Front vehicle departure reminder method, device and storage medium

Abstract

The application relates to the field of assisted driving, and discloses a front vehicle departure reminding method, equipment and a storage medium, the method comprising the following steps: acquiring a road category corresponding to a current vehicle and a road state; in response to the road category being a main road and the road state being a non-clustered state, acquiring a dynamic state of the current vehicle; in response to the dynamic state being a static state, acquiring front perception information of the current vehicle; wherein the front perception information comprises front traffic object perception information and front vehicle perception information; and according to the front perception information, it is judged whether the current vehicle is controlled to send a front vehicle departure reminding. Through the technical scheme of the application, the effect of accurately judging whether to send a front vehicle departure reminding in combination with a vehicle scene is realized, the reminding false alarm is reduced, and the user experience is improved.

Description

Technical Field

[0001] This invention relates to the field of driver assistance systems, and more particularly to a method, device, and storage medium for alerting when a vehicle ahead departs. Background Technology

[0002] Current intelligent driving systems activate a "lead vehicle departure warning" when the vehicle is stationary. This warning alerts the driver via sound after the vehicle in front has moved away from the stop line, prompting them to take over the vehicle promptly.

[0003] However, in actual driving, especially in congested areas, vehicles ahead often stop and start, leading to frequent alerts for the driver. Furthermore, when the vehicle is at an intersection and in the lead position, frequent alerts indicating the vehicle ahead is leaving the road can also occur while waiting at a traffic light. Moreover, the current alert recognition system may misidentify non-motorized vehicles as vehicles ahead in scenarios where two-wheeled vehicles have entered the motorized vehicle lane, motorized vehicles have entered the non-motorized vehicle lane, or in crowded situations, and may also misidentify a vehicle turning ahead as if it is leaving the road, all of which can lead to false alarms. Frequent alerts and false alarms can cause driver frustration and even negatively impact driving safety.

[0004] In view of this, the present invention is proposed to improve the accuracy of issuing warnings when the vehicle in front leaves by combining the current scene of the vehicle and accurately analyzing the perception information ahead. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a method, device, and storage medium for issuing a forward vehicle departure warning, which achieves the effect of accurately determining whether to issue a forward vehicle departure warning based on the vehicle scenario, reducing false alarms and improving user experience.

[0006] This invention provides a method for alerting when a vehicle in front has left the lane, the method comprising:

[0007] Obtain the road category and road status corresponding to the current vehicle;

[0008] In response to the road category being a main road and the road state being non-crowded, the current vehicle's dynamic and static status is obtained.

[0009] In response to the dynamic state being a stationary state, the forward perception information of the current vehicle is acquired; wherein, the forward perception information includes forward traffic object perception information and forward vehicle perception information.

[0010] Based on the forward perception information, determine whether to control the current vehicle to issue a warning that the vehicle in front has left.

[0011] This invention provides an electronic device, the electronic device comprising:

[0012] Processor and memory;

[0013] The processor executes the steps of the preceding vehicle departure warning method described in any embodiment by calling the program or instructions stored in the memory.

[0014] This invention provides a computer-readable storage medium storing a program or instructions that cause a computer to perform the steps of the preceding vehicle departure warning method described in any embodiment.

[0015] The embodiments of the present invention have the following technical effects: by obtaining the road category and road status corresponding to the current vehicle, in response to the road category being a main road and the road status being non-crowded, the dynamic and static status of the current vehicle is obtained to determine whether it is necessary to continue sensing. In response to the dynamic and static status being static, the forward sensing information of the current vehicle is obtained to monitor the forward environment and the situation of the vehicles in front. Furthermore, based on the forward sensing information, it is determined whether to control the current vehicle to issue a forward vehicle departure warning. This achieves the effect of accurately determining whether to issue a forward vehicle departure warning by combining the vehicle scenario, reducing false alarms and improving the user experience. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the system structure of an intelligent driving ACC system;

[0018] Figure 2 This is a flowchart of a method for alerting a vehicle to leave the road, provided in an embodiment of the present invention;

[0019] Figure 3 This is a schematic diagram illustrating a method for identifying road conditions according to an embodiment of the present invention;

[0020] Figure 4 This is a flowchart of another method for alerting a vehicle to leave, provided in an embodiment of the present invention;

