Vehicle starting control method and device, vehicle and storage medium

Abstract

The invention provides a vehicle starting control method and device, a vehicle and a storage medium, the method is applied to the technical field of intelligent auxiliary driving, and when the vehicle is braked at an intersection with a traffic signal lamp, based on preset calling priorities corresponding to a plurality of cameras in the vehicle, the vehicle is started according to the preset calling priorities. Sequentially judging whether the traffic signal lamp is located in the image acquisition range of each camera or not; if it is judged that the target camera with the traffic signal lamp located in the image acquisition range exists, the signal lamp state of the traffic signal lamp is acquired through the target camera, and the signal lamp state is that the green lamp is turned on or not turned on; and when the signal lamp is in a green light state, controlling the vehicle to start. When the vehicle is braked at the intersection, the system can automatically judge and activate the most suitable camera to perform relay detection according to the priority sequence, so that the problem of green light leak detection caused by view limitation of a single camera is solved, the system can stably capture the traffic light passing authority information at various parking positions, and unnecessary manual takeover is reduced.

Description

Technical Field

[0001] The present application relates to the field of intelligent assisted driving, and more specifically, to a vehicle starting control method, device, vehicle and storage medium in the vehicle field. Background Art

[0002] To meet the diverse scenarios and demands of the current market, intelligent vehicle services are becoming an increasingly important core element of the automotive industry. As a key intelligent function serving users, the development of intelligent assisted driving is increasingly focused on implementing features and optimizing the user experience in complex urban scenarios. Urban traffic conditions are dynamic and complex, with numerous intersections, pedestrians, and other vehicles. This poses a significant challenge to intelligent assisted driving systems, and ensuring safe and efficient vehicle operation at intersections has become a key research issue. Summary of the Invention

[0003] The present application provides a vehicle starting control method, device, vehicle and storage medium, which can solve the technical problem of inaccurate signal light status detection results in related technologies.

[0004] In a first aspect, a method for vehicle starting control is provided, the method comprising:

[0005] When the vehicle stops at an intersection with a traffic light, the vehicle determines whether the traffic light is within the image acquisition range of each camera based on the preset call priority corresponding to the multiple cameras in the vehicle.

[0006] If it is determined that there is a target camera within the image acquisition range of the traffic light, the signal light state of the traffic light is captured by the target camera, and the signal light state is green or not;

[0007] When the signal light is green, the vehicle is controlled to start.

[0008] The beneficial effects brought about by the technical solution of the first aspect above include at least the following: when a vehicle stops at an intersection, the system can automatically determine and activate the most appropriate camera for relay detection based on the priority order, and obtain the signal light status through the camera that can accurately detect the signal light, so that the vehicle can accurately control its own starting when the green light comes on. The necessary cameras are activated step by step according to the priority to collect signal light information, and the abundant camera resources in the vehicle are used to compensate for the blind spots of the cameras in the previous stage. This solves the problem of missed green light detection caused by the limited field of view of a single camera, ensures that the system can stably capture the access permission information indicated by the signal light in various parking positions, and reduces unnecessary manual takeover due to signal light detection failure. At the same time, this adaptive camera activation and detection mechanism can dynamically schedule the camera working status based on real-time scene requirements, and realizes on-demand camera resource management while ensuring the reliability of signal light detection results.

[0009] In some possible implementations, the vehicle includes at least a front-view camera and a first side-view camera located on the same side as the traffic light, and the front-view camera has a higher calling priority than the first side-view camera in the preset calling priority.

[0010] Through the technical solutions in the above possible implementation methods, the vehicle has at least a front-view camera and a first side-view camera located on the same side of the vehicle as the traffic light. When the vehicle is controlled, the front-view camera has a higher calling priority than the first side-view camera, that is, the status of the traffic light is obtained through the forward-view perception system in priority. When the field of view of the forward-view perception system is limited, the side-view perception camera on the same side as the traffic light is further used to supplement the information collection of the forward blind spot, thereby ensuring the accuracy of detection and making more rational use of various types of camera resources in the vehicle.

[0011] In some possible implementations, the above-mentioned preset calling priorities corresponding to multiple cameras in the above-mentioned vehicle are used to determine in sequence whether the above-mentioned traffic light is within the image acquisition range of each camera, including: determining whether the above-mentioned traffic light is within the image acquisition range of the front-view camera; if the above-mentioned traffic light is within the image acquisition range of the above-mentioned front-view camera, determining that the above-mentioned front-view camera is the target camera; if the above-mentioned traffic light is outside the image acquisition range of the above-mentioned front-view camera, determining whether the above-mentioned traffic light is within the image acquisition range of the first side-view camera; if the above-mentioned traffic light is within the image acquisition range of the above-mentioned first side-view camera, determining that the above-mentioned first side-view camera is the target camera.

[0012] Through the technical solutions in the above possible implementations, the vehicle first determines whether the traffic light is within the image acquisition range of the forward-facing camera. This prioritizes the forward-facing perception system when it can accurately capture the light status, reducing unnecessary camera resource usage and conserving vehicle energy. If the forward-facing perception system is unable to accurately capture the light status, the first side-view camera is further activated to supplement the forward-facing perception system's blind spots, enabling accurate traffic light recognition and subsequent precise control of the start.

[0013] In some possible implementations, the vehicle further includes at least a second side-view camera located on a different side from the traffic light, and the method further includes: if the traffic light is outside the image acquisition range of the first side-view camera, determining whether there is a reference traffic light within the image acquisition range of the second side-view camera at the intersection; if there is a reference traffic light within the image acquisition range of the second side-view camera, capturing a reference light state of the reference traffic light through the second side-view camera, the reference light state being either green on or off; and controlling the vehicle to start based on the reference light state.

