Automobile door control method and system, automobile and storage medium
By monitoring the idle computing power of the vehicle and selecting suitable three-dimensional or two-dimensional anti-collision strategies, the collision risk problem of large vehicle doors when opening automatically is solved, and the adaptability and safety improvement to different models and usage scenarios is achieved.
Patent Information
- Application Number
- CN202311502733.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-09
- Publication Date
- 2025-05-13
AI Technical Summary
When the doors of large vehicles are opened automatically, they are prone to opening collision risks because they are too close to the rear target or the roof of the house. The existing anti-collision plan cannot match different models and usage scenarios.
By monitoring the vehicle's idle computing power, determine whether it meets the three-dimensional computing power requirements. If it is met, implement a three-dimensional anti-collision strategy, otherwise implement a two-dimensional anti-collision strategy. In both strategies, if a collision risk is detected during door opening, the door is controlled to stop.
It realizes anti-collision prediction of the door in different models and usage scenarios, avoids the door from hitting the vehicle's internal structure or external targets, reduces maintenance costs and personnel damage risks, and improves the safety of door opening.
Smart Images
Figure CN119981579A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle technology, and in particular to a door control method, a control system, a vehicle and a storage medium. Background Art
[0002] Since the door structure of large vehicles is large, whether it is opened horizontally or upwards, in the automatic door opening function mode, there is a risk of collision when the vehicle is close to the object behind the vehicle or the top of the house. In the related technology, the anti-collision solution cannot match different vehicle models and has limited usage scenarios. Summary of the invention
[0003] The present application provides a door control method, a control system, a car and a storage medium with multiple usage scenarios.
[0004] The present application provides a vehicle door control method, comprising:
[0005] Monitor the vehicle's idle computing power;
[0006] Determining whether the idle computing power of the vehicle meets the three-dimensional computing power requirements;
[0007] If satisfied, the three-dimensional collision avoidance strategy is executed;
[0008] If not, the two-dimensional collision avoidance strategy is executed;
[0009] Wherein in the three-dimensional anti-collision strategy or the two-dimensional anti-collision strategy, if it is determined that there is a risk of collision when the vehicle door is opened, the vehicle door is controlled to stop.
[0010] Optionally, the three-dimensional collision avoidance strategy includes:
[0011] Acquire the environmental depth information of the environment around the vehicle door and the positive image of the vehicle door facing the target;
[0012] Fusing the acquired environment depth information with the target forward image to add the environment depth information to the target forward image;
[0013] Determining spatial coordinate information of the target forward image according to the target forward image carrying the environment depth information; and
[0014] The spatial coordinate information of the target forward image is matched with the edge position of the vehicle door in the open state, and whether there is a collision risk during the opening process of the vehicle door is determined according to the matching result.
[0015] Optionally, determining the spatial coordinate information of the target forward image according to the target forward image carrying the environment depth information includes:
[0016] Determining initial spatial coordinate information of the target forward image according to the target forward image carrying the environment depth information; and
[0017] Performing mesh reconstruction, mesh optimization and texture mapping processing on the point cloud fusion image obtained by fusing the environment depth information with the target forward image, so as to optimize the initial space coordinate information; and
[0018] The optimized initial coordinate information is determined as the final spatial coordinate information.
[0019] Optionally, matching the spatial coordinate information of the target forward image with the edge position of the door in the open state, and determining whether there is a collision risk during the opening of the door according to the matching result, includes:
[0020] Determining whether the distance between the edge position of the door in the open state and the spatial coordinate information is less than an interval threshold;
[0021] If it is less than the interval threshold, it indicates that there is a risk of collision when the door is opened, and the door is controlled to stop.
[0022] Optionally, the acquiring of the environmental depth information of the environment surrounding the vehicle door includes:
[0023] Acquire multiple frames of environmental images of the environment around the vehicle door and motion state information of the vehicle;
[0024] Performing dense reconstruction and fusion on the multiple frames of environment images; and
[0025] The environmental depth information of the environment around the door is obtained according to the fused image and the running status information of the vehicle.
[0026] Optionally, the two-dimensional collision avoidance strategy includes:
[0027] Projecting the edge position of the door in the open state onto the ground to calibrate it as a collision risk marking line;
[0028] Acquire a static image of the target facing the vehicle door, and mark the static image of the target; and
[0029] It is determined whether the collision risk marking line touches the edge of the marked target static image, and whether there is a collision risk for the vehicle door is determined according to the determination result.
