Video generation method and device, vehicle and product
Through the vehicle intelligent driving system, the driving control event is automatically controlled and the driving recording video and the on-board screen video are integrated to generate driving videos that match the driving control event, which solves the safety and efficiency problems of drivers shooting and editing videos in intelligent driving scenarios. It realizes efficient video generation and informative driving video content.
Patent Information
- Application Number
- CN202411132160.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-11-22
AI Technical Summary
In the intelligent driving scenario of vehicles, the prior art requires drivers to pay attention to the shooting equipment during driving, which poses driving safety risks, and video editing work is cumbersome, affecting the efficiency of video generation.
Use the vehicle intelligent driving system to automatically control driving control events and record the time of the event. Combining driving recording videos and on-board screen videos, intercepting video clips based on the time of the event occurrence to generate driving videos that match the driving control events, realizing automatic driving videos generate.
It reduces the driver's need to shoot and edit videos on his own during the vehicle's driving process, improves the video generation efficiency, and the generated driving video content has high information value, and can fully understand the driving environment and driving conditions during the vehicle's autonomous driving process.
Smart Images

Figure CN119011970A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of video processing technology, and in particular to a video generation method, device, vehicle and product. Background Art
[0002] As vehicles develop towards intelligence and automation, the vehicle's intelligent driving system can support full or partial hands-free autonomous driving, improving the user's driving experience.
[0003] When the vehicle is driving, if you want to shoot videos for intelligent driving scenes, you usually need to fix the camera equipment in the car for shooting. If you need to edit the video, you need to edit the video later after shooting. This will cause the driver to pay attention to the shooting of the camera while driving, which poses certain driving safety risks and also brings about tedious editing work in the later stage, affecting the efficiency of video production. Summary of the invention
[0004] The embodiments of the present disclosure at least provide a video generation method, device, vehicle and product.
[0005] The present disclosure provides a video generation method, the method comprising:
[0006] Acquire driving control events executed by the intelligent driving system during vehicle driving, as well as recorded driving video and on-board screen video; the driving video displays the road environment outside the vehicle; the on-board screen video displays the driving trajectory of the vehicle in the three-dimensional rendering scene;
[0007] According to the event occurrence time indicated by the driving control event, respectively intercepting video clips matching the driving control event from the driving record video and the vehicle screen video;
[0008] The video clips are fused to generate a driving video matching the driving control event.
[0009] In the disclosed embodiment, the intelligent driving system provided by the vehicle itself is effectively utilized. The intelligent driving system can automatically control the vehicle to execute driving control events and record the time of the event, and the vehicle can output driving record videos and on-board screen videos. For intelligent driving scenarios, video clips matching the driving control events are respectively intercepted from the driving record videos and on-board screen videos according to the time of the event, and the video clips are merged to generate driving videos matching the driving control events, thereby realizing the automatic generation of driving videos. There is no need for users to shoot videos by themselves during the driving of the vehicle and edit the videos later, which reduces the driving safety risks of users and helps to improve the efficiency of video generation. In addition, the generated driving video corresponds to the driving control event, and its content has a high information value. Moreover, the driving video contains both video content reflecting the road environment outside the vehicle and video content reflecting the driving trajectory, which can enable video viewers to fully understand the driving environment and vehicle driving conditions during the vehicle's automatic driving process, and meet the need to understand the vehicle driving process.
[0010] In an optional implementation, the extracting video clips matching the driving control event from the driving record video and the vehicle screen video respectively according to the event occurrence time indicated by the driving control event includes:
[0011] Determine the redundant duration of video capture based on the road condition information recorded by the intelligent driving system when the driving control event occurs;
[0012] Determine the start time and end time of video capture according to the start time and end time of the event indicated by the driving control event and the redundant time;
[0013] The video clips are respectively captured from the driving record video and the vehicle screen video according to the start time and the end time of the video capture.
[0014] In the disclosed embodiments, the redundant time length of the video capture can be determined in combination with the actual road conditions when the driving control event occurs. For example, if the road conditions are relatively stable, the redundant time length can be relatively short, but it is sufficient to obtain a video clip that records the complete driving control event. For example, if the road conditions are relatively complex, the redundant time length can be relatively long, thereby enriching the content of the driving video. The start time and end time of the video capture can be determined based on the redundant time length in combination with the start time and end time of the event, so as to capture the video clip, which helps to ensure the compatibility of the video clip with the driving control event.
[0015] In an optional implementation manner, fusing the video clips to generate a driving video matching the driving control event includes:
[0016] Merging the video clips captured from the driving recording video and the vehicle screen video to obtain a fused video picture;
[0017] Generate video description information based on the event information of the driving control event;
[0018] The driving video is generated based on the video description information and the fused video picture.