[0021] Figure 5 This is a schematic diagram of a scenario showing a change in the motion state of a vehicle ahead, provided by an embodiment of the present invention;

[0022] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0024] Currently, the intelligent driving ACC (Adaptive Cruise Control) system includes a sensor layer, a decision-making layer, and an execution layer. The sensor layer can include millimeter-wave radar, cameras, wheel speed sensors, etc.; the decision-making layer mainly includes the controller, used for data processing, target tracking, and various control algorithms; the execution layer includes the powertrain and braking systems, specifically... Figure 1 As shown, a "vehicle ahead has departed" warning function is available when the vehicle is stationary. However, in actual engineering practice, the warning is triggered only when no vehicle is detected in front of the vehicle. However, this warning should not be triggered when the vehicle is the lead vehicle at an intersection, or when the vehicle is waiting at a traffic light. Therefore, this false "vehicle ahead has departed" warning is frequently encountered in various vehicle projects, causing significant inconvenience to end users.

[0025] The preceding vehicle departure warning method provided in this embodiment of the invention is mainly applicable to situations where the vehicle's surrounding environment and the vehicle ahead are detected and identified, accurately providing a preceding vehicle departure warning. The preceding vehicle departure warning method provided in this embodiment of the invention can be executed by electronic devices such as an onboard controller.

[0026] Figure 2 This is a flowchart of a method for alerting a vehicle to leave the road, provided in an embodiment of the present invention. See also... Figure 2 The specific methods for alerting the vehicle in front to leave include:

[0027] S110. Obtain the road category and road status corresponding to the current vehicle.

[0028] Here, "current vehicle" refers to the vehicle currently being driven, which is the vehicle that will issue the warning when the vehicle in front leaves. Road categories include main roads and off-road roads. Road status describes the road congestion situation, including congested and non-congested states. Congested state means that the area corresponding to the current vehicle is congested and moving slowly. Non-congested state means that the area corresponding to the current vehicle is experiencing smooth traffic flow.

[0029] Specifically, by using various sensors installed on the vehicle, it is possible to analyze the road type the vehicle is currently on, as well as the road conditions around the vehicle. Navigation maps and other tools can also be used to determine the road type the vehicle is currently on.

[0030] Based on the above example, the road category corresponding to the current vehicle can be obtained in the following way:

[0031] Based on the visual sensors on the vehicle, identify the positions of the left and right lane lines corresponding to the current vehicle.

[0032] Determine the lane width based on the positions of the left and right lane lines;

[0033] If the lane width is greater than the first preset width, the roadside information corresponding to the current vehicle is identified based on the visual sensor.

[0034] Based on the curb information, determine the road category corresponding to the current vehicle.

[0035] The vision sensor is used to acquire image information. The left lane line position is the position of the lane line to the left of the current vehicle and adjacent to it, and the right lane line position is the position of the lane line to the right of the current vehicle and adjacent to it. The lane width is the horizontal distance between the left and right lane line positions. The first preset width is a pre-set lane width used to identify the main road lane, such as 2.8m. Curb information may include the number of captured curbs and their positions.

[0036] Specifically, the vehicle's vision sensors acquire lane lines on both sides, allowing analysis and identification of the left and right lane line positions. The distance between these positions is defined as the lane width. Further, it's determined whether the lane width exceeds a preset width. If it does, the lane is considered wide enough, and the road type is likely a main road. Further, the vision sensors are used to acquire information about the curbs on both sides of the vehicle to determine if the overall road width is sufficient to classify the road. For example, if the road is wide enough, it's considered a main road; otherwise, it's considered a non-main road. If the lane width is less than the preset width, the lane is too narrow and not a main road lane, thus classifying the road as a non-main road.

[0037] Based on the above example, the road category corresponding to the current vehicle can be determined according to the curb information in the following way:

[0038] If the number of curbs in the curb information is 0 or 1, then the road category corresponding to the current vehicle is determined to be a main road.

[0039] If the number of curbs in the curb information is 2, then the width of the adjacent curbs is determined based on the curb positions in the curb information.

[0040] If the width of the adjacent curb is greater than the second preset width, the road category corresponding to the current vehicle is determined to be a main road.

[0041] The second preset width is a pre-set width of the adjacent curb used to identify the main road lane, such as 3m.

