Ghost probe scene identification and control method and system, vehicle, device and medium

Abstract

A method, system, vehicle, device, and medium for identifying and controlling "ghost peek-out" scenarios are disclosed, relating to the field of intelligent driving technology. Specifically, the method includes determining a ghost peek-out scenario based on the state of a target vehicle, a first real-time distance, and a second real-time distance. The target vehicle is the foremost vehicle in the adjacent lane. The first real-time distance is the distance between the target vehicle and the pedestrian crossing, and the second real-time distance is the lateral distance between the target vehicle and the vehicle itself. In a ghost peek-out scenario, the vehicle is controlled to decelerate based on its real-time speed and a third real-time distance, where the third real-time distance is the distance between the front of the vehicle and the target vehicle. This application achieves early identification and effective intervention of potential collision risks in intersections with limited visibility, without relying on V2X technology.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, specifically to a method, system, vehicle, device, and medium for ghost-protruding scene recognition and control. Background Technology

[0002] With the rapid development of automotive intelligence and active safety technologies, the Automatic Emergency Braking (AEB) system has been widely used in various vehicles. The overall technical requirement for this system is to identify collision risks through sensors and brake automatically to assist drivers in avoiding traffic accidents in complex traffic environments.

[0003] In related technologies, AEB systems typically rely on sensors such as vehicle-mounted radar and cameras to detect targets ahead or crossing the road, and provide warnings and emergency braking when there is a risk of collision. For scenarios with blind spots, such as intersections, some existing technologies use V2X (Vehicle-to-Everything) technology, which enables beyond-line-of-sight target recognition and risk prediction through information communication between vehicles and between vehicles and road traffic equipment.

[0004] However, V2X technology is limited by factors such as technology cost and traffic infrastructure construction, and is not yet widely used. As a result, when most vehicles pass through an intersection without relying on V2X technology and a vehicle in the adjacent lane obstructs the sensor's field of vision, if a pedestrian or two-wheeled vehicle suddenly darts out from the blind spot, the system cannot provide timely warnings and braking due to limited recognition time. It is difficult to identify potential collision risks in advance and intervene effectively in intersection scenarios with limited visibility.

[0005] Therefore, how to identify and effectively intervene in potential collision risks in intersections with limited visibility without relying on V2X technology is an urgent problem to be solved. Summary of the Invention

[0006] This application provides a method, system, vehicle, device, and medium for identifying and controlling "ghost pedestrian" scenarios, which can achieve early identification and effective intervention of potential collision risks in intersection scenarios with limited visibility without relying on V2X technology.

[0007] In a first aspect, embodiments of this application provide a method for identifying and controlling ghost peeping scenarios, the method comprising: The ghost peek scenario is determined based on the status of the target vehicle, the first real-time distance, and the second real-time distance. The target vehicle is the vehicle at the front of the adjacent lane. The first real-time distance is the distance between the target vehicle and the pedestrian crossing. The second real-time distance is the lateral distance between the target vehicle and the vehicle itself. In the scenario of a vehicle suddenly appearing out of nowhere, the vehicle decelerates based on its real-time speed and a third real-time distance, where the third real-time distance is the distance between the front of the vehicle and the target vehicle.

[0008] In conjunction with the first aspect, in one implementation, determining the ghost-peeping scenario based on the target vehicle's state, a first real-time distance, and a second real-time distance includes: If the target vehicle is detected to be stationary, the first ghost peek scenario is determined based on the first real-time distance and the second real-time distance. If the target vehicle is detected to be decelerating, a second ghost peek scenario is determined based on the target vehicle's real-time deceleration, the first real-time distance, and the second real-time distance. The risk level of the first ghost peek scenario is lower than that of the second ghost peek scenario.

[0009] In conjunction with the first aspect, in one implementation, determining the first ghost-peeking scene based on a first real-time distance and a second real-time distance includes: If the first real-time distance is less than the first preset pedestrian crossing distance threshold and the second real-time distance is less than the preset lateral distance threshold, then it is determined that there is a first ghost peek scene. If the first real-time distance is not less than the first preset pedestrian crossing distance threshold or the second real-time distance is not less than the preset lateral distance threshold, it is determined that there is no first ghost peek scene.

[0010] In conjunction with the first aspect, in one implementation, determining the second ghost-peeking scenario based on the target vehicle's real-time deceleration, a first real-time distance, and a second real-time distance includes: If the real-time deceleration of the target vehicle is detected to be greater than the preset deceleration threshold, the first real-time distance is less than the second preset pedestrian crossing distance threshold, and the second real-time distance is less than the preset lateral distance threshold, then it is determined that there is a second ghost peek scenario. If the real-time deceleration of the target vehicle is not greater than a preset deceleration threshold, or the first real-time distance is not less than a second preset pedestrian crossing distance threshold, or the second real-time distance is not less than a preset lateral distance threshold, then it is determined that there is no second ghost peek scenario.

[0011] In conjunction with the first aspect, in one implementation, controlling the vehicle's deceleration based on the vehicle's real-time speed and a third real-time distance includes: The system defensive deceleration distance threshold is determined based on the vehicle's real-time speed, preset safe braking distance, preset system response time, preset actuator delay time, and preset system defensive deceleration time. The vehicle deceleration is controlled based on the real-time vehicle speed, a first preset speed threshold, a second preset speed threshold, a third real-time distance, and a system defensive deceleration distance threshold, wherein the first preset speed threshold is less than the second preset speed threshold.

