Vehicle collision warning method and device for merging lane and vehicle terminal

Abstract

The application relates to the field of vehicle early warning technology and discloses a vehicle collision early warning method and device for a merging lane and a vehicle terminal. The application divides a collision early warning section into an obstacle section and an open section according to the obstacle detection result of the area between the collision early warning section and a target vehicle, so that when there is an obstacle between the obstacle section and the target lane, the vehicle collision early warning is carried out according to the merging point distance between the self and the merging point, and when there is no obstacle between the obstacle section and the target lane, the vehicle collision early warning is carried out according to the merging point distance between the self and the obstacle on the target lane, the user is warned when the vehicle is in danger of collision, invalid early warning information is filtered, the intelligentization of the merging entrance early warning mechanism is realized, the user is prevented from being distracted or ignoring invalid early warning information, and the collision risk of the vehicle at the merging entrance is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle collision warning, and in particular to a vehicle collision warning method and device for merging lanes and a vehicle terminal. BACKGROUND

[0002] In contemporary society, with the acceleration of urbanization and the continuous expansion of the transportation network, the merging entrance of the highway, road ramp and other traffic nodes as an important channel connecting the city inside and outside, its entrance has also become a high-incidence area of traffic accidents, and the collision between vehicles occurs frequently, which seriously threatens the safety and smoothness of road traffic.

[0003] In order to solve the collision risk of the merging entrance, with the rapid development of vehicle intelligent technology, automobile manufacturers, map service providers and intelligent transportation system developers have introduced vehicle merging entrance warning mechanisms to provide information about merging vehicles to drivers in time, so as to enhance the alertness of drivers and reduce collision accidents caused by blind spots or judgment errors.

[0004] However, the current warning mechanism will broadcast reminders when the vehicle approaches any merging entrance, regardless of the traffic conditions of the merging entrance. Frequent and indiscriminate warning broadcasts cause drivers to face a large amount of redundant information, increase their information processing burden, and may distract the driver's attention to the road and traffic environment ahead. Moreover, drivers who are exposed to a large amount of indiscriminate warning information for a long time will habitually ignore the warning information, resulting in a significant reduction in the actual effectiveness of the warning mechanism. SUMMARY

[0005] In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not a general review, nor is it intended to determine key / important components or delineate the scope of protection of these embodiments, but as a prelude to the detailed description below.

[0006] In view of the above-mentioned shortcomings of the prior art, the present application provides a vehicle collision warning method and device for merging lanes and a vehicle terminal to realize the intelligentization of the merging entrance warning mechanism, thereby reducing the collision risk of vehicles at the merging entrance.

[0007] The present application provides a vehicle collision warning method for merging lanes, comprising: obtaining a collision warning section between a target vehicle and a lane intersection, wherein the target vehicle is traveling in a current lane, and the current lane intersects with the target lane at the lane intersection; performing obstacle detection on an area between the collision warning section and the target lane, and dividing the collision warning section into an obstacle section and an open section according to the obstacle detection result, wherein there is an obstacle between the obstacle section and the target lane, and there is no obstacle between the open section and the target lane; if the target vehicle is traveling in the obstacle section, a vehicle collision warning is performed based on the intersection distance between the target vehicle and the lane intersection; if the target vehicle is traveling in the open section, obstacle detection is performed on the target lane by a vehicle sensor provided on the target vehicle to obtain a target lane obstacle, and a vehicle collision warning is performed based on the obstacle distance between the target vehicle and the target lane obstacle.

[0008] In one embodiment of the present application, it is determined that the target vehicle is traveling in the current lane in the following manner: if the target vehicle is traveling on a vehicle road, road information corresponding to the vehicle road is obtained, wherein the vehicle road is composed of driving lanes, and the road information includes the number of lanes corresponding to the driving lanes and the lane types corresponding to each of the driving lanes; lane lines are identified on the vehicle road to obtain the lane line types corresponding to each of the lane lines, and lane edges corresponding to each of the driving lanes are determined from each of the lane lines based on the lane line types and the lane types; the current lane is determined from each of the driving lanes based on the number of lanes and the lane types; if the target vehicle is located between the lane edges of the current lane, it is determined that the target vehicle is traveling in the current lane.

[0009] In one embodiment of the present application, a lane intersection is determined in the following manner: detection is performed based on preset intersection features, wherein the intersection features include at least one of a first feature, a second feature, and a third feature, the first feature including that the lane line of the current lane changes from a solid line to a dashed line at the lane intersection, the second feature includes a guide line corresponding to the lane intersection, and the third feature includes that a road sign located at the lane intersection is marked with preset intersection information corresponding to the lane intersection; in response to detecting any intersection feature, the lane intersection is determined from the current vehicle based on the detected intersection feature.