[0042] Specifically, if the number of curbs in the curb information is 0 or 1, it means that the vehicle's visual sensors cannot completely detect adjacent curbs, indicating that the road is wide enough and the road category corresponding to the vehicle can be determined as a main road. If the number of curbs in the curb information is 2, further identification and judgment are required. The distance between the two adjacent curb positions in the curb information is taken as the adjacent curb width. If the adjacent curb width is greater than a second preset width, it means that the road is wide enough and the road category corresponding to the vehicle can be determined as a main road; otherwise, the road category corresponding to the vehicle is determined to be a non-main road.

[0043] Based on the above example, the current road status of the vehicle can be obtained in the following way:

[0044] The surrounding area corresponding to the current vehicle is determined based on the preset forward distance and preset lateral distance;

[0045] Based on the visual sensors on the vehicle, identify the length of the lane line corresponding to the current vehicle and information on moving objects in the surrounding area;

[0046] If the lane line length is greater than or equal to a preset length, the road state corresponding to the current vehicle is determined to be non-crowded.

[0047] If the lane line length is less than the preset length, the road condition corresponding to the current vehicle is determined based on the information of surrounding moving objects.

[0048] The preset forward distance and preset lateral distance are pre-set distances used to plan the area surrounding the current vehicle. For example, the preset forward distance is 2m, and the preset lateral distance is 5m. The surrounding area is the area observed by the current vehicle when recognizing road conditions, typically including the area in front and the areas on both sides. The lane line length is the length of the lane lines on both sides of the current vehicle that can be detected. The surrounding moving object information is relevant information about moving objects in the surrounding area, which can include type, speed, etc. The preset length is a pre-set length used to determine whether lane lines cannot be continuously detected, such as 10m.

[0049] Specifically, based on preset forward and lateral distances, the surrounding area corresponding to the current vehicle is planned. Using the vehicle's vision sensors, lane lines on both sides of the vehicle are identified to obtain lane line lengths. Furthermore, moving objects within the surrounding area are monitored to obtain information about these moving objects. If the lane line length is greater than or equal to the preset length, it indicates that a relatively long lane line can be continuously detected, meaning the lane line is not obstructed by other objects, and the road condition corresponding to the current vehicle can be determined as non-crowded. If the lane line length is less than the preset length, it indicates that the lane line is obstructed. In this case, the type and speed of the moving objects need to be analyzed to determine whether there is slow traffic or lane lapse, in order to further determine the road condition corresponding to the current vehicle.

[0050] Based on the above example, the road condition corresponding to the current vehicle can be determined according to information about surrounding moving objects in the following way:

[0051] If the type of moving object in the surrounding moving object information is the first category and the minimum speed of the moving object in the surrounding moving object information is less than the preset speed, then the road state corresponding to the current vehicle is determined to be a crowded state.

[0052] If the type of moving object in the surrounding moving object information is not the first category and / or the lowest moving speed in the surrounding moving object information is greater than or equal to a preset speed, then the road state corresponding to the current vehicle is determined to be a non-crowded state.

[0053] The first category can be non-motorized vehicles, such as two-wheeled vehicles or pedestrians. For example, an image of the surrounding environment can be captured by a camera installed on the vehicle. Image recognition can then be used to identify the types of moving objects in the surrounding environment. For instance, each moving object in the environment can be classified and identified to determine if it belongs to the first category. Of course, other methods for identifying moving object types can also be used, without specific limitations. The classification algorithm can be K-Means clustering, hierarchical clustering, DBSCAN (Density-Based Spatial Clustering of Applications with Noise), spectral clustering, GMM (Gaussian Mixture Model), etc. The minimum speed is the slowest speed among all surrounding moving objects. The preset speed is a pre-set speed used to determine slow movement, such as 10 kph.

[0054] Specifically, if the type of moving object in the surrounding moving object information is Category 1 and the minimum speed in the surrounding moving object information is less than the preset speed, it indicates that there are non-motorized vehicles around the current vehicle, and their speed is relatively slow. Therefore, the road state corresponding to the current vehicle can be determined to be a congested state. If the type of moving object in the surrounding moving object information is not Category 1 and / or the minimum speed in the surrounding moving object information is greater than or equal to the preset speed, it can be considered that the current vehicle is surrounded by wide open space, and its movement speed can be guaranteed. Therefore, the road state corresponding to the current vehicle is determined to be a non-congested state.