[0014] Through the technical solutions in the above possible implementations, if the vehicle also includes at least a second side-view camera located on a different side from the traffic light, and the current-view camera and the first side-view camera on the same side of the traffic light are insufficient to capture the status of the traffic light, the second side-view camera on the other side can be used to collect the status of other reference traffic lights at the intersection. This allows for blind spot detection on the other side of the traffic light by using other traffic lights at the intersection and the vehicle's other cameras, thereby enriching the vehicle's signal light information sources and improving the accuracy and robustness of the vehicle's launch control function.

[0015] In some possible implementations, the above-mentioned control of the vehicle starting based on the above-mentioned reference light status includes: if the above-mentioned reference light status is the same as the above-mentioned signal light status at the same time, then controlling the above-mentioned vehicle to start when the above-mentioned reference light status is the green light on; if the above-mentioned reference light status is opposite to the above-mentioned signal light status at the same time, then controlling the above-mentioned vehicle to start after a preset time period when the above-mentioned reference light status is the green light not on.

[0016] Through the technical solutions in the above possible implementation methods, there are two possible situations for other signal lights that can be used as reference at the intersection: if the instantaneous state of the reference signal light is the same as the instantaneous state of the traffic signal light at the same moment, it means that the vehicle should also control its own vehicle to start when the green light of the reference signal light is on; on the other hand, if the instantaneous state of the reference signal light is opposite to the instantaneous state of the traffic signal light at the same moment, it means that the vehicle should control its own vehicle to start when the green light of the reference signal light is not on. At this time, considering the existence of red and yellow lights, a delayed start mechanism with a preset time length is formulated for the vehicle to increase the vehicle's fault tolerance when responding to the instructions of opposite signal lights.

[0017] In some possible implementations, the method further includes: if there is no reference signal light within the image acquisition range of the second side-view camera, issuing a manual vehicle control prompt message in a preset prompt mode, wherein the preset prompt mode includes at least one of a voice prompt and a visual graphic prompt.

[0018] Through the technical solutions in the above possible implementation methods, when the vehicle cannot collect reliable traffic light status through the front-view camera and the side-view cameras on both sides, a variety of notification prompts are used to promptly remind the user to manually take over the vehicle and manually control the vehicle to ensure the driving safety of the vehicle and the user at the intersection.

[0019] In some possible implementations, before the vehicle brakes to a stop at an intersection with a traffic light, the method further includes: in response to an activation instruction for the intelligent assisted driving function, starting the intelligent assisted driving function, and controlling the vehicle to brake to a stop when the vehicle drives to an intersection with a traffic light and the traffic light is in a green light that is not on.

[0020] Through the technical solutions in the above possible implementation methods, the vehicle can activate the intelligent assisted driving function based on user instructions. Based on the intelligent assisted driving function, the vehicle can autonomously control its own brakes to stop when it drives to an intersection with a traffic light and the traffic light is green and not on. This enables the vehicle to have a complete and reliable autonomous intersection passage function.

[0021] In a second aspect, a vehicle starting control device is provided, the device comprising:

[0022] A camera calling module is used to determine, when a vehicle stops at an intersection with a traffic light, whether the traffic light is within the image acquisition range of each camera based on the preset calling priorities corresponding to multiple cameras in the vehicle;

[0023] A signal status acquisition module is configured to acquire the signal status of the traffic light through the target camera if it is determined that the traffic light is located within the image acquisition range, where the signal status is green or not;

[0024] The starting control module is used to control the vehicle to start when the signal light is green.

[0025] In a third aspect, a vehicle is provided, comprising a memory for storing executable program code; and a processor for calling and running the executable program code from the memory, so that the vehicle executes the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0026] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0027] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 An example image of a traffic light status captured by a single perception system in a vehicle according to an embodiment of the present application;

[0029] Figure 2 An exemplary system architecture diagram of a vehicle start control method provided in an embodiment of the present application;

[0030] Figure 3 A schematic flow chart of a vehicle starting control method provided in an embodiment of the present application;

[0031] Figure 4 A schematic diagram of a framework for an intelligent assisted driving function of a vehicle provided in an embodiment of the present application;

[0032] Figure 5 An example diagram of a perception system in a vehicle provided in an embodiment of the present application;

[0033] Figure 6 A schematic flow chart of a vehicle starting control method provided in an embodiment of the present application;

[0034] Figure 7 A schematic structural diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] To make the features and advantages of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0036] When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments 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. And in the description of the embodiments of the present application, unless otherwise indicated, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" refers to two or more than two.

[0037] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0038] With the continuous development of the automotive industry, intelligent vehicle services have become a core element in enhancing user experience and market competitiveness. In this context, intelligent assisted driving, a key intelligent function designed to assist users in driving their vehicles, faces a critical development challenge. Urban environments, with their dense road networks, frequent intersections, and dynamic and ever-changing traffic, effectively address these complex scenarios and enhance the user experience.

[0039] Specifically, in actual application, when a vehicle is driving on urban roads using the intelligent assisted driving function, when approaching a small intersection, after detecting a red light signal on the side (such as the side of the intersection) and completing the braking to a stop line in accordance with regulations, if the green light indicating the vehicle's straight ahead direction is on at this time, the system cannot autonomously control the vehicle to start and pass, and the driver must manually take over the operation to pass the intersection. This leads to the interruption of the continuity of the intelligent assisted driving function, and the lagging and inconsistent start control also hinders normal traffic operation, significantly reducing user trust and user satisfaction.

