Online identification method for narrow road meeting scene and related product

Abstract

The invention discloses an online identification method for a narrow road meeting scene and a related product, which can be applied to the technical field of automatic driving, and the method comprises the steps: obtaining the current driving environment information collected by a vehicle; the driving environment information comprises road side lines, parking individuals and motion individuals; when a vehicle comes in the opposite direction, whether a vehicle meeting limiting area exists or not is judged based on the current driving environment information; the restricted meeting area is an area in which two individuals driving in opposite directions are not allowed to pass at the same time; and if yes, prompting that the vehicle is currently in the narrow road meeting scene. Therefore, whether the restricted vehicle meeting area exists or not is determined through the current driving environment information with the time-varying characteristic, then whether the vehicle is in the narrow road vehicle meeting scene or not is determined, and the accuracy of narrow road vehicle meeting scene recognition is improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to an online recognition method for a narrow road meeting scene and related products. Background Art

[0002] Autonomous driving is a technology that uses artificial intelligence, sensors, computer vision and other technologies to enable vehicles to drive automatically, perceive the surrounding environment and make driving decisions without human intervention.

[0003] Most existing autonomous driving navigation systems use the framework of "determine the scene first, then call the corresponding algorithm" to ensure driving safety and efficiency. However, existing scene recognition methods usually use offline pre-built high-precision maps + online real-time scene positioning for comprehensive determination. Based on the periodic driving of human-driven vehicles on daily roads, and using on-board radar to scan and model the road environment, the scene type is pre-defined through manual annotation. Afterwards, during the operation of the autonomous driving vehicle, the vehicle first locates its own position, and then determines the type of scene it is in based on the manual annotation. As a result, the existing scene recognition methods are inflexible and difficult to accurately identify narrow road meeting scenes with time-varying characteristics.

[0004] Therefore, how to improve the accuracy of narrow road meeting scene recognition is a problem that technicians in this field need to solve urgently. Summary of the invention

[0005] Based on the above problems, the present application provides an online recognition method and related products for narrow road meeting scenes, which determines whether there is a restricted meeting area through the time-varying current driving environment information, and then determines whether the vehicle is in a narrow road meeting scene, thereby improving the accuracy of narrow road meeting scene recognition.

[0006] In a first aspect, an embodiment of the present application provides a method for identifying a narrow road meeting scene, comprising:

[0007] Acquire current driving environment information collected by the vehicle; the driving environment information includes: road edges, parked individuals and moving individuals;

[0008] When there is an oncoming vehicle, based on the current driving environment information, it is determined whether there is a restricted passing area; the restricted passing area is an area where two individuals traveling in opposite directions are not allowed to pass at the same time;

[0009] If it exists, it will prompt that the vehicle is currently in a narrow road meeting scene.

[0010] Optionally, before determining whether there is a restricted passing area, the method further includes:

[0011] Taking the vehicle as the main body, a two-dimensional top view corresponding to the current driving environment is constructed; each entity in the two-dimensional top view is represented in the form of a contour with corner points;

[0012] The vehicle's contour trajectory is simulated when the vehicle is driving along the specified side close to the road edge.

[0013] Optionally, the deducing of the vehicle contour trajectory when the vehicle is traveling along a specified side close to the road edge includes:

[0014] Determine a first sideline trajectory corresponding to the ego vehicle; the first sideline trajectory is a motion trajectory of the center of the ego vehicle's rear wheel when the ego vehicle is traveling along a specified side close to the road sideline without considering the parked individuals;

[0015] Based on the effective corner points of each docked individual, the first corner point trajectory corresponding to the vehicle avoiding each docked individual is deduced;

[0016] Connecting the first edgeline trajectory and all first corner point trajectories to form a rear wheel center trajectory of the vehicle;

[0017] The vehicle contour trajectory is determined based on the vehicle contour and the center trajectory of the rear wheels of the vehicle.

[0018] Optionally, before determining whether there is a restricted passing area, the method further includes:

[0019] Determine a second sideline trajectory corresponding to the oncoming vehicle; the second sideline trajectory is a motion trajectory of the center of the rear wheel of the oncoming vehicle when the oncoming vehicle is driving along the specified side close to the road sideline without considering the parked individual;

[0020] Based on the effective corner points of each parking entity, the second corner point trajectory corresponding to each parking entity is deduced for the oncoming vehicle to avoid.