[0055] An example diagram illustrating road condition identification is shown below. Figure 3 As shown, based on the visual sensors on the vehicle, the system identifies the lane information and surrounding moving objects. If the lane length (t) is less than 10 meters, and there are two-wheeled vehicles or pedestrians (of the first category of moving objects) within 5 meters to either side of the vehicle, and the distance (df) between the vehicle and the vehicle in front is less than 2 meters, and the lowest speed (v) of the surrounding moving objects within 5 meters to either side of the vehicle is less than 10 kph, then the system is considered to be crowding. All parameters can be calibrated and adjusted based on vehicle size, real-world driving experience, etc. Specific values ​​are not limited in this embodiment.

[0056] S120. In response to the road category being a main road and the road state being non-crowded, the current vehicle's dynamic and static status is obtained.

[0057] Among them, dynamic and static states are used to describe whether the vehicle is currently moving or stationary, including stationary and moving states.

[0058] Specifically, if the road type is a main road and the road status is non-crowded, it means that the road is wide and easy to drive on, which can trigger the subsequent process of reminding the vehicle in front to leave. Therefore, the current vehicle's dynamic and static status can be obtained. For example, the current vehicle's speed can be obtained. If the vehicle speed is 0, the current vehicle's dynamic and static status is determined to be stationary. Otherwise, the current vehicle's dynamic and static status is determined to be in motion.

[0059] S130, in response to the dynamic state being stationary, obtain the forward perception information of the current vehicle.

[0060] Among them, the forward perception information is the information perceived directly in front of the current vehicle, including the perception information of traffic objects ahead and the perception information of vehicles ahead. The perception information of traffic objects ahead may include traffic lights, stop lines, etc., and the perception information of vehicles ahead may include the type, speed, direction, etc. of the vehicles ahead of the current vehicle.

[0061] Specifically, if the dynamic state is stationary, it means that the current vehicle may have stopped due to the vehicle in front stopping. Therefore, the subsequent warning process of the vehicle in front leaving can be triggered, which requires obtaining the forward perception information of the current vehicle through various sensors on the current vehicle.

[0062] S140. Based on the information perceived ahead, determine whether to control the current vehicle to issue a warning that the vehicle in front has left.

[0063] Among them, the vehicle ahead departure reminder is a notification issued by the current vehicle that the vehicle in front has left, and the driver can activate the vehicle's reminder function.

[0064] Specifically, analyzing the forward-facing perception information first requires determining if there are any tracking vehicles traveling in the same direction ahead. This can be achieved by continuously detecting a vehicle ahead and using radar or other sensors to detect its information. The relative motion between this vehicle and the current vehicle is then assessed to determine if it is a tracking vehicle traveling in the same direction. For example, relevant information includes longitudinal relative speed, lateral angle, and the vehicle's orientation. Combining the lateral angle with the forward-facing vehicle's orientation helps determine if they are in the same lane, thus eliminating vehicles in other lanes. Further analysis can be conducted on vehicles whose orientation is the same as or roughly the same as the current vehicle's direction of movement. If the longitudinal relative speed is positive or close to zero, it indicates that the vehicle ahead is traveling in the same direction as the current vehicle, i.e., traveling in the same direction.

[0065] If so, it is necessary to further determine whether the vehicle in front has moved away and whether the current vehicle can start safely. If both conditions are met, it means that the departure of the vehicle in front can remind the current vehicle to start. Therefore, it is necessary to control the current vehicle to issue a reminder that the vehicle in front has moved away.

[0066] Building upon the examples above, there are also cases where the road category is a main road and the road status is non-crowded. In such cases, the following operations can be performed:

[0067] In response to a road category of non-main road and / or a road condition of congestion, the current vehicle is prohibited from issuing a warning that the vehicle in front has left.

[0068] Specifically, if the road category is non-main road and / or the road status is congested, it means that the current road is not suitable for triggering the preceding vehicle departure reminder. If enabled, it may issue reminders frequently, affecting the user experience. Therefore, it is possible to directly prohibit the current vehicle from issuing the preceding vehicle departure reminder.

[0069] The present invention has the following technical effects: by obtaining the road category and road status corresponding to the current vehicle, in response to the road category being a main road and the road status being non-crowded, the dynamic and static status of the current vehicle is obtained to determine whether to continue sensing. In response to the dynamic and static status being static, the forward sensing information of the current vehicle is obtained to monitor the forward environment and the situation of the vehicles in front. Furthermore, based on the forward sensing information, it is determined whether to control the current vehicle to issue a forward vehicle departure warning. This achieves the effect of accurately determining whether to issue a forward vehicle departure warning by combining the vehicle scenario, reducing false alarms and improving user experience.

