the playback order of the first video frame is before the playback order of the second video frame. As an example, after obtaining the video frame, based on every two adjacent video frames, after identifying the elements of the first video frame, cross-frame information retention processing is performed on the same element in the second video frame, and cross-frame information supplement processing is performed on the motion trajectory of the element, so that the position, size, shape, and motion trajectory of the element in the second video frame remain consistent and continuous with those of the element in the first video frame.

[0040] The processed video frames are combined based on the playback order to obtain the target video.

[0041] In some embodiments, after obtaining the target video, the preview image and video description information of the target video can be determined; the sharing image corresponding to the target video is determined based on the preview image and the video description information, and the sharing image is used to instruct the vehicle end to perform at least one of the following operations: preview, download, and share the target video. Among them, at least one key frame in the target video can be extracted, and the key frame is used to indicate the main content of the video, and a preview image of the target video is generated based on one of the key frames, or based on the user's selection of the key frame; the video description information can be determined based on the picture features in each key frame of the target video, or based on the user's editing content of the description information of the target video.

[0042] In some embodiments, a sharing picture corresponding to the target video can be determined based on the preview picture and the video description information, and the sharing picture is used to instruct the vehicle end to perform at least one of previewing, downloading and sharing the target video.

[0043] In some embodiments, the user's rating of the target video can also be obtained, and the parameters of the high-score recognition algorithm can be updated based on the rating. The highlight recognition algorithm obtains at least one of the scene dimension score, composition dimension score, color dimension score, and aesthetic dimension score of the candidate video frame based on the updated parameters, and obtains a comprehensive score based on the weighted sum of various scores.

[0044] In this embodiment, by continuously identifying the highlight moment images from the video frames taken by the cameras at different angles inside and outside the vehicle at a preset period, and determining the target camera for recording the video material based on the camera corresponding to the highlight moment, it is possible to efficiently obtain high-quality video materials; by judging whether to start recording the video based on the target camera through vehicle information and preset recording conditions, it is ensured that the video material is obtained at the right time and the success rate of obtaining the video material is guaranteed; by fusing the video image label and the vehicle status label based on the timestamp, generating a vehicle-side label file, and determining the target video at least based on the vehicle-side label file, it is possible to improve the generation quality of the target video; when determining the target video, the corresponding editing template is determined based on the vehicle-side label file, the vehicle buried point information and the user portrait information, so that the content of the target video can be personalized and more in line with the user's expectations; when determining the target video, by performing cross-frame information processing and cross-frame supplementary processing on adjacent video frames, it is determined that the elements in the target video maintain consistency and continuity between consecutive frames, thereby improving the viewing experience of the target video. Finally, this embodiment can also update the parameters of the high-score recognition algorithm based on the user's rating of the target video, further improve the recognition accuracy of the highlight moment images, and ensure the generation quality of the target video.

[0045] The vehicle-mounted video production method of the present application can realize the automatic creation of the entire process of video shooting, video editing, video generation, and video sharing during the operation of the vehicle, can efficiently generate high-quality target videos, reduce manual intervention, and improve the efficiency of video processing.

[0046] Figure 2 It is a structural diagram of a vehicle-mounted video editing system according to an embodiment of the present application.

[0047] The in-vehicle video editing system may include the vehicle-side intelligent driving domain controller, cockpit domain controller and intelligent antenna module, central computing platform, third-party network platform and terminal equipment. The vehicle-side may be a vehicle terminal, and the terminal equipment may be electronic devices such as smart phones, smart tablets, laptops, and smart wearable devices.

[0048] The intelligent driving domain controller is deployed with an outside-vehicle video fusion perception model, which can obtain video frames taken by different cameras outside the vehicle. Every preset period, such as 1 second, at least one candidate video frame is randomly extracted from the video frames taken by each camera. Through the high-score recognition algorithm, the comprehensive score of the candidate video frame is determined according to at least one of the scene dimension, composition dimension, color dimension and aesthetic dimension of the candidate video frame. If the comprehensive score is greater than or equal to the preset threshold, the candidate video frame is determined as a highlight moment picture. Among them, the camera may include a panoramic video head and a surround-view camera.