[0019] In the disclosed embodiment, video description information may be generated based on event information of a driving control event. Adding the video description information during the process of generating a driving video helps to improve the richness of the driving video content.
[0020] In an optional implementation, each frame of the fused video includes a driving record video frame and a vehicle screen video frame corresponding to the same time point.
[0021] In the disclosed embodiment, by ensuring that each frame of the fused video includes a driving record video frame and a vehicle screen video frame corresponding to the same time point, it is possible to meet the need for synchronously observing the road environment outside the vehicle and the vehicle driving conditions at the same time, thereby realizing an understanding of the real-time driving conditions of the vehicle in a real-time environment.
[0022] In an optional implementation manner, the generating of video description information based on the event information of the driving control event includes:
[0023] Acquire real-time vehicle status information and driving environment information during the period when the driving control event occurs, which is recorded by the intelligent driving system;
[0024] The video description information is generated based on the event information of the driving control event, the real-time vehicle state information and the driving environment information.
[0025] In the disclosed embodiment, the event information of the driving control event, the real-time vehicle status information and the driving environment information during the driving control event are integrated to generate video description information, so that the generated driving video has a video description that matches the video screen, further improving the video generation quality and video viewing experience. The video description information here can also be played in the form of voice to meet the audio-visual experience.
[0026] In an optional implementation, generating the driving video based on the video description information and the fused video picture includes:
[0027] Determining background music for the driving video according to the event type of the driving control event;
[0028] The driving video is generated based on the video description information, the fused video picture, and the background music.
[0029] In the disclosed embodiment, background music may also be added to the driving video to enhance the audio-visual experience of the driving video.
[0030] In an optional implementation manner, after generating the driving video matching the driving control event, the method further includes:
[0031] Performing video desensitization processing on the driving video to obtain a video to be released;
[0032] The video open platform is called to publish the video to be published.
[0033] In the disclosed embodiment, the driving video is desensitized to ensure the legality of the content of the video to be released.
[0034] In an optional implementation manner, the method further includes:
[0035] After generating a plurality of driving videos of driving control events, determining an adjacency relationship between the plurality of driving videos according to driving trajectories corresponding to the plurality of driving control events;
[0036] The driving videos of the plurality of driving control events are synthesized according to the adjacency relationship to obtain a synthesized driving video.
[0037] In the disclosed embodiment, multiple driving videos can be synthesized based on the driving trajectory, and based on the adjacency relationship between the multiple driving videos, the driving videos of driving control events corresponding to similar road positions can be connected to avoid abrupt connections in the synthesized driving video.
[0038] In an optional implementation manner, synthesizing the driving videos of the plurality of driving control events according to the adjacency relationship to obtain a synthesized driving video includes:
[0039] generating a transition video between adjacent driving videos according to the adjacent driving videos indicated by the adjacency relationship;
[0040] The driving videos of the multiple driving control events and the transition video are synthesized according to the adjacency relationship to obtain a synthesized driving video.
[0041] In the disclosed embodiment, a transition video is added between adjacent driving videos, thereby helping to improve the smoothness of the connection between video images in the synthesized driving video.
[0042] An embodiment of the present disclosure also provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions are executed by the processor to perform steps in any possible implementation of the above-mentioned video generation method.
[0043] The present disclosure also provides a vehicle, including a controller, wherein the controller includes:
[0044] a memory for storing machine-readable instructions; and
[0045] The processor is used to call and execute the machine-readable instructions stored in the memory to implement the steps in any possible implementation of the above-mentioned video generation method.
[0046] The embodiments of the present disclosure further provide a computer program product, on which a computer program is stored. When the computer program is executed by a processor, the steps in any possible implementation of the above-mentioned video generation method are executed.
[0047] For a description of the effects of the above-mentioned electronic device, vehicle and computer program product, please refer to the description of the above-mentioned external vehicle voice recognition method, which will not be repeated here.
[0048] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present disclosure.
[0049] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.
[0051] Figure 1 A flow chart of a video generation method provided by an embodiment of the present disclosure is shown;
[0052] Figure 2a One of the schematic diagrams of a fused video screen provided by an embodiment of the present disclosure is shown;
[0053] Figure 2b A second schematic diagram of a fused video screen provided by an embodiment of the present disclosure is shown;
[0054] Figure 3 A schematic diagram of a video generation process provided by an embodiment of the present disclosure is shown;
[0055] Figure 4 A flow chart of video generation and publishing provided by an embodiment of the present disclosure is shown;
[0056] Figure 5 A schematic diagram of a process of video generation and publishing provided by an embodiment of the present disclosure is shown;
[0057] Figure 6 One of the schematic diagrams of a video generating device provided by an embodiment of the present disclosure is shown;
[0058] Figure 7 A second schematic diagram of a video generating device provided by an embodiment of the present disclosure is shown;
[0059] Figure 8 A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION
[0060] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.