[0040] The main reason for this problem is the limited field of view of the vehicle's perception system. While driving, the vehicle generally uses a forward perception system (usually consisting of multiple cameras with different field of view) to collect and judge the road conditions in front of the vehicle to control the vehicle's braking and starting. Therefore, when approaching an intersection from a distance, the forward perception system also continuously detects the red light signal at the intersection. Figure 1 , Figure 1 The embodiment of the present application provides a single perception system in a vehicle to collect example images of the state of a traffic light. Figure 1 As shown in the figure, when the vehicle finally stops at the stop line, the zebra crossing ahead appears trapezoidal due to lens distortion. Due to the parking position, the vehicle can only see the traffic light on the right side of the intersection, and the longitudinal distance to the traffic light is very close. This traffic light target is easily beyond the effective coverage of the forward-looking narrow-angle camera (field of view approximately 30°) and may be at the edge of the field of view of the forward-looking wide-angle camera (field of view approximately 120°). At the edge of the wide-angle camera's field of view, the accuracy and stability of traffic light detection are significantly negatively affected. The forward perception system struggles to collect accurate traffic light information, resulting in signal misses. In this case, if the intelligent assisted driving control system fails to reliably detect a green light, it conservatively uses the last valid traffic light status information (i.e., the red light) as the basis for vehicle control. Therefore, even if the actual right of way has changed to green, the system still determines that the stop and wait command should be executed based on the outdated red light information. Ultimately, the vehicle cannot start autonomously when the light turns green, resulting in unnecessary manual control.

[0041] Therefore, an embodiment of the present application provides a vehicle starting control method to solve the above-mentioned technical problem of inaccurate signal light status detection results.

[0042] See also Figure 2 , Figure 2 This is an exemplary system architecture diagram of a vehicle starting control method provided in an embodiment of the present application.

[0043] like Figure 2 As shown, the system architecture may include a vehicle 201, a network 202, and a server 203. The network 202 is used to provide a medium for a communication link between the vehicle 201 and the server 203. The network 202 may include various types of wireless communication links, such as a near field communication link (NFC), an ultra-wideband communication link (UWB), a Bluetooth communication link, a wireless fidelity (Wi-Fi) communication link, or a microwave communication link.

[0044] The vehicle 201 can interact with the server 203 through the network 202 to receive messages from the server 203 or send messages to the server 203, or the vehicle 201 can interact with the server 203 through the network 202 to receive messages or data sent to the server 203 by other users. The server 203 can be a business server that provides various services. It should be noted that the server 203 can be hardware or software. When the server 203 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server 203 is software, it can be implemented as multiple software or software modules (for example, for providing distributed services), or it can be implemented as a single software or software module, which is not specifically limited here.

[0045] In an embodiment of the present application, when the vehicle brakes to a stop at an intersection with a traffic light, the vehicle 201 determines whether the traffic light is within the image acquisition range of each camera based on the preset call priority corresponding to multiple cameras in the vehicle; if it is determined that there is a target camera with a traffic light within the image acquisition range, the vehicle 201 further collects the signal light status of the traffic light through the target camera, and the signal light status is green or not; when the signal light status is green, the vehicle 201 controls the vehicle to start.

[0046] The system architecture may include the server 203 or may not include the server 203. In other words, the server 203 may be an optional device in the embodiments of this specification, that is, the method provided in the embodiments of this application may be applied to a system structure including only the vehicle 201, and the embodiments of this application do not limit this.

[0047] It should be understood that Figure 2 The number of vehicles, networks, and servers in the figure is only illustrative and can be any number of vehicles, networks, and servers according to implementation requirements.

[0048] See also Figure 3 , Figure 3 This is a flowchart of a vehicle start control method provided in an embodiment of the present application. The execution entity of this embodiment of the present application can be the vehicle executing the vehicle start control, a processor within the vehicle executing the vehicle start control method, or a vehicle start control service within the vehicle executing the vehicle start control method. For ease of description, the specific execution process of the vehicle start control method is described below using the vehicle processor as an example.

[0049] like Figure 3 As shown, the vehicle starting control method may at least include:

[0050] S302. When the vehicle stops at an intersection with a traffic light, based on the preset call priorities corresponding to multiple cameras in the vehicle, it is determined in sequence whether the traffic light is within the image acquisition range of each camera.

[0051] Alternatively, in traditional traffic light detection methods, the limited field of view of a single sensing module can easily lead to missed or incorrect detection of traffic signals, affecting the reliability of the vehicle control function and the user experience. To address this issue, the embodiments of the present application utilize other cameras in the vehicle with different field of view to perform blind spot detection. This allows accurate capture of traffic light authorization information even when a traffic light appears in the blind spot of a single sensing module, thus eliminating unnecessary manual takeover due to failed traffic light detection.

[0052] Furthermore, considering that the various types of body cameras in a vehicle have different field of view accuracy, detection distance, and scene adaptability, and that not all cameras are always in the on state, but rather the working state of each body camera varies according to different functions and needs, for example, the front-view camera is mainly used to identify the road conditions ahead and is usually always working during driving; the surround-view cameras distributed around the vehicle body provide a 360° panoramic view, but the recognition distance is relatively short, so they mainly assist the vehicle in identifying the surrounding environment and usually work when the vehicle is started or a panoramic view is required; the side-view cameras located on the left and right sides are used for blind spot monitoring and lane change assistance and usually work when needed (such as when turning on the turn signal); the rear-view camera is located at the rear of the vehicle to help identify the situation behind the vehicle and usually works when reversing or when rearview is required. Therefore, if all cameras are directly activated at the intersection to identify traffic lights, there will undoubtedly be a waste of resources and unnecessary vehicle energy consumption. Then, in the embodiment of the present application, corresponding calling priorities are pre-set for multiple cameras in the vehicle according to the functions and field of view of each camera, so that when driving to the intersection, necessary cameras are started step by step according to the priority to collect traffic light information, thereby ensuring the reliability of traffic light detection results while realizing on-demand scheduling of camera resource management.

[0053] Specifically, when a vehicle autonomously controls itself using intelligent assisted driving, after braking at a traffic light-controlled intersection, the vehicle will continue to monitor the traffic light indicating straight ahead. At this point, the vehicle first determines the position of the traffic light relative to the vehicle for each camera in the vehicle, based on the preset call priority of the multiple cameras in the vehicle. The determination is then made based on the preset priority order, to determine whether the traffic light is within the camera's image acquisition range.