[0070] Figure 4 This is a flowchart of another method for alerting a departing vehicle provided in an embodiment of the present invention. See also... Figure 4 The specific methods for alerting the vehicle in front to leave include:

[0071] S210. Obtain the road category and road status corresponding to the current vehicle.

[0072] S220. In response to the road category being a main road and the road state being non-crowded, the current vehicle's dynamic and static status is obtained.

[0073] S230, in response to the vehicle being stationary in a dynamic or static state, obtain the forward perception information of the current vehicle.

[0074] S240. Based on the forward perception information, determine whether the current vehicle is at the stop line. If yes, proceed to S250; otherwise, proceed to S260.

[0075] Specifically, by using the information on the traffic ahead in the forward perception information, it can be determined whether the vehicle in front is at the stop line, that is, whether it is in the first position when stopping, such as when there are no other vehicles in front while waiting at a red light, and the current vehicle is in the first position.

[0076] S250, Prohibit the current vehicle from issuing a warning that the vehicle in front has left.

[0077] Specifically, since the current vehicle is at the stop line, which is the first position and there are no vehicles blocking its path, the current vehicle is prohibited from issuing a "vehicle ahead departs" warning to avoid frequently triggering the warning due to the absence of vehicles ahead.

[0078] S260. Based on the information perceived ahead, determine whether the traffic light is in a prohibited state. If yes, proceed to S270; otherwise, proceed to S280.

[0079] The prohibited state is the red light state, while the permitted state can include the green light state, no light state, etc.

[0080] Specifically, by using the information on traffic objects ahead in the forward perception information, the status of traffic lights can be determined, that is, whether the traffic lights are in a prohibited state.

[0081] S270. Prohibit the current vehicle from issuing a warning that the vehicle in front has left.

[0082] Specifically, if the traffic light is in a no-passing state, it means that the current vehicle is waiting for the red light and there is no need to trigger the reminder for the vehicle in front to leave.

[0083] S280. Based on the information of the vehicle ahead in the forward perception information, determine whether to control the current vehicle to issue a warning that the vehicle ahead has left.

[0084] Specifically, since the current vehicle is not at the stop line and the traffic light is not in a prohibited state, the vehicle in front of the current vehicle may move away at any time, and the current vehicle can continue driving. Therefore, it is necessary to monitor the vehicle in front in a timely manner. That is, to obtain the information of the vehicle in front from the forward perception information in real time, determine whether the vehicle in front has started to move in the same direction, and leave a safe distance for the current vehicle to start moving. If so, the current vehicle can be controlled to issue a warning that the vehicle in front has moved away, so as to remind the driver of the current vehicle to start the vehicle. If not, monitoring continues.

[0085] It is understandable that information about vehicles ahead can be obtained through the perception and recognition capabilities of visual sensors and intelligent driving sensors.

[0086] Based on the above example, if the information about the vehicle ahead includes the speed of the vehicle ahead, the relative distance between the vehicle ahead and the current vehicle, whether the vehicle ahead and the current vehicle are in the same lane, the type of moving object in the vehicle ahead, whether the vehicle ahead and the current vehicle are traveling in the same direction, and whether the vehicle ahead is being followed by the current vehicle, then the following method can be used to determine whether to control the current vehicle to issue a warning that the vehicle ahead has left, based on the information about the vehicle ahead in the forward perception information:

[0087] Based on the information of the vehicles ahead, determine whether the conditions for each vehicle to leave are met.

[0088] In response to the condition that all preceding vehicles have departed being met, the current vehicle is controlled to issue a warning that the preceding vehicle has departed.

[0089] If at least one condition for the preceding vehicle to leave is not met, the current vehicle is prohibited from issuing a preceding vehicle departure warning.