[0010] In one embodiment of the present application, detection is performed based on preset intersection features, including: obtaining map data corresponding to the target vehicle; determining whether there is a lane interaction point within a preset distance range of the target vehicle based on the map data; if there is a lane interaction point within the preset distance range of the target vehicle, detection is performed based on the preset intersection features.

[0011] In one embodiment of the present application, in response to detecting any intersection feature, a lane intersection is determined from the current vehicle based on the detected intersection feature, including: obtaining the confidence corresponding to the intersection feature through a preset image recognition model, wherein the intersection feature is obtained by image recognition by the image recognition model; calculating according to each of the confidences to obtain an average confidence value; if the execution average value is greater than a preset average value threshold, determining the lane intersection from the current vehicle based on the target feature, wherein the target feature is the intersection feature with the highest confidence value.

[0012] In one embodiment of the present application, obstacle detection is performed on the area between the collision warning section and the target lane, including: performing target object detection on the area between the collision warning section and the target vehicle through a vehicle sensor set on the target vehicle, and receiving detection information output by the vehicle sensor; if the vehicle sensor does not output detection information, setting the obstacle detection result to the presence of an obstacle in the area between the collision warning section and the target vehicle; if the vehicle sensor outputs detection information, setting the obstacle detection result to the absence of an obstacle in the area between the collision warning section and the target vehicle.

[0013] In one embodiment of the present application, a vehicle collision warning is performed based on the intersection distance between the target vehicle and the lane intersection, including: obtaining the driving parameters of the target vehicle, wherein the driving parameters include vehicle speed and / or vehicle acceleration; calculating based on the driving parameters to obtain a warning distance threshold, wherein the vehicle speed and the warning distance threshold are positively correlated, and the vehicle acceleration and the warning distance threshold are positively correlated; if the intersection distance between the target vehicle and the lane intersection is less than or equal to the warning distance threshold, matching the current warning strategy according to the warning level corresponding to the warning distance threshold, and executing the current warning strategy to perform a vehicle collision warning, wherein the warning distance threshold and the warning level are positively correlated.

[0014] In one embodiment of the present application, a vehicle collision warning is performed based on the obstacle distance between the target vehicle and the target lane obstacle, including: obtaining movement parameters corresponding to the target vehicle and the target lane obstacle, respectively, wherein the movement parameters include movement speed and movement angle; calculating each of the movement parameters according to a preset collision direction to obtain the collision direction speed of the target vehicle and the target lane obstacle in the preset collision direction; calculating the obstacle distance between the target vehicle and the target lane obstacle according to each of the collision direction speeds to obtain a collision time; matching a current warning strategy according to the collision time, and executing the current warning strategy to perform a vehicle collision warning.

[0015] The present application provides a vehicle collision warning system for merging lanes, comprising: an acquisition module, configured to acquire a collision warning section between a target vehicle and a lane intersection, wherein the target vehicle is traveling in a current lane and the current lane intersects with the target lane at the lane intersection; a detection module, configured to perform obstacle detection on an area between the collision warning section and the target lane, and to divide the collision warning section into an obstacle section and an open section based on the obstacle detection result, wherein an obstacle exists between the obstacle section and the target lane, and no obstacle exists between the open section and the target lane; a first warning module, configured to issue a vehicle collision warning based on an intersection distance between the target vehicle and the lane intersection if the target vehicle is traveling in the obstacle section; and a second warning module, configured to perform obstacle detection on the target lane using a vehicle sensor provided on the target vehicle to obtain a target lane obstacle if the target vehicle is traveling in the open section, and to issue a vehicle collision warning based on an obstacle distance between the target vehicle and the target lane obstacle.

[0016] The present application provides a vehicle terminal, comprising: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the vehicle terminal performs the above method.

[0017] Beneficial effects of this application:

[0018] By analyzing the obstacle detection results in the area between the collision warning section and the target vehicle, the collision warning section is divided into an obstructed section and an open section. Therefore, when an obstacle exists between the obstructed section and the target lane, a collision warning is issued based on the intersection distance between the vehicle and the lane intersection. When no obstacle exists between the obstructed section and the target lane, a collision warning is issued based on the intersection distance between the vehicle and the obstacle in the target lane. This not only determines the reference object based on the presence of an obstacle between the collision warning section and the target vehicle, but also issues a collision warning based on the distance between the vehicle and the reference object. This allows the user to be alerted only when the vehicle is in danger of collision. Compared to broadcasting each confluence point to the user, this filter filters out invalid warning information, making the confluence point warning mechanism intelligent, preventing users from being distracted or ignoring invalid warning information, and thus reducing the risk of collision at the confluence point. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of a vehicle collision warning method for merging lanes in an embodiment of the present application;

[0020] Figure 2 is a schematic diagram of an obstructed road section and an open road section in an embodiment of the present application;

[0021] Figure 3 This is a flow chart of another vehicle collision warning method for merging lanes in an embodiment of the present application;

[0022] Figure 4 This is a schematic structural diagram of a vehicle collision warning system for merging lanes in an embodiment of the present application;

[0023] Figure 5 It is a structural diagram of a vehicle terminal in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and sub-samples in the embodiments can be combined with each other unless there is a conflict.