[0061] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.
[0062] The term "and / or" herein only describes an association relationship, indicating that three relationships may exist. For example, A and / or B may represent the following three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set consisting of A, B, and C.
[0063] According to research, if you want to shoot videos for smart driving scenes while the vehicle is driving, you first need to prepare shooting equipment, such as mobile phones and cameras. Most of the time, the camera equipment needs to be fixed in the car for shooting, which will cause the driver to pay attention to the shooting of the camera equipment while driving, which poses certain driving safety risks. If there is a need for editing, the video needs to be edited later after the shooting is completed, which will bring about tedious editing work in the later stage and affect the efficiency of video generation.
[0064] Based on the above research, the present disclosure provides a video generation method, which effectively utilizes the intelligent driving system set up in the vehicle itself, and can automatically control the vehicle to execute driving control events and record the time of event occurrence through the intelligent driving system, and the vehicle can output driving recording videos and on-board screen videos. For intelligent driving scenarios, it can realize the automatic generation of driving videos, without the need for users to shoot videos by themselves during vehicle driving and edit them later, reducing the user's driving safety risks and helping to improve video generation efficiency. In addition, the generated driving video corresponds to the driving control event, and its content has a high information value. In addition, the driving video contains both video content reflecting the road environment outside the vehicle and video content reflecting the driving trajectory, which can enable video viewers to fully understand the driving environment and vehicle driving conditions during the vehicle's automatic driving process, meeting the need to understand the vehicle driving process.
[0065] To facilitate understanding of this embodiment, a video generation method disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the video generation method provided in the embodiment of the present disclosure is generally an electronic device with certain computing capabilities. In this embodiment, the electronic device can be a server. Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data and artificial intelligence platforms.
[0066] In other implementations, the electronic device may also be a terminal device or other processing device, and the terminal device may be a user equipment (UE), a mobile device, a terminal, a computing device, a vehicle-mounted device, etc. Other processing devices may be devices including a processor and a memory, which are not limited here. In some possible implementations, the video generation method may be implemented by a processor calling a computer-readable instruction stored in a memory.
[0067] A video generation method provided by an embodiment of the present disclosure is described below in conjunction with the accompanying drawings.
[0068] See also Figure 1 As shown, it is a flow chart of a video generation method provided by an embodiment of the present disclosure, such as Figure 1 As shown in , the video generation method provided by the embodiment of the present disclosure includes steps S101 to S103, wherein:
[0069] S101: Acquire driving control events executed by the intelligent driving system during vehicle driving, as well as recorded driving video and vehicle screen video; the driving video displays the road environment outside the vehicle; the vehicle screen video displays the driving trajectory of the vehicle in a three-dimensional rendering scene.
[0070] Here, the intelligent driving system can automatically judge the road conditions and automatically execute corresponding driving control events during the vehicle's driving process.
[0071] The driving control events here can be various control events when the intelligent driving system controls the vehicle's driving, such as merging events, avoiding events, overtaking events, turning events, braking events, etc.
[0072] The driving record video may be a picture taken by a vehicle camera showing the road environment outside the vehicle, and the vehicle camera may be a driving recorder. The vehicle screen video may be a driving track of the vehicle in a three-dimensional rendering scene output by the vehicle screen.
[0073] It can be understood that the driving record video records the real driving scene outside the vehicle, which is used to reflect the driving environment around the vehicle, including road conditions and other environmental information; the on-board screen video records the three-dimensional rendering scene rendered by the driving environment data collected by the sensor, which can show the process of the vehicle model driving in the three-dimensional rendering scene. In addition, it can also display vehicle driving data such as instrument information.
[0074] In this way, by adopting multi-faceted videos to record intelligent driving scenarios, it helps to improve the richness and comprehensiveness of driving videos.
[0075] S102: According to the event occurrence time indicated by the driving control event, video clips matching the driving control event are respectively captured from the driving record video and the vehicle screen video.
[0076] In this step, the intelligent driving system can issue driving control instructions, such as overtaking instructions, when executing driving control events. The intelligent driving system can also synchronously record the driving control instructions it issues, the time when the driving control instructions are issued, and the time when the driving control event is completed.
[0077] Among them, the event occurrence time includes the start time and end time of the event. It can be understood that the time when the intelligent driving system issues the driving control instruction is the start time of the event, and the time when the driving control event is executed is the end time of the event.
[0078] In some possible implementations, according to the time of occurrence of the event, video clips corresponding to the time of occurrence of the event may be respectively captured from the driving record video and the vehicle screen video as video clips matching the driving control event.