[0049] The cockpit domain controller is deployed with an in-vehicle environment perception model, which can obtain video frames taken by different cameras in the car. Every preset period, such as 1 second, at least one candidate video frame is randomly extracted from the video frames taken by each camera. Through the high-score recognition algorithm, the comprehensive score of the candidate video frame is determined according to at least one of the scene dimension, composition dimension, color dimension and aesthetic dimension of the candidate video frame. If the comprehensive score is greater than or equal to the preset threshold, the candidate video frame is determined as a highlight moment picture. Among them, the camera may include a panoramic video head and a surround camera.

[0050] The central computing platform includes a highlight arbitration management module. After obtaining the highlight moment picture, the intelligent driving domain controller or the cockpit domain controller determines the camera corresponding to the highlight moment picture. If at least one candidate video frame extracted from the video frame taken by the camera is all a highlight moment picture, a notification is sent to the highlight arbitration management module of the central computing platform. The highlight arbitration management module obtains vehicle information, which includes at least one of vehicle speed information, vehicle location, battery power, memory capacity, driving mode and safety status. If the vehicle information meets the preset recording conditions, the target camera is used to record the video.

[0051] During the target camera recording process, the high-light arbitration management module obtains the vehicle status tag of the vehicle in real time, and the vehicle status tag includes: at least one of inertial measurement unit IMU information, throttle information, pedal information, in-vehicle temperature information, out-vehicle temperature information and surrounding target object information.

[0052] The central computing platform also includes an image AI detection module, which is used to obtain the video picture label corresponding to each frame of the video material during the target video recording process. The video picture label may include an in-car picture label and an out-car picture label. The in-car picture label may include: at least one of the number of passengers in the car, in-car scene features, and character expression features; the out-car picture label may include: at least one of the out-car scene features, out-car sky features, out-car weather features, out-car surrounding vehicle features, out-car character features, and out-car aesthetics scores.

[0053] The intelligent driving domain controller and the cockpit domain controller are respectively deployed with video processing modules, which are used to desensitize the video materials recorded by the target camera, and further encode them to convert them into video materials in standard video formats, such as MP4 format.

[0054] The central computing platform also includes a vehicle-side label fusion module and an editing module, which are used to sequentially align the in-vehicle image labels and vehicle status labels of the video material based on the timestamp, and fuse the video image labels and vehicle status labels corresponding to each timestamp to obtain a vehicle-side label file sorted based on the timestamp. The vehicle-side label file obtained after fusion is compressed and packaged and uploaded to the editing module of the central computing platform.

[0055] The editing module performs video editing on the video material at least according to the vehicle-side tag file to generate a target video. Among them, the vehicle tracking information and user portrait information of the vehicle can be obtained, the vehicle tracking information is used to indicate the vehicle monitoring data at the preset monitoring point of the vehicle, and the user portrait information is used to indicate the basic information and behavior preferences of the user; according to the vehicle-side tag file, the vehicle tracking information and the user portrait information, the editing template is determined; the video material is video-cut according to the editing template to generate the target video; it is also possible to obtain the video frame corresponding to the preset scene information in the video material according to the scene information corresponding to each timestamp in the vehicle-side tag file; for the first video frame and the second video frame adjacent in the playback order in the video frame, the element in the first video frame is identified, the cross-frame information retention processing is performed on the element in the second video frame, and the cross-frame information supplement processing is performed on the movement trajectory of the element in the second video frame to obtain the processed second video frame; the processed video frames are combined based on the playback order to obtain the target video; wherein, the element includes the object, the action of the object and the scene where the object is located, and the playback order of the first video frame is before the playback order of the second video frame. User portrait information and vehicle tracking data can be obtained through the vehicle-side smart antenna module. The vehicle-side smart antenna module obtains the user's basic information and behavioral preferences, as well as vehicle monitoring data during driving, through a third-party network platform.

[0056] The central computing platform also includes an album module. After obtaining the target video, the target video can be saved to the album module corresponding to the user, and the preview image and video description information of the target video can be determined; the sharing image corresponding to the target video is determined according to the preview image and the video description information, and the sharing image is used to instruct the vehicle end to perform at least one of preview, download and share the target video.

