Lane traffic cone recognition method and apparatus for vehicle, electronic device and storage medium

Abstract

Disclosed in the present invention are a lane traffic cone recognition method and apparatus, an electronic device and a storage medium. The method is characterized by comprising: acquiring information by means of an autonomous driving sensing system of a target vehicle, so as to obtain obstacle information of a lane obstacle; constructing traffic cone groups by means of a preset high-precision map and the obstacle information, and determining at least one target traffic cone group; and performing fusion recognition on the target traffic cone group individually, so as to determine target traffic cone information corresponding to the target vehicle. Performing fusion recognition on the target traffic cone group individually can accurately recognize consecutive traffic cones on roads, thereby improving the autonomous driving safety and reliability of vehicles.

Description

Vehicle lane cone barrel recognition method and device, electronic equipment and storage medium TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a vehicle lane cone barrel recognition method and device, electronic equipment and storage medium. BACKGROUND

[0002] Vehicle automatic driving can collect road information and obstacle information in the road through vehicle-mounted sensors, and then automatically drive according to the road information and obstacle information through the vehicle-mounted automatic driving function without human operation by the vehicle driver. However, in the existing vehicle automatic driving process, the automatic driving system of the vehicle cannot effectively recognize and detect the cone barrels in the road. The cone barrels are small in size and weak in signal reflection, and are usually placed continuously at the edge of the vehicle road or intersection. The vehicle sensors of the automatic driving vehicle are easily disturbed by the lane environment, which further makes it difficult to accurately recognize each cone barrel, resulting in a great safety hazard in the automatic driving route of the vehicle. In the prior art, the vehicle sensors are often increased and the recognition intensity of the cone barrels is increased, but this increases the equipment cost and computing cost of the vehicle.

[0003] SUMMARY

[0004] The present application provides a lane cone barrel recognition method, device, electronic equipment and storage medium to realize cone barrel recognition fusion and improve the recognition accuracy of continuous cone barrels and the safety and reliability of vehicle automatic driving.

[0005] According to an aspect of the present application, a vehicle lane cone barrel recognition method is provided, comprising:

[0006] Collecting information through an automatic driving perception system of a target vehicle to obtain obstacle information of lane obstacles; wherein the obstacle information includes obstacle coordinates, obstacle categories and obstacle corner point information;

[0007] Constructing a cone barrel group through a pre-set high-precision map and the obstacle information, and determining at least one target cone barrel group;

[0008] Fusion recognizing the target cone barrel groups one by one to determine the target cone barrel information corresponding to the target vehicle.

[0009] According to another aspect of the present application, a vehicle lane cone barrel recognition device is provided, comprising:

[0010] A perception module is configured to collect information through an automatic driving perception system of a target vehicle to obtain obstacle information of lane obstacles; wherein the obstacle information includes obstacle coordinates, obstacle categories and obstacle corner point information;

[0011] an information processing module, configured to construct a cone group based on the preset high-precision map and the obstacle information, and determine at least one target cone group;

[0012] a recognition module, configured to perform fusion recognition on the target cone groups one by one, and determine target cone information corresponding to the target vehicle.

[0013] According to another aspect of the present application, an electronic device is provided, which comprises:

[0014] at least one processor; and

[0015] a memory in communication with the at least one processor; wherein

[0016] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the vehicle lane cone recognition method according to any one of the embodiments of the present application.

[0017] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to perform the vehicle lane cone recognition method according to any one of the embodiments of the present application.

[0018] The technical scheme of the embodiments of the present application realizes accurate recognition of the cone by collecting information through an automatic driving perception system of a target vehicle, obtaining obstacle information of lane obstacles, determining the recognized cone through the obstacle information, and then processing the cone, thereby improving the safety of automatic driving. The cone group is constructed based on the preset high-precision map and the obstacle information, at least one target cone group is determined, the lane of the vehicle is recognized through the high-precision map, and the cone is recognized according to the information corresponding to the cone and the lane, thereby constructing an effective cone group of the cone, effectively reducing the number of recognitions, and improving the efficiency and accuracy of recognition. The target cone group is recognized one by one, and the target cone information corresponding to the target vehicle is determined. The continuous cone in the road can be accurately recognized by performing fusion recognition on the target cone group one by one, thereby improving the success rate of recognizing the continuous cone, solving the technical problem that the continuous cone cannot be recognized in the prior art, and improving the safety and reliability of vehicle automatic driving.

[0019] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to make the technical solution in the embodiments of the present application clearer, the accompanying drawings needed in the embodiments description will be briefly introduced as follows. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of the accompanying drawings.