[0079] In some possible implementations, the extracting video clips matching the driving control event from the driving record video and the vehicle screen video respectively according to the event occurrence time indicated by the driving control event includes:
[0080] Determine the redundant duration of video capture based on the road condition information recorded by the intelligent driving system when the driving control event occurs;
[0081] Determine the start time and end time of video capture according to the start time and end time of the event indicated by the driving control event and the redundant time;
[0082] The video clips are respectively captured from the driving record video and the vehicle screen video according to the start time and the end time of the video capture.
[0083] In the above steps, the redundant time of the video capture can be determined in combination with the actual road conditions when the driving control event occurs. For example, if the road conditions are relatively stable, the redundant time can be shorter, but it is sufficient to obtain a video clip that records the complete driving control event. For example, if the road conditions are more complicated and the driving difficulty is greater, the redundant time can be longer, so that the content of the driving video can be richer to attract more attention after the video is released later.
[0084] Then, based on the start time and end time of the event, the start time and end time of the video capture can be determined in combination with the redundant duration, and then according to the start time and end time of the video capture, the video clips between the start time and end time of the video capture can be respectively captured from the driving record video and the vehicle screen video.
[0085] In this way, the redundant time of video capture is determined based on the actual road conditions when the traffic control event occurs. The start time and end time of the video capture are determined based on the redundant time and the start time and end time of the event. This helps to capture video clips, which helps ensure the compatibility of video clips with traffic control events.
[0086] S103: Fusing the video clips to generate a driving video matching the driving control event.
[0087] In this step, the driving video matching the driving control event is generated by fusing the video clip captured from the driving record video and the video clip captured from the vehicle screen video.
[0088] In some possible implementations, fusing the video clips to generate a driving video matching the driving control event includes:
[0089] Merging the video clips captured from the driving recording video and the vehicle screen video to obtain a fused video picture;
[0090] Generate video description information based on the event information of the driving control event;
[0091] The driving video is generated based on the video description information and the fused video picture.
[0092] In the above steps, after the two video clips are fused, video description information is added to generate the driving video.
[0093] The event information is used to describe the specific execution actions of the vehicle during the occurrence of the driving control event.
[0094] In this way, video description information can be generated based on the event information of the driving control event. Adding the video description information in the process of generating the driving video helps to improve the richness of the driving video content.
[0095] Specifically, each frame of the fused video includes a frame of a driving record video frame and a frame of a vehicle screen video frame corresponding to the same time point.
[0096] In this way, by ensuring that each frame of the fused video includes the driving record video frame and the vehicle screen video frame corresponding to the same time point, the video viewers can synchronously observe the road environment outside the vehicle and the vehicle driving conditions at the same time, and realize the real-time driving conditions of the vehicle in a real-time environment.
[0097] Specifically, when the fused video screen is obtained, considering that the driving video will be published on a video open platform later, the layout of the fused video screen may be determined according to the display method of the video open platform.
[0098] For example, please refer to Figure 2a and Figure 2b , Figure 2a This is one of the schematic diagrams of a fused video screen provided by an embodiment of the present disclosure. Figure 2b This is a second schematic diagram of a fused video screen provided by an embodiment of the present disclosure. If the display mode of the video open platform is longer vertically and shorter horizontally, then in the fused video screen, the screen of the driving record video and the screen of the vehicle screen video corresponding to the same time point can be distributed up and down, such as Figure 2a As shown in , in the fused video screen 200 , the screen 201 of the driving record video is located at the top, and the screen 202 of the vehicle screen video is located at the bottom.
[0099] If the display mode of the video open platform is longer horizontally and shorter vertically, then in the fused video screen, the screen of the driving record video and the screen of the vehicle screen video corresponding to the same time point can be distributed left and right, such as Figure 2b As shown in , in the fused video screen 200 , the screen 201 of the driving record video is located on the left, and the screen 202 of the vehicle screen video is located on the right.
[0100] When generating video description information based on the event information of the driving control event, in some possible implementations, real-time vehicle status information and driving environment information during the occurrence of the driving control event recorded by the intelligent driving system can be obtained; and the video description information is generated based on the event information of the driving control event, the real-time vehicle status information and the driving environment information.
[0101] In the above steps, when generating the video description information, the vehicle's own status information and surrounding environment information may be added on the basis of the event information, so as to obtain richer and more comprehensive video description information.
[0102] Among them, the real-time vehicle status information includes but is not limited to the vehicle's position, steering angle, speed, acceleration, etc., and the driving environment information includes but is not limited to the road conditions and weather around the vehicle, etc.
[0103] In this way, the event information of the driving control event, as well as the real-time vehicle status information and driving environment information during the driving control event, is integrated to generate video description information, which helps to improve the richness of the video description information. In this way, the generated driving video has a video description that matches the video screen, further improving the video generation quality and video viewing experience. The video description information here can also be presented in the form of video subtitles, or can also be played in the form of voice to meet the audio-visual experience.
