Method, system and vehicle for video generation

Abstract

This disclosure relates to a method, system, and vehicle for video generation. The method includes: acquiring environmental videos of the vehicle's surroundings captured by multiple video acquisition devices; acquiring a predetermined target pixel range for each video acquisition device, wherein the target pixel range is the pixel range in the video display device of the vehicle's AVM system used to display the corresponding video of the video acquisition device; for each environmental video acquired by a video acquisition device, acquiring a target sub-video corresponding to the target pixel range of each video acquisition device from the environmental video; and performing video fusion processing on the multiple target sub-videos to obtain a target video.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle technology, and more specifically, to a method, system, and vehicle for video generation. Background Technology

[0002] With the advancement of technology, vehicle safety performance is receiving increasing attention. To avoid the impact of blind spots on driving safety, AVM (Around View Monitor) systems have been successfully applied to many vehicle models. To reduce vehicle wiring costs, AVM systems typically reuse cameras from other systems on the vehicle to achieve panoramic surround view functionality.

[0003] However, transmitting video between different systems consumes a lot of encoding and decoding resources, which may exceed the capacity of the AVM system, affecting the real-time response of the AVM system, causing the panoramic surround view function to fail to be activated in real time, affecting the user's driving experience, and may even affect driving safety. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this disclosure provides a method, system, and vehicle for video generation.

[0005] According to a first aspect of the present disclosure, a method for video generation is provided, comprising:

[0006] The system acquires environmental videos of the vehicle's surroundings from multiple video acquisition devices; it acquires a predetermined target pixel range for each video acquisition device, where the target pixel range is the pixel range used to display the corresponding video from the video display device of the vehicle's AVM system; for each environmental video acquired by a video acquisition device, it acquires a target sub-video corresponding to the target pixel range of each video acquisition device from the environmental video; and it performs video fusion processing on the multiple target sub-videos to obtain the target video.

[0007] Optionally, obtaining the target pixel range predetermined by each video acquisition device includes: determining the target preset conditions satisfied by the vehicle from multiple preset conditions; and taking the pixel range corresponding to the target preset conditions as the target pixel range, with different preset conditions corresponding to different pixel ranges.

[0008] Optionally, the target pixel range is predetermined by: acquiring calibration videos of the target calibration object captured by the plurality of video acquisition devices under each preset condition; and determining the target pixel range of each video acquisition device under each preset condition based on the acquired calibration videos.

[0009] Optionally, determining the target pixel range of each video acquisition device under each preset condition based on the acquired multiple calibration object videos includes: for each video acquisition device, determining the feature pixel range corresponding to the calibration object video acquired by the video acquisition device, displaying the calibration object video on the video display device of the AVM system, and using the feature pixel range as the target pixel range when the target calibration object is identified based on the displayed calibration object video.

[0010] Optionally, the preset conditions include at least one of the following: the vehicle is shifted to reverse (R); the vehicle turns on its left turn signal; the vehicle turns on its right turn signal; the vehicle speed is less than or equal to a preset speed; the vehicle's radar detects an obstacle within a preset area.

[0011] Optionally, the method further includes: displaying the target video through the video display device of the AVM system.

[0012] According to a second aspect of the present disclosure, a video generation system is provided, comprising:

[0013] The system includes multiple video acquisition devices, an AVM system, and an autonomous driving controller. The AVM system comprises an AVM controller and a video display device. The AVM controller is connected to both the video display device and the autonomous driving controller, and the autonomous driving controller is connected to the multiple video acquisition devices. The autonomous driving controller is configured to acquire environmental videos of the vehicle's surroundings captured by the multiple video acquisition devices, and to acquire a pre-determined target pixel range for each video acquisition device. The target pixel range is defined as the pixel range in the video display device of the AVM system used to display the corresponding video of the video acquisition device. Furthermore, for each video acquisition device's environmental video, the controller acquires a target sub-video corresponding to the target pixel range of each video acquisition device from the environmental video and sends the target sub-video to the AVM controller. The AVM controller is configured to perform video fusion processing on the multiple target sub-videos to obtain a target video.