[0090] The conditions for the preceding vehicle to leave include: the preceding vehicle's speed being greater than a preset preceding vehicle speed; the relative distance between the preceding vehicle and the current vehicle being greater than a preset distance; the preceding vehicle and the current vehicle being in the same lane; the preceding vehicle's moving object being of the second category; the preceding vehicle and the current vehicle being traveling in the same direction; and the preceding vehicle being tracked by the current vehicle. The preceding vehicle speed is the speed detected by the current vehicle, and the preset preceding vehicle speed is a pre-set speed used to determine whether the preceding vehicle has fully started moving. The relative distance between the preceding vehicle and the current vehicle can be the distance between the two vehicles detected by radar, etc., and the preset distance is a pre-set distance used to determine whether the preceding vehicle has left enough space for the current vehicle to start moving. The second category can include two-wheeled vehicles, cars, trucks, etc. Being tracked by the current vehicle can refer to whether the preceding vehicle is continuously tracked (the relative distance and speed of the preceding vehicle do not change continuously), that is, whether the identifier of the preceding vehicle remains unchanged continuously through continuous detection by software. The identifier of the preceding vehicle refers to the fixed identifier assigned to each identified preceding vehicle by the sensing end. The identifier can be understood as a number; that is, the vehicle provides an identifier for each detected preceding vehicle to distinguish it from other vehicles. This identifier can be randomly generated. The marker remains unchanged as long as the vehicle ahead is continuously detected and tracked. If the marker changes, it indicates a new vehicle ahead. This implies a change in the relative distance between the current and preceding vehicles, leading to its identification as a new vehicle ahead. This confirms a change in the preceding vehicle's motion state, including: oncoming traffic, traveling in the same direction, crossing from the left, and crossing from the right. The motion state can be determined by analyzing the vehicle's own forward perception information. For example,... Figure 5The diagram illustrates a scenario where the movement of a vehicle ahead changes. When the vehicle ahead turns, its movement changes from crossing to traveling in the same direction. Although this changes the movement and causes a tracking disconnection, it does not meet the condition that the vehicle ahead is being tracked by the current vehicle. Therefore, such vehicles should be excluded from the tracking list and no alarm should be triggered.

[0091] Specifically, by continuously acquiring information about vehicles ahead, it's possible to continuously determine whether the conditions for a vehicle to leave are met. These conditions include: the speed of the vehicle ahead is greater than a preset speed; the relative distance between the vehicle ahead and the current vehicle is greater than a preset distance; the vehicle ahead and the current vehicle are in the same lane; the moving object type of the vehicle ahead is category two; the vehicle ahead and the current vehicle are traveling in the same direction; and the vehicle ahead is being followed by the current vehicle. If all conditions for a vehicle to leave are met, it means the vehicle ahead has left, and the current vehicle can start. Therefore, it can be controlled to issue a warning that the vehicle ahead has left. If at least one condition for a vehicle to leave is not met, to avoid frequent false alarms, the current vehicle is prohibited from issuing a warning that the vehicle ahead has left.

[0092] For example, the vehicle can use visual sensors to determine the surrounding operating environment information, that is, to obtain the road category and road status corresponding to the vehicle, to confirm whether the road category is a main road, and to determine whether the current road status is congested. If all conditions are met, the vehicle can use the perception and recognition capabilities of the intelligent driving sensors and the motion posture of each target (forward perception information) to make a combined judgment and make a confirmation to reduce false alarms of the vehicle leaving the road. If the vehicle enters a congested road and / or a non-main road, the visual sensors can identify the current scene and turn off the vehicle leaving the road warning.

[0093] Specifically, lane lines and road edges are identified through visual sensors. Based on lane width and road edge information, it is determined whether the current road is a main road. If the identified lane width is greater than 2.8m and meets any of the following conditions: adjacent road edge width is greater than 3m, a single road edge exists, or there is no road edge, then it is determined to be a main road. Lane line information and surrounding moving object information are detected through visual sensors. If the detected lane line length is less than 10m, and there are two-wheeled vehicles or pedestrians (Category 1) within 5m on either side of the current vehicle, and the distance between the current vehicle and the vehicle in front is less than 2m, and the speed of each target within 5m on either side of the current vehicle is less than 10kph, then it is determined to be a crowded state.