[0021] Connecting the second edgeline trajectory and all the second corner point trajectories to form a rear wheel center trajectory of the oncoming vehicle;

[0022] The oncoming vehicle contour trajectory is determined based on the oncoming vehicle contour and the rear wheel center trajectory of the oncoming vehicle.

[0023] Optionally, the determining whether there is a restricted passing area includes:

[0024] Detect whether there is an overlapping area between the vehicle contour trajectory and the oncoming vehicle contour trajectory.

[0025] Optionally, the method further includes:

[0026] If the vehicle is currently in a narrow road meeting scene, the two-dimensional top view marked with a restricted meeting area and a permitted meeting area is output and displayed;

[0027] The passing area is an area where two vehicles traveling in opposite directions are allowed to pass at the same time.

[0028] Optionally, the method further includes:

[0029] If it does not exist, it indicates that the vehicle is not currently in a narrow road meeting scenario.

[0030] In a second aspect, an embodiment of the present application provides a device for identifying a narrow road meeting scene, including:

[0031] The object detection and tracking module is used to obtain the current driving environment information collected by the vehicle; the driving environment information includes: road edges, parked individuals and moving individuals;

[0032] An identification module is used to determine whether there is a restricted passing area based on the current driving environment information when there is an oncoming vehicle; the restricted passing area is an area where two individuals traveling in opposite directions are not allowed to pass at the same time;

[0033] The output module is used to prompt that the vehicle is currently in a narrow road meeting scenario when there is a restricted meeting area.

[0034] In a third aspect, an embodiment of the present application provides a device for identifying a narrow road meeting scene, including:

[0035] Memory for storing computer programs;

[0036] A processor is used to implement the steps of the above-mentioned method for identifying a narrow road meeting scene when executing the computer program.

[0037] In a fourth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for identifying a narrow road meeting scene as described above are implemented.

[0038] It can be seen from the above technical solutions that compared with the prior art, the present application has the following advantages:

[0039] This application first obtains the current driving environment information collected by the vehicle. Among them, the driving environment information includes: road sidelines, parked individuals and moving individuals. Then when there is an oncoming vehicle, based on the current driving environment information, it is determined whether there is a restricted meeting area. Among them, the restricted meeting area is an area where two individuals traveling in opposite directions are not allowed to pass at the same time; if it exists, it is prompted that the vehicle is currently in a narrow road meeting scene. In this way, it is determined whether there is a restricted meeting area through the time-varying current driving environment information, and then it is determined whether the vehicle is in a narrow road meeting scene, thereby improving the accuracy of narrow road meeting scene recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A flowchart of a method for identifying a narrow road meeting scene provided in an embodiment of the present application;

[0041] Figure 2 A two-dimensional top view constructed based on an algorithm provided in an embodiment of the present application;

[0042] Figure 3 A schematic diagram of a prompt message provided in an embodiment of the present application;

[0043] Figure 4 A flowchart of an algorithm provided in an embodiment of the present application;

[0044] Figure 5 A schematic diagram of the structure of a device for identifying a narrow road meeting scene provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0046] In the description of the embodiments of the present application, words such as "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a concrete way.

[0047] In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, B exists alone, and A and B exist at the same time. In addition, unless otherwise specified, the term "multiple" means two or more. For example, multiple systems refers to two or more systems, and multiple terminals refers to two or more terminals.

[0048] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprises", "has" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0049] Hereinafter, some terms used in this embodiment are explained. It should be noted that these explanations are for the convenience of understanding by those skilled in the art and do not constitute a limitation on the scope of protection claimed by the present invention.

[0050] Individuals: including but not limited to motor vehicles, non-motor vehicles, pedestrians, animals, etc.

[0051] Parked individuals: individuals that are stationary on the roadside, such as cars parked in roadside parking spaces, snack stalls, waiting bicycles, pedestrians, etc.

[0052] Moving individuals: individuals moving on the road, such as moving cars, bicycles, etc.