[0012] In conjunction with the first aspect, in one embodiment, controlling the vehicle's deceleration based on the vehicle's real-time speed, a first preset speed threshold, a second preset speed threshold, a third real-time distance, and a system defensive deceleration distance threshold includes: If the real-time speed of the vehicle is detected to be less than the first preset speed threshold, there is no need to control the vehicle to decelerate. If the vehicle's real-time speed is detected to be not less than the first preset speed threshold, the vehicle will decelerate based on its real-time speed, the second preset speed threshold, the third real-time distance, and the system's defensive deceleration distance threshold.

[0013] In conjunction with the first aspect, in one implementation, controlling the vehicle's deceleration based on the vehicle's real-time speed, a second preset speed threshold, a third real-time distance, and a system defensive deceleration distance threshold includes: If the vehicle's real-time speed is detected to be less than the second preset speed threshold and the third real-time distance is less than the system's defensive deceleration distance threshold, a deceleration reminder will be issued. If the vehicle's real-time speed is detected to be no less than the second preset speed threshold and the third real-time distance is less than the system's defensive deceleration distance threshold, then the vehicle will be controlled to decelerate at a preset deceleration rate.

[0014] In conjunction with the first aspect, in one embodiment, the method further includes: If the detected third real-time distance is not less than the system's defensive deceleration distance threshold, then there is no need to control the vehicle's deceleration.

[0015] In conjunction with the first aspect, in one implementation, prior to the step of determining the ghost-peeking scenario based on the target vehicle's state, a first real-time distance, and a second real-time distance, the method further includes: If the target condition is detected, the ghost peek scene recognition is initiated. If no target conditions are detected, the ghost peek scene recognition will not be activated. The target conditions include the current road type being an urban road, the presence of an intersection ahead, the vehicle being in a straight lane, and the traffic light being green.

[0016] Secondly, embodiments of this application provide a ghost peeping scene recognition and control system, the ghost peeping scene recognition and control system comprising: The first processing module is used to determine the ghost peek scenario based on the state of the target vehicle, the first real-time distance and the second real-time distance. The target vehicle is the vehicle at the front of the adjacent lane, the first real-time distance is the distance between the target vehicle and the pedestrian crossing, and the second real-time distance is the lateral distance between the target vehicle and the vehicle itself. The second processing module is used to control the vehicle to decelerate based on the vehicle's real-time speed and a third real-time distance in the ghost-peeking scenario. The third real-time distance is the distance between the front of the vehicle and the target vehicle.

[0017] In conjunction with the second aspect, in one implementation, the first processing module is specifically used for: If the target vehicle is detected to be stationary, the first ghost peek scenario is determined based on the first real-time distance and the second real-time distance. If the target vehicle is detected to be decelerating, a second ghost peek scenario is determined based on the target vehicle's real-time deceleration, the first real-time distance, and the second real-time distance. The risk level of the first ghost peek scenario is lower than that of the second ghost peek scenario.

[0018] In conjunction with the second aspect, in one implementation, the first processing module is specifically used for: If the first real-time distance is less than the first preset pedestrian crossing distance threshold and the second real-time distance is less than the preset lateral distance threshold, then it is determined that there is a first ghost peek scene. If the first real-time distance is not less than the first preset pedestrian crossing distance threshold or the second real-time distance is not less than the preset lateral distance threshold, it is determined that there is no first ghost peek scene.

[0019] Thirdly, embodiments of this application provide a vehicle, including the aforementioned ghost-probe scene recognition and control system.

[0020] Fourthly, this application provides a ghost peeping scene recognition and control device, which includes a processor, a memory, and a ghost peeping scene recognition and control program stored in the memory and executable by the processor. When the ghost peeping scene recognition and control program is executed by the processor, it implements the ghost peeping scene recognition and control method as described above.

[0021] Fifthly, embodiments of this application provide a computer-readable storage medium storing a ghost peeping scene recognition and control program, wherein when the ghost peeping scene recognition and control program is executed by a processor, it implements the aforementioned ghost peeping scene recognition and control method.

[0022] The beneficial effects of the technical solutions provided in this application include: The "ghost peek" scenario is determined by analyzing the status of the target vehicle (the vehicle at the front of the adjacent lane), the first real-time distance between the target vehicle and the pedestrian crossing, and the second real-time lateral distance between the target vehicle and the vehicle itself. This approach utilizes the status and distance information of neighboring vehicles obtainable by the vehicle's sensors to replace the less common V2X communication. This allows the system to indirectly infer blind spot risks by analyzing the relative relationship between neighboring vehicles and the pedestrian crossing, even when the view is obstructed and direct pedestrian detection is impossible. This enables early identification of potential collision risks without relying on V2X technology. In the "ghost peek" scenario, the system controls the vehicle's deceleration based on its real-time speed and the third real-time distance between the vehicle and the target vehicle's front end. By proactively reducing speed before the actual risk occurs, sufficient reaction time and braking distance redundancy are provided for potential emergency braking, thus solving the problem of insufficient warning and braking due to limited recognition time. This achieves effective intervention in intersections with limited visibility. Attached Figure Description

[0023] Figure 1 This is a flowchart illustrating an embodiment of the ghost peek-out scene recognition and control method of this application; Figure 2 For this application Figure 1 A detailed flowchart of step S10; Figure 3 This is a detailed flowchart illustrating an embodiment of the ghost peek-out scene recognition and control method of this application; Figure 4 This is a schematic diagram of the hardware structure of the ghost protrusion scene recognition and control device involved in the embodiments of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0026] In a first aspect, embodiments of this application provide a method for identifying and controlling ghost peek-out scenes.