[0057] The central computing platform can also obtain the user's rating of the target video based on the terminal device, and update the parameters of the high-score recognition algorithm based on the rating. The highlight recognition algorithm re-obtains at least one of the scene dimension score, composition dimension score, color dimension score and aesthetic dimension score of the candidate video frame based on the updated parameters, and obtains a comprehensive score based on the weighted sum of various scores.

[0058] In the embodiment of the present application, through the in-vehicle video production system, it is possible to automatically capture and shoot the highlight moment images, and automatically edit based on the shot video materials, thereby improving the creation efficiency and quality of the in-vehicle video content.

[0059] It should be noted that the in-vehicle video production system of this embodiment is used to implement the corresponding in-vehicle video production method in the aforementioned method embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0060] Car video production device

[0061] Corresponding to the above-mentioned vehicle-mounted video production method embodiment, Figure 3 A schematic diagram of a vehicle-mounted video production device according to an embodiment of the present application is shown. Figure 3 As shown, the vehicle-mounted video production device 300 includes:

[0062] The recognition module 301 is used to recognize highlight moment images from video frames captured by cameras at different viewing angles inside and outside the vehicle according to a preset period.

[0063] A recording module 302, configured to determine a target camera according to the camera where the highlight moment image is located, and use the target camera to record a video to obtain a video material;

[0064] A fusion module 303 is used to fuse the video image label and the vehicle status label corresponding to the video material according to the timestamp to obtain a vehicle-side label file;

[0065] The editing module 304 is used to perform video editing on the video material based on at least the vehicle-side tag file to generate a target video.

[0066] It should be noted that the in-vehicle video production device of this embodiment is used to implement the corresponding in-vehicle video production method in the aforementioned method embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0067] Electronic devices

[0068] Figure 4 A schematic diagram of the structure of an electronic device according to an embodiment of the present application is shown. The specific embodiment of the present application does not limit the specific implementation of the electronic device.

[0069] like Figure 4 As shown, the electronic device may include: a processor (processor) 402 , a communication interface (Communications Interface) 404 , a memory (memory) 406 , and a communication bus 408 .

[0070] in:

[0071] The processor 402 , the communication interface 404 , and the memory 406 communicate with each other via a communication bus 408 .

[0072] The communication interface 404 is used to communicate with other electronic devices or servers.

[0073] The processor 402 is used to execute the program 410, and specifically can execute the relevant steps in the above-mentioned embodiment of the vehicle-mounted video production method.

[0074] Specifically, the program 410 may include program codes, which include computer operation instructions.

[0075] The processor 402 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0076] The memory 406 is used to store the program 410. The memory 406 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0077] The program 410 may be specifically configured to enable the processor 402 to perform the following operations:

[0078] In an optional implementation, the program 410 is also used to enable the processor 402 to implement each step in the program 410. The specific implementation can refer to the corresponding steps and corresponding descriptions of the device in the above-mentioned vehicle video production method embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described device and module can refer to the corresponding process description in the above-mentioned method embodiment, which will not be repeated here.

[0079] An embodiment of the present application also provides a computer program product, including computer instructions, which instruct a computing device to perform operations corresponding to any of the in-vehicle video production methods in the above-mentioned multiple method embodiments.

[0080] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.

[0081] The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk or magneto-optical disk), or implemented as a computer code originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded through a network and to be stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor or programmable or dedicated hardware (such as an ASIC or FPGA). It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the vehicle-mounted video production method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the vehicle-mounted video production method shown herein, the execution of the code converts the general-purpose computer into a dedicated computer for executing the vehicle-mounted video production method shown herein.

[0082] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. 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 the embodiments of the present application.

[0083] The above implementation methods are only used to illustrate the embodiments of the present application, and are not limitations on the embodiments of the present application. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present application. The scope of patent protection of the embodiments of the present application should be limited by the claims.

Claims

1. A method for producing an in-vehicle video, characterized in that: The method comprises: Identify highlight moments from video frames captured by cameras at different viewing angles inside and outside the vehicle at a preset period; Determine a target camera according to the camera where the highlight moment image is located, and use the target camera to record a video to obtain a video material; The video image label and the vehicle status label corresponding to the video material are merged according to the timestamp to obtain a vehicle-side label file; The video material is edited at least based on the vehicle-side tag file to generate a target video.