[0053] An embodiment of the present application provides a method for identifying a narrow road meeting scene, comprising: first obtaining the current driving environment information collected by the vehicle. The driving environment information includes: road sidelines, parked individuals, and moving individuals. Then, when there is an oncoming vehicle, based on the current driving environment information, determine whether there is a restricted meeting area. The restricted meeting area is an area where two individuals traveling in opposite directions are not allowed to pass at the same time; if it exists, it indicates that the vehicle is currently in a narrow road meeting scene.

[0054] In this way, whether there is a restricted meeting area is determined by using the current driving environment information with time variation, and then whether the vehicle is in a narrow road meeting scene is determined, thereby improving the accuracy of narrow road meeting scene recognition.

[0055] It should be noted that the online recognition method for a narrow road meeting scene and related products provided by the present application can be applied to the field of autonomous driving technology. The above is only an example and does not limit the application field of the online recognition method for a narrow road meeting scene and related products provided by the present application.

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] Figure 1 A flowchart of a method for identifying a narrow road meeting scene provided in an embodiment of the present application. Figure 1 As shown, a method for identifying a narrow road meeting scene provided in an embodiment of the present application may include:

[0058] S101: Acquire current driving environment information collected by the vehicle; the driving environment information includes: road edges, parked entities, and moving entities.

[0059] In actual applications, when a driver is driving a car on the road, the vehicle's onboard module "object detection and tracking" can be used to collect and process the vehicle's current driving environment information, which is then input into the recognition device for narrow road meeting scenes for scene judgment. Driving environment information includes road edges, parked individuals, and moving individuals. Specifically, it can be based on the information of the autonomous driving vehicle's onboard camera and laser as input, and deep learning can be used to detect and estimate the position, speed, shape, and even rear wheel center of other vehicles, pedestrians, animals, and other individuals in the environment, as well as the width of the road in the environment.

[0060] S102: When there is an oncoming vehicle, based on the current driving environment information, it is determined whether there is a restricted passing area; the restricted passing area is an area where two vehicles traveling in opposite directions are not allowed to pass at the same time.

[0061] In practical applications, when considering the narrow road meeting scene, there must be two factors: "narrow road" and "meeting". The narrow road meeting scene refers to the scene where there is a restricted meeting area, which is widely seen in narrow roads with irregular construction, residential communities with complicated roadside parking, and auxiliary roads with vehicles traveling in the opposite direction. The restricted meeting area refers to an area where the width does not allow two individuals traveling in opposite directions to pass at the same time due to the narrowness of the road and the squeezing of parked individuals. Therefore, when the self-driving vehicle detects an oncoming vehicle, it determines whether there is a restricted meeting area based on the current driving environment information. For example, if the road is 5m wide, then in the absence of parked individuals, there is no restricted meeting area for two vehicles traveling in opposite directions with a width of 1.8m; if the above conditions are still met, and a 1.8m wide and 2.4m long car is parked on one side of the road, it can be understood that there will be a restricted meeting area (near the parked vehicle), that is, the self-driving vehicle is in a narrow road meeting scene, and the relevant algorithms for the narrow road meeting scene will be called later to determine the actions that the autonomous driving vehicle should take at present, such as overtaking, pulling over, etc.

[0062] In addition, since the methods of deducing the movement of the vehicle are different, the embodiment of the present application can illustrate a possible deduction method.

[0063] In one case, before determining whether there is a restricted passing area, the method further includes:

[0064] Taking the vehicle as the main body, a two-dimensional top view corresponding to the current driving environment is constructed; each entity in the two-dimensional top view is represented in the form of a contour with corner points;

[0065] The vehicle's contour trajectory is simulated when the vehicle is driving along the specified side close to the road edge.

[0066] In practical applications, after obtaining the current driving environment information, the recognition device for the narrow road meeting scene will perform proportional composition based on the road sideline (width), moving individuals (size and position of the vehicle, size and position of the oncoming vehicle), and parked individuals (size and position) to obtain a two-dimensional top view corresponding to the current driving environment. In order to simplify the composition, each element in the figure can be represented in the form of an outline with corner points, for example, the outline of the vehicle can be simplified into a rectangle with corner points. Then, based on the position of the road sideline and the simplified vehicle outline and corner points, the vehicle outline trajectory when the vehicle is driving along the specified side close to the road sideline is deduced. The specified side generally refers to the right side, which needs to be further determined according to the specific area.