[0054] In a feasible embodiment, the image acquisition range may refer to the entire range that the camera can capture, or it may refer to the effective acquisition range that the camera can capture and output effective recognition results. Preferably, when the image acquisition range is the effective acquisition range, even if the current camera can capture the image of the traffic light but cannot effectively recognize the status information, it is still determined that the next priority camera needs to be started for blind spot detection, which improves the reliability and accuracy of the traffic light information collected by the vehicle. In this case, the vehicle specifically determines whether the traffic light is within the effective acquisition range of the current camera by comparing the pixel coordinates of the traffic light detected in the camera imaging plane with the effective recognition boundary pre-calibrated by the camera. The effective recognition boundary is specifically calibrated by the functional parameters of the camera and the corresponding image processing module, and the embodiments of the present application do not specifically limit this.

[0055] S304: If it is determined that there is a target camera with a traffic light within the image acquisition range, the target camera is used to capture the traffic light status, where the traffic light status is green or not.

[0056] Optionally, by setting the above-mentioned call priority for each camera on the vehicle body, the embodiment of the present application can dynamically schedule the camera working status based on real-time scene requirements. When, in the judgment link of a certain priority camera, it is found that the traffic light is within the image acquisition range, then the camera is used as the target camera to collect the signal light status of the traffic light, so that the vehicle control start logic can be executed according to whether the green light is on or not. When, in the judgment link of a certain priority camera, it is found that the imaging position of the traffic light is beyond the field of view boundary because the vehicle is parked too close, that is, it is not within the image acquisition range, it will automatically switch to the next priority camera to continue judgment. If the traffic light target is identified at this time and it falls within the preset valid image acquisition range, the camera judged at this time is determined to be the target camera, and the signal light status of the traffic light is collected, so that the vehicle control start logic can be executed according to whether the green light is on or not.

[0057] Specifically, when a target camera captures the signal status of a traffic light, the vehicle activates the target camera's dedicated image acquisition and analysis module, processing the output video stream in real time. This module then intercepts the region of interest (ROI) containing the signal light from the live video stream. This ROI can be identified directly by pixel color or by using a deep learning-based signal status classification model. By establishing a camera call priority strategy that matches the vehicle's physical layout and functional characteristics, the problem of target loss caused by a single camera's blind spot is effectively overcome.

[0058] In one feasible embodiment, if the traffic light status is identified directly based on the pixel color in the image, the proportion distribution of green pixels can be extracted. When the proportion of green pixels reaches a preset threshold and a preset shape, such as a circular or arrow-shaped traffic light outline, is detected through a shape and contour matching algorithm, it is determined that "the green light is on"; if the proportion of green pixels reaches a preset threshold, it is determined that "the green light is not on", and traffic light states such as red light, yellow light, and fault state are all classified as "green light is not on". In another feasible embodiment, if the traffic light status is identified through a pre-trained traffic light status classification model, the model can be controlled to perform color space conversion, brightness normalization, and stroboscopic filtering pre-processing on the captured image, and then output the current traffic light status classification result. The status classification result includes two status types: "green light is on" and "green light is not on", the latter of which includes red light, yellow light, and fault state.

[0059] S306: When the traffic light turns green, the vehicle starts to move.

[0060] Optionally, see Figure 4 , Figure 4 This is a schematic diagram of a framework for a vehicle intelligent assisted driving function provided by an embodiment of the present application. Figure 4 As shown, when the vehicle realizes the intelligent assisted driving function, the external environment information is collected through the camera in the intelligent assisted driving perception system, and the intelligent assisted driving control system performs action judgment according to the external environment information. The vehicle steering system is responsible for responding to the lateral control request issued by the intelligent assisted driving control system: steering request to achieve steering; the vehicle braking system is responsible for responding to the longitudinal control request issued by the intelligent assisted driving control system: braking request to achieve braking; the vehicle power system is responsible for responding to the longitudinal control request issued by the intelligent assisted driving control system: torque request to achieve starting and driving.

[0061] Specifically, if and only if the traffic light is green, the intelligent assisted driving module determines that the vehicle should start and continue driving. At this point, it autonomously generates a start control command, which sends a brake release command to the vehicle's braking system. This command first releases the parking brake, then sends a torque request to the vehicle's powertrain to initiate the start. Initially, the vehicle maintains a low speed. During the start, the vehicle continuously monitors traffic light status and road conditions. If the green light remains stable and the road conditions are normal, acceleration is gradually increased to the preset cruise control value. If a sudden change in status is detected (such as a yellow light or an obstacle), deceleration planning is immediately triggered or the driver is prompted to manually take over control of the vehicle to ensure the safety of the vehicle and its users.

[0062] In an embodiment of the present application, a vehicle start control method is provided. When a vehicle stops at an intersection with a traffic light, the system determines, based on the preset call priorities corresponding to multiple cameras in the vehicle, whether the traffic light is within the image acquisition range of each camera. If a target camera is determined to have a traffic light within the image acquisition range, the target camera is used to capture the traffic light status, which can be either green or off. The vehicle is controlled to start when the light is green. When the vehicle stops at an intersection, the system automatically determines and activates the most appropriate camera based on the priority order for relay detection. The camera that can accurately detect the traffic light acquires the traffic light status, allowing the vehicle to accurately control its own start when the green light is on. Necessary cameras are activated step by step according to priority to collect traffic light information. The vehicle's abundant camera resources are utilized to compensate for the blind spots of the previous camera, resolving the problem of missed green light detection due to the limited field of view of a single camera. This ensures that the system can reliably capture the traffic light's access information at various parking positions and reduces unnecessary manual control due to traffic light detection failures. At the same time, this adaptive camera activation and detection mechanism can dynamically schedule the camera's working status based on real-time scene requirements, and realize on-demand camera resource management while ensuring the reliability of traffic light detection results.