2. The method according to claim 1, characterized in that The step of identifying highlight moment images from video frames captured by cameras with different viewing angles inside and outside the vehicle according to a preset period includes: At every preset period, randomly extract at least one candidate video frame from the video frames captured by each camera; Determine a comprehensive score of the candidate video frame according to at least one of the scene dimension, the composition dimension, the color dimension, and the aesthetic dimension of the candidate video frame; If the comprehensive score is greater than or equal to a preset threshold, the candidate video frame is determined as the highlight moment picture.

3. The method according to claim 1, characterized in that Before recording a video with the target camera to obtain video material, the method includes: Acquiring vehicle information of the vehicle at the current moment, the vehicle information including at least one of vehicle speed information, vehicle position, battery power, memory capacity, driving mode, and safety status; If the vehicle information meets the preset recording conditions, the target camera is used to record the video.

4. The method according to claim 1, characterized in that The video image label and the vehicle status label corresponding to the video material are merged according to the timestamp to obtain a vehicle-side label file, including: For each frame of the video material, obtain an in-vehicle image label and an out-vehicle image label of the image, wherein the in-vehicle image label includes at least one of the number of passengers in the vehicle, in-vehicle scene features, and character expression features, and the out-vehicle image label includes at least one of the out-vehicle scene features, out-vehicle sky features, out-vehicle weather features, out-vehicle surrounding vehicle features, out-vehicle character features, and out-vehicle aesthetic score; Acquire a vehicle status tag of the vehicle in real time, wherein the vehicle status tag includes at least one of: inertial measurement unit IMU information, throttle information, pedal information, in-vehicle temperature information, out-vehicle temperature information, and surrounding target object information; The in-car image label and the vehicle status label are sequentially aligned based on the timestamp, and the video image label and the vehicle status label corresponding to each timestamp are fused to obtain a vehicle-side label file arranged based on the timestamp.

5. The method according to claim 1, characterized in that: The step of performing video editing on the video material at least based on the vehicle-side tag file to generate a target video includes: Obtaining vehicle tracking information and user portrait information of the vehicle, wherein the vehicle tracking information is used to indicate vehicle monitoring data at a preset monitoring point of the vehicle, and the user portrait information is used to indicate basic information and behavior preferences of the user; Determine a clipping template according to the vehicle-side label file, the vehicle tracking information and the user portrait information; The video material is edited according to the editing template to generate the target video.

6. The method according to claim 1, characterized in that The step of performing video editing on the video material at least based on the vehicle-side tag file to generate a target video includes: According to the scene information corresponding to each timestamp in the vehicle-side tag file, a video frame corresponding to the preset scene information in the video material is obtained; For a first video frame and a second video frame that are adjacent in playback order in the video frames, identifying an element in the first video frame, performing cross-frame information retention processing on the element in the second video frame, and performing cross-frame information supplement processing on a motion trajectory of the element in the second video frame to obtain a processed second video frame; Combining the processed video frames based on the playback order to obtain the target video; The elements include an object, an action of the object and a scene in which the object is located, and the playback order of the first video frame is before the playback order of the second video frame.

7. The method according to claim 1, characterized in that The method further comprises: Determine a preview image and video description information of the target video; A sharing picture corresponding to the target video is determined according to the preview picture and the video description information, and the sharing picture is used to instruct the vehicle end to perform at least one of previewing, downloading and sharing the target video.

8. A vehicle-mounted video production device, characterized in that: include: A recognition module, used to recognize highlight moment images from video frames captured by cameras at different viewing angles inside and outside the vehicle according to a preset period; A recording module, used to determine a target camera according to the camera where the highlight moment picture is located, and use the target camera to record a video to obtain a video material; A fusion module, used to fuse the video picture label and the vehicle status label corresponding to the video material according to the timestamp to obtain a vehicle-side label file; The editing module is used to edit the video material based on at least the vehicle-side tag file to generate a target video.

9. An electronic device, comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the in-vehicle video production method according to any one of claims 1-7.

10. A computer storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the vehicle-mounted video production method according to any one of claims 1 to 7 is implemented.

Images