[0094] On the main road, in a non-congested traffic situation, while waiting at a traffic light:

[0095] 1. If the current vehicle is stationary and at the stop line, it is prohibited to issue a warning that the vehicle in front has moved away;

[0096] 2. If the vehicle is not at the stop line, a warning will be issued if the traffic light is green or off (the traffic light is not in a no-passing state, and the speed of the vehicle in front is greater than the preset speed T_v, the relative distance between the vehicle in front and the current vehicle is greater than the preset distance T_r, the vehicle in front and the current vehicle are in the same lane and the moving object of the vehicle in front is any one of the second category, the vehicle in front and the current vehicle are traveling in the same direction, and the target tracking status is tracking (the vehicle in front is being tracked by the current vehicle), and all of the above conditions are met simultaneously. If any one or more of the above conditions are not met, a warning will be prohibited from being issued.

[0097] In cases of congestion and / or off-road conditions, the system will disable the forward vehicle departure warning function based on information detected by the visual sensors, determining whether the road is off-road or congested.

[0098] Optionally, the determination of whether a traffic light is in a prohibited state, i.e., traffic light information, can be obtained not only through visual sensors but also through V2X (Vehicle To Everything). The current environmental information of the vehicle, such as road type, can also be obtained by relying on high-precision maps and high-precision positioning. The lane line information (such as lane width) can also be obtained through urban high-precision maps.

[0099] This invention has the following technical effects: By determining whether the current vehicle is at the stop line based on forward perception information, if so, the current vehicle is prohibited from issuing a preceding vehicle departure warning to avoid false alarms when the current vehicle is in the lead. If not, the forward perception information determines whether the traffic light is in a prohibited state. If so, the current vehicle is prohibited from issuing a preceding vehicle departure warning to avoid reminding the driver to start the vehicle when the light is red. If not, the forward perception information determines whether to control the current vehicle to issue a preceding vehicle departure warning, thereby monitoring the forward scene and the vehicles ahead to facilitate timely issuance of preceding vehicle departure warnings. This achieves the effect of combining vehicle scene analysis for reasonable analysis and timely and accurate issuance of preceding vehicle departure warnings, and directly prohibiting the generation of the warning in unreasonable situations, thus improving the user experience.

[0100] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. For example... Figure 6 As shown, the electronic device 600 includes one or more processors 601 and memory 602.

[0101] The processor 601 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 600 to perform desired functions.

[0102] The memory 602 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 601 may execute the program instructions to implement the preceding vehicle departure warning method of any embodiment of the present invention described above, and / or other desired functions. Various contents such as initial external parameters and thresholds may also be stored in the computer-readable storage medium.

[0103] In one example, electronic device 600 may further include an input device 603 and an output device 606, these components being interconnected via a bus system and / or other forms of connection mechanisms (not shown). The input device 603 may include, for example, a keyboard, a mouse, etc. The output device 606 may output various information to the outside, including warning messages, braking force, etc. The output device 606 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0104] Of course, for the sake of simplicity, Figure 6 Only some of the components of the electronic device 600 relevant to the present invention are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device 600 may include any other suitable components depending on the specific application.

[0105] In addition to the methods and devices described above, embodiments of the present invention may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps of the preceding vehicle departure warning method provided in any embodiment of the present invention.

[0106] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of the present invention. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0107] Furthermore, embodiments of the present invention may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps of the preceding vehicle departure warning method provided in any embodiment of the present invention.

[0108] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0109] It should be noted that the terminology used in this invention is for describing specific embodiments only and is not intended to limit the scope of this application. As shown in this specification, unless the context clearly indicates otherwise, words such as "a," "an," "an," and / or "the" do not specifically refer to the singular and may include the plural. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, or apparatus. Without further limitations, an element defined by the phrase "comprising an..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element.