[0063] See also Figure 5 , Figure 5 This is an example diagram of a perception system in a vehicle provided in an embodiment of the present application. Figure 5 As shown, in the embodiment of the present application, the vehicle includes at least a plurality of cameras with different viewing angles and a signal processing module. The size and position of each camera and the vehicle are only exemplary and do not represent the actual size and position. Among them, the plurality of cameras with different viewing angles include at least one front-view camera in the front-view perception system and at least one side-view camera in the side-view perception system on both sides, preferably including (1) a front-view narrow-angle camera, Figure 5 The blue camera icon is used to indicate that the camera has a viewing angle of 30° and is installed in the center above the front windshield of the vehicle for high-precision close-range detection; (2) Front-view wide-angle camera, Figure 5 The yellow camera icon is used to indicate that the viewing angle is 120° and it is installed in parallel with the narrow-angle camera to cover a wider field of view; (3) two side-view cameras facing the left front and left rear, and two side-view cameras facing the right front and right rear, respectively. Figure 5A green camera icon is used to represent a 90° viewing angle, mounted on the outside of the left and right rearview mirrors, to detect side traffic conditions. When equipped with a front-view camera and side-view cameras on both sides of the vehicle, the front-view camera should be prioritized over the side-view cameras, taking into account their image acquisition range, detection accuracy, and function during driving. Furthermore, the first side-view camera on the same side as the traffic light should have a higher priority than the second side-view camera on a different side from the traffic light. This means that when the traffic light is on the right side of the vehicle, the right-side camera should have a higher priority than the left-side camera.

[0064] See also Figure 6 , Figure 6 A flowchart of a vehicle starting control method provided in an embodiment of the present application.

[0065] like Figure 6 As shown, the vehicle starting control method may further include at least:

[0066] S602: In response to an activation instruction for the intelligent assisted driving function, the intelligent assisted driving function is started, and when the vehicle drives to an intersection with a traffic light and the traffic light is in a green light state and is not on, the vehicle is controlled to brake to a stop.

[0067] Optionally, when the vehicle is driving, the driver can issue an activation request for the intelligent assisted driving function through the physical buttons on the steering wheel, voice commands, or the on-board human-computer interaction screen. The vehicle processor (ECU) responds to the activation request to activate the intelligent assisted driving function, so that the vehicle can achieve self-control through the intelligent assisted driving function. When activated, the vehicle first needs to verify whether the current driving environment meets the preset activation conditions, including but not limited to whether the current vehicle speed is in the applicable range (for example, 0-120km / h), whether the hardware facilities such as the front-view camera and millimeter-wave radar sensor are working normally, whether the high-precision positioning signal is valid, and whether the road condition recognition confidence meets the preset threshold conditions (for example, greater than 95%). If the preset activation conditions are met, the intelligent assisted driving function is started.

[0068] Furthermore, while the intelligent assisted driving function is in operation, the vehicle monitors road conditions in real time through a multi-sensor fusion framework. When the vehicle approaches a traffic light-controlled intersection along the planned path, the target detection algorithm identifies the traffic light device in the intersection area based on the RGB image and lidar point cloud data collected by the front-view camera. The vehicle maps the pixel position of the traffic light in the image coordinate system to the vehicle coordinate system through perspective projection transformation, and combines the intersection topology information provided by the high-precision map to confirm the association between the target traffic light and the current vehicle lane. When the traffic light used to indicate the vehicle's driving authority is located, the traffic light status is further identified. When the determined traffic light status is that the green light is not on, the vehicle is controlled to stop.

[0069] Specifically, a layered braking control strategy can be specifically adopted when the vehicle brakes to a stop. First, a deceleration request instruction is sent to the vehicle braking system via the CAN bus, requiring linear braking with the calculated initial deceleration. At the same time, based on the millimeter-wave radar, the relative distance to the preceding vehicle or the stop line is monitored in real time, and the deceleration curve is dynamically adjusted using an exponential decay algorithm to ensure that the vehicle stops smoothly 2-3 meters behind the preceding vehicle or in front of the stop line. After the vehicle comes to a complete stop, the vehicle further controls itself according to the vehicle starting control method provided in the embodiment of the present application. When monitoring the status information of traffic lights, if the status of the traffic lights continues to be not updated for more than a preset time, such as 60 seconds, 90 seconds, etc., a corresponding prompt can be issued to the driver to remind the driver to manually take over control of the vehicle.

[0070] In a feasible implementation, during the vehicle control process, the intelligent assisted driving function can display the current working camera and signal light recognition results in real time in the vehicle-mounted human-computer interaction interface. To ensure safety, when controlling the vehicle based on the signal status of traffic lights, the vehicle body sensors such as millimeter-wave radar are also used to detect whether there are pedestrians or obstacles around the vehicle. The recognition results of various sensors and cameras are combined to make vehicle control decisions, thereby further ensuring driving safety.

[0071] S604: When the vehicle stops at an intersection with a traffic light, determine whether the traffic light is within the image acquisition range of the front-view camera.

[0072] Optionally, from the introduction of the aforementioned embodiments, it can be known that the front-view camera is usually in a normally open state during vehicle driving. Therefore, when the vehicle brakes at an intersection with a traffic light, you can give priority to trying to use the front-view camera to collect the traffic light status, that is, to determine whether the traffic light is within the image acquisition range of the front-view camera.

[0073] Specifically, of the two forward-looking cameras, the narrow-angle camera has a higher call priority than the wide-angle camera due to its higher long-distance target resolution capability. When the narrow-angle camera is the primary detection unit, the wide-angle camera maintains a low-power standby state; the wide-angle camera processing link is activated only when the narrow-angle detection fails. In addition, the vehicle can also simultaneously activate the narrow-angle camera and the wide-angle camera to establish a dual-camera collaborative detection mode. The two cameras' fields of view are integrated through an image registration algorithm to expand the effective detection range of forward perception.