[0027] In one embodiment, reference is made to Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the ghost peek-out scene recognition and control method of this application. Figure 1 As shown, the methods for ghost peek-out scene recognition and control include: Step S10: Determine the ghost peek scenario based on the state of the target vehicle, the first real-time distance, and the second real-time distance. The target vehicle is the vehicle at the front of the adjacent lane. The first real-time distance is the distance between the target vehicle and the pedestrian crossing. The second real-time distance is the lateral distance between the target vehicle and the pedestrian crossing.

[0028] In this exemplary embodiment, the system first obtains information on road type, the intersection ahead, the pedestrian crossing, and traffic lights through a map. It then uses a forward-facing camera and radar sensors to detect the position, speed, and lane information of vehicles ahead and in adjacent lanes. Based on this, the target vehicle is preferably the vehicle at the front of the adjacent lane, whose stationary or decelerating state can be detected by the forward-facing camera and radar sensors. This information is used to characterize whether there are signs of the vehicle stopping to yield to pedestrians. The first real-time distance is the distance between the target vehicle and the pedestrian crossing, calculated by combining the pedestrian crossing location information provided by the vehicle's map with the target vehicle's location information detected by the sensors. This distance is used to assess the degree to which the target vehicle is close to a risk area. The second real-time distance is the lateral distance between the target vehicle and the vehicle, determined by the lane information detected by the sensors and the relative position of the vehicle. This distance is used to determine whether the target vehicle is located in a critical obstruction position within the vehicle's blind spot. The combination of these three factors allows the system to indirectly identify the risk of invisible pedestrians through vehicle characteristics without relying on V2X technology, thereby achieving accurate determination of potential "ghost pedestrian" scenarios at intersections.

[0029] Step S20: In the ghost peek scenario, control the vehicle to decelerate based on the vehicle's real-time speed and the third real-time distance, where the third real-time distance is the distance between the front of the vehicle and the target vehicle.

[0030] In this embodiment, the real-time speed of the vehicle can be obtained through onboard sensors or vehicle bus to reflect the current driving kinetic energy and braking distance requirements; the third real-time distance is the distance between the front of the vehicle and the target vehicle, which can be detected in real time through a forward-looking camera or radar ranging function, representing the longitudinal safety buffer space between the vehicle and the obstructing vehicle; the system calculates the defensive deceleration distance threshold based on the real-time speed of the vehicle and compares it with the third real-time distance, and controls the vehicle to decelerate according to the comparison result, aiming to reduce the driving speed in advance before the actual risk occurs, and reserve sufficient reaction time and braking distance redundancy for subsequent possible emergency braking, thereby effectively improving the collision avoidance performance in intersection with limited visibility without relying on V2X technology.

[0031] It should be noted that a preliminary risk assessment mechanism based on the relationship between the third real-time distance and the defensive deceleration distance threshold can also be established first. If the safety braking redundancy at the current vehicle speed is insufficient and there is a potential collision risk, then the system will further initiate the ghost peek scenario identification process, combine the target vehicle's status and location information to confirm the risk level and execute the corresponding deceleration control strategy. Conversely, if there is sufficient safety buffer space between the vehicle and the target vehicle, even if there is obstruction, there is no immediate collision risk, and the system does not need to perform subsequent scenario identification and deceleration control.

[0032] This application determines the "ghost peek" scenario by using the status of the target vehicle (the vehicle at the front of the adjacent lane), the first real-time distance between the target vehicle and the pedestrian crossing, and the second real-time lateral distance between the target vehicle and the vehicle itself. It replaces the less common V2X communication with the status and distance information of neighboring vehicles obtainable by the vehicle's sensors. This allows the system to indirectly infer blind spot risks through the relative relationship between neighboring vehicles and the pedestrian crossing even when the view is obstructed and pedestrians cannot be directly detected. This achieves early identification of potential collision risks without relying on V2X technology. In the ghost peek scenario, the system controls the vehicle to decelerate based on the real-time speed of the vehicle and the third real-time distance between the vehicle and the front of the target vehicle. By proactively reducing the vehicle speed before the actual risk occurs, sufficient reaction time and braking distance redundancy are reserved for subsequent emergency braking, thus solving the problem of insufficient timely warning and braking due to limited recognition time. This achieves effective intervention in intersection scenarios with limited visibility.

[0033] Furthermore, in one embodiment, reference is made to Figure 2 As shown, determining the ghost-peeking scenario based on the target vehicle's state, the first real-time distance, and the second real-time distance includes: Step S101: If the target vehicle is detected to be stationary, the first ghost peek scenario is determined based on the first real-time distance and the second real-time distance; Step S102: If the target vehicle is detected to be in a deceleration state, then a second ghost peek scenario is determined based on the real-time deceleration of the target vehicle, the first real-time distance, and the second real-time distance. The risk level of the first ghost peek scenario is lower than that of the second ghost peek scenario.

[0034] In this embodiment of the application, the first "ghost peek" scenario represents the risk of static visual obstruction caused by a stationary adjacent vehicle, and the second "ghost peek" scenario represents the risk of a dynamic sudden collision caused by a sudden deceleration of an adjacent vehicle. The risk level of the first "ghost peek" scenario is lower than that of the second "ghost peek" scenario. The sudden deceleration behavior of the adjacent vehicle represents the driver's active avoidance response to a sudden obstacle. Compared with the stationary state, the sudden deceleration more directly points to the possibility of the target crossing the road. Moreover, the dynamic change process means that the dangerous situation is rapidly escalating, resulting in a relatively shorter reaction window available to the vehicle. Therefore, such dynamic scenarios need to be identified as having a higher risk priority in order to match a more proactive defense strategy.