[0030] Optionally, acquiring the static image of the vehicle door facing the target and marking the static image of the target includes:
[0031] Acquire a static image of the door facing the target;
[0032] Select the entire target static image for annotation;
[0033] The determining whether the collision risk marking line touches the edge of the marked target static image, and determining whether the vehicle door has a collision risk according to the determination result, includes:
[0034] If it is determined that the collision risk marking line touches the edge of the framed target static image, it is determined that there is a collision risk for the vehicle door, and the vehicle door is controlled to stop.
[0035] Optionally, after the vehicle door is controlled to stop, a warning prompt message is output; wherein the warning prompt message includes at least one of text, voice, and light.
[0036] The present application also provides a computer-readable storage medium having a program stored thereon, and when the program is executed by a processor, the vehicle door control method as described in any one of the above embodiments is implemented.
[0037] The present application also provides a vehicle door control system, comprising: one or more processors, for implementing a vehicle door control method as described in any one of the above embodiments.
[0038] The present application also provides a vehicle, comprising: a door control system as described in the above embodiment.
[0039] The door control method, control system, automobile and storage medium of the embodiment of the present application. The door control method monitors the idle computing power of the vehicle to determine whether the idle computing power of the vehicle meets the three-dimensional computing power requirements, and executes a three-dimensional anti-collision strategy if it meets the requirements, and executes a two-dimensional anti-collision strategy if it does not meet the requirements, wherein in the three-dimensional anti-collision strategy or the two-dimensional anti-collision strategy, if it is determined that there is a risk of collision during the opening of the door, the door is controlled to stop. With such a configuration, regardless of whether the idle computing power of the vehicle is sufficient, the door of the vehicle can be predicted for anti-collision, so that different vehicle models can be matched and the usage scenarios are increased; and when there is a risk of collision during the opening of the door, the door is controlled to stop, which can avoid hitting the bottom edge of the door, reduce maintenance costs, and avoid unnecessary damage caused by hitting people or vehicles passing close to the door. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 Shown is a flow chart of an embodiment of a vehicle door control method of the present application.
[0041] Figure 2 Shown Figure 1 A flowchart of the three-dimensional anti-collision strategy of the door control method shown.
[0042] Figure 3 Shown Figure 1 A flowchart of a two-dimensional collision avoidance strategy for a door control method is shown.
[0043] Figure 4 Shown is a functional block diagram of an embodiment of a vehicle door control system of the present application. DETAILED DESCRIPTION
[0044] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0045] The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit this application. Unless otherwise defined, the technical terms or scientific terms used in this application should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the specification and claims of this application do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one" or "one" do not indicate a quantity limit, but indicate that there is at least one. "Multiple" or "several" means at least two. Unless otherwise specified, words such as "front", "rear", "lower" and / or "upper" are only for convenience of explanation and are not limited to one position or one spatial orientation. Words such as "include" or "comprise" mean that the elements or objects appearing in front of "include" or "comprise" include the elements or objects listed after "include" or "comprise" and their equivalents, and do not exclude other elements or objects. Words such as "connect" or "connected" are not limited to physical or mechanical connections, and can include electrical connections, whether direct or indirect.
[0046] The singular forms "a", "an", "the" and "said" used in this specification and the appended claims are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.
[0047] The embodiment of the present application provides a door control method, a control system, a car and a storage medium. The door control method includes: monitoring the idle computing power of the vehicle; judging whether the idle computing power of the vehicle meets the three-dimensional computing power requirement; if it meets the requirement, executing the three-dimensional anti-collision strategy; if it does not meet the requirement, executing the two-dimensional anti-collision strategy; wherein in the three-dimensional anti-collision strategy or the two-dimensional anti-collision strategy, if it is determined that there is a risk of collision during the opening of the door, the door is controlled to stop.
[0048] The door control method of the embodiment of the present application monitors the idle computing power of the vehicle to determine whether the idle computing power of the vehicle meets the three-dimensional computing power requirements, and executes the three-dimensional anti-collision strategy if it meets the requirements, and executes the two-dimensional anti-collision strategy if it does not meet the requirements, wherein in the three-dimensional anti-collision strategy or the two-dimensional anti-collision strategy, if it is determined that there is a risk of collision during the opening of the door, the door is controlled to stop. With such a setting, regardless of whether the idle computing power of the vehicle is sufficient, the door of the vehicle can be predicted for anti-collision, so that different models can be matched and the usage scenarios are increased; and when there is a risk of collision during the opening of the door, the door is controlled to stop, which can avoid hitting the lower edge of the door, reduce maintenance costs, and avoid unnecessary damage caused by hitting people or vehicles passing by close to the door.