[0025] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0026] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the embodiments of the present invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the embodiments of the present invention.

[0027] In the description and claims of the embodiments of the present disclosure, as well as in the accompanying drawings, the terms "first," "second," and the like are used to distinguish similar items and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate to describe the embodiments of the present disclosure herein. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions.

[0028] Unless otherwise stated, the term "plurality" means two or more.

[0029] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0030] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0031] Combine Figure 1 As shown, an embodiment of the present disclosure provides a vehicle collision warning method for merging lanes, comprising:

[0032] Step S101, obtaining a collision warning section between the target vehicle and the lane intersection;

[0033] The target vehicle is traveling in the current lane, and the current lane intersects with the target lane at a lane intersection;

[0034] Step S102: performing obstacle detection on the area between the collision warning section and the target lane, and dividing the collision warning section into an obstacle section and an open section based on the obstacle detection result;

[0035] Among them, there is an obstacle between the obstacle section and the target lane, and there is no obstacle between the open section and the target lane;

[0036] In step S103, if the target vehicle is running on the obstacle road section, a vehicle collision warning is performed according to the intersection distance between the target vehicle and the intersection point.

[0037] In step S104, if the target vehicle is running on the open road section, an obstacle detection is performed on the target lane by the vehicle sensor arranged on the target vehicle to obtain a target lane obstacle, and a vehicle collision warning is performed according to the obstacle distance between the target vehicle and the target lane obstacle.

[0038] The vehicle collision warning method for intersection lanes provided by the embodiment of the present disclosure divides the collision warning road section into an obstacle road section and an open road section according to the obstacle detection result of the region between the collision warning road section and the target vehicle, so that when there is an obstacle between the obstacle road section and the target lane, a vehicle collision warning is performed according to the intersection distance between the target vehicle and the intersection point, and when there is no obstacle between the obstacle road section and the target lane, a vehicle collision warning is performed according to the intersection distance between the target vehicle and the obstacle on the target lane. In this way, not only is the reference determined according to whether there is an obstacle between the collision warning road section and the target vehicle, but also a vehicle collision warning is performed according to the distance between the target vehicle and the reference, which makes the user warned when the vehicle is in danger of collision from two aspects. Compared with broadcasting each intersection to the user, invalid warning information is filtered, the intelligentization of the intersection warning mechanism is realized, the user is prevented from being distracted or ignoring invalid warning information, and the collision risk of the vehicle at the intersection is reduced.

[0039] Optionally, the target vehicle is determined to run on the current lane in the following manner: if the target vehicle runs on a vehicle road, road information corresponding to the vehicle road is obtained, wherein the vehicle road is composed of running lanes, and the road information includes the number of lanes corresponding to the running lanes and the type of each running lane; lane line recognition is performed on the vehicle road to obtain the lane line type corresponding to each lane line, and the lane edge corresponding to each running lane is determined from each lane line according to the lane line type and the lane type; the current lane is determined from each running lane according to the number of lanes and the lane type; and if the target vehicle is located between the lane edges of the current lane, it is determined that the target vehicle runs on the current lane.

[0040] In some embodiments, an image sensor provided on the target vehicle continuously captures images of the vehicle's front and surrounding environment. The images captured by the image sensor are processed using an edge detection algorithm and a Hough transform to detect lane markings in the images, and the detected lane markings are classified to distinguish between solid lines, dashed lines, and lane markings of different colors. The driving lanes are distinguished in combination with road information in the map data to determine the current lane. For example, if the vehicle road is a highway and consists of three driving lanes, the map data output shows that the vehicle road includes two main lanes and one emergency lane. If four lane markings are identified, the driving lane between the third and fourth lane markings is the emergency lane, and the driving lane between the second and third lane markings is the rightmost drivable lane. Similarly, the rightmost drivable lane is also the lane that intersects with the ramp. Therefore, the driving lane between the second and third lane markings is the current lane, and the second and third lane markings are the lane edges of the current lane. Considering the width and length of the vehicle, when the entire vehicle is within the lane edge, the target vehicle is determined to be in the current parking space.