[0067] In addition, since the methods of deducing the contour trajectory of the vehicle when the vehicle is traveling along a specified side close to the road edge are different, the embodiment of the present application can illustrate a possible deduction method.

[0068] In one case, the deducing of the vehicle contour trajectory when the vehicle is traveling along a specified side close to the road edge includes:

[0069] Determine a first sideline trajectory corresponding to the ego vehicle; the first sideline trajectory is a motion trajectory of the center of the ego vehicle's rear wheel when the ego vehicle is traveling along a specified side close to the road sideline without considering the parked individuals;

[0070] Based on the effective corner points of each docked individual, the first corner point trajectory corresponding to the vehicle avoiding each docked individual is deduced;

[0071] Connecting the first edgeline trajectory and all first corner point trajectories to form a rear wheel center trajectory of the vehicle;

[0072] The vehicle contour trajectory is determined based on the vehicle contour and the center trajectory of the rear wheels of the vehicle.

[0073] Figure 2 A two-dimensional top view based on an algorithm is provided in an embodiment of the present application. Figure 2As shown, (a) shows a simple two-dimensional top view corresponding to the current driving environment constructed with the vehicle as the center, including the vehicle moving straight forward, the road sideline, and a parked individual on the right side of the vehicle near the road sideline. Simplify the vehicle outline, as shown in (b), mark the direction of the vehicle, mark the corner points, etc. starting from the center of the rear wheel of the vehicle. Deducing the trajectory of the vehicle outline when the vehicle is driving along the specified side close to the road sideline specifically includes: as shown in (c), first determine the motion trajectory of the center of the rear wheel of the vehicle when the vehicle is driving along the specified side close to the road sideline with the center of the rear wheel of the vehicle along the vehicle driving direction, and record it as the first along-sideline trajectory, which is used to determine the extreme meeting position of the vehicle. In addition, because the two corner points of the parked individual close to the road sideline of the driving vehicle will not be used to determine the trajectory of the vehicle around the corner point, the embodiment of the present application defines that when the position of a corner point of the parked individual falls between the along-sideline trajectory and the road sideline of the driving vehicle, the corner point is invalid, and the remaining corner points are valid corner points. As shown in (d1) and (d2), the corner point trajectory formed by the center trace of the rear wheel of the ego vehicle during the process of the ego vehicle approaching each effective corner point of the docking individual is deduced in combination with the outline of the ego vehicle. The starting posture point and the ending posture point respectively show that the ego vehicle starts from close to the road edge and finally falls back to close to the road edge. The necessary posture points in the figure show the corner point positions of the extreme detour, which can generally be set manually, and the orientation and position of different docking individuals are generally different, and need to be calculated in combination with the actual situation. As shown in (e), the corner point trajectory formed by all the corner points corresponding to each docking individual is smoothly linked to deduce a smooth trajectory around the docking individual (the first corner point trajectory). Combined with (f1) and (f2), since the number of docking individuals is uncertain, multiple trajectories around the docking individual may be deduced. Specifically, when there are no other docking individuals around the docking individual, the ego vehicle only transitions from the along-edge trajectory state to the around-the-dock individual trajectory state, and then returns to the along-edge trajectory state, and the around-the-individual trajectory is naturally and smoothly connected to the along-edge trajectory state. However, when two docked individuals are close to each other, the docked individual trajectory will intersect with other docked individual trajectories before falling back to the sideline trajectory, and the two trajectories need to be smoothly connected. When all docked individual trajectories and sideline trajectories are smoothly connected together, a rear wheel center trajectory of the ego vehicle is formed. Finally, it can be understood that, as shown in (g), when the rear wheel center of the ego vehicle is driving along the deduced rear wheel center trajectory of the ego vehicle, the area covered by the ego vehicle contour is the ego vehicle contour trajectory.

[0074] In addition, since the methods of deducing the movement of oncoming vehicles are not the same, the embodiment of the present application can illustrate a possible deduction method.