[0021] Fig. 1 is a flow chart of a vehicle lane cone barrel recognition method provided by an embodiment of the present application;

[0022] Fig. 2 is a flow chart of another vehicle lane cone barrel recognition method provided by an embodiment of the present application;

[0023] Fig. 3 is a flow chart of another vehicle lane cone barrel recognition method provided by an embodiment of the present application;

[0024] Fig. 4 is a structural schematic diagram of a vehicle lane cone barrel recognition device provided by an embodiment of the present application;

[0025] Fig. 5 shows a structural schematic diagram of an electronic device 10 which can be used to implement an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the technical solution in the embodiments of the present application clearer, the accompanying drawings needed in the embodiments description will be briefly introduced as follows. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of the accompanying drawings.

[0027] It should be noted that the terms "first", "second", and the like in the description and claims of the present application and the above-mentioned accompanying drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to the process, method, product or device.

[0028] FIG. 1 is a flowchart of a method for identifying a lane cone barrel by a vehicle according to an embodiment of the present application. The embodiment can be applied to the case where an autonomous vehicle detects a lane cone barrel during driving. The method can be executed by a lane cone barrel identification device for a vehicle. The lane cone barrel identification device can be implemented in the form of hardware and / or software, and can be configured in an electronic device. As shown in FIG. 1, the method includes:

[0029] S110, collecting information by an automatic driving perception system of a target vehicle to obtain obstacle information of a lane obstacle.

[0030] The target vehicle can be a vehicle with autonomous driving capability.

[0031] The automatic driving perception system can be a system for collecting and processing information around the target vehicle in the target vehicle. The automatic driving perception system is usually composed of multiple different types of sensors. Each type of sensor can collect different environmental information. Different types of sensors can cooperate to perceive the environment around the vehicle and achieve information collection around the vehicle. Optionally, the types of sensors that make up the automatic driving perception system can include monocular, binocular or multi-view cameras, long-range radars and short-range radars, laser radars, and ultrasonic sensors.

[0032] The lane obstacle can be an obstacle detected in the driving road of the target vehicle. Optionally, there are various types of lane obstacles, such as obstacles left over from traffic accidents, artificial devices, pedestrians and non-motor vehicles, temporary or permanent roadblocks, vehicles and public facilities.

[0033] The obstacle information can be information obtained after the automatic driving perception system detects the lane obstacle and processes it. The obstacle information includes obstacle coordinates, obstacle categories, and obstacle corner point information. The obstacle coordinates can be coordinate information of the lane obstacle in a vehicle coordinate system constructed by the autonomous vehicle. The obstacle category can be category information identified by the automatic driving perception system. The obstacle corner point information can be a point on the edge of the lane obstacle. The obstacle corner point information can be used to describe the shape of the obstacle, and can reflect the edge point or contour point of the obstacle, which is used to determine the edge and contour of the obstacle. Optionally, in an autonomous driving scenario, the corner point information can help continuously monitor the lane obstacle, and tracking the corner points of the lane obstacle can help more stably predict its motion trajectory.

[0034] Specifically, after the target vehicle enters the autonomous driving mode, the automatic driving perception system in the target vehicle continuously perceives and collects information about the environment around the target vehicle, and processes the collected data to determine the obstacle information of the lane obstacle in the road where the target vehicle is located.

[0035] S120, construct a cone group by the preset high-precision map and the obstacle information, and determine at least one target cone group.

[0036] The high-precision map can be a highly precise and detailed map dataset. The high-precision map can accurately distinguish different lanes of a road and road signs, and determine detailed information of each lane in the road. For example, lane width, lane line position and type, and lane curvature of the lane.

[0037] Optionally, the preset high-precision map can be pre-set in the target vehicle, and the map information can be updated in real time through networking of the target vehicle.

[0038] The target cone group can be a group of cones with similar distances and consistent arrangement directions. The target cone group can include a transverse cone group and a longitudinal cone group. The transverse cone group can be a group of cones with similar distances and transverse arrangement directions. The longitudinal cone group can be a group of cones with similar distances and longitudinal arrangement directions.

[0039] Specifically, after obtaining the obstacle information, the cones around the target vehicle are determined according to the obstacle information, and the cones around the target vehicle are grouped to obtain at least one target cone group by constructing a cone group through the preset high-precision map and the recognized cones.

[0040] S130, fuse and identify the target cone groups one by one to determine the target cone information corresponding to the target vehicle.