[0041] Optionally, the lane intersection is determined in the following manner: detection is performed based on preset intersection features, wherein the intersection features include at least one of a first feature, a second feature, and a third feature, the first feature including that the lane line of the current lane changes from a solid line to a dashed line at the lane intersection, the second feature includes a guide line corresponding to the lane intersection, and the third feature includes that a road sign located at the lane intersection is marked with preset intersection information corresponding to the lane intersection; in response to detecting any intersection feature, the lane intersection is determined from the current vehicle based on the detected intersection feature.

[0042] In some embodiments, an image sensor installed in the target vehicle continuously captures images of the front of the vehicle and the surrounding environment, and performs image recognition on the captured images, so as to use an image processing algorithm to analyze the color, shape, continuity and other characteristics of the markings, and determine whether the analysis results meet the intersection characteristics; if the analysis results meet the intersection characteristics, the lane intersection can be determined according to the intersection characteristics, thereby accurately determining the location of the merging entrance.

[0043] In some embodiments, near the merging entrance, the lane line will often gradually change from a solid line to a dashed line, indicating that the vehicle can change lanes or merge here; when it is recognized that the lane line gradually changes from a solid line to a dashed line, the change point between the solid line and the dashed line is used as the lane intersection point.

[0044] In some embodiments, some confluences are marked with guide lines, which are used to guide vehicles from branch lines into the main line. The shape of the guide lines is usually special, distributed in the confluence area in the shape of a triangle or trapezoid. If a guide line is identified, the preset position of the guide line is determined as the position of the lane intersection according to the shape of the guide line.

[0045] In some embodiments, road signs located at lane intersections usually indicate intersection information, such as target road information such as the road name of the target road, the driving direction of the target road, and intersection keywords such as "merge" and "front intersection", as well as specific graphic signs; if the road sign is marked with the above-mentioned intersection information, the location of the lane interaction point is determined according to the intersection information and the location of the road sign.

[0046] Optionally, detection is performed based on preset intersection features, including: obtaining map data corresponding to the target vehicle; determining whether there is a lane interaction point within a preset distance range of the target vehicle based on the map data; if there is a lane interaction point within the preset distance range of the target vehicle, detection is performed based on the preset intersection features.

[0047] In some embodiments, if the intersection point is determined by the precise map position of the map data, the warning may be issued too late. At the same time, in order to reduce the data processing pressure of the vehicle, after the map data determines that there is a lane interaction point within a preset distance range of the target vehicle, the intersection point features are detected by the sensor. Alternatively, if the map data determines that there is no lane interaction point within the preset distance range of the target vehicle, the intersection point features detected by the sensor are ignored.

[0048] Optionally, in response to detecting any intersection feature, a lane intersection is determined from the current vehicle based on the detected intersection feature, including: obtaining a confidence level corresponding to the intersection feature through a preset image recognition model, wherein the intersection feature is obtained by image recognition through the image recognition model; calculating based on each confidence level to obtain an average confidence level; if the execution average level is greater than a preset average level threshold, determining the lane intersection from the current vehicle based on the target feature, wherein the target feature is the intersection feature with the highest confidence level.

[0049] In some embodiments, images of the road in front of the vehicle are continuously captured and transmitted to an image recognition module in real time; the received images are analyzed using a preset image recognition model to identify possible lane intersection features, and a confidence value is assigned to each feature; the average value of these confidences is calculated by arithmetic averaging, and compared with a preset average value threshold, for example, the average value threshold is 0.8; if the average value is greater than the threshold, it means that the recognition result is relatively reliable, and the intersection feature with the highest confidence is further searched as the target feature, and the lane intersection is determined from the current vehicle through the target feature.

[0050] Optionally, obstacle detection is performed on the area between the collision warning section and the target lane, including: performing target object detection on the area between the collision warning section and the target vehicle through a vehicle sensor set on the target vehicle, and receiving detection information output by the vehicle sensor; if the vehicle sensor does not output detection information, the obstacle detection result is set to that there is an obstacle in the area between the collision warning section and the target vehicle; if the vehicle sensor outputs detection information, the obstacle detection result is set to that there is no obstacle in the area between the collision warning section and the target vehicle.

[0051] In some embodiments, the area between the collision warning section and the target vehicle is the right front area of ​​the target vehicle.

[0052] In some embodiments, the conditions for determining whether there is an obstacle in the area between the collision warning section and the target vehicle include at least one of the following: the map data outputs that there is a confluence within a preset distance range in front of the target vehicle; the image sensor recognizes that there is a confluence feature in the right front of the target vehicle, for example, the right front area has a guide line; the radar sensor and / or infrared sensor recognizes that there is no target object information in the right front of the target vehicle, wherein the radar sensor is used to output elevation information. If the radar sensor does not output the elevation information of the target vehicle in the right front, it means that there is no target object information in the right front of the target vehicle, that is, there is an obstacle in the right front of the target vehicle.