[0049] Figure 1 FIG. 1 is a flow chart of an embodiment of the vehicle door control method of the present application. Figure 1 As shown, the door control method includes steps S1 to S6. Step S3 or step S4 is executed after step S2, and step S5 is executed after step S3 or step S4.
[0050] Step S1, monitor the vehicle's idle computing power. Vehicle idle computing power refers to the computing power that can be provided by the on-board computer when the vehicle is not running. In this embodiment, the vehicle is equipped with an on-board computer and multiple sensors, which use multiple sensors to collect various data during the vehicle's driving process and transmit them to the on-board computer for processing and analysis. When the vehicle is parked or these computing resources are not used while driving, these resources can be the vehicle's idle computing power. By monitoring the vehicle's real-time vehicle idle computing power, the actual vehicle idle computing power of the vehicle can be understood, which is conducive to the subsequent selection of a more suitable anti-collision strategy.
[0051] Step S2: Determine whether the idle computing power of the vehicle meets the three-dimensional computing power requirement. Since the spatial perception ability of the three-dimensional space is strong, it involves processing and analyzing the depth information of the target image. The required three-dimensional computing power requirement involves larger-scale data and more complex computing tasks, so higher computing resources and computing power support are required. This embodiment prioritizes the selection of a three-dimensional collision avoidance strategy by first determining whether the idle computing power of the vehicle meets the three-dimensional computing power requirement.
[0052] If the requirements are met, then execute step S3. Step S3: Execute the three-dimensional anti-collision strategy. When the three-dimensional computing power requirements are met, execute the three-dimensional anti-collision strategy. The three-dimensional collision strategy uses the three-dimensional space to process and analyze the depth information of the target image to make the acquired data more accurate.
[0053] If not, execute step S4. Step S4, execute the two-dimensional anti-collision strategy. In the case of insufficient three-dimensional computing power, execute the two-dimensional anti-collision strategy. This two-dimensional anti-collision strategy uses the low computing power and high timeliness characteristics of two-dimensional images, and is used as an alternative when the three-dimensional computing power is insufficient, which is conducive to adapting to more car models and increasing application scenarios.
[0054] In the three-dimensional anti-collision strategy of step S3 or the two-dimensional anti-collision strategy of step S4, if it is determined that there is a risk of collision during the opening of the door, step S5 is executed. Step S5, control the door to stop. In this embodiment, if it is determined that there is a risk of collision during the opening of the door, the door is controlled to stop, which can avoid hitting the lower edge of the door, reduce maintenance costs, and avoid unnecessary damage caused by hitting people or vehicles passing close to the door.
[0055] exist Figure 1 In the illustrated embodiment, after the door is controlled to stop, step S6 is executed. Step S6, output warning prompt information. The warning prompt information includes at least one of text, voice, and light. In this embodiment, when it is determined that there is a risk of collision within the opening range of the door, the risk of collision is notified through a text prompt, and an alarm prompt is given by controlling the lights of the vehicle. In some other embodiments, light prompts, voice prompts, text prompts, and animation prompts are supported during the door opening / closing process. When it is determined that there is a risk of collision within the opening range of the door, the door will automatically stop and give light and sound prompts, there will also be corresponding text prompts, and an operation button for opening / closing the door will be provided for the user to select and execute after judgment. When the driver intervenes and makes a judgment, it is allowed to execute the previous cycle of opening / closing the door again; it is also allowed to re-execute the opening / closing of the door. The above-mentioned door can be a spare door of the vehicle or a side door of the vehicle, which is not limited in this application.
[0056] In the above scheme, the three-dimensional anti-collision strategy is prioritized by first judging whether the vehicle's idle computing power meets the three-dimensional computing power requirements. In the case of insufficient three-dimensional computing power requirements, the two-dimensional anti-collision strategy is implemented as an alternative, which is conducive to adapting to more vehicle models and increasing application scenarios. Regardless of whether the vehicle's idle computing power is sufficient, the vehicle's doors can be predicted for anti-collision, and different vehicle models can be matched. When there is a risk of collision during the door opening process, the door is controlled to stop, which can avoid hitting the bottom edge of the door, reduce maintenance costs, and avoid unnecessary damage caused by hitting people or vehicles passing close to the door, thereby improving the safety of door opening.