[0014] Optionally, the AVM controller is further configured to determine the target preset conditions satisfied by the vehicle from a plurality of preset conditions; the autonomous driving controller is further configured to take the pixel range corresponding to the target preset conditions as the target pixel range according to the target preset conditions determined by the AVM controller, and different preset conditions correspond to different pixel ranges.

[0015] Optionally, the autonomous driving controller is further configured to acquire calibration videos of the target calibration objects captured by the plurality of video acquisition devices under each preset condition, and send the calibration videos to the AVM controller; the AVM controller is further configured to determine the target pixel range of each video acquisition device under each preset condition based on the plurality of calibration videos captured by the plurality of video acquisition devices, and send the target pixel range to the autonomous driving controller.

[0016] Optionally, the AVM controller is further configured to determine, for each video acquisition device, the feature pixel range corresponding to the calibration object video acquired by the video acquisition device, display the calibration object video on the video display device of the AVM system, and, if the target calibration object is identified based on the displayed calibration object video, use the feature pixel range as the target pixel range.

[0017] Optionally, the preset conditions include at least one of the following: the vehicle is shifted to reverse (R); the vehicle turns on its left turn signal; the vehicle turns on its right turn signal; the vehicle speed is less than or equal to a preset speed; the vehicle's radar detects an obstacle within a preset area.

[0018] Optionally, the AVM controller is also configured to display the target video through the video display device of the AVM system.

[0019] According to a third aspect of the present disclosure, a vehicle is provided, including the video generation system described in the second aspect.

[0020] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects:

[0021] This disclosure enables the pre-determining of the target pixel range in the video display device of the AVM system used to display the video corresponding to the video acquisition device. By acquiring the target sub-videos corresponding to the target pixel range and fusing them, a target video for display is obtained. Thus, when the AVM system needs to reuse cameras from other vehicle systems to enable the panoramic surround view function, it can obtain the sub-videos corresponding to the target pixel range through a pre-established correspondence between the video display device and the camera in the AVM system. These sub-videos are then fused to obtain the target video, eliminating the need to transmit all the video captured by the cameras. This reduces the amount of video transmitted, lowers the encoding and decoding load of the AVM system, and improves the response rate of the AVM system, thereby enhancing the driving experience and driving safety.

[0022] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0023] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0024] Figure 1 This is a flowchart illustrating a video generation method according to an exemplary embodiment.

[0025] Figure 2 This is a flowchart illustrating another method for video generation according to an exemplary embodiment.

[0026] Figure 3 This is a block diagram illustrating a video generation system according to an exemplary embodiment.

[0027] Figure 4 This is a structural block diagram of a vehicle according to an exemplary embodiment. Detailed Implementation

[0028] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0029] It should be noted that all actions involving the acquisition of signals, information, or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where the application is located, and with the authorization granted by the owner of the relevant device.

[0030] In related technologies, to reduce vehicle wiring costs, AVM systems typically reuse cameras from other systems on the vehicle to achieve panoramic surround view functionality. However, transmitting video between different systems consumes significant encoding and decoding resources, potentially exceeding the AVM system's capacity and affecting its real-time response. This can prevent the panoramic surround view function from activating in real time, impacting the user's driving experience and possibly even affecting driving safety.

[0031] To address the aforementioned issues, this disclosure predetermines the target pixel range in the video display device of the AVM system used to display the video corresponding to the video acquisition device. By acquiring the target sub-videos corresponding to the target pixel range and fusing them, a target video for display is obtained. Thus, when the AVM system needs to reuse cameras from other vehicle systems to enable the panoramic surround view function, it can obtain the sub-videos corresponding to the target pixel range through a pre-established correspondence between the video display device and the camera's target pixel range in the AVM system. These sub-videos are then fused to obtain the target video, eliminating the need to transmit all video captured by the cameras. This reduces the amount of video transmitted, lowers the encoding and decoding load on the AVM system, and improves the response rate of the AVM system, thereby enhancing the driving experience and driving safety.