[0035] Specifically, if the target vehicle is detected to be stationary, it indicates that a pedestrian or two-wheeled vehicle may suddenly appear from in front of a vehicle in the adjacent lane. The first real-time distance and the second real-time distance are used to determine the first ghost peek scenario. If the target vehicle is detected to be decelerating, it indicates that the target vehicle may be avoiding a pedestrian or two-wheeled vehicle crossing the road. The second ghost peek scenario is determined based on the target vehicle's real-time deceleration, the first real-time distance, and the second real-time distance. By introducing real-time deceleration as a dynamic risk characterization parameter, the system can distinguish between two different risk levels of ghost peek scenarios: static occlusion and dynamic emergency braking. This enables refined identification of potential risks at intersections.

[0036] Further, in one embodiment, determining the first ghost-peeping scene based on the first real-time distance and the second real-time distance includes: If the first real-time distance is less than the first preset pedestrian crossing distance threshold and the second real-time distance is less than the preset lateral distance threshold, then it is determined that there is a first ghost peek scene. If the first real-time distance is not less than the first preset pedestrian crossing distance threshold or the second real-time distance is not less than the preset lateral distance threshold, it is determined that there is no first ghost peek scene.

[0037] As an example, in this embodiment, the specific values ​​of the first preset pedestrian crossing distance threshold and the preset lateral distance threshold can be determined according to actual needs and are not limited here. For example, the first preset pedestrian crossing distance threshold can preferably be 5m, and the preset lateral distance threshold can preferably be 4m. If the first real-time distance is detected to be less than the first preset pedestrian crossing distance threshold and the second real-time distance is detected to be less than the preset lateral distance threshold, it indicates that the target vehicle has entered the pedestrian crossing risk area and effectively obstructs the view of the vehicle, thus meeting the spatial conditions for triggering the first ghost peeping scene determination, and is therefore determined to be a first ghost peeping scene. If the first real-time distance is detected to be not less than the first preset pedestrian crossing distance threshold or the second real-time distance is not less than the preset lateral distance threshold, it indicates that the target vehicle has not entered the pedestrian crossing risk area or has not effectively obstructed the view of the vehicle, thus meeting the spatial conditions for triggering the first ghost peeping scene determination, and is therefore determined to be a first ghost peeping scene.

[0038] Further, in one embodiment, determining the second ghost-peeking scenario based on the target vehicle's real-time deceleration, a first real-time distance, and a second real-time distance includes: If the real-time deceleration of the target vehicle is detected to be greater than the preset deceleration threshold, the first real-time distance is less than the second preset pedestrian crossing distance threshold, and the second real-time distance is less than the preset lateral distance threshold, then it is determined that there is a second ghost peek scenario. If the real-time deceleration of the target vehicle is not greater than a preset deceleration threshold, or the first real-time distance is not less than a second preset pedestrian crossing distance threshold, or the second real-time distance is not less than a preset lateral distance threshold, then it is determined that there is no second ghost peek scenario.

[0039] As an example, in the embodiments of this application, the specific values ​​of the preset deceleration threshold and the second preset pedestrian crossing distance threshold can be determined according to actual needs and are not limited here; for example, the preset deceleration threshold can preferably be -4m / s 2 The second preset pedestrian crossing distance threshold can preferably be set to 10m. If the real-time deceleration of the target vehicle is greater than the preset deceleration threshold, the first real-time distance is less than the second preset pedestrian crossing distance threshold, and the second real-time distance is less than the preset lateral distance threshold, it indicates that the target vehicle is braking urgently and has entered the pedestrian crossing risk area, effectively obstructing the view of the vehicle. This meets the dynamic risk conditions for triggering the second ghost peek scenario determination, and thus the second ghost peek scenario is determined to exist. If the real-time deceleration of the target vehicle is not greater than the preset deceleration threshold, or the first real-time distance is not less than the second preset pedestrian crossing distance threshold, or the second real-time distance is not less than the preset lateral distance threshold, it indicates that the target vehicle is not braking urgently, has not entered the pedestrian crossing risk area, or has not effectively obstructed the view of the vehicle. This does not meet the dynamic risk conditions for triggering the second ghost peek scenario determination, and thus the second ghost peek scenario is determined to not exist.

[0040] Furthermore, in one embodiment, controlling the vehicle's deceleration based on the vehicle's real-time speed and a third real-time distance includes: The system defensive deceleration distance threshold is determined based on the vehicle's real-time speed, preset safe braking distance, preset system response time, preset actuator delay time, and preset system defensive deceleration time. The vehicle deceleration is controlled based on the real-time vehicle speed, a first preset speed threshold, a second preset speed threshold, a third real-time distance, and a system defensive deceleration distance threshold, wherein the first preset speed threshold is less than the second preset speed threshold.

[0041] In this exemplary embodiment, the specific values ​​of the preset safe braking distance, preset system response time (time required for the system to respond from the appearance of the ghost-peeking target), preset actuator delay time (actuator response delay time), and preset system defensive deceleration time (system defensive deceleration time) can be determined according to actual needs and are not limited here. For example, the preset safe braking distance can preferably be 2m; the preset system defensive deceleration time can preferably be 2s in the first ghost-peeking scenario, and 3s in the second ghost-peeking scenario where the potential risk is higher; specifically, the distance required for AEB braking and collision avoidance is first determined based on the vehicle's real-time speed, preset safe braking distance, preset system response time, and preset actuator delay time. The calculation formula is as follows:

[0042] In the formula, This refers to the vehicle's real-time speed. To preset a safe stopping distance; Preset system response time; Preset actuator delay duration; The distance required for AEB to stop and avoid a collision.