[0074] S606: If the traffic light is within the image acquisition range of the front-view camera, determine that the front-view camera is the target camera; acquire the signal light status of the traffic light through the target camera; and control the vehicle to start when the signal light status is green.

[0075] Optionally, if the traffic light is within the image acquisition range of the forward-facing camera, the forward-facing camera is determined to be the target camera; the traffic light status is captured via the target camera; and the vehicle is controlled to start when the traffic light status is green. This prioritizes the forward-facing perception system when it can accurately capture the traffic light status, reduces unnecessary camera resource calls, and conserves vehicle energy. The method and logic for capturing the traffic light status and controlling vehicle start when the forward-facing camera is the target camera are described in detail in steps S304-S306 and are not further detailed here.

[0076] S608: If the traffic light is outside the image acquisition range of the front-view camera, determine whether the traffic light is within the image acquisition range of the first side-view camera.

[0077] Optionally, if the traffic light is outside the image acquisition range of the front-view camera, then further attempt is made to use the first side-view camera to acquire the status of the traffic light, that is, to determine whether the traffic light is within the image acquisition range of the first side-view camera.

[0078] Specifically, for the two first side-view cameras configured on the vehicle body, one is usually responsible for the front side and the other for the rear side. Considering that traffic lights are often located in front of the vehicle, the first side-view camera on the front side can be used first to try to detect the signal of the traffic light status. When the first side-view camera on the front side is used as the preferred detection unit, the first side-view camera on the rear side maintains a low-power standby state; when the first side-view camera on the front side fails to detect, the first side-view camera processing link on the rear side is activated. In addition, the vehicle can also activate the two first side-view cameras simultaneously to establish a dual-camera collaborative detection mode, and fuse the fields of view of the two through an image registration algorithm to expand the effective detection range of side-view perception.

[0079] S610: If the traffic light is within the image acquisition range of the first side-view camera, determine the first side-view camera as the target camera; acquire the signal light status of the traffic light through the target camera; and control the vehicle to start when the signal light status is green.

[0080] Optionally, if the traffic light is within the image acquisition range of the first side-view camera, the first side-view camera is determined to be the target camera; the traffic light status is captured by the target camera; and the vehicle is controlled to start when the traffic light status is green, thereby accurately identifying the traffic light and facilitating subsequent precise control of the start. The method and logic for capturing the traffic light status and controlling the vehicle start when the first side-view camera is the target camera are described in detail in steps S304-S306 and are not further described here.

[0081] S612. The vehicle further includes at least a second side-view camera located on a different side from the traffic light. If the traffic light is outside the image acquisition range of the first side-view camera, determine whether there is a reference traffic light within the image acquisition range of the second side-view camera at the intersection.

[0082] Optionally, in the case that the vehicle also includes at least a second side-view camera located on a different side as the traffic light, if the traffic light is outside the image acquisition range of the first side-view camera, that is, the front-view camera and the first side-view camera on the same side of the traffic light are insufficient to capture the status of the traffic light, then further attempts are made to use the second side-view camera to collect the status of the traffic light, that is, to determine whether there is a reference traffic light at the intersection that is within the image acquisition range of the second side-view camera.

[0083] Specifically, similar to the first side-view camera, the two second side-view cameras configured on the vehicle body can also prioritize the first side-view camera on the front side to try to detect the signal light status signal. When the second side-view camera on the front side is used as the preferred detection unit, the second side-view camera on the rear side maintains a low-power standby state; the processing link of the second side-view camera on the rear side is activated only when the second side-view camera on the front side fails to detect. In addition, the vehicle can also simultaneously activate the two second side-view cameras to establish a dual-camera collaborative detection mode, and fuse the fields of view of the two through an image registration algorithm to expand the effective detection range of side-view perception.

[0084] S614. If there is a reference signal light within the image acquisition range of the second side view camera, capture a reference light state of the reference signal light through the second side view camera, where the reference light state is either green or not; and control the vehicle to start based on the reference light state.

[0085] Optionally, if a reference signal light is located within the image capture range of the second side-view camera, the second side-view camera further captures a reference light state of the reference signal light. The reference light state should also be green or off. The method and logic for capturing the reference light state are described in the relevant description of capturing the signal light state in step S304 and are not further described here.

[0086] Furthermore, in actual scenarios, there are two possible situations for other signal lights that can be used as reference at the intersection: if the instantaneous state of the reference signal light is the same as the instantaneous state of the traffic light at the same moment, then the vehicle should also control its own vehicle to start when the green light of the reference signal light is on. However, in another case, if the instantaneous state of the reference signal light is opposite to the instantaneous state of the traffic light at the same moment, then the vehicle should control its own vehicle to start when the green light of the reference signal light is not on. At this time, considering the presence of red and yellow lights in the traffic light, a delayed start mechanism with a preset time is formulated for the vehicle, and the vehicle is controlled to start after the preset time, thereby increasing the vehicle's fault tolerance when responding to the instruction of the opposite signal light. Among them, the preset time can be set to 3 seconds, 5 seconds, etc., and this is not limited in the embodiment of the present application. For the method and logic of controlling the vehicle to start, please refer to the detailed description in step S306, which will not be repeated here. In this way, the other side of the traffic light is detected by other signal lights at the intersection and other cameras of the vehicle, thereby enriching the vehicle's signal light information source and improving the accuracy and robustness of the vehicle's start control function.

[0087] S616: If there is no reference signal light within the image acquisition range of the second side view camera, a manual vehicle control prompt message is issued according to a preset prompt method, where the preset prompt method includes at least one of a voice prompt and a visual graphic prompt.

[0088] Optionally, if there is no reference signal light within the image acquisition range of the second side-view camera, it means that the vehicle cannot collect reliable signal light status through the front-view camera and the side-view cameras on both sides. At this time, through a variety of notification prompts, such as voice prompts and visual graphic prompt lights on the on-board human-computer interaction screen, the user is promptly reminded to manually take over the vehicle and manually control the vehicle to ensure the driving safety of the vehicle and the user at the intersection.