[0032] Figure 1 This is a flowchart illustrating a video generation method according to an exemplary embodiment, such as... Figure 1 As shown, the subject executing this method can be a vehicle, and the method can include:

[0033] In step S11, environmental videos of the vehicle's surroundings are acquired from multiple video acquisition devices.

[0034] Specifically, the vehicle's autonomous driving controller can acquire environmental videos of the vehicle's surroundings from multiple video capture devices within the autonomous driving system. These video capture devices can be cameras, with adjustable shooting angles and focal lengths. There can be up to four cameras, installed at the front, rear, left, and right sides of the vehicle. The environmental videos can cover a preset area around the vehicle (e.g., 100 meters around the vehicle). For instance, cameras installed at the front, rear, left, and right sides of the vehicle can acquire videos of the front, rear, left, and right environments, respectively.

[0035] In step S12, the target pixel range predetermined for each video acquisition device is obtained.

[0036] The target pixel range refers to the pixel range in the video display device of the vehicle's AVM system used to display the video corresponding to the video acquisition device.

[0037] For example, the vehicle's autonomous driving controller can receive the range of multiple pixels to be displayed in the video display device of the AVM system from the AVM controller in the AVM system. By using the correspondence between the display area to be displayed in the video display device and the pixel range in each video acquisition device, the pixel range of the corresponding pixel in each video acquisition device can be obtained.

[0038] In step S13, for each video acquisition device, the target sub-video corresponding to the target pixel range of each video acquisition device is obtained from the environmental video.

[0039] For example, the vehicle's autonomous driving controller can extract multiple pixels corresponding to the target pixel range from all pixels in each captured environmental video, and then stitch the pixels together to obtain the target sub-video corresponding to each video capture device.

[0040] It should be noted that the specific algorithm for video stitching can be found in the implementation methods of video stitching in related technologies, and will not be elaborated here.

[0041] In step S14, the multiple target sub-videos are fused to obtain the target video.

[0042] The vehicle's autonomous driving controller can transmit the multiple target sub-videos to the AVM system. The AVM system can perform video fusion processing on the multiple target sub-videos to obtain the target video. After obtaining the target video, it can be displayed through the video display device in the AVM system.

[0043] It should be noted that the specific algorithms for video fusion can be found in the implementation methods of video fusion in related technologies, and will not be elaborated here.

[0044] Using the above method, the target pixel range for displaying the video from the video capture device in the AVM system can be predetermined. By acquiring the target sub-videos corresponding to the target pixel range and fusing them, the target video for display can be obtained. Thus, when the AVM system needs to reuse cameras from other vehicle systems to enable the surround-view function, it can obtain the corresponding sub-videos based on the pre-established correspondence between the target pixel ranges of the video display device and the cameras in the AVM system. These sub-videos can then be fused to obtain the target video, eliminating the need to transmit all the video captured by the cameras. This reduces the amount of video transmitted, lowers the encoding and decoding load on the AVM system, and improves its response rate, thereby enhancing the driving experience and safety.

[0045] In some embodiments, step S12 may include: determining the target preset condition satisfied by the vehicle from a plurality of preset conditions, and taking the pixel range corresponding to the target preset condition as the target pixel range.

[0046] Different preset conditions correspond to different pixel ranges. Preset conditions may include at least one of the following: the vehicle is shifted into reverse (R); the vehicle's left turn signal is on; the vehicle's right turn signal is on; the vehicle speed is less than or equal to a preset speed; the vehicle's radar detects an obstacle within a preset area.