[0075] In one case, before determining whether there is a restricted passing area, the method further includes:

[0076] Determine a second sideline trajectory corresponding to the oncoming vehicle; the second sideline trajectory is a motion trajectory of the center of the rear wheel of the oncoming vehicle when the oncoming vehicle is driving along the specified side close to the road sideline without considering the parked individual;

[0077] Based on the effective corner points of each parking entity, the second corner point trajectory corresponding to each parking entity is deduced for the oncoming vehicle to avoid.

[0078] Connecting the second edgeline trajectory and all the second corner point trajectories to form a rear wheel center trajectory of the oncoming vehicle;

[0079] The oncoming vehicle contour trajectory is determined based on the oncoming vehicle contour and the rear wheel center trajectory of the oncoming vehicle.

[0080] In practical applications, the deduction method of the oncoming vehicle contour trajectory corresponding to the oncoming vehicle is the same as the deduction method of the self-vehicle contour trajectory described above. Specifically, first ignore the existence of the parking individual, only consider the simplified outline of the oncoming vehicle, and deduce the motion trajectory of the center of the rear wheel of the oncoming vehicle when it is driving along the specified side close to the road edge, which is recorded as the second trajectory along the edge. It should be noted that the specified side here is specified with the oncoming vehicle as the main body. Then take the oncoming vehicle as the analysis object, for each parking individual, consider its various effective corner points respectively, and deduce the corner point trajectory formed by the center trace of the rear wheel of the oncoming vehicle during the process of the oncoming vehicle contour circling the corner point. Then smoothly connect all the corner point trajectories of each parking individual to form one or more trajectories around the parking individual (second corner point trajectory). All the trajectories around the parking individual are smoothly connected with the second trajectory along the edge to form the center trajectory of the rear wheel of the oncoming vehicle, and then deduce in combination with the simplified outline of the oncoming vehicle to determine the contour trajectory of the oncoming vehicle.

[0081] In addition, since there are different ways to determine whether there is a restricted passing area, the embodiment of the present application can illustrate a possible determination method.

[0082] In one case, the determining whether there is a restricted passing area includes:

[0083] Detect whether there is an overlapping area between the vehicle contour trajectory and the oncoming vehicle contour trajectory.

[0084] In practical applications, the overlapping area between the contour trajectory of the own vehicle and the contour trajectory of the oncoming vehicle is an area where two individuals traveling in opposite directions are not allowed to pass at the same time. Therefore, the determination of whether there is a restricted meeting area can be determined by whether there is an overlapping area between the contour trajectory of the own vehicle and the contour trajectory of the oncoming vehicle.

[0085] S103: If yes, it is prompted that the vehicle is currently in a narrow road meeting scene.

[0086] In actual applications, if there is a restricted passing area in the current driving environment, it means that the vehicle is in a narrow road passing scene, and a similar prompt message such as "The vehicle is currently in a narrow road passing scene" can be displayed on the vehicle display screen.

[0087] In addition, since the output contents are not the same, the embodiments of the present application can describe one possible output content.

[0088] In one embodiment, the method further comprises:

[0089] If the vehicle is currently in a narrow road meeting scene, the two-dimensional top view marked with a restricted meeting area and a permitted meeting area is output and displayed;

[0090] The passing area is an area where two vehicles traveling in opposite directions are allowed to pass at the same time.

[0091] Figure 3 A schematic diagram of a prompt message provided in an embodiment of the present application. Figure 3 As shown, a connecting line farthest from the bicycle in the contour trajectory of the own vehicle and the contour trajectory of the oncoming vehicle can be used as a basis for judging whether there is a restricted passing area. If there is an overlapping area between the two connecting lines, it indicates that there is a restricted passing area in the current driving environment of the own vehicle, and the own vehicle is in a narrow road passing scene. The recognition device of the narrow road passing scene will add a shadow to the overlapping area on the simplified two-dimensional top view and mark it as a restricted passing area, and mark the non-overlapping area as a passing area (an area where two individuals traveling in opposite directions are allowed to pass at the same time). Finally, the marked two-dimensional top view is displayed as a prompt message on the vehicle display screen.

[0092] In addition, since the output contents are not the same, the embodiments of the present application can describe one possible output content.

[0093] In one embodiment, the method further comprises:

[0094] If it does not exist, it indicates that the vehicle is not currently in a narrow road meeting scenario.