[0053] In some embodiments, if the radar sensor starts to output elevation information of the target vehicle in front of the right side, it indicates that the target vehicle has entered an open road section.

[0054] Combine Figure 2 As shown, the embodiment of the present disclosure provides an obstacle section and an open section, and the area between the target vehicle and the obstacle end point is used as the obstacle section, and the area between the vehicle merging point and the obstacle end point is used as the open section.

[0055] Optionally, a vehicle collision warning is performed based on the intersection distance between the target vehicle and the lane intersection, including: obtaining the driving parameters of the target vehicle, wherein the driving parameters include vehicle speed and / or vehicle acceleration; calculating based on the driving parameters to obtain a warning distance threshold, wherein the vehicle speed is positively correlated with the warning distance threshold, and the vehicle acceleration is positively correlated with the warning distance threshold; if the intersection distance between the target vehicle and the lane intersection is less than or equal to the warning distance threshold, matching the current warning strategy according to the warning level corresponding to the warning distance threshold, and executing the current warning strategy to perform a vehicle collision warning, wherein the warning distance threshold is positively correlated with the warning level.

[0056] In some embodiments, if the vehicle speed of the target vehicle is lower than a first speed threshold, no vehicle collision warning is performed.

[0057] In some embodiments, if the target vehicle is outside the current lane, no vehicle collision warning is performed.

[0058] In some embodiments, if the target vehicle is located in the current lane and the vehicle speed of the target vehicle is between the first speed threshold and the second speed threshold, the warning distance threshold corresponding to the first warning level is obtained, and when the intersection distance is less than or equal to the warning distance threshold corresponding to the first warning level, the current warning strategy corresponding to the first warning level is executed, and a visual alarm is triggered, that is, the instrument displays "There is a confluence ahead, please slow down", where the first speed threshold is less than the second speed threshold.

[0059] In some embodiments, if the target vehicle is located in the current lane and the vehicle speed of the target vehicle is between the second speed threshold and the third speed threshold, the warning distance threshold corresponding to the second warning level is obtained, and when the intersection distance is less than or equal to the warning distance threshold corresponding to the second warning level, the current warning strategy corresponding to the second warning level is executed, and a sound alarm is triggered, that is, a voice reminder is given "There is a confluence ahead, please slow down", where the second speed threshold is less than the third speed threshold, and the first warning level is less than the second warning level.

[0060] In some embodiments, if the target vehicle is located in the current lane and the vehicle speed of the target vehicle is greater than or equal to the third speed threshold, the warning distance threshold corresponding to the third warning level is obtained, and when the intersection distance is less than or equal to the warning distance threshold corresponding to the third warning level, the current warning strategy corresponding to the third warning level is executed, triggering AEB (Autonomous Emergency Braking), taking over control of the target vehicle, slowing the target vehicle down to below the first speed threshold, and providing a voice reminder to the user.

[0061] Optionally, a vehicle collision warning is performed based on the obstacle distance between the target vehicle and the target lane obstacle, including: obtaining movement parameters corresponding to the target vehicle and the target lane obstacle, respectively, wherein the movement parameters include movement speed and movement angle; calculating each movement parameter according to a preset collision direction to obtain the collision direction speed of the target vehicle and the target lane obstacle in the preset collision direction; calculating the obstacle distance between the target vehicle and the target lane obstacle according to each collision direction speed to obtain the collision time; matching the current warning strategy according to the collision time, and executing the current warning strategy to perform a vehicle collision warning.

[0062] In some embodiments, a high-precision positioning system is used to determine the moving speed and moving angle of the target vehicle.

[0063] In some embodiments, a lidar is used to emit a laser beam and receive the reflected laser to create a three-dimensional point cloud map of the surrounding environment, thereby detecting the outer contours and surface features of obstacles in the target lane, where the target vehicle obstacles include other vehicles located in the target lane; by analyzing the point cloud data over a continuous period of time, the moving speed and angle of the target vehicle obstacle can be determined by changes in position and distance.

[0064] In some embodiments, the preset collision direction is perpendicular to the driving direction of the target vehicle, that is, directly to the right of the target vehicle.

[0065] In some embodiments, the collision direction speed of the target vehicle and the target lane obstacle is obtained by multiplying the moving speed by the cosine value corresponding to the moving angle.

[0066] In some embodiments, the collision time is calculated by the following formula:

[0067]

[0068] In formula (1), TTC is the time to collision (Time-to-Collision), S is the obstacle distance between the target vehicle and the target lane obstacle, and V is the difference in collision direction speed between the target vehicle and the target lane obstacle.

[0069] In some embodiments, if the target lane obstacle is located behind the target vehicle, no vehicle collision warning is performed.