[0057] Figure 2 Shown Figure 1 Flow chart of the three-dimensional anti-collision strategy of the door control method shown in FIG. Figure 1 and Figure 2 As shown, the three-dimensional anti-collision strategy includes steps S31 to S34.
[0058] Step S31, obtain the environmental depth information of the environment around the door, and the positive image of the door facing the target. In step S31, first obtain multiple frames of environmental images of the environment around the door and the motion state information of the vehicle. Then reconstruct and fuse the multiple frames of environmental images. Finally, obtain the environmental depth information of the environment around the door based on the fused image and the running state information of the vehicle. In this embodiment, the vehicle's on-board rear camera, rear surround camera, GPS (Global Positioning System) and IMU (Inertial measurement unit) are used to obtain the environmental depth information of the environment around the door and the positive image of the door facing the target. The environmental depth information refers to the distance between each point in the environment around the door and the camera, which can be used to indicate the distance between each point in the environment around the door and the camera. The target positive image represents the image captured by the camera perspective, which can be such as building fire protection accessories, walls, charging piles, pipes, green plants, parking space limiters, rear vehicles or passers-by, etc., which are not limited in this application.
[0059] Step S32: Fusing the acquired environment depth information with the target forward image to add the environment depth information to the target forward image. In this way, a target forward image carrying depth information can be obtained, and the depth information is beneficial to subsequent three-dimensional reconstruction and spatial analysis.
[0060] Step S33, determine the spatial coordinate information of the target forward image according to the target forward image carrying the environmental depth information. In step S33, first determine the initial spatial coordinate information of the target forward image according to the target forward image carrying the environmental depth information. Then, the point cloud fusion image after the fusion of the environmental depth information and the target forward image is meshed, meshed and optimized, and texture mapped to optimize the initial spatial coordinate information. Finally, the optimized initial coordinate information is determined as the final spatial coordinate information. In this embodiment, according to the fused target forward image and the environmental depth information, the preliminary spatial coordinate information of the target forward image is calculated by a corresponding algorithm or method, and the preliminary spatial coordinate information indicates the position and posture of the target forward image. Then, accurate spatial coordinate information can be obtained by meshing the point cloud fusion image, meshing and texture mapping. With this arrangement, the spatial coordinate information of the determined target forward image is more accurate, which is conducive to predicting the risk of collision.
[0061] Step S34, match the spatial coordinate information of the target positive image with the edge position of the door in the open state, and determine whether there is a collision risk during the opening process of the door based on the matching result. In step S34, first determine whether the distance between the edge position of the door in the open state and the spatial coordinate information is less than the interval threshold. The distance between the edge position and the spatial coordinate information refers to the distance between the edge of the door when it is fully opened and the spatial coordinate information. The interval threshold is pre-set. If it is less than the interval threshold, it means that during the opening process of the door, the edge of the door in the open state may touch the target positive image, and there is a collision risk. At this time, step S5 is executed, that is, the door is controlled to stop, and the collision risk of the door during the opening process can be predicted in advance to reduce unnecessary damage. If it is not less than the interval threshold, it means that the door will not touch the target positive image during the opening process, there is no collision risk, and the door is controlled to continue to open.
[0062] Figure 3 Shown Figure 1 The flowchart of the two-dimensional collision avoidance strategy of the door control method shown in FIG. Figure 1 and Figure 3 As shown, the two-dimensional anti-collision strategy includes steps S41 to S43.
[0063] Step S41, projecting the edge position of the door in the open state onto the ground as a collision risk marking line. In this embodiment, a grating projection module is provided in the vehicle, and the edge position of the door is projected as a collision risk marking line during the opening process of the door. Since the door opens from bottom to top, the collision risk marking line also moves dynamically. The collision risk marking line moves from near to far in the horizontal direction and from bottom to top in the vertical direction as the door opens. Marking the edge position of the door in the open state is conducive to real-time judgment of collision risk.
[0064] Step S42, obtain the target static image of the vehicle door, and mark the target static image. In step S42, first obtain the target static image of the vehicle door. Then select the entire target static image for marking. In this embodiment, the rear-facing camera of the vehicle is used to obtain the target static image. The target static image represents the static image captured by the rear-facing camera. After obtaining the target static image, the entire target static image is framed, and the entire target static image is framed in the marking frame.