[0095] In actual applications, if there is no restricted passing area in the current driving environment of the vehicle, it means that the vehicle is not in a narrow road passing scenario. At this time, a text message similar to "The vehicle is not currently in a narrow road passing scenario" can also be prompted through the vehicle display screen.

[0096] In summary, Figure 4 A flowchart of an algorithm provided in an embodiment of the present application. Figure 4As shown, (1) the information detected by the perception module is input, and the current driving environment information of the vehicle is processed based on the predecessor module, and then input into the recognition device of the narrow road meeting scene for scene judgment. (2) A two-dimensional top view is constructed, and each individual is fitted into a contour with several corner points. Then the contour trajectory of the vehicle and the contour trajectory of the oncoming vehicle are deduced, that is, (3) the forward deduction of the vehicle and (4) the forward deduction of the oncoming vehicle. Specifically, the forward deduction of the vehicle includes (3.1) assuming that the vehicle is driving close to the right side of the road, and deducing a "track along the sideline" that ignores the existence of the parked individual, (3.2) considering each valid corner point of the single parked individual separately, and deducing a "track around the corner point", and (3.3) smoothly connecting multiple "tracks around the corner point" of a single parked individual to deduce a "track around the parked individual". (3.4) Determine whether the individual trajectory around the parking lot intersects with the trajectory along the edge first. If so, the individual trajectory around the parking lot is connected to the trajectory along the edge to obtain the center trajectory of the rear wheel of the vehicle; if not, the individual trajectory around the parking lot is smoothly connected with the intersecting individual trajectory around the parking lot to obtain the center trajectory of the rear wheel of the vehicle. Finally, the center trajectory of the rear wheel of the vehicle is extended according to the contour of the vehicle, and the point closest to the left (away from the driving measurement) is selected along the center line of the road to obtain the contour trajectory of the vehicle. The forward deduction of the oncoming vehicle includes (4.1) assuming that the oncoming vehicle is driving close to the right side of the road, and deducing a "track along the edge" that ignores the existence of the parking individual, (4.2) considering each valid corner point of the single parking individual separately, and deducing a "track around the corner point", (4.3) Smoothly connecting multiple "trajectories around the corner point" of a single parking individual to deduce a "track around the parking individual". (4.4) Determine whether the individual trajectory of the bypassing and parking intersects with the trajectory along the edge first. If so, the individual trajectory of the bypassing and parking is connected to the trajectory along the edge to obtain the center trajectory of the rear wheel of the oncoming vehicle; if not, the individual trajectory of the bypassing and parking is smoothly connected with the intersecting individual trajectory of the bypassing and parking to obtain the center trajectory of the rear wheel of the oncoming vehicle. Finally, the center trajectory of the rear wheel of the oncoming vehicle is expanded according to the contour of the oncoming vehicle, and the point closest to the left (away from the driving test) is selected along the center line of the road to obtain the contour trajectory of the oncoming vehicle. Then proceed to step (5) to overlap and detect the overlapping area of ​​the contour trajectory of the own vehicle and the contour trajectory of the oncoming vehicle. If there is an overlapping area, it is output that the own vehicle is in a narrow road meeting scene, and the "restricted meeting area" and "allowed meeting area" are displayed. If there is no overlapping area, it is output that the own vehicle is not in a narrow road meeting scene.

[0097] In summary, the present application first obtains the current driving environment information collected by the vehicle. Among them, the driving environment information includes: road sidelines, parked individuals, and moving individuals. Then when there is an oncoming vehicle, based on the current driving environment information, it is determined whether there is a restricted meeting area. Among them, the restricted meeting area is an area where two individuals traveling in opposite directions are not allowed to pass at the same time; if it exists, it is prompted that the vehicle is currently in a narrow road meeting scene. In this way, it is determined whether there is a restricted meeting area through the time-varying current driving environment information, and then it is determined whether the vehicle is in a narrow road meeting scene, thereby improving the accuracy of narrow road meeting scene recognition.

[0098] Based on the method for identifying a narrow road meeting scene provided by the above embodiment, the present application also provides a device for identifying a narrow road meeting scene. The device for identifying a narrow road meeting scene is described below in conjunction with the embodiments and drawings.