[0070] In some embodiments, if the TTC is greater than 5, no reminder is given; if the TTC is between 4 and 5, a visual alarm is triggered, that is, the instrument displays "There is a vehicle ahead, please slow down"; if the TTC is between 3 and 4, an audio alarm is triggered, that is, a voice reminder "There is a vehicle ahead, please slow down" is given; if the TTC is less than 3, AEB is triggered, taking over control of the target vehicle, slowing the target vehicle down to below the first speed threshold, and giving a voice reminder to the user.

[0071] Combine Figure 3 As shown, an embodiment of the present disclosure provides a vehicle collision warning method for merging lanes, comprising:

[0072] Step S301, passing a target vehicle traveling on a vehicle road;

[0073] Step S302: determine whether there is a lane merging point near the target vehicle. If so, jump to step S303; if not, jump to step S301;

[0074] Step S303, determine whether the target vehicle is in the current lane, if so, jump to step S304, if not, jump to step S301;

[0075] Step S304, performing detection according to preset intersection features;

[0076] Step S305, determine whether the intersection feature is detected, if so, jump to step S306, if not, jump to step S304;

[0077] Step S306 , determining a lane intersection point from the current vehicle based on the detected intersection point features, and obtaining a collision warning section between the target vehicle and the lane intersection point;

[0078] Step S307: performing obstacle detection on the area between the collision warning section and the target lane to obtain an obstacle detection result;

[0079] Step S308, dividing the collision warning section into an obstacle section and an open section according to the obstacle detection result;

[0080] Step S309, determining whether the target vehicle is traveling on an obstructed road section, if so, skipping to step S310, if not, skipping to step S312;

[0081] Step S310, calculating based on the driving parameters of the target vehicle to obtain a warning distance threshold;

[0082] Wherein, the driving parameters include vehicle speed and / or vehicle acceleration;

[0083] Among them, there is a positive correlation between vehicle speed and warning distance threshold, and there is a positive correlation between vehicle acceleration and warning distance threshold;

[0084] In step S311 , a warning distance threshold is compared according to the intersection distance between the target vehicle and the lane intersection, so as to issue a vehicle collision warning according to the comparison result.

[0085] Step S312, performing obstacle detection on the target lane by using a vehicle sensor provided on the target vehicle to obtain obstacles in the target lane;

[0086] Step S313: Calculate the movement parameters corresponding to the target vehicle and the target lane obstacle respectively according to the preset collision direction to obtain the collision direction speeds of the target vehicle and the target lane obstacle respectively in the preset collision direction;

[0087] Step S314, calculating the obstacle distance between the target vehicle and the target lane obstacle based on the speeds in each collision direction to obtain the collision time;

[0088] Step S315: issuing a vehicle collision warning based on the collision time.

[0089] The vehicle collision warning method for merging lanes provided by the disclosed embodiment divides the collision warning section into an obstacle section and an open section based on the obstacle detection results in the area between the collision warning section and the target vehicle. Thus, when an obstacle exists between the obstacle section and the target lane, a vehicle collision warning is issued based on the intersection distance between the vehicle and the lane intersection. Furthermore, when no obstacle exists between the obstacle section and the target lane, a vehicle collision warning is issued based on the intersection distance between the vehicle and the obstacle in the target lane. In this way, not only is a reference object determined based on whether an obstacle exists in the area between the collision warning section and the target vehicle, but a vehicle collision warning is also issued based on the distance between the vehicle and the reference object. This allows the user to be warned when the vehicle is in danger of collision from two perspectives. Compared to broadcasting each confluence point to the user, invalid warning information is filtered out, achieving an intelligent confluence point warning mechanism, preventing users from being distracted or ignoring invalid warning information, and thereby reducing the risk of vehicle collision at the confluence point.

[0090] Combine Figure 4 As shown, an embodiment of the present disclosure provides a vehicle collision warning system for merging lanes, comprising:

[0091] The acquisition module 401 is used to acquire a collision warning section between a target vehicle and a lane intersection, wherein the target vehicle is traveling in a current lane, and the current lane intersects with the target lane at the lane intersection;

[0092] The detection module 402 is configured to perform obstacle detection on the area between the collision warning section and the target lane, and divide the collision warning section into an obstacle section and an open section based on the obstacle detection result, wherein an obstacle exists between the obstacle section and the target lane, and no obstacle exists between the open section and the target lane;

[0093] The first warning module 403 is used to issue a vehicle collision warning based on the intersection distance between the target vehicle and the lane intersection if the target vehicle is traveling on an obstructed road section;

[0094] The second warning module 404 is used to detect obstacles in the target lane through the vehicle sensor installed on the target vehicle if the target vehicle is traveling on an open road, obtain the target lane obstacle, and issue a vehicle collision warning based on the obstacle distance between the target vehicle and the target lane obstacle.