[0065] Step S43, determine whether the collision risk marking line touches the edge of the marked target static image, and determine whether the door has a collision risk based on the judgment result. Determine whether the collision risk marking line touches the edge of the marked target static image to determine whether the door has a collision risk. It does not require too much idle computing power of the vehicle. This prediction method is simple and fast. In step S43, if it is determined that the collision risk marking line touches the edge of the framed target static image, it is determined that the door has a collision risk, and step S5 is executed, that is, the door is controlled to stop. Since the door opens from bottom to top, the collision risk marking line moves from near to far in the horizontal direction with the door, and moves from bottom to top in the vertical direction. If the collision risk marking line touches the edge of the frame of the entire target static image during the door opening process, it means that there is a collision risk. At this time, the door is controlled to stop, which can avoid hitting the bottom edge of the door, reduce maintenance costs, and avoid unnecessary damage caused by hitting people or vehicles passing by close to the door. In step S43, if it is determined that the collision risk marking line does not touch the edge of the framed target static image, it means that there is a sufficient distance between the target static image and the vehicle door and no collision will occur. It is determined that there is no collision risk for the vehicle door and the vehicle door is controlled to continue to open.
[0066] This application adds a two-dimensional collision avoidance strategy on the basis of the three-dimensional collision avoidance strategy. When the idle computing power of the vehicle is insufficient, the two-dimensional collision avoidance strategy is used to distinguish the characteristics of the static image of the target. Compared with the three-dimensional collision avoidance strategy, the idle computing power required to execute the two-dimensional collision avoidance strategy is lower, and the method is simple and fast. This ensures that the vehicle can effectively and quickly detect the target behind the vehicle regardless of whether the idle computing power of the vehicle is sufficient, and it can be adapted to different models.
[0067] The present application also provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the above Figures 1 to 3 The door control method shown in the embodiment. In some embodiments, the computer-readable storage medium may be an internal storage unit of the aforementioned vehicle, such as a hard disk or a memory. The computer-readable storage medium may also be an external storage device of the vehicle, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), an SD card, a flash card (Flash Card), etc. equipped on the device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the vehicle and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the vehicle, and may also be used to temporarily store data that has been output or is to be output. From a hardware perspective, such as Figure 4 As shown, it is a hardware structure diagram of the vehicle in which the processor of the present application is located, except Figure 4 In addition to the processor, memory, network interface, and non-volatile memory shown, the vehicle in which the control system is located in the embodiment may also include other hardware according to the actual functions of the vehicle, which will not be described in detail.
[0068] The present application also provides a door control system, comprising: one or more processors for implementing the above Figures 1 to 3 The door control method of any one of the embodiments shown. For the system embodiments, they basically correspond to the method embodiments, so please refer to the partial description of the method embodiments for the relevant parts. The system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present application. A person of ordinary skill in the art may understand and implement it without creative work.
[0069] The vehicle includes a door control system. The vehicle uses the door control system to implement Figures 1 to 3The door control method described in any one of the above. This application will utilize a vehicle body visual camera, such as an ADAS rear-facing camera and a rear surround view camera; by picking up environmental features with the camera, the environmental features of the vehicle during the door opening process are determined, including: environmental targets and the distance between the targets and the vehicle, thereby constructing a three-dimensional space between the vehicle and the environmental targets; during the door opening process, the door movement trajectory is continuously tracked to reduce the risk of collision with the nearest target. At the same time, in order to ensure the real-time performance of target recognition, the idle computing power of the vehicle is monitored before the calculation. When the idle computing power of the vehicle is insufficient, a two-dimensional image target recognition algorithm is used. The low computing power and high timeliness characteristics of the two-dimensional image are utilized to ensure collision avoidance of risky targets behind the vehicle during the dynamic process of door opening. If the computing power is sufficient, target judgment can be performed according to three-dimensional modeling. Comprehensively utilize visual two-dimensional and three-dimensional space, and reasonably allocate two-dimensional algorithms or three-dimensional algorithms according to the actual idle computing power of the vehicle. When the vehicle's idle computing power is sufficient, a three-dimensional space algorithm is used to predict the collision of the target's forward image. At the same time, a two-dimensional space algorithm is used as a backup solution. When the vehicle's idle computing power is low, the target image in the direction facing the vehicle door is recognized in real time to ensure the response speed and accuracy of all functions. Avoid collisions with objects in the environment during the opening of the vehicle door to reduce the risk of vehicle damage, and avoid collisions with people passing behind during the opening of the vehicle door to avoid personal injury. At the same time, the attention to potential dangerous environments for the risk of door opening collisions is increased to reduce the risk of accidents. Improve vehicle interaction, achieve the ultimate pursuit of intelligent vehicle interaction, and enhance brand power.