[0104] In some possible implementations, generating the driving video based on the video description information and the fused video picture includes:
[0105] Determining background music for the driving video according to the event type of the driving control event;
[0106] The driving video is generated based on the video description information, the fused video picture, and the background music.
[0107] In this way, by adding background music to the driving video, the audio-visual experience of the driving video is improved.
[0108] To clearly demonstrate the process of video generation, please refer to Figure 3 , Figure 3 A schematic diagram of a video generation process provided by an embodiment of the present disclosure. Figure 3 As shown in , during the driving process of the vehicle, the on-board camera can capture the real driving environment outside the vehicle, and the on-board screen can display a three-dimensional rendering scene. The intelligent driving system uploads the recorded driving record video to the cloud (video storage space), and the intelligent cockpit system also uploads the recorded vehicle screen video to the cloud (video storage space). Here, the video storage space can specifically be a content delivery network (Content Delivery Network, CDN). CDN can avoid bottlenecks and links on the Internet that may affect the data transmission speed and stability as much as possible, making content transmission faster and more stable.
[0109] The intelligent driving system generates a driving control event and sends it to the video fusion system, wherein the video fusion system can be set on the vehicle side, the cloud, or other local devices, and there is no specific limitation here.
[0110] The video fusion system generates an event occurrence time indicated by the driving control event based on the driving control event, respectively captures video clips matching the driving control event from the driving record video and the vehicle screen video, fuses the video clips, and generates a driving video matching the driving control event. The description of the specific steps refers to the aforementioned embodiments, which will not be repeated here.
[0111] The video generation method provided by the embodiment of the present disclosure effectively utilizes the intelligent driving system set up in the vehicle itself, and the ability of the intelligent driving system to automatically control the vehicle to execute driving control events and record the time of event occurrence, as well as the ability of the vehicle to output driving record videos and vehicle-mounted screen videos. For intelligent driving scenarios, video clips matching the driving control events are respectively intercepted from the driving record videos and vehicle-mounted screen videos according to the time of event occurrence, and the video clips are merged to generate driving videos matching the driving control events, thereby realizing the automatic generation of driving videos, without the need for users to shoot videos by themselves during vehicle driving and later edit the videos, reducing the user's driving safety risks and helping to improve video generation efficiency. In addition, the generated driving video corresponds to the driving control event, and its content has a high information value. In addition, the driving video contains both video content reflecting the road environment outside the vehicle and video content reflecting the driving trajectory, which can enable video viewers to fully understand the driving environment and vehicle driving conditions during the vehicle's automatic driving process, meeting the need to understand the vehicle driving process.
[0112] See also Figure 4 As shown, Figure 4 A flowchart for video generation and publishing provided by an embodiment of the present disclosure is as follows: Figure 4 As shown in , it includes steps S401 to S404, wherein:
[0113] S401: Acquire driving control events executed by the intelligent driving system during vehicle driving, as well as recorded driving video and vehicle screen video; the driving video displays the road environment outside the vehicle; the vehicle screen video displays the driving trajectory of the vehicle in a three-dimensional rendering scene.
[0114] S402: According to the event occurrence time indicated by the driving control event, video clips matching the driving control event are respectively captured from the driving record video and the vehicle screen video.
[0115] S403: Fusing the video clips to generate a driving video matching the driving control event.
[0116] Among them, the description of step S401 to step S403 can refer to the description of step S101 to step S103, and can achieve the same technical effects and solve the same technical problems, and will not be repeated here.
[0117] S404: Perform video desensitization processing on the driving video to obtain a video to be released; and call a video open platform to release the video to be released.
[0118] The driving video may include some content that is not suitable for publication, such as uncivilized content, or personal privacy information, such as license plate numbers of vehicles on the road.
[0119] In this step, the driving video may be subjected to a video content review. When it is detected that the driving video contains content that is not suitable for publication, the driving video may be subjected to a video desensitization process to obtain a video to be published.
[0120] Here, the video open platform includes various short video platforms, long video platforms, video number platforms, etc., and no specific restrictions are made here.
[0121] In this way, by desensitizing the driving video, the legality of the content of the video to be released is guaranteed.
[0122] In other implementations, after a plurality of driving videos of driving control events are generated, the plurality of driving videos may be classified according to business scenarios to obtain videos to be released.
[0123] For example, if it is necessary to highlight the overtaking and avoidance capabilities of the intelligent driving system, the driving video matching the overtaking event and the avoidance event can be extracted from the multiple driving videos to obtain the video to be released.