[0043] Furthermore, the system's defensive deceleration distance threshold is determined based on the distance required for AEB to stop and avoid a collision, the vehicle's real-time speed, and the preset system defensive deceleration duration. The calculation formula is as follows:

[0044] In the formula, The distance required for AEB to stop and avoid a collision; The preset defensive deceleration duration of the system; This is the threshold for the system's defensive deceleration distance.

[0045] It should be noted that the specific values ​​of the first and second preset speed thresholds can be determined according to actual needs, as long as the first preset speed threshold is less than the second preset speed threshold. There is no limitation here. For example, the first preset speed threshold can be preferably 20 km / h, and the second preset speed threshold can be preferably 40 km / h. Specifically, the real-time speed of the vehicle is classified using the first and second preset speed thresholds to determine the risk intervention level. At the same time, the system's defensive deceleration distance threshold is used to determine the risk of the third real-time distance to determine the deceleration triggering time. Then, the control logic that combines the speed classification result and the distance judgment result executes the vehicle deceleration, so that the system can dynamically match the deceleration strategy according to the vehicle's driving speed and the relative distance to the vehicle in front, and realize preventive deceleration control based on the coordination of speed classification and distance threshold, so as to ensure timely intervention according to distance risk at different driving speeds.

[0046] Further, in one embodiment, controlling the vehicle's deceleration based on the vehicle's real-time speed, a first preset speed threshold, a second preset speed threshold, a third real-time distance, and a system defensive deceleration distance threshold includes: If the real-time speed of the vehicle is detected to be less than the first preset speed threshold, there is no need to control the vehicle to decelerate. If the vehicle's real-time speed is detected to be not less than the first preset speed threshold, the vehicle will decelerate based on its real-time speed, the second preset speed threshold, the third real-time distance, and the system's defensive deceleration distance threshold.

[0047] In an exemplary embodiment of this application, if the real-time vehicle speed is detected to be less than the first preset speed threshold, it indicates that the vehicle is in a low-speed safe driving range, the collision risk is controllable, and the braking redundancy is sufficient, so there is no need to control the vehicle to decelerate; if the real-time vehicle speed is detected to be not less than the first preset speed threshold, it indicates that the vehicle has entered a potentially risky speed range, and further judgment needs to be made in conjunction with distance information. The risk intervention level is divided by using the real-time vehicle speed and the second preset speed threshold, and the deceleration triggering time is determined by combining the relationship between the third real-time distance and the system's defensive deceleration distance threshold, thereby performing defensive deceleration control based on the coordinated matching of vehicle speed and distance.

[0048] Further, in one embodiment, controlling the vehicle's deceleration based on the vehicle's real-time speed, a second preset speed threshold, a third real-time distance, and a system defensive deceleration distance threshold includes: If the vehicle's real-time speed is detected to be less than the second preset speed threshold and the third real-time distance is less than the system's defensive deceleration distance threshold, a deceleration reminder will be issued. If the vehicle's real-time speed is detected to be no less than the second preset speed threshold and the third real-time distance is less than the system's defensive deceleration distance threshold, then the vehicle will be controlled to decelerate at a preset deceleration rate.

[0049] In an exemplary embodiment of this application, if the real-time vehicle speed is detected to be less than the second preset speed threshold and the third real-time distance is detected to be less than the system's defensive deceleration distance threshold, it indicates that the vehicle is at risk of collision but is in a medium-speed driving range, and the driver has the capacity to decelerate autonomously. In this case, a deceleration warning is issued, for example, the system may warn the driver in advance that "there is a blind spot at the intersection ahead, please slow down." If the real-time vehicle speed is detected to be not less than the second preset speed threshold and the third real-time distance is detected to be less than the system's defensive deceleration distance threshold, it indicates that the vehicle is at risk of collision and is in a high-speed driving range, requiring the system to actively intervene to ensure driving safety. In this case, the system controls the vehicle to decelerate at a preset deceleration rate and warns the driver that "there is a blind spot at the intersection ahead, and we are slowing down." Once the vehicle speed decelerates to the second preset speed threshold, the system stops braking. The specific value of the preset deceleration rate can be determined according to actual needs and is not limited here. For example, the preset deceleration rate can preferably be 1~3 m / s². 2 .

[0050] Furthermore, in one embodiment, the method further includes: If the detected third real-time distance is not less than the system's defensive deceleration distance threshold, then there is no need to control the vehicle's deceleration.

[0051] As an example, in this embodiment of the application, if the detected third real-time distance is not less than the system's defensive deceleration distance threshold, it indicates that the current longitudinal distance between the front of the vehicle and the target vehicle is sufficient to cover the distance required to deal with a potential blind spot suddenly crossing the target. This indicates that the vehicle has sufficient safety redundancy space. Even if a dangerous target appears in the blind spot, the conventional braking capability at the current vehicle speed is sufficient to ensure safe collision avoidance. The system determines that the current traffic risk is within a controllable range, so there is no need to control the vehicle to decelerate.

[0052] Furthermore, in one embodiment, before the step of determining the ghost-peeking scenario based on the target vehicle's state, the first real-time distance, and the second real-time distance, the method further includes: If the target condition is detected, the ghost peek scene recognition is initiated. If no target conditions are detected, the ghost peek scene recognition will not be activated. The target conditions include the current road type being an urban road, the presence of an intersection ahead, the vehicle being in a straight lane, and the traffic light being green.

[0053] In an exemplary embodiment of this application, the target conditions include the current road type being an urban road, the presence of an intersection ahead, the vehicle's lane being a straight lane, and the traffic light being green. The system can first obtain information on the road type, the intersection ahead, the pedestrian crossing, and the traffic light from the map. If it is identified that the current road type is an urban road, there is an intersection ahead (e.g., within 100m), the vehicle's lane is a straight lane, and the traffic light for the straight lane is green, it indicates that the vehicle is about to proceed straight through the intersection, and thus the potential ghost peek scene recognition is initiated.