[0095] The vehicle collision warning system for merging lanes provided by the disclosed embodiment divides the collision warning section into an obstructed section and an open section based on the obstacle detection results in the area between the collision warning section and the target vehicle. Thus, when an obstacle exists between the obstructed section and the target lane, a vehicle collision warning is issued based on the intersection distance between the system and the lane intersection. Furthermore, when no obstacle exists between the obstructed section and the target lane, a vehicle collision warning is issued based on the intersection distance between the system and the obstacle on the target lane. In this way, not only is a reference object determined based on whether an obstacle exists in the area between the collision warning section and the target vehicle, but a vehicle collision warning is also issued based on the distance between the system and the reference object. This allows the user to be warned when the vehicle is in danger of collision from two perspectives. Compared to broadcasting each confluence point to the user, invalid warning information is filtered out, achieving an intelligent confluence point warning mechanism, preventing users from being distracted or ignoring invalid warning information, and thereby reducing the risk of vehicle collision at the confluence point.

[0096] An embodiment of the present disclosure further provides a vehicle terminal, comprising: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the vehicle terminal executes the above method.

[0097] Figure 5 The following is a schematic diagram showing the structure of a computer system of a vehicle terminal suitable for implementing the embodiment of the present application. Figure 5 The computer system 500 of the vehicle terminal shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0098] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage part 508 into the random access memory (RAM) 503, such as executing the method in the above embodiment. Various programs and data required for system operation are also stored in the RAM 503. The CPU 501, ROM 502 and RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0099] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, and the like; an output section 507 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 508 including a hard disk; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. Removable media 511, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 510 as needed, so that computer programs read therefrom can be installed into the storage section 508 as needed.

[0100] The vehicle terminal disclosed in this embodiment includes a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store computer programs, the communication interface is used to communicate, and the processor and the transceiver are used to run the computer program, so that the vehicle terminal executes each step of the above method.

[0101] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible variations. Unless expressly required, individual components and functions are optional, and the order of operations may vary. Parts and subsamples of some embodiments may be included in or replace parts and subsamples of other embodiments. Moreover, the terms used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to also include plural forms. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more associated listings. In addition, when used in this application, the term "comprise" and its variations "comprises" and / or comprising refer to the presence of a stated subsample, whole, step, operation, element, and / or component, but do not exclude the presence or addition of one or more other subsamples, wholes, steps, operations, elements, components and / or groups of these. In the absence of further restrictions, an element defined by the statement "comprises a..." does not exclude the presence of other identical elements in the process, method or device that includes the element. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments can be referenced to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can be found in the description of the method part.

[0102] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. Technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present disclosure. Technicians can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0103] In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, apparatuses, etc.) can be implemented in other manners. For example, the described device embodiments are merely schematic. For example, the division of the units is merely a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some of the components can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms. The unit illustrated as a separate component can or can not be physically separate, and can or can not be a physical component. Some or all of the units can be selected according to actual needs to implement the embodiments. In addition, the units in the embodiments disclosed herein can be integrated into one processing unit, or each unit can exist physically as a separate entity, or two or more units can be integrated into one unit.

[0104] The flowcharts and block diagrams in the drawings show the possible implementation architectures, functions and operations of the system, method and computer program product according to the embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment or a part of code containing one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks can occur in different orders than those noted in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the drawings, the operations or steps corresponding to different blocks can also occur in different orders from those disclosed in the descriptions, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. Each block in the block diagrams and / or flowcharts, and the combination of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A vehicle collision warning method for merging lanes, characterized in that: include: Obtaining a collision warning road section between a target vehicle and a lane intersection, wherein the target vehicle is traveling in a current lane, and the current lane intersects the target lane at the lane intersection; performing obstacle detection on an area between the collision warning section and the target lane, and dividing the collision warning section into an obstacle section and an open section according to the obstacle detection result, wherein an obstacle exists between the obstacle section and the target lane, and no obstacle exists between the open section and the target lane; If the target vehicle is traveling on the obstacle section, a vehicle collision warning is issued based on the intersection distance between the target vehicle and the lane intersection; If the target vehicle is traveling on the open road section, the target lane is detected by a vehicle sensor provided on the target vehicle to obtain a target lane obstacle, and a vehicle collision warning is issued based on the obstacle distance between the target vehicle and the target lane obstacle.

2. The method according to claim 1, characterized in that Determine that the target vehicle is traveling in the current lane by: If the target vehicle is traveling on a vehicle road, obtaining road information corresponding to the vehicle road, wherein the vehicle road is composed of driving lanes, and the road information includes the number of lanes corresponding to the driving lanes and the lane type corresponding to each driving lane; Performing lane line recognition on the vehicle road to obtain lane line types corresponding to the lane lines, and determining lane edges corresponding to the driving lanes from the lane lines according to the lane line types and the lane types; determining a current lane from each of the driving lanes according to the number of lanes and the lane type; If the target vehicle is located between lane edges of the current lane, it is determined that the target vehicle is traveling in the current lane.