[0047] For example, when the vehicle is in reverse (R), it indicates the driver intends to reverse. At this time, there may be safety hazards to the side and rear of the vehicle, allowing the video capture device to acquire the first target pixel range. When the vehicle's left turn signal is on, it indicates the driver intends to turn left, change lanes to the left, or make a U-turn. The driver needs to observe the left rear of the vehicle and oncoming traffic, allowing the video capture device to acquire the second target pixel range. When the vehicle's right turn signal is on, it indicates the driver intends to turn right or change lanes to the right, requiring the driver to observe the right side of the vehicle, allowing the video capture device to acquire the third target pixel range. When the vehicle speed is less than or equal to... At the preset speed, it indicates that the vehicle is on a narrow road or a road with poor conditions. At this time, the driver needs to observe the distance between the vehicle and oncoming vehicles or the edge of the road, and can obtain the fourth target pixel range of the video acquisition device. The preset speed can be 20 km / h, and this disclosure does not limit it. When the vehicle's radar detects an obstacle in the preset area, the driver needs to judge the distance between the vehicle and the obstacle, and can obtain the fifth target pixel range of the video acquisition device. The obstacle can include moving obstacles and fixed obstacles, and can also include people and animals. The preset area can be an area within 2.5m of the vehicle, and this disclosure does not limit it.

[0048] In this way, by determining the activation conditions of the AVM system's panoramic surround view function, the panoramic surround view function can be activated, thereby improving its real-time performance and applicability, and enhancing vehicle driving safety.

[0049] In some embodiments, the target pixel range can be predetermined through the following steps:

[0050] S121. Obtain the calibration video of the target calibration object collected by the multiple video acquisition devices under each preset condition.

[0051] The target calibration object can be multiple calibration boards, each containing multiple feature detection points, each with defined coordinate values. The target calibration objects can be placed vertically on the ground around the vehicle or mounted on the walls around the vehicle. Each target calibration object corresponds one-to-one with a video acquisition device, which captures video of the calibration object containing the corresponding calibration board with multiple feature detection points.

[0052] S122. Based on the collected videos of multiple calibration objects, determine the target pixel range of each video acquisition device under each preset condition.

[0053] In one possible implementation, for each video acquisition device, the range of feature pixels corresponding to the calibration object video acquired by the video acquisition device can be determined, and the calibration object video can be displayed on the video display device of the AVM system. If the target calibration object is identified based on the displayed calibration object video, the range of feature pixels can be used as the target pixel range.

[0054] For example, the pixel position of each feature detection point in the target calibration object can be obtained in the corresponding video acquisition device. Based on the pixel position, the feature pixel range corresponding to the calibration object video acquired by the video acquisition device can be determined. The AVM controller of the AVM system can send a video acquisition command to the autopilot controller. The autopilot controller can reduce the frame rate of the calibration object video acquired by the video acquisition device and send the reduced frame rate calibration object video to the AVM system. For example, the frame rate of the calibration object video can be reduced from 30 frames / second to 10 frames / second, which can reduce the size of the transmitted video file and reduce the requirements for system transmission bandwidth. After receiving the calibration object video, the AVM system can display the fused calibration object video on the video display device and identify the feature detection points of the target calibration object in the video displayed on the video display device using video recognition technology. If all feature detection points of the target calibration object are identified, it means that the video acquisition device has been successfully matched with the video display device of the AVM system, and the feature pixel range corresponding to the calibration object video can be used as the target pixel range displayed on the video display device. In this way, the target pixel range of each video acquisition device corresponding to the display area of ​​the video display device of the AVM system can be determined, which makes it easier for the autonomous driving controller to obtain the target video according to the target pixel range, improves the accuracy of video calibration, and reduces the number of video files transmitted.

[0055] In other embodiments, if unidentified feature detection points exist in the video displayed by the video display device, it indicates that the video acquisition device has not yet successfully matched with the video display device of the AVM system. In this case, relevant parameters of the video acquisition device, such as focal length and field of view, can be adjusted, and steps S121 to S122 can be executed repeatedly until all feature detection points of the target calibration object are identified in the video displayed by the video display device. In this way, by adjusting the parameters of the video acquisition device, the video acquisition device can be precisely matched with the video display device of the AVM system, improving the accuracy of video calibration.