[0124] To more clearly demonstrate the process of video generation and publishing, you can also refer to Figure 5 .like Figure 5 As shown in , when a driving control event executed by the intelligent driving system during vehicle driving is read, the start time and end time of the video capture are determined; according to the start time and end time of the video capture, the video clips are respectively captured from the driving record video and the vehicle screen video; the video clips are merged to generate a driving video matching the driving control event; the driving video is audited for video content, and when abnormal content is detected in the driving video, the driving video is desensitized to obtain a video to be released; and the video open platform is called to release the video to be released. The description of the specific steps refers to the aforementioned embodiments, which will not be repeated here.
[0125] In some possible implementations, the method further includes:
[0126] After generating a plurality of driving videos of driving control events, determining an adjacency relationship between the plurality of driving videos according to driving trajectories corresponding to the plurality of driving control events;
[0127] The driving videos of the plurality of driving control events are synthesized according to the adjacency relationship to obtain a synthesized driving video.
[0128] In the above steps, considering that a vehicle may perform multiple driving control events during a trip, in order to reflect the process of a single vehicle trip through video, after generating driving videos of multiple driving control events, the adjacency relationship between the driving videos with similar road positions is determined according to the driving trajectories corresponding to the multiple driving control events, and based on the adjacency relationship, the driving videos of the multiple driving control events are synthesized to obtain a synthesized driving video.
[0129] Specifically, if the distance between the end position corresponding to one driving video and the start position corresponding to another driving video is less than a preset distance, it can be determined that there is an adjacency relationship between the one driving video and the other driving video, and the other driving video is connected to the one driving video.
[0130] In this way, multiple driving videos can be synthesized based on the driving trajectory, and based on the adjacency relationship between the multiple driving videos, the driving videos of driving control events corresponding to similar road positions can be connected to avoid abrupt connections in the synthesized driving video.
[0131] When the driving videos of the multiple driving control events are synthesized according to the adjacency relationship to obtain a synthesized driving video, in some possible implementations, a transition video between adjacent driving videos can be generated according to the adjacent driving videos indicated by the adjacency relationship; and the driving videos of the multiple driving control events and the transition video are synthesized according to the adjacency relationship to obtain a synthesized driving video.
[0132] In actual applications, driving control events often do not occur continuously, so the connection between two adjacent driving videos may be abrupt. In this regard, a transition video is generated between the adjacent driving videos, and the two adjacent driving videos are connected through the transition video.
[0133] Wherein, when generating the transition video, the transition video can be generated based on an image generation model. Specifically, for two adjacent driving videos indicated by the adjacency relationship, a first video frame and a second video frame can be determined, wherein the first video frame is the last video frame of the previous driving video, and the second video frame is the first video frame of the subsequent driving video; the first video frame and the second video frame are input into the image generation model to obtain a transition video frame; and the transition video is generated based on at least one transition video frame.
[0134] In this way, adding transition videos between adjacent driving videos helps to improve the smoothness of the connection of video images in the synthesized driving video.
[0135] Correspondingly, in an optional implementation, after obtaining the synthesized driving video, the synthesized driving video may be subjected to video desensitization processing to obtain a video to be released; and the video open platform may be called to release the video to be released.
[0136] The above-mentioned video generation method intercepts video clips matching the driving control event from the driving record video and the vehicle screen video respectively according to the time of the event, merges the video clips, generates a driving video matching the driving control event, and performs video desensitization processing on the driving video to obtain the video to be released, and finally automatically calls the video open platform to release the video to be released. Thereby, the automatic generation and release of the driving video is realized, and the user does not need to shoot the video by himself during the driving process of the vehicle and edit the video later, and the user does not need to manually upload and release it, which improves the efficiency of video generation and release. The driving video contains both video content reflecting the road environment outside the vehicle and video content reflecting the driving trajectory, which can enable the video viewer to fully understand the driving environment and vehicle driving conditions during the vehicle's automatic driving process, and meet the need to understand the vehicle driving process. In addition, the released driving video corresponds to the driving control event, and its content has a high information value. At the same time, by desensitizing the video, the legality and safety of the released driving video are high, and it can be used for effective publicity, such as by presenting the driving flexibility of the vehicle under various driving control events, to achieve publicity significance.
[0137] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.
[0138] Based on the same inventive concept, a video generating device corresponding to the video generating method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the video generating device in the embodiment of the present disclosure is similar to the above-mentioned video generating method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.
[0139] See also Figure 6 and Figure 7 , Figure 6 This is one of the schematic diagrams of a video generating device provided in an embodiment of the present disclosure, Figure 7 This is a second schematic diagram of a video generation device provided by an embodiment of the present disclosure. Figure 6 As shown in , the video generating device 600 provided by the embodiment of the present disclosure includes:
[0140] The event acquisition module 610 is used to acquire the driving control events executed by the intelligent driving system during the driving process of the vehicle, as well as the recorded driving video and the on-board screen video; the driving video shows the road environment outside the vehicle; the on-board screen video shows the driving trajectory of the vehicle in the three-dimensional rendering scene;
[0141] The video capture module 620 is used to capture video clips matching the driving control event from the driving record video and the vehicle screen video respectively according to the event occurrence time indicated by the driving control event;
[0142] The video fusion module 630 is used to fuse the video clips to generate a driving video matching the driving control event.