[0099] Figure 5 A schematic diagram of the structure of a device for identifying a narrow road meeting scene provided in an embodiment of the present application. Figure 5 As shown, the recognition device 500 for a narrow road meeting scene provided in an embodiment of the present application includes:

[0100] The object detection and tracking module 501 is used to obtain the current driving environment information collected by the vehicle; the driving environment information includes: road edges, parked individuals and moving individuals;

[0101] The identification module 502 is used to determine whether there is a restricted passing area based on the current driving environment information when there is an oncoming vehicle; the restricted passing area is an area where two individuals traveling in opposite directions are not allowed to pass at the same time;

[0102] The output module 503 is used to prompt that the vehicle is currently in a narrow road meeting scene when there is a restricted meeting area.

[0103] As an implementation method, with respect to how to deduce the contour trajectory of the vehicle, the above-mentioned identification device 500 for a narrow road meeting scene further includes: a first deduction module;

[0104] The first deduction module is used to construct a two-dimensional top view corresponding to the current driving environment with the vehicle as the main body; each individual in the two-dimensional top view is represented in the form of a contour with corner points;

[0105] The vehicle's contour trajectory is simulated when the vehicle is driving along the specified side close to the road edge.

[0106] As an implementation method, regarding how to deduce the vehicle contour trajectory, the first deduction module is specifically used to:

[0107] Determine a first sideline trajectory corresponding to the ego vehicle; the first sideline trajectory is a motion trajectory of the center of the ego vehicle's rear wheel when the ego vehicle is traveling along a specified side close to the road sideline without considering the parked individuals;

[0108] Based on the effective corner points of each docked individual, the first corner point trajectory corresponding to the vehicle avoiding each docked individual is deduced;

[0109] Connecting the first edgeline trajectory and all first corner point trajectories to form a rear wheel center trajectory of the vehicle;

[0110] The vehicle contour trajectory is determined based on the vehicle contour and the center trajectory of the rear wheels of the vehicle.

[0111] As an implementation manner, with respect to how to deduce the contour trajectory of an oncoming vehicle, the above-mentioned narrow road meeting scene recognition device 500 further includes: a second deduction module;

[0112] The second deduction module is used to determine a second trajectory along the sideline corresponding to the oncoming vehicle; the second trajectory along the sideline is the motion trajectory of the center of the rear wheel of the oncoming vehicle when the oncoming vehicle is driving along the specified side close to the road sideline without considering the parked individual;

[0113] Based on the effective corner points of each parking entity, the second corner point trajectory corresponding to each parking entity is deduced for the oncoming vehicle to avoid.

[0114] Connecting the second edgeline trajectory and all the second corner point trajectories to form a rear wheel center trajectory of the oncoming vehicle;

[0115] The oncoming vehicle contour trajectory is determined based on the oncoming vehicle contour and the rear wheel center trajectory of the oncoming vehicle.

[0116] As an implementation manner, regarding how to determine whether there is a restricted passing area, the identification module 502 is specifically used to:

[0117] Detect whether there is an overlapping area between the vehicle contour trajectory and the oncoming vehicle contour trajectory.

[0118] As an implementation method, with respect to how to output the recognition result, the above-mentioned narrow road meeting scene recognition device 500 further includes: a first output submodule

[0119] A first output submodule is used for outputting and displaying the two-dimensional top view marked with a restricted passing area and a permitted passing area when the vehicle is currently in a narrow road passing scene;

[0120] The passing area is an area where two vehicles traveling in opposite directions are allowed to pass at the same time.

[0121] As an implementation method, with respect to how to output the recognition result, the above-mentioned recognition device 500 for the narrow road vehicle-meeting scene further includes: a second output submodule

[0122] The second output submodule is used to prompt that the vehicle is not currently in a narrow road meeting scenario when there is no restricted meeting area.

[0123] In summary, the present application first obtains the current driving environment information collected by the vehicle. Among them, the driving environment information includes: road sidelines, parked individuals, and moving individuals. Then when there is an oncoming vehicle, based on the current driving environment information, it is determined whether there is a restricted meeting area. Among them, the restricted meeting area is an area where two individuals traveling in opposite directions are not allowed to pass at the same time; if it exists, it is prompted that the vehicle is currently in a narrow road meeting scene. In this way, it is determined whether there is a restricted meeting area through the time-varying current driving environment information, and then it is determined whether the vehicle is in a narrow road meeting scene, thereby improving the accuracy of narrow road meeting scene recognition.