[0041] The target cone information can be position and distribution information of the cones around the target vehicle.

[0042] Specifically, after obtaining at least one target cone group, all cones included in each target cone group are fused and identified one by one to determine the target cone information of the target vehicle.

[0043] The technical scheme of the embodiment of the present application collects information through an automatic driving perception system of a target vehicle to obtain obstacle information of a lane obstacle, determines a recognized cone barrel through the obstacle information, and further processes the cone barrel, thereby realizing accurate identification of the cone barrel and improving the safety of automatic driving; a cone barrel group is constructed through a preset high-precision map and the obstacle information, at least one target cone barrel group is determined, the lane of the vehicle is recognized through the high-precision map, and the target cone barrel group is recognized according to the information corresponding to the cone barrel, thereby constructing an effective cone barrel group of the cone barrel, effectively reducing the number of recognitions, and improving the efficiency and accuracy of recognition; the target cone barrel group is recognized in a fusion manner one by one to determine target cone barrel information corresponding to the target vehicle, the continuous cone barrels in the road can be accurately recognized through the fusion recognition of the target cone barrel group one by one, the safety and reliability of vehicle automatic driving are improved, the technical problem that the continuous cone barrels cannot be recognized in the prior art is solved, and the safety and reliability of vehicle automatic driving are improved.

[0044] Fig. 2 is a flowchart of another vehicle lane cone barrel recognition method provided by the embodiment of the present application, and the relationship between the present embodiment and the above-mentioned embodiment is that the specific method of constructing a cone barrel group through a preset high-precision map and obstacle information is illustrated. As shown in Fig. 2, the method comprises:

[0045] S210, collecting information through an automatic driving perception system of a target vehicle to obtain obstacle information of a lane obstacle.

[0046] S220, constructing a target cone barrel cluster according to the high-precision map and the obstacle information.

[0047] The target cone barrel cluster can be a cluster composed of multiple cone barrels around the target vehicle, and the target cone barrel cluster includes multiple cone barrels around the lane where the target vehicle is located in the longitudinal and transverse directions.

[0048] Specifically, after the obstacle information is obtained, the cone barrels around the target vehicle are determined according to the obstacle information, and a target cone barrel cluster is constructed through a preset high-precision map and the recognized cone barrels.

[0049] Optionally, in another optional embodiment of the present application, the construction of the target cone barrel cluster according to the high-precision map and the obstacle information comprises:

[0050] In the case where the obstacle category of the lane obstacle is a cone barrel type, the target cone barrel cluster is determined according to the high-precision map and the obstacle coordinates of the lane obstacle.

[0051] The cone barrel type can be a cone barrel type obstacle, the cone barrel type can include different types of cone barrels, such as traffic cones, warning cones, roadblock cone barrels, road marker barrels, and ice cream cones, the cone barrels are usually bright in color and have reflective light strips, and can play a warning role.

[0052] Specifically, after the target vehicle obtains the obstacle information of the vehicle obstacle, the obstacle category of the lane obstacle of the target vehicle is identified, in the case that the obstacle category of the lane obstacle is the cone barrel type, whether the obstacle coordinates of the vehicle obstacle can be merged is identified through the high-precision map, and after it is determined that the vehicle obstacle can be merged, the obstacle category that can be merged is merged into the cone barrel category to obtain the target cone barrel cluster.

[0053] Optionally, in another optional embodiment of the present application, the high-precision map and the obstacle coordinates of the lane obstacle are merged to determine the target cone barrel cluster, including:

[0054] According to the high-precision map and the obstacle coordinates, the position of the lane obstacle corresponding to the obstacle lane is identified;

[0055] According to the obstacle coordinates, the distance of each lane obstacle is calculated to determine the obstacle distance corresponding to each lane obstacle;

[0056] According to the obstacle lane and the obstacle distance of the lane obstacle, the target cone barrel cluster is determined.

[0057] The obstacle vehicle can be the road lane in which the lane obstacle is located in the high-precision map. Optionally, after the obstacle coordinates of the lane obstacle are obtained, the obstacle lane corresponding to the lane obstacle in the high-precision map is determined according to the vehicle coordinates corresponding to the target vehicle and the high-precision map.

[0058] The obstacle distance can be the distance between each lane obstacle. Optionally, the obstacle distance corresponding to each lane obstacle is obtained by calculating the distance between the obstacle coordinates of the lane obstacle in the vehicle coordinate system and the obstacle coordinates of other lane obstacles in the vehicle coordinate system.