[0054] It should be understood that if the current road type is not an urban road, or there is no intersection ahead, or the vehicle's lane is not a straight lane, or the traffic light for the straight lane is not green, it means that the vehicle's current driving condition does not meet the necessary environmental characteristics for a potential "ghost peek" risk scenario, and there is no scenario basis for implementing a preventive deceleration strategy. Therefore, it is determined not to activate the ghost peek scenario recognition to reduce the system's computational load and avoid erroneous intervention in non-ghost peek scenarios, ensuring the rigor of the control logic, and thereby improving the reliability of the driver assistance system and user trust.

[0055] It should be noted that, referring to Figure 3 As shown, the system first acquires road information, the position and speed of vehicles ahead using sensors such as maps, cameras, and radar, including the distance of the foremost vehicle in the adjacent lane relative to the pedestrian crossing and its lateral distance from the vehicle. Then, it uses information such as road type, intersection, lane, and traffic lights to determine if the vehicle is about to proceed straight through the intersection, such as in urban areas where the straight-ahead green light is valid. Next, when about to proceed straight through the intersection, the system determines whether a potential "ghost peek" scenario has occurred based on the stationary or rapidly decelerating status of adjacent vehicles and their position information. Once a potential "ghost peek" scenario occurs, the system calculates a defensive deceleration distance threshold based on the vehicle's speed to determine the timing for defensive warnings or deceleration. Finally, when the system determines that the timing for defensive deceleration is met, it provides a defensive warning to the driver or actively applies braking force to reduce speed based on the vehicle's speed range. This proactively controls collision risks without relying on V2X technology, ensuring that AEB can avoid collisions in time when targets appear in blind spots.

[0056] This application determines the "ghost peek" scenario by using the status of the target vehicle (the vehicle at the front of the adjacent lane), the first real-time distance between the target vehicle and the pedestrian crossing, and the second real-time lateral distance between the target vehicle and the vehicle itself. It replaces the less common V2X communication with the status and distance information of neighboring vehicles obtainable by the vehicle's sensors. This allows the system to indirectly infer blind spot risks through the relative relationship between neighboring vehicles and the pedestrian crossing even when the view is obstructed and pedestrians cannot be directly detected. This achieves early identification of potential collision risks without relying on V2X technology. In the ghost peek scenario, the system controls the vehicle to decelerate based on the real-time speed of the vehicle and the third real-time distance between the vehicle and the front of the target vehicle. By proactively reducing the vehicle speed before the actual risk occurs, sufficient reaction time and braking distance redundancy are reserved for subsequent emergency braking, thus solving the problem of insufficient timely warning and braking due to limited recognition time. This achieves effective intervention in intersection scenarios with limited visibility.

[0057] Secondly, embodiments of this application also provide a ghost peeping scene recognition and control system, the ghost peeping scene recognition and control system comprising: The first processing module is used to determine the ghost peek scenario based on the state of the target vehicle, the first real-time distance and the second real-time distance. The target vehicle is the vehicle at the front of the adjacent lane, the first real-time distance is the distance between the target vehicle and the pedestrian crossing, and the second real-time distance is the lateral distance between the target vehicle and the vehicle itself. The second processing module is used to control the vehicle to decelerate based on the vehicle's real-time speed and a third real-time distance in the ghost-peeking scenario. The third real-time distance is the distance between the front of the vehicle and the target vehicle.

[0058] Furthermore, in one embodiment, the first processing module is specifically used for: If the target vehicle is detected to be stationary, the first ghost peek scenario is determined based on the first real-time distance and the second real-time distance. If the target vehicle is detected to be decelerating, a second ghost peek scenario is determined based on the target vehicle's real-time deceleration, the first real-time distance, and the second real-time distance. The risk level of the first ghost peek scenario is lower than that of the second ghost peek scenario.

[0059] Furthermore, in one embodiment, the first processing module is specifically used for: If the first real-time distance is less than the first preset pedestrian crossing distance threshold and the second real-time distance is less than the preset lateral distance threshold, then it is determined that there is a first ghost peek scene. If the first real-time distance is not less than the first preset pedestrian crossing distance threshold or the second real-time distance is not less than the preset lateral distance threshold, it is determined that there is no first ghost peek scene.

[0060] Furthermore, in one embodiment, the first processing module is specifically used for: If the real-time deceleration of the target vehicle is detected to be greater than the preset deceleration threshold, the first real-time distance is less than the second preset pedestrian crossing distance threshold, and the second real-time distance is less than the preset lateral distance threshold, then it is determined that there is a second ghost peek scenario. If the real-time deceleration of the target vehicle is not greater than a preset deceleration threshold, or the first real-time distance is not less than a second preset pedestrian crossing distance threshold, or the second real-time distance is not less than a preset lateral distance threshold, then it is determined that there is no second ghost peek scenario.

[0061] Furthermore, in one embodiment, the second processing module is specifically used for: The system defensive deceleration distance threshold is determined based on the vehicle's real-time speed, preset safe braking distance, preset system response time, preset actuator delay time, and preset system defensive deceleration time. The vehicle deceleration is controlled based on the real-time vehicle speed, a first preset speed threshold, a second preset speed threshold, a third real-time distance, and a system defensive deceleration distance threshold, wherein the first preset speed threshold is less than the second preset speed threshold.