[0143] In an optional implementation manner, the video capture module 620 is specifically used for:
[0144] Determine the redundant duration of video capture based on the road condition information recorded by the intelligent driving system when the driving control event occurs;
[0145] Determine the start time and end time of video capture according to the start time and end time of the event indicated by the driving control event and the redundant time;
[0146] The video clips are respectively captured from the driving record video and the vehicle screen video according to the start time and the end time of the video capture.
[0147] In an optional implementation manner, the video fusion module 630 is specifically used for:
[0148] Merging the video clips captured from the driving recording video and the vehicle screen video to obtain a fused video picture;
[0149] Generate video description information based on the event information of the driving control event;
[0150] The driving video is generated based on the video description information and the fused video picture.
[0151] In an optional implementation, each frame of the fused video includes a driving record video frame and a vehicle screen video frame corresponding to the same time point.
[0152] In an optional implementation manner, when the video fusion module 630 is used to generate the video description information based on the event information of the driving control event, it is specifically used to:
[0153] Acquire real-time vehicle status information and driving environment information during the period when the driving control event occurs, which is recorded by the intelligent driving system;
[0154] The video description information is generated based on the event information of the driving control event, the real-time vehicle state information and the driving environment information.
[0155] In an optional implementation manner, when the video fusion module 630 is used to generate the driving video based on the video description information and the fused video picture, it is specifically used to:
[0156] Determining background music for the driving video according to the event type of the driving control event;
[0157] The driving video is generated based on the video description information, the fused video picture, and the background music.
[0158] In an optional implementation, Figure 7 As shown in , the video generating device 600 further includes a video publishing module 640, and the video publishing module 640 is used to:
[0159] Performing video desensitization processing on the driving video to obtain a video to be released;
[0160] The video open platform is called to publish the video to be published.
[0161] In an optional implementation, if Figure 7 As shown in , the video generating device 600 further includes a video synthesis module 650, and the video synthesis module 650 is used to:
[0162] After generating a plurality of driving videos of driving control events, determining an adjacency relationship between the plurality of driving videos according to driving trajectories corresponding to the plurality of driving control events;
[0163] The driving videos of the plurality of driving control events are synthesized according to the adjacency relationship to obtain a synthesized driving video.
[0164] In an optional implementation manner, when the video synthesis module 650 is used to synthesize the driving videos of the multiple driving control events according to the adjacency relationship to obtain the synthesized driving video, it is specifically used to:
[0165] generating a transition video between adjacent driving videos according to the adjacent driving videos indicated by the adjacency relationship;
[0166] The driving videos of the multiple driving control events and the transition video are synthesized according to the adjacency relationship to obtain a synthesized driving video.
[0167] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference may be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.
[0168] The video generating device provided by the embodiment of the present disclosure effectively utilizes the intelligent driving system provided in the vehicle itself. The intelligent driving system can automatically control the vehicle to execute driving control events and record the time when the events occur, and the vehicle can output driving recording videos and on-board screen videos. For intelligent driving scenarios, video clips matching the driving control events are respectively captured from the driving recording videos and on-board screen videos according to the time when the events occur, and the video clips are fused to generate a driving video matching the driving control events, thereby realizing automatic generation of driving videos. There is no need for users to shoot videos by themselves during vehicle driving and edit them later, which reduces users' driving safety risks and helps to improve video generation efficiency.
[0169] Corresponds to Figure 1 The video generation method in the present disclosure also provides an electronic device 800, such as Figure 8 FIG. 8 is a schematic diagram of the structure of an electronic device 800 provided in an embodiment of the present disclosure, including:
[0170] Processor 810, memory 820, and bus 830. The memory 820 is used to store execution instructions, including internal memory 821 and external memory 822; the internal memory 821 is also called internal memory, which is used to temporarily store the operation data in the processor 810 and the data exchanged with the external memory 822 such as a hard disk. The processor 810 exchanges data with the external memory 822 through the internal memory 821.
[0171] In the embodiment of the present application, the memory 820 is specifically used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 810. That is, when the electronic device 800 is running, the processor 810 communicates with the memory 820 through the bus 830, so that the processor 1010 executes the application code stored in the memory 820, and then executes the steps of the video generation method described in any of the above embodiments.