[0059] Optionally, after identifying that the obstacle class of the lane obstacle is the cone type, an obstacle lane to which the cone type lane obstacle belongs is obtained, cone type lane obstacles in the same lane are selected for merging, cone type lane obstacles in different obstacle lanes are eliminated, one cone type lane obstacle is selected as a center of a target cone cluster, a distance between the cone type lane obstacle corresponding to the center of the target cone cluster and other cone type lane obstacles is obtained, if the distance between the cone type lane obstacle and the cone type lane obstacle corresponding to the center of the target cone cluster is greater than a preset merging distance threshold, the cone type lane obstacle is not merged, and if the distance between the cone type lane obstacle and the cone type lane obstacle corresponding to the center of the target cone cluster is less than the preset merging distance threshold, the cone type lane obstacle is merged into the target cone cluster.

[0060] S230, determining at least one target cone group based on the target cone cluster and the obstacle coordinates.

[0061] Specifically, the target vehicle determines a target cone cluster corresponding to the cone type lane obstacle, groups lane obstacles in the target cone cluster through the obstacle coordinates, and determines at least one target cone group.

[0062] Optionally, in another optional embodiment of the present application, the determination of at least one target cone group based on the target cone cluster and the obstacle coordinates comprises:

[0063] The lane obstacles in the target cone cluster are divided according to the obstacle coordinates through a preset cone group division rule, and at least one target cone group is determined; wherein the target cone group comprises a horizontal cone group and a vertical cone group.

[0064] The cone group division rule can be a rule preset for grouping vehicle obstacles. In the embodiment of the present application, the target cone group comprises a horizontal cone group and a vertical cone group, and the cone division rule can set different division rules for the vertical cone group and the horizontal cone group.

[0065] Preferably, the division rule for the longitudinal cone barrel group can be that a lane barrier corresponding to the barrier coordinate of a cone barrel type is taken as the center coordinate, and the barrier coordinates of the lane barriers of other cone barrel types and the center coordinate are judged. If the absolute value of the change of the horizontal coordinate is not greater than 0.5 m and the absolute value of the change of the vertical coordinate is not greater than 10 m, the lane barriers can be merged into the same longitudinal cone barrel group. When the number of lane barriers in the longitudinal cone barrel group is greater than 2, the barrier coordinates of the lane barriers of other cone barrel types and the barrier coordinates of each lane barrier in the longitudinal cone barrel group are judged. If the absolute value of the change of the horizontal coordinate of the barrier coordinate of the lane barrier of other cone barrel types and the barrier coordinate of any lane barrier in the longitudinal cone barrel group is not greater than 0.5 m and the absolute value of the change of the vertical coordinate is not greater than 10 m, the lane barrier is merged into the longitudinal cone barrel group.

[0066] The division rule for the horizontal cone barrel group can be that a lane barrier corresponding to the barrier coordinate of a cone barrel type is taken as the center coordinate, and the barrier coordinates of the lane barriers of other cone barrel types and the center coordinate are judged. If the absolute value of the change of the vertical coordinate is not greater than 0.5 m and the absolute value of the change of the horizontal coordinate is not greater than 1.5 m, the lane barriers can be merged into the same horizontal cone barrel group. When the number of lane barriers in the horizontal cone barrel group is greater than 2, the barrier coordinates of the lane barriers of other cone barrel types and the barrier coordinates of each lane barrier in the horizontal cone barrel group are judged. If the absolute value of the change of the vertical coordinate of the barrier coordinate of the lane barrier of other cone barrel types and the barrier coordinate of any lane barrier in the horizontal cone barrel group is not greater than 0.5 m and the absolute value of the change of the horizontal coordinate is not greater than 1.5 m, the lane barrier is merged into the horizontal cone barrel group.

[0067] Optionally, when the lane barriers in the target cone barrel cluster are divided, each lane barrier is judged only once by one target cone barrel group when the lane barriers are judged by a target cone barrel group, and the lane barriers that have been divided into the target cone barrel group are no longer judged by other target cone barrel groups.

[0068] Optionally, when the lane obstacles in the target cone barrel cluster are divided, the division is performed simultaneously through the rules corresponding to the longitudinal cone barrel group and the transverse cone barrel group. After the first two lane obstacles are detected to satisfy the rules corresponding to the longitudinal cone barrel group or the transverse cone barrel group, the first two lane obstacles are divided into the longitudinal cone barrel group or the transverse cone barrel group. If the first two lane obstacles are the longitudinal cone barrel group, the rules corresponding to the transverse cone barrel group are no longer used to judge other lane obstacles, and only the rules corresponding to the longitudinal cone barrel group are used to judge other lane obstacles. If the first two lane obstacles are the transverse cone barrel group, the rules corresponding to the longitudinal cone barrel group are no longer used to judge other lane obstacles, and only the rules corresponding to the transverse cone barrel group are used to judge other lane obstacles.