[0062] Furthermore, in one embodiment, the second processing module is specifically used for: If the real-time speed of the vehicle is detected to be less than the first preset speed threshold, there is no need to control the vehicle to decelerate. If the vehicle's real-time speed is detected to be not less than the first preset speed threshold, the vehicle will decelerate based on its real-time speed, the second preset speed threshold, the third real-time distance, and the system's defensive deceleration distance threshold.

[0063] Furthermore, in one embodiment, the second processing module is specifically used for: If the vehicle's real-time speed is detected to be less than the second preset speed threshold and the third real-time distance is less than the system's defensive deceleration distance threshold, a deceleration reminder will be issued. If the vehicle's real-time speed is detected to be no less than the second preset speed threshold and the third real-time distance is less than the system's defensive deceleration distance threshold, then the vehicle will be controlled to decelerate at a preset deceleration rate.

[0064] Furthermore, in one embodiment, the second processing module is specifically used for: If the detected third real-time distance is not less than the system's defensive deceleration distance threshold, then there is no need to control the vehicle's deceleration.

[0065] Furthermore, in one embodiment, the first processing module is specifically used for: If the target condition is detected, the ghost peek scene recognition is initiated. If no target conditions are detected, the ghost peek scene recognition will not be activated. The target conditions include the current road type being an urban road, the presence of an intersection ahead, the vehicle being in a straight lane, and the traffic light being green.

[0066] This application determines the "ghost peek" scenario by using the status of the target vehicle (the vehicle at the front of the adjacent lane), the first real-time distance between the target vehicle and the pedestrian crossing, and the second real-time lateral distance between the target vehicle and the vehicle itself. It replaces the less common V2X communication with the status and distance information of neighboring vehicles obtainable by the vehicle's sensors. This allows the system to indirectly infer blind spot risks through the relative relationship between neighboring vehicles and the pedestrian crossing even when the view is obstructed and pedestrians cannot be directly detected. This achieves early identification of potential collision risks without relying on V2X technology. In the ghost peek scenario, the system controls the vehicle to decelerate based on the real-time speed of the vehicle and the third real-time distance between the vehicle and the front of the target vehicle. By proactively reducing the vehicle speed before the actual risk occurs, sufficient reaction time and braking distance redundancy are reserved for subsequent emergency braking, thus solving the problem of insufficient timely warning and braking due to limited recognition time. This achieves effective intervention in intersection scenarios with limited visibility.

[0067] The functions of each module in the above-mentioned ghost peep scene recognition and control system correspond to the steps in the above-mentioned ghost peep scene recognition and control method embodiment, and their functions and implementation processes will not be described in detail here.

[0068] Thirdly, embodiments of this application also provide a vehicle having the ghost-protruding scene recognition and control system described above.

[0069] Fourthly, embodiments of this application provide a ghost peeping scene recognition and control device, which can be a personal computer (PC), laptop computer, server or other device with data processing capabilities.

[0070] Reference Figure 4 , Figure 4 This is a schematic diagram of the hardware structure of the ghost peep scene recognition and control device involved in the embodiments of this application. In the embodiments of this application, the ghost peep scene recognition and control device may include a processor, a memory, a communication interface, and a communication bus.

[0071] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0072] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting internal components of the ghost peep scene recognition and control equipment, as well as interfaces used for interconnecting the ghost peep scene recognition and control equipment with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0073] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0074] The processor can be a general-purpose processor, which can call the ghost peep scene recognition and control program stored in the memory and execute the ghost peep scene recognition and control method provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the ghost peep scene recognition and control program is called can be referred to in the various embodiments of the ghost peep scene recognition and control method of this application, and will not be repeated here.

[0075] Those skilled in the art will understand that Figure 4 The hardware structure shown does not constitute a limitation of this application and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0076] Fifthly, embodiments of this application also provide a readable storage medium.

[0077] The present application has a readable storage medium storing a ghost peep scene recognition and control program, wherein when the ghost peep scene recognition and control program is executed by a processor, it implements the steps of the ghost peep scene recognition and control method described above.

[0078] The method implemented when the ghost peek scene recognition and control program is executed can be referred to in the various embodiments of the ghost peek scene recognition and control method of this application, and will not be repeated here.

[0079] The terms "comprising" and "having," and any variations thereof, in the specification and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0080] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0081] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0082] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0083] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0084] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0085] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A ghosting scene recognition and control method, characterized in that, The method for identifying and controlling ghost peek-out scenes includes: The ghost peek scenario is determined based on the status of the target vehicle, the first real-time distance, and the second real-time distance. The target vehicle is the vehicle at the front of the adjacent lane. The first real-time distance is the distance between the target vehicle and the pedestrian crossing. The second real-time distance is the lateral distance between the target vehicle and the vehicle itself. In the scenario of a vehicle suddenly appearing out of nowhere, the vehicle decelerates based on its real-time speed and a third real-time distance, where the third real-time distance is the distance between the front of the vehicle and the target vehicle.

2. The method of claim 1, wherein the ghosting scene recognition and control method is characterized by, The method of determining the ghost peek scenario based on the target vehicle's state, the first real-time distance, and the second real-time distance includes: If the target vehicle is detected to be stationary, the first ghost peek scenario is determined based on the first real-time distance and the second real-time distance. If the target vehicle is detected to be decelerating, a second ghost peek scenario is determined based on the target vehicle's real-time deceleration, the first real-time distance, and the second real-time distance. The risk level of the first ghost peek scenario is lower than that of the second ghost peek scenario.

3. The method of claim 2, wherein the ghosting scene recognition and control method is characterized by, The determination of the first ghost peek scene based on the first real-time distance and the second real-time distance includes: If the first real-time distance is less than the first preset pedestrian crossing distance threshold and the second real-time distance is less than the preset lateral distance threshold, then it is determined that there is a first ghost peek scene. If the first real-time distance is not less than the first preset pedestrian crossing distance threshold or the second real-time distance is not less than the preset lateral distance threshold, it is determined that there is no first ghost peek scene.