[0124] In addition, the present application also provides a device for identifying a narrow road meeting scene, including: a memory for storing a computer program; a processor for implementing the steps of the method for identifying a narrow road meeting scene as described in any one of the above items when executing the computer program.

[0125] In addition, the present application also provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for identifying a narrow road meeting scene as described in any one of the above items are implemented.

[0126] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying a narrow road meeting scene, characterized in that: The method comprises: Acquire current driving environment information collected by the vehicle; the driving environment information includes: road edges, parked individuals and moving individuals; When there is an oncoming vehicle, based on the current driving environment information, it is determined whether there is a restricted passing area; the restricted passing area is an area where two individuals traveling in opposite directions are not allowed to pass at the same time; If it exists, it will prompt that the vehicle is currently in a narrow road meeting scene.

2. The method according to claim 1, characterized in that: Before determining whether there is a restricted passing area, the method further includes: Taking the vehicle as the main body, a two-dimensional top view corresponding to the current driving environment is constructed; each entity in the two-dimensional top view is represented in the form of a contour with corner points; The vehicle's contour trajectory is simulated when the vehicle is driving along the specified side close to the road edge.

3. The method according to claim 2, characterized in that The deducing of the vehicle contour trajectory when the vehicle is traveling along the specified side close to the road edge line includes: Determine a first sideline trajectory corresponding to the ego vehicle; the first sideline trajectory is a motion trajectory of the center of the ego vehicle's rear wheel when the ego vehicle is traveling along a specified side close to the road sideline without considering the parked individuals; Based on the effective corner points of each docked individual, the first corner point trajectory corresponding to the vehicle avoiding each docked individual is deduced; Connecting the first edgeline trajectory and all first corner point trajectories to form a rear wheel center trajectory of the vehicle; The vehicle contour trajectory is determined based on the vehicle contour and the center trajectory of the rear wheels of the vehicle.

4. The method according to claim 2, characterized in that: Before determining whether there is a restricted passing area, the method further includes: Determine a second sideline trajectory corresponding to the oncoming vehicle; the second sideline trajectory is a motion trajectory of the center of the rear wheel of the oncoming vehicle when the oncoming vehicle is driving along the specified side close to the road sideline without considering the parked individual; Based on the effective corner points of each parking entity, the second corner point trajectory corresponding to each parking entity is deduced for the oncoming vehicle to avoid. Connecting the second edgeline trajectory and all the second corner point trajectories to form a rear wheel center trajectory of the oncoming vehicle; The oncoming vehicle contour trajectory is determined based on the oncoming vehicle contour and the rear wheel center trajectory of the oncoming vehicle.

5. The method according to claim 4, characterized in that The determining whether there is a restricted passing area includes: Detect whether there is an overlapping area between the vehicle contour trajectory and the oncoming vehicle contour trajectory.

6. The method according to claim 2, characterized in that The method further comprises: If the vehicle is currently in a narrow road meeting scene, the two-dimensional top view marked with a restricted meeting area and a permitted meeting area is output and displayed; The passing area is an area where two vehicles traveling in opposite directions are allowed to pass at the same time.

7. The method according to claim 1, characterized in that The method further comprises: If it does not exist, it indicates that the vehicle is not currently in a narrow road meeting scenario.

8. A device for identifying a narrow road meeting scene, characterized in that: include: The object detection and tracking module is used to obtain the current driving environment information collected by the vehicle; The driving environment information includes: road edges, parked individuals and moving individuals; An identification module is used to determine whether there is a restricted passing area based on the current driving environment information when there is an oncoming vehicle; the restricted passing area is an area where two individuals traveling in opposite directions are not allowed to pass at the same time; The output module is used to prompt that the vehicle is currently in a narrow road meeting scenario when there is a restricted meeting area.

9. A recognition device for a narrow road meeting scene, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the method for identifying a narrow road meeting scene as claimed in any one of claims 1 to 7 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for identifying a narrow road meeting scene as claimed in any one of claims 1 to 7 are implemented.

Images