[0110] It should also be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Unless otherwise expressly specified and limited, the terms "installed," "connected," "linked," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components. For those skilled in the art, the specific meaning of the above terms in the present invention can be understood according to the specific circumstances.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A method for alerting when a vehicle ahead has departed, characterized in that, include: Obtain the road category and road status corresponding to the current vehicle; In response to the road category being a main road and the road state being non-crowded, the current vehicle's dynamic and static status is obtained. In response to the dynamic state being a stationary state, the forward perception information of the current vehicle is acquired; wherein, the forward perception information includes forward traffic object perception information and forward vehicle perception information. Based on the forward perception information, determining whether to control the current vehicle to issue a preceding vehicle departure warning includes: determining whether the current vehicle is located at a stop line based on the forward perception information; if not located at a stop line, determining whether the traffic light is in a no-passing state based on the forward perception information; if in a no-passing state, prohibiting the current vehicle from issuing a preceding vehicle departure warning; if not in a no-passing state, determining whether to control the current vehicle to issue a preceding vehicle departure warning based on the preceding vehicle information in the forward perception information. The information about the vehicle ahead includes the speed of the vehicle ahead, the relative distance between the vehicle ahead and the current vehicle, whether the vehicle ahead and the current vehicle are in the same lane, the type of moving object of the vehicle ahead, whether the vehicle ahead and the current vehicle are traveling in the same direction, and whether the vehicle ahead is being tracked by the current vehicle. The step of determining whether to control the current vehicle to issue a warning that the vehicle in front has left based on the information of the vehicle in front of it in the forward perception information includes: Based on the information of the vehicles ahead, it is determined whether the information of the vehicles ahead meets the conditions for each vehicle to leave; in response to the condition that all conditions for leaving the vehicles ahead are met, the current vehicle is controlled to issue a warning that the vehicle ahead has left; in response to at least one condition that the vehicle ahead has left is not met, the current vehicle is prohibited from issuing a warning that the vehicle ahead has left; wherein, the conditions for leaving the vehicles ahead include the speed of the vehicle ahead being greater than a preset speed of the vehicle ahead, the relative distance between the vehicle ahead and the current vehicle being greater than a preset distance, the vehicle ahead and the current vehicle being in the same lane, the moving object of the vehicle ahead being of the second category, the vehicle ahead and the current vehicle being traveled in the same direction, and the vehicle ahead being followed by the current vehicle; the second category is a two-wheeled vehicle or a car.

2. The method according to claim 1, characterized in that, The step of obtaining the road category corresponding to the current vehicle includes: Based on the visual sensors on the current vehicle, identify the position of the left lane line and the position of the right lane line corresponding to the current vehicle; The lane width is determined based on the positions of the left and right lane lines. In response to the lane width being greater than a first preset width, the roadside information corresponding to the current vehicle is identified based on the visual sensor; Based on the curb information, the road category corresponding to the current vehicle is determined.

3. The method according to claim 2, characterized in that, The step of determining the road category corresponding to the current vehicle based on the curb information includes: If the number of road edges in the road edge information is 0 or 1, then the road category corresponding to the current vehicle is determined to be a main road. If the number of curbs in the curb information is 2, then the width of the adjacent curbs is determined based on the curb positions in the curb information. If the width of the adjacent road edge is greater than the second preset width, then the road category corresponding to the current vehicle is determined to be a main road.

4. The method according to claim 1, characterized in that, The step of obtaining the road status corresponding to the current vehicle includes: The surrounding area corresponding to the current vehicle is determined based on the preset forward distance and the preset lateral distance; Based on the visual sensors on the current vehicle, identify the lane line length corresponding to the current vehicle and the information of moving objects in the surrounding area; If the lane line length is greater than or equal to a preset length, the road state corresponding to the current vehicle is determined to be a non-crowded state. If the lane line length is less than the preset length, the road state corresponding to the current vehicle is determined based on information about surrounding moving objects.

5. The method according to claim 4, characterized in that, Determining the road state corresponding to the current vehicle based on information about surrounding moving objects includes: If the type of moving object in the surrounding moving object information is the first category and the minimum speed in the surrounding moving object information is less than a preset speed, then the road state corresponding to the current vehicle is determined to be a crowded state. If the type of moving object in the surrounding moving object information is not a first category and / or the lowest moving speed in the surrounding moving object information is greater than or equal to the preset speed, then the road state corresponding to the current vehicle is determined to be a non-crowded state; the first category is a two-wheeled vehicle or a pedestrian.

6. The method according to claim 1, characterized in that, The step of determining whether to control the current vehicle to issue a warning that the vehicle in front has left based on the forward perception information further includes: If the vehicle is located at the stop line, it is prohibited from issuing a warning that the vehicle in front has left.

7. The method according to claim 1, characterized in that, Also includes: In response to the road category being a non-main road and / or the road status being a congested state, the current vehicle is prohibited from issuing a warning that the vehicle in front has left.

8. An electronic device, characterized in that, The electronic device includes: Processor and memory; The processor executes the steps of a method for alerting a vehicle to leave as described in any one of claims 1 to 7 by calling programs or instructions stored in the memory.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program or instructions that cause a computer to perform the steps of a method for alerting a vehicle to leave as described in any one of claims 1 to 7.

Images