[0089] In an embodiment of the present application, a vehicle start control method is provided. A vehicle can activate an intelligent assisted driving function based on user commands. Based on this intelligent assisted driving function, the vehicle can autonomously brake to a stop when it reaches an intersection with a traffic light and the traffic light is not green. This provides the vehicle with complete and reliable autonomous intersection navigation capabilities. The vehicle has at least a front-facing camera and a first side-facing camera located on the same side of the vehicle as the traffic light. During vehicle control, the front-facing camera takes precedence over the first side-facing camera, ensuring detection accuracy while also making more efficient use of the various camera resources in the vehicle. The vehicle first determines whether the traffic light is within the image acquisition range of the front-facing camera. If the front-facing perception system can accurately capture the light status, the front-facing perception system is prioritized, reducing unnecessary camera resource usage and conserving vehicle energy. If the front-facing perception system cannot accurately capture the light status, the first side-facing camera is further activated to supplement the front-facing perception system's blind spots, accurately identifying the traffic light and facilitating subsequent precise start control. In the case where the vehicle also includes at least a second side-view camera located on a different side than the traffic light, if the front-view camera and the first side-view camera on the same side as the traffic light are insufficient to capture the status of the traffic light, the second side-view camera on the other side is further used to collect the status of other reference traffic lights at the intersection. In this way, blind spots on the other side of the traffic light are detected by other traffic lights at the intersection and other cameras of the vehicle, thereby enriching the vehicle's signal light information source and improving the accuracy and robustness of the vehicle's starting control function. When the vehicle cannot collect reliable signal light status through the front-view camera and the side-view cameras on both sides, the user is promptly reminded to manually take over the vehicle and perform manual control through a variety of notification prompts to ensure the driving safety of the vehicle and the user at the intersection.

[0090] See Figure 7 , Figure 7 This is a schematic diagram of the structure of a vehicle provided in an embodiment of the present application. Figure 7 As shown, the vehicle 700 may include: at least one vehicle processor 701 , at least one network interface 704 , a user interface 703 , a memory 705 , and at least one communication bus 702 .

[0091] The communication bus 702 is used to implement the connection and communication between these components.

[0092] The user interface 703 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 703 may also include a standard wired interface and a wireless interface.

[0093] The network interface 704 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0094] Among them, the vehicle processor 701 may include one or more processing cores. The vehicle processor 701 uses various interfaces and lines to connect various parts within the entire vehicle 700, and performs various functions and processes data of the vehicle 700 by running or executing instructions, programs, code sets or instruction sets stored in the memory 705, and calling data stored in the memory 705. Optionally, the vehicle processor 701 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used to handle wireless communications. It is understandable that the above-mentioned modem may not be integrated into the vehicle processor 701, but may be implemented separately through a chip.

[0095] Among them, the memory 705 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 705 includes a non-transitory computer-readable storage medium. The memory 705 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 705 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 705 may also optionally be at least one storage device located away from the aforementioned vehicle processor 701. As Figure 7 As shown, the memory 705 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a vehicle starting control program.

[0096] exist Figure 7 In the vehicle 700 shown, the user interface 703 is mainly used to provide an input interface for the user and obtain data input by the user; and the vehicle processor 701 can be used to call the vehicle starting control program stored in the memory 705 to specifically execute the above-mentioned related method steps to implement a vehicle starting control method provided in the above embodiment.

[0097] In addition, embodiments of the present application also protect a device. This embodiment may divide the device into functional modules according to the above-described method examples. For example, each functional module may be corresponding to the functional module, or two or more functions may be integrated into a processing module. The above-described integrated module may be implemented in the form of hardware. It should be noted that the module division in this embodiment is schematic and is merely a logical functional division. In actual implementation, other division methods may be used.

[0098] In the case of dividing the functional modules into corresponding modules, the vehicle starting control device includes:

[0099] The camera call module is used to determine whether the traffic light is within the image acquisition range of each camera based on the preset call priority corresponding to multiple cameras in the vehicle when the vehicle stops at an intersection with a traffic light;

[0100] A signal status acquisition module is used to acquire the signal status of the traffic light through the target camera if there is a traffic light within the image acquisition range, where the signal status is green or not;

[0101] The start control module is used to control the vehicle to start when the signal light is green.

[0102] Optionally, the vehicle includes at least a front-view camera and a first side-view camera located on the same side as the traffic light, and the front-view camera has a higher calling priority than the first side-view camera in a preset calling priority.

[0103] Optionally, the camera calling module is also used to determine whether the traffic light is within the image acquisition range of the front-view camera; if the traffic light is within the image acquisition range of the front-view camera, the front-view camera is determined to be the target camera; if the traffic light is outside the image acquisition range of the front-view camera, it is determined whether the traffic light is within the image acquisition range of the first side-view camera; if the traffic light is within the image acquisition range of the first side-view camera, the first side-view camera is determined to be the target camera.

[0104] Optionally, the vehicle further includes at least a second side-view camera located on a different side than the traffic light, and the vehicle starting control device further includes: a non-same-side camera calling module, for determining whether there is a reference traffic light within the image acquisition range of the second side-view camera at the intersection if the traffic light is outside the image acquisition range of the first side-view camera; if there is a reference traffic light within the image acquisition range of the second side-view camera, capturing a reference light status of the reference traffic light through the second side-view camera, the reference light status being either green on or not; and controlling the vehicle starting based on the reference light status.

[0105] Optionally, the non-side camera calling module is also used to control the vehicle to start when the reference light status is green and on if the reference light status is the same as the signal light status at the same moment; if the reference light status is opposite to the signal light status at the same moment, then when the reference light status is green and not on, control the vehicle to start after a preset time.