[0070] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.
Claims
1. A door control method, characterized in that: include: Monitor the vehicle's idle computing power; Determining whether the idle computing power of the vehicle meets the three-dimensional computing power requirements; If satisfied, the three-dimensional collision avoidance strategy is executed; If not, the two-dimensional collision avoidance strategy is executed; Wherein in the three-dimensional anti-collision strategy or the two-dimensional anti-collision strategy, if it is determined that there is a risk of collision when the vehicle door is opened, the vehicle door is controlled to stop.
2. The vehicle door control method according to claim 1, characterized in that: The three-dimensional anti-collision strategy includes: Acquire the environmental depth information of the environment around the vehicle door and the positive image of the vehicle door facing the target; Fusing the acquired environment depth information with the target forward image to add the environment depth information to the target forward image; Determining spatial coordinate information of the target forward image according to the target forward image carrying the environment depth information; and The spatial coordinate information of the target forward image is matched with the edge position of the vehicle door in the open state, and whether there is a collision risk during the opening process of the vehicle door is determined according to the matching result.
3. The vehicle door control method according to claim 2, characterized in that: The determining, according to the target forward image carrying the environment depth information, the spatial coordinate information of the target forward image comprises: Determining initial spatial coordinate information of the target forward image according to the target forward image carrying the environment depth information; and Performing mesh reconstruction, mesh optimization and texture mapping processing on the point cloud fusion image obtained by fusing the environment depth information with the target forward image, so as to optimize the initial space coordinate information; and The optimized initial coordinate information is determined as the final spatial coordinate information.
4. The vehicle door control method according to claim 3, characterized in that: The step of matching the spatial coordinate information of the target forward image with the edge position of the door in the open state, and determining whether there is a collision risk during the opening process of the door according to the matching result, includes: Determining whether the distance between the edge position of the door in the open state and the spatial coordinate information is less than an interval threshold; If it is less than the interval threshold, it indicates that there is a risk of collision when the door is opened, and the door is controlled to stop.
5. The vehicle door control method according to claim 2, characterized in that: The step of obtaining the environmental depth information of the environment surrounding the vehicle door includes: Acquire multiple frames of environmental images of the environment around the vehicle door and motion state information of the vehicle; Performing dense reconstruction and fusion on the multiple frames of environment images; and The environmental depth information of the environment around the door is obtained according to the fused image and the running status information of the vehicle.
6. The vehicle door control method according to claim 1, characterized in that: The two-dimensional collision avoidance strategy includes: Projecting the edge position of the door in the open state onto the ground to calibrate it as a collision risk marking line; Acquire a static image of the target facing the vehicle door, and mark the static image of the target; and It is determined whether the collision risk marking line touches the edge of the marked target static image, and whether there is a collision risk for the vehicle door is determined according to the determination result.
7. The vehicle door control method according to claim 6, characterized in that: The step of obtaining the static image of the vehicle door facing the target and marking the static image of the target includes: Acquire a static image of the door facing the target; Select the entire target static image for annotation; The determining whether the collision risk marking line touches the edge of the marked target static image, and determining whether the vehicle door has a collision risk according to the determination result, includes: If it is determined that the collision risk marking line touches the edge of the framed target static image, it is determined that there is a collision risk for the vehicle door, and the vehicle door is controlled to stop.
8. The vehicle door control method according to claim 1, characterized in that: After the vehicle door is controlled to stop, a warning prompt message is output; wherein the warning prompt message includes at least one of text, voice, and light.
9. A computer-readable storage medium, characterized in that: A program is stored thereon, and when the program is executed by a processor, the vehicle door control method as claimed in any one of claims 1 to 8 is implemented.
10. A vehicle door control system, characterized in that: include: One or more processors, used to implement the vehicle door control method as described in any one of claims 1 to 8.
11. A vehicle, characterized in that: include: The door control system as claimed in claim 10.