[0056] It should be noted that the specific methods for adjusting the parameters of video recognition technology and video acquisition equipment can be found in the implementation methods of parameter adjustment for video recognition and video acquisition equipment in related technologies, and will not be elaborated here.

[0057] In some embodiments, the target video can be displayed through the video display device of the AVM system.

[0058] The panoramic video can be displayed through the display area of ​​the screen in the video display device, or it can be displayed through screen projection or on other terminals. This disclosure does not limit this.

[0059] This provides the driver with information about the vehicle's surroundings, assisting them in making driving decisions and improving safety when driving in complex environments.

[0060] Figure 2 This is a flowchart illustrating another method for video generation according to an exemplary embodiment, such as... Figure 2 As shown, the method includes:

[0061] S201. Obtain the calibration video of the target calibration object captured by the multiple video acquisition devices under each preset condition.

[0062] The target calibration objects can be multiple calibration boards, each containing multiple feature detection points, each with defined coordinate values. The target calibration objects can be placed vertically on the ground around the vehicle or mounted on the walls around the vehicle, with each target calibration object corresponding to a video acquisition device.

[0063] S202. For each video acquisition device, determine the range of feature pixels corresponding to the calibration object video acquired by that video acquisition device.

[0064] Specifically, the pixel position of the feature detection point in each target calibration object in the corresponding video acquisition device can be obtained, and the feature pixel range corresponding to the calibration object video acquired by the video acquisition device can be determined based on the pixel position.

[0065] S203. Display the calibration object video on the video display device of the AVM system.

[0066] The AVM controller of the AVM system can send video acquisition instructions to the autonomous driving controller. The autonomous driving controller can reduce the frame rate of the calibration object video acquired by the video acquisition device and send the reduced frame rate calibration object video to the AVM system. After receiving the calibration object video, the AVM system can display the fused calibration object video on the video display device.

[0067] S204. Determine whether the target marker is identified based on the displayed video of the marker.

[0068] Among them, the AVM system can identify the feature detection points of the target calibrator in the video displayed on the video display device through video recognition technology.

[0069] If the target marker is identified based on the displayed video of the marker, steps S205, S207 to S210 are executed.

[0070] If the target marker is not identified based on the displayed video of the marker, proceed to step S206.

[0071] S205. Use the range of the feature pixels as the range of the target pixels.

[0072] S206. Adjust the relevant parameters of the video acquisition device and execute steps S201 to S204.

[0073] S207. In response to the vehicle meeting preset conditions, acquire environmental videos of the vehicle's surroundings collected by multiple video acquisition devices.

[0074] The preset conditions include at least one of the following: the vehicle is shifted into reverse (R); the vehicle turns on its left turn signal; the vehicle turns on its right turn signal; the vehicle speed is less than or equal to the preset speed; the vehicle's radar detects an obstacle within the preset area.

[0075] S208. For each video acquisition device that acquires an environmental video, obtain the target sub-video corresponding to the target pixel range of each video acquisition device from the environmental video.

[0076] In this process, multiple pixels corresponding to the target pixel range can be extracted from all pixels in each captured environmental video, and the pixels can be stitched together to obtain the target sub-video corresponding to each video capture device.

[0077] S209. Perform video fusion processing on the multiple target sub-videos to obtain the target video.

[0078] The target video can be obtained by fusing the multiple target sub-videos using the vehicle's AVM system.

[0079] S210. Display the target video through the video display device of the AVM system.

[0080] The panoramic video can be displayed in the display area of ​​the screen in the video display device, or it can be displayed by screen projection or on other terminals.

[0081] By adopting the above scheme, the correspondence between the display area in the video display device of the AVM system and the target pixel range of multiple video acquisition devices in the autonomous driving controller can be predetermined. When the vehicle meets preset conditions, the autonomous driving controller acquires environmental videos of the vehicle's surroundings captured by the video acquisition devices, extracts the target sub-video corresponding to the target pixel range from the environmental videos, and sends it to the AVM system. The AVM system performs video fusion on the target sub-videos to obtain the target video for display, which is then displayed on the video display device. Thus, when the AVM system needs to reuse cameras from other vehicle systems to activate the panoramic surround view function, it can obtain the sub-video corresponding to the target pixel range through the pre-established correspondence between the video display device and the camera's target pixel range in the AVM system, and fuse the sub-videos to obtain the target video. This eliminates the need to transmit all the videos captured by the cameras, reducing the amount of video transmission, lowering the encoding and decoding load of the AVM system, and improving the response rate of the AVM system, thereby improving the driving experience and driving safety.