[0172] Among them, the memory 820 can be, but is not limited to, random access memory (Random Access Memory, RAM), read only memory (Read Only Memory, ROM), programmable read-only memory (Programmable Read-Only Memory, PROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable read-only memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
[0173] The processor 810 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0174] It is to be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 800. In other embodiments of the present application, the electronic device 800 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.
[0175] The embodiment of the present disclosure also provides a vehicle, including a controller, the controller including: a memory for storing machine-readable instructions; and a processor for calling and executing the machine-readable instructions stored in the memory to implement the steps of the video generation method described in the above method embodiment. The vehicle may be a vehicle provided with an intelligent driving system.
[0176] The present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the video generation method described in the above method embodiment are executed. The storage medium can be a volatile or non-volatile computer-readable storage medium.
[0177] In addition, an embodiment of the present disclosure further provides a computer program product, on which a computer program is stored. When the computer program is executed by a processor, the steps of the video generation method provided in any of the above embodiments of the present disclosure are executed. For details, please refer to the above method embodiments, which will not be repeated here.
[0178] The computer program product may be implemented in hardware, software or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium, which may be a volatile or non-volatile computer-readable storage medium. In another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK) and the like.
[0179] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the above-described equipment and devices can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0180] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0181] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0182] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0183] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.
Claims
1. A video generation method, It is characterized in that The method comprises: Acquire driving control events executed by the intelligent driving system during vehicle driving, as well as recorded driving video and on-board screen video; the driving video displays the road environment outside the vehicle; the on-board screen video displays the driving trajectory of the vehicle in the three-dimensional rendering scene; According to the event occurrence time indicated by the driving control event, respectively intercepting video clips matching the driving control event from the driving record video and the vehicle screen video; The video clips are fused to generate a driving video matching the driving control event.
2. The method according to claim 1, It is characterized in that The method of capturing video clips matching the driving control event from the driving record video and the vehicle screen video respectively according to the event occurrence time indicated by the driving control event includes: Determine the redundant duration of video capture based on the road condition information recorded by the intelligent driving system when the driving control event occurs; Determine the start time and end time of video capture according to the start time and end time of the event indicated by the driving control event and the redundant time; The video clips are respectively captured from the driving record video and the vehicle screen video according to the start time and the end time of the video capture.
3. The method according to claim 1, It is characterized in that The step of fusing the video clips to generate a driving video matching the driving control event includes: Merging the video clips captured from the driving recording video and the vehicle screen video to obtain a fused video picture; Generate video description information based on the event information of the driving control event; The driving video is generated based on the video description information and the fused video picture.
4. The method according to claim 3, It is characterized in that Each frame of the fused video includes a frame of the driving record video frame and a frame of the vehicle screen video frame corresponding to the same time point.
5. The method according to claim 3, It is characterized in that The generating of video description information based on the event information of the driving control event includes: Acquire real-time vehicle status information and driving environment information during the period when the driving control event occurs, which is recorded by the intelligent driving system; The video description information is generated based on the event information of the driving control event, the real-time vehicle state information and the driving environment information.
6. The method according to any one of claims 3 to 5, It is characterized in that The generating the driving video based on the video description information and the fused video picture includes: Determining background music for the driving video according to the event type of the driving control event; The driving video is generated based on the video description information, the fused video picture, and the background music.
7. The method according to claim 1, It is characterized in that After generating the driving video matching the driving control event, the method further includes: Performing video desensitization processing on the driving video to obtain a video to be released; The video open platform is called to publish the video to be published.
8. The method according to claim 1, It is characterized in that The method further comprises: After generating a plurality of driving videos of driving control events, determining an adjacency relationship between the plurality of driving videos according to driving trajectories corresponding to the plurality of driving control events; The driving videos of the plurality of driving control events are synthesized according to the adjacency relationship to obtain a synthesized driving video.
9. The method according to claim 8, It is characterized in that The step of synthesizing the driving videos of the plurality of driving control events according to the adjacency relationship to obtain a synthesized driving video includes: generating a transition video between adjacent driving videos according to the adjacent driving videos indicated by the adjacency relationship; The driving videos of the multiple driving control events and the transition video are synthesized according to the adjacency relationship to obtain a synthesized driving video.
10. An electronic device, It is characterized in that include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions are executed by the processor to perform the steps of the video generation method according to any one of claims 1 to 9.
11. A vehicle, It is characterized in that A controller is included, the controller comprising: a memory for storing machine-readable instructions; and A processor, configured to call and execute the machine-readable instructions stored in the memory to implement the steps of the video generation method according to any one of claims 1 to 9.
12. A computer program product, It is characterized in that The computer program product stores a computer program, and when the computer program is executed by a processor, the steps of the video generation method according to any one of claims 1 to 9 are executed.
Citation Information
Cited By
Method and system for fusing intelligent driving data and driving video and sharing same
WO2026144979A1