3. The method according to claim 1, characterized in that Lane intersections are determined by: Detection is performed based on preset intersection features, wherein the intersection features include at least one of a first feature, a second feature, and a third feature, the first feature including the lane line of the current lane changing from a solid line to a dashed line at the lane intersection, the second feature including the guide line corresponding to the lane intersection, and the third feature including the road sign at the lane intersection being marked with preset intersection information corresponding to the lane intersection; In response to detecting any junction feature, a lane junction is determined from the current lane according to the detected junction feature.

4. The method according to claim 3, characterized in that Detection is performed based on preset intersection features, including: Obtaining map data corresponding to the target vehicle; Determining whether there is a lane interaction point within a preset distance range of the target vehicle based on the map data; If there is a lane intersection point within the preset distance range of the target vehicle, detection is performed based on the preset intersection features.

5. The method according to claim 3, characterized in that In response to detecting any intersection feature, determining a lane intersection from the current lane according to the detected intersection feature, including: Obtaining a confidence level corresponding to the intersection feature through a preset image recognition model, wherein the intersection feature is obtained by performing image recognition through the image recognition model; Calculating according to each of the confidence levels to obtain an average confidence level; If the confidence average is greater than a preset average threshold, a lane intersection point is determined from the current lane according to a target feature, wherein the target feature is the intersection feature with the highest confidence.

6. The method according to claim 1, characterized in that Performing obstacle detection on the area between the collision warning section and the target lane includes: Performing target object detection on an area between the collision warning road section and the target vehicle by using a vehicle sensor provided on the target vehicle, and receiving detection information output by the vehicle sensor; If the vehicle sensor does not output detection information, setting the obstacle detection result as an obstacle existing in the area between the collision warning section and the target vehicle; If the vehicle sensor outputs detection information, the obstacle detection result is set as no obstacle exists in the area between the collision warning section and the target vehicle.

7. The method according to any one of claims 1 to 6, characterized in that Providing a vehicle collision warning according to the intersection point distance between the target vehicle and the lane intersection point includes: Acquiring driving parameters of the target vehicle, wherein the driving parameters include vehicle speed and / or vehicle acceleration; Calculating according to the driving parameters to obtain a warning distance threshold, wherein there is a positive correlation between the vehicle speed and the warning distance threshold, and there is a positive correlation between the vehicle acceleration and the warning distance threshold; If the intersection distance between the target vehicle and the lane intersection is less than or equal to the warning distance threshold, the current warning strategy is matched according to the warning level corresponding to the warning distance threshold, and the current warning strategy is executed to perform a vehicle collision warning, wherein there is a positive correlation between the warning distance threshold and the warning level.

8. The method according to any one of claims 1 to 6, characterized in that Providing a vehicle collision warning according to the obstacle distance between the target vehicle and the target lane obstacle, including: Obtaining movement parameters corresponding to the target vehicle and the target lane obstacle, respectively, wherein the movement parameters include movement speed and movement angle; Calculating each of the movement parameters according to a preset collision direction to obtain collision direction velocities of the target vehicle and the target lane obstacle in the preset collision direction respectively; Calculating the obstacle distance between the target vehicle and the target lane obstacle according to each collision direction speed to obtain a collision time; A current warning strategy is matched according to the collision time, and the current warning strategy is executed to perform a vehicle collision warning.

9. A vehicle collision warning system for merging lanes, characterized in that: include: an acquisition module, configured to acquire a collision warning section between a target vehicle and a lane intersection, wherein the target vehicle is traveling in a current lane, and the current lane intersects the target lane at the lane intersection; a detection module, configured to perform obstacle detection on an area between the collision warning section and the target lane, and divide the collision warning section into an obstacle section and an open section according to the obstacle detection result, wherein an obstacle exists between the obstacle section and the target lane, and no obstacle exists between the open section and the target lane; A first warning module is configured to issue a vehicle collision warning based on an intersection distance between the target vehicle and the lane intersection if the target vehicle is traveling on the obstacle section; The second warning module is used to detect obstacles in the target lane through a vehicle sensor installed on the target vehicle if the target vehicle is traveling on the open road section, obtain obstacles in the target lane, and issue a vehicle collision warning based on the obstacle distance between the target vehicle and the obstacle in the target lane.

10. A vehicle terminal, characterized in that: include: processor and memory; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the vehicle terminal performs the method according to any one of claims 1 to 8.

Images