[0082] It should be noted that the above Figure 2 The descriptions of each step in the illustrated embodiments can be found in the descriptions of the relevant steps in the foregoing embodiments, and will not be repeated here.

[0083] Figure 3 This is a block diagram of a video generation system 300 as illustrated by an example. (Refer to...) Figure 3 The system includes:

[0084] Multiple video acquisition devices 301, an AVM system 302, and an autopilot controller 303 are provided. The AVM system 302 includes an AVM controller 304 and a video display device 305. The AVM controller 304 is connected to the video display device 305 and the autopilot controller 303, respectively. The autopilot controller 303 is connected to the multiple video acquisition devices 301.

[0085] The autonomous driving controller 303 is used to acquire environmental videos around the vehicle collected by multiple video acquisition devices 301 of the vehicle, and to acquire a predetermined target pixel range for each video acquisition device 301. The target pixel range is the pixel range in the video display device 305 of the AVM system 302 used to display the corresponding video of the video acquisition device 301. For each environmental video acquired by the video acquisition device 301, the controller obtains the target sub-video corresponding to the target pixel range of each video acquisition device 301 from the environmental video, and sends the target sub-video to the AVM controller 304.

[0086] The AVM controller 304 is used to perform video fusion processing on the multiple target sub-videos to obtain the target video.

[0087] Optionally, the AVM controller 304 is further configured to determine the target preset conditions satisfied by the vehicle from a plurality of preset conditions; the autonomous driving controller 303 is further configured to use the pixel range corresponding to the target preset conditions as the target pixel range according to the target preset conditions determined by the AVM controller 304, and different preset conditions correspond to different pixel ranges.

[0088] Optionally, the autonomous driving controller 303 is further configured to acquire the calibration video of the target calibration object captured by the plurality of video acquisition devices 301 under each preset condition, and send the calibration video to the AVM controller 304; the AVM controller 304 is further configured to determine the target pixel range of each video acquisition device 301 under each preset condition based on the plurality of calibration video acquired by the plurality of video acquisition devices 301, and send the target pixel range to the autonomous driving controller 303.

[0089] Optionally, the AVM controller 304 is further configured to determine, for each video acquisition device 301, the feature pixel range corresponding to the calibration object video acquired by the video acquisition device 301, display the calibration object video on the video display device 305 of the AVM system, and, if the target calibration object is identified based on the displayed calibration object video, use the feature pixel range as the target pixel range.

[0090] Optionally, the preset conditions include at least one of the following: the vehicle is shifted into reverse (R); the vehicle turns on its left turn signal; the vehicle turns on its right turn signal; the vehicle speed is less than or equal to a preset speed; the vehicle's radar detects an obstacle within a preset area.

[0091] Optionally, the AVM controller 304 is also used to display the target video through the video display device 305 of the AVM system 302.

[0092] By employing the aforementioned system, the correspondence between the display area in the video display device of the AVM system and the target pixel range of multiple video acquisition devices in the autonomous driving controller can be predetermined. When the vehicle meets preset conditions, the autonomous driving controller acquires environmental videos of the vehicle's surroundings captured by the video acquisition devices, extracts the target sub-video corresponding to the target pixel range from the environmental videos, and sends it to the AVM system. The AVM system performs video fusion on the target sub-videos to obtain the target video for display, which is then displayed on the video display device. Thus, when the AVM system needs to reuse cameras from other vehicle systems to activate the panoramic surround view function, it can obtain the sub-video corresponding to the target pixel range through the pre-established correspondence between the video display device and the camera's target pixel range in the AVM system, and fuse the sub-videos to obtain the target video. This eliminates the need to transmit all the videos captured by the cameras, reducing the amount of video transmission, lowering the encoding and decoding load of the AVM system, and improving the response rate of the AVM system, thereby enhancing the driving experience and driving safety.