[0106] Optionally, the vehicle starting control device also includes: a vehicle control takeover prompt module, which is used to issue manual vehicle control prompt information in a preset prompt method if there is no reference signal light within the image acquisition range of the second side-view camera. The preset prompt method includes at least one of a voice prompt and a visual graphic prompt.

[0107] Optionally, the vehicle starting control device also includes: an intelligent assisted driving function module, which is used to start the intelligent assisted driving function in response to an activation instruction for the intelligent assisted driving function, and control the vehicle to brake when the vehicle drives to an intersection with a traffic light and the signal status of the traffic light is green and not on.

[0108] It should be understood that the device provided in this embodiment is used to execute the above-mentioned vehicle starting control method, and thus can achieve the same effect as the above-mentioned implementation method.

[0109] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is used in a vehicle, the processing module may be used to control and manage the vehicle's movements, while the storage module may be used to support the vehicle's execution of relevant program codes.

[0110] The processing module may be a processor or controller that implements or executes the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processing system (DSP) and a microprocessor, and the storage module may be a memory.

[0111] In addition, the device provided in the embodiments of the present application can specifically be a chip, component or module, and the chip may include a connected processor and memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a vehicle starting control method provided in the above embodiment.

[0112] This embodiment also provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned related method steps to implement a vehicle starting control method provided by the above embodiment.

[0113] This embodiment further provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement a vehicle starting control method provided in the above embodiment.

[0114] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0115] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules 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 interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0116] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of these modules may be selected to achieve the purpose of this embodiment based on actual needs.

[0117] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The above-mentioned computer program product includes one or more computer instructions. When the above-mentioned computer program instructions are loaded and executed on a computer, the above-mentioned process or function according to the embodiment of this specification is generated in whole or in part. The above-mentioned computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The above-mentioned computer instructions can be stored in a computer-readable storage medium or transmitted by the above-mentioned computer-readable storage medium. The above-mentioned computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The above-mentioned computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The above-mentioned available media can be magnetic media (for example, floppy disks, hard disks, tapes), optical media (for example, digital versatile discs (DVDs)), or semiconductor media (for example, solid state disks (SSDs)).

[0118] It should be noted that for the aforementioned method embodiments, for ease of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0119] In addition, it should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in the embodiments of this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions.

[0120] The foregoing description describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0121] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0122] The above is a description of a vehicle starting control method, device, storage medium, and vehicle provided in this application. For those skilled in the art, based on the ideas of the embodiments of this application, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting this application.

Claims

1. A vehicle starting control method, characterized in that: The method comprises: When the vehicle stops at an intersection with a traffic light, it is determined in sequence whether the traffic light is within the image acquisition range of each camera based on the preset call priority corresponding to multiple cameras in the vehicle; If it is determined that there is a target camera within the image acquisition range of the traffic light, the traffic light state is captured by the target camera, where the traffic light state is green or not. When the signal light is in the green state, the vehicle is controlled to start.

2. The method according to claim 1, characterized in that The vehicle includes at least a front-view camera and a first side-view camera located on the same side as the traffic light, and the front-view camera has a higher calling priority than the first side-view camera in the preset calling priority.

3. The method according to claim 2, characterized in that The determining, based on preset call priorities corresponding to the plurality of cameras in the vehicle, whether the traffic light is within the image acquisition range of each camera in sequence includes: Determining whether the traffic light is within the image acquisition range of the front-view camera; If the traffic light is within the image acquisition range of the front-view camera, determining that the front-view camera is the target camera; If the traffic light is outside the image acquisition range of the front-view camera, determining whether the traffic light is within the image acquisition range of the first side-view camera; If the traffic light is located within the image acquisition range of the first side-view camera, the first side-view camera is determined to be a target camera.

4. The method according to claim 3, characterized in that The vehicle further includes at least a second side-view camera located on a side other than the traffic light, and the method further includes: If the traffic light is outside the image acquisition range of the first side-view camera, determining whether there is a reference traffic light at the intersection within the image acquisition range of the second side-view camera; If there is a reference signal light within the image acquisition range of the second side-view camera, collecting a reference light state of the reference signal light through the second side-view camera, where the reference light state is green or not. The vehicle start is controlled based on the reference lamp state.

5. The method according to claim 4, characterized in that The controlling the vehicle starting based on the reference light state includes: If the reference light state is the same as the signal light state at the same time, then the vehicle is controlled to start when the reference light state is green; If the reference light state is opposite to the signal light state at the same time, when the reference light state is the green light not on, the vehicle is controlled to start after a preset time.

6. The method according to claim 4 or 5, characterized in that The method further comprises: If there is no reference signal light within the image acquisition range of the second side-view camera, a manual vehicle control prompt message is issued according to a preset prompt method, wherein the preset prompt method includes at least one of a voice prompt and a visual graphic prompt.

7. The method according to claim 1, characterized in that Before the vehicle stops at an intersection with a traffic light, the process also includes: In response to an activation instruction for an intelligent assisted driving function, the intelligent assisted driving function is started, and when the vehicle travels to an intersection with a traffic light and the signal state of the traffic light is green and not on, the vehicle is controlled to brake to a stop.

8. A vehicle starting control device, characterized in that: The device comprises: a camera calling module for determining, when a vehicle stops at an intersection with a traffic light, whether the traffic light is within the image acquisition range of each camera based on preset calling priorities corresponding to multiple cameras in the vehicle; a signal state acquisition module, configured to acquire the signal state of the traffic light through the target camera if it is determined that the traffic light is located within the image acquisition range, wherein the signal state is green or not; The starting control module is used to control the vehicle to start when the signal light is green.

9. A vehicle, characterized in that: The vehicle comprises: a memory for storing executable program code; A processor is configured to call and run the executable program code from the memory, so that the vehicle executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 is implemented.

Images