4. The method of claim 2, wherein the ghosting scene recognition and control method is characterized by, The determination of the second "ghost peek" scenario based on the target vehicle's real-time deceleration, first real-time distance, and second real-time distance includes: If the real-time deceleration of the target vehicle is detected to be greater than the preset deceleration threshold, the first real-time distance is less than the second preset pedestrian crossing distance threshold, and the second real-time distance is less than the preset lateral distance threshold, then it is determined that there is a second ghost peek scenario. If the real-time deceleration of the target vehicle is not greater than a preset deceleration threshold, or the first real-time distance is not less than a second preset pedestrian crossing distance threshold, or the second real-time distance is not less than a preset lateral distance threshold, then it is determined that there is no second ghost peek scenario.

5. The ghost peek scene recognition and control method as described in claim 1, characterized in that, The method of controlling the vehicle's deceleration based on the vehicle's real-time speed and a third real-time distance includes: The system defensive deceleration distance threshold is determined based on the vehicle's real-time speed, preset safe braking distance, preset system response time, preset actuator delay time, and preset system defensive deceleration time. The vehicle deceleration is controlled based on the real-time vehicle speed, a first preset speed threshold, a second preset speed threshold, a third real-time distance, and a system defensive deceleration distance threshold, wherein the first preset speed threshold is less than the second preset speed threshold.

6. The ghost peek scene recognition and control method as described in claim 5, characterized in that, The method of controlling the vehicle's deceleration based on the vehicle's real-time speed, a first preset speed threshold, a second preset speed threshold, a third real-time distance, and a system defensive deceleration distance threshold includes: If the real-time speed of the vehicle is detected to be less than the first preset speed threshold, there is no need to control the vehicle to decelerate. If the vehicle's real-time speed is detected to be not less than the first preset speed threshold, the vehicle will decelerate based on its real-time speed, the second preset speed threshold, the third real-time distance, and the system's defensive deceleration distance threshold.

7. The ghost peek scene recognition and control method as described in claim 6, characterized in that, The method of controlling the vehicle's deceleration based on the vehicle's real-time speed, a second preset speed threshold, a third real-time distance, and a system defensive deceleration distance threshold includes: If the vehicle's real-time speed is detected to be less than the second preset speed threshold and the third real-time distance is less than the system's defensive deceleration distance threshold, a deceleration reminder will be issued. If the vehicle's real-time speed is detected to be no less than the second preset speed threshold and the third real-time distance is less than the system's defensive deceleration distance threshold, then the vehicle will be controlled to decelerate at a preset deceleration rate.

8. The ghost peek scene recognition and control method as described in claim 7, characterized in that, The method further includes: If the detected third real-time distance is not less than the system's defensive deceleration distance threshold, then there is no need to control the vehicle's deceleration.

9. The ghost peek scene recognition and control method as described in claim 1, characterized in that, Before the step of determining the ghost-peeking scenario based on the target vehicle's state, the first real-time distance, and the second real-time distance, the method further includes: If the target condition is detected, the ghost peek scene recognition is initiated. If no target conditions are detected, the ghost peek scene recognition will not be activated. The target conditions include the current road type being an urban road, the presence of an intersection ahead, the vehicle being in a straight lane, and the traffic light being green.

10. A ghost peek-out scene recognition and control system, characterized in that, The ghost peek scene recognition and control system includes: The first processing module is used to determine the ghost peek scenario based on the state of the target vehicle, the first real-time distance and the second real-time distance. The target vehicle is the vehicle at the front of the adjacent lane, the first real-time distance is the distance between the target vehicle and the pedestrian crossing, and the second real-time distance is the lateral distance between the target vehicle and the vehicle itself. The second processing module is used to control the vehicle to decelerate based on the vehicle's real-time speed and a third real-time distance in the ghost-peeking scenario. The third real-time distance is the distance between the front of the vehicle and the target vehicle.

11. The ghost peek scene recognition and control system as described in claim 10, characterized in that, The first processing module is specifically used for: If the target vehicle is detected to be stationary, the first ghost peek scenario is determined based on the first real-time distance and the second real-time distance. If the target vehicle is detected to be decelerating, a second ghost peek scenario is determined based on the target vehicle's real-time deceleration, the first real-time distance, and the second real-time distance. The risk level of the first ghost peek scenario is lower than that of the second ghost peek scenario.

12. The ghost peek scene recognition and control system as described in claim 10, characterized in that, The first processing module is specifically used for: If the first real-time distance is less than the first preset pedestrian crossing distance threshold and the second real-time distance is less than the preset lateral distance threshold, then it is determined that there is a first ghost peek scene. If the first real-time distance is not less than the first preset pedestrian crossing distance threshold or the second real-time distance is not less than the preset lateral distance threshold, it is determined that there is no first ghost peek scene.

13. A vehicle, characterized in that, Including the ghost peek scene recognition and control system as described in any one of claims 10-12.

14. A device for recognizing and controlling ghost peek-out scenes, characterized in that, The ghost peep scene recognition and control device includes a processor, a memory, and a ghost peep scene recognition and control program stored in the memory and executable by the processor, wherein when the ghost peep scene recognition and control program is executed by the processor, it implements the steps of the ghost peep scene recognition and control method as described in any one of claims 1 to 9.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a ghost peep scene recognition and control program, wherein when the ghost peep scene recognition and control program is executed by a processor, it implements the steps of the ghost peep scene recognition and control method as described in any one of claims 1 to 9.

Images