[0093] Regarding the systems in the above embodiments, the specific ways in which each subsystem performs operations have been described in detail in the embodiments concerning the video generation method, and will not be elaborated upon here.

[0094] Figure 4 This is a structural block diagram of a vehicle 400 according to an exemplary embodiment, the vehicle 400 including the video generation system 300 described above.

[0095] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0096] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0097] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A method for video generation, characterized in that, Applied to vehicles, the method includes: Acquire environmental videos of the vehicle's surroundings from multiple video capture devices; Obtain a pre-determined target pixel range for each video acquisition device, wherein the target pixel range is the pixel range in the video display device of the vehicle's AVM system used to display the corresponding video of the video acquisition device; For each video capture device, a target sub-video corresponding to the target pixel range of each video capture device is obtained from the environmental video. The multiple target sub-videos are fused together to obtain the target video. The process of obtaining the pre-determined target pixel range for each video capture device includes: The target preset condition satisfied by the vehicle is determined from multiple preset conditions; The pixel range corresponding to the target preset condition is taken as the target pixel range, and different preset conditions correspond to different pixel ranges; The target pixel range is predetermined in the following manner: Acquire the calibration video of the target calibration object captured by the plurality of video acquisition devices under each preset condition; For each video acquisition device, the feature pixel range corresponding to the calibration object video acquired by the video acquisition device is determined, and the calibration object video is displayed on the video display device of the AVM system. If the target calibration object is identified based on the displayed calibration object video, the feature pixel range is taken as the target pixel range.

2. The method according to claim 1, characterized in that, The preset conditions include at least one of the following: The vehicle's gear is shifted to reverse (R). The vehicle turns on its left turn signal; The vehicle turns on its right turn signal; The vehicle speed is less than or equal to the preset speed; The vehicle's radar detected an obstacle within a preset area.

3. The method according to claim 1 or 2, characterized in that, The method further includes: The target video is displayed through the video display device of the AVM system.

4. A video generation system, characterized in that, The system, applicable to vehicles, includes: multiple video acquisition devices, an AVM system, and an autonomous driving controller. The AVM system includes an AVM controller and a video display device. The AVM controller is connected to both the video display device and the autonomous driving controller. The autonomous driving controller is connected to the multiple video acquisition devices. The autonomous driving controller is used to acquire environmental videos around the vehicle collected by multiple video acquisition devices of the vehicle, and to acquire a target pixel range predetermined for each video acquisition device. The target pixel range is the pixel range in the video display device of the AVM system used to display the corresponding video of the video acquisition device. For the environmental video collected by each video acquisition device, the controller acquires a target sub-video corresponding to the target pixel range of each video acquisition device from the environmental video, and sends the target sub-video to the AVM controller. The AVM controller is used to perform video fusion processing on the multiple target sub-videos to obtain the target video; The AVM controller is also configured to determine the target preset conditions satisfied by the vehicle from a plurality of preset conditions; The autonomous driving controller is further configured to use the pixel range corresponding to the target preset conditions as the target pixel range according to the target preset conditions determined by the AVM controller, and different preset conditions correspond to different pixel ranges; The autonomous driving controller is also used to acquire the calibration video of the target calibration object captured by the plurality of video acquisition devices under each preset condition, and send the calibration video to the AVM controller; The AVM controller is further configured to determine, for each video acquisition device, the feature pixel range corresponding to the calibration object video acquired by the video acquisition device, display the calibration object video on the video display device of the AVM system, and, if the target calibration object is identified based on the displayed calibration object video, use the feature pixel range as the target pixel range and send the target pixel range to the autonomous driving controller.

5. A vehicle, characterized in that, The system for video generation as described in claim 4.

Images