[0069] Optionally, when the lane obstacles in the target cone barrel cluster are divided, if it is detected that a transverse cone barrel group cannot detect a rule corresponding to the transverse cone barrel group or a longitudinal cone barrel group cannot detect a rule corresponding to the longitudinal cone barrel group, the division of the lane obstacles into the transverse cone barrel group or the longitudinal cone barrel group is stopped.

[0070] Specifically, the lane obstacles are divided in the target cone barrel cluster according to the obstacle coordinates of the lane obstacles through the preset cone barrel group division rules, and at least one target cone barrel group is determined.

[0071] S240, the target cone barrel groups are fused and recognized one by one to determine the target cone barrel information corresponding to the target vehicle.

[0072] The technical scheme of the embodiment of the application acquires information through an automatic driving perception system of a target vehicle to obtain obstacle information of lane obstacles; constructs a target cone barrel cluster according to the high-precision map and the obstacle information, which can effectively identify lane obstacles and filter lane obstacles according to the distance and coordinates of the obstacles, aggregate lane obstacles meeting the requirements into the target cone barrel cluster, reduce the number of to-be-identified lane obstacles, and improve the identification efficiency of the cone barrels; at least one target cone barrel group is determined based on the target cone barrel cluster and the obstacle coordinates, the cone barrels are classified in the target cone barrel cluster through the obstacle coordinates, which can prevent the range of the merged cone barrels from being too large and the area of the obstacles from being too large, and further improve the accuracy and precision of identification; the target cone barrel groups are fused and recognized one by one to determine the target cone barrel information corresponding to the target vehicle, which solves the technical problem that continuous cone barrels cannot be identified in the prior art, and improves the safety and reliability of vehicle automatic driving.

[0073] FIG. 3 is a flowchart of another vehicle lane cone barrel identification method provided by the embodiment of the application. The relationship between the embodiment and the above-mentioned embodiment is that the specific method of fusing the target cone barrel group is illustrated. As shown in FIG. 3, the method comprises:

[0074] S310, information collection is performed by an automatic driving perception system of a target vehicle to obtain obstacle information of a lane obstacle.

[0075] S320, a cone barrel group is constructed by a preset high-precision map and the obstacle information, and at least one target cone barrel group is determined.

[0076] S330, the obstacle corner point information of the lane obstacle in each target cone barrel group is fused one by one to determine a target obstacle convex hull polygon corresponding to each target cone barrel group.

[0077] The target obstacle convex hull polygon can be an irregular polygon obtained by connecting and fusing the obstacle corner point information. It should be noted that the obstacle corner point information can be an edge point of the lane obstacle. By connecting the edge points of all vehicle obstacles in a target cone barrel group, an irregular polygon composed of vehicle obstacles is obtained, and the irregular polygon is determined as the target obstacle convex hull polygon corresponding to the target cone barrel group.

[0078] Specifically, each target cone barrel group is processed individually, the obstacle corner point information of all lane obstacles in each target cone barrel group is obtained, the edge points of all lane obstacles are determined according to the obstacle corner point information, and these edge points are sequentially connected to obtain an irregular polygon. All lane obstacles are contained in the irregular polygon, and the irregular polygon is determined as the target obstacle convex hull polygon corresponding to each target cone barrel group.

[0079] S340, the target obstacle convex hull polygon is calculated for a minimum bounding box one by one to determine a target minimum bounding box corresponding to the target obstacle convex hull polygon and vertex coordinate information corresponding to the target minimum bounding box.

[0080] The target minimum bounding box can be a regular polygon containing all vehicle obstacles in the target cone barrel group.

[0081] Optionally, the OpenCV (Open Source Computer Vision Library) is preset to calculate the minimum bounding box of the target obstacle convex hull polygon, the minAreaRect function of the OpenCV is used to calculate the minimum bounding box, the target minimum bounding box corresponding to the target obstacle convex hull polygon is determined, and the vertex coordinate information corresponding to the target minimum bounding box is output by the minAreaRect function. The target minimum bounding box output by the minAreaRect function is a rectangle.

[0082] Specifically, for each target obstacle convex polygon, the target obstacle convex polygon is sequentially calculated by OpenCV to determine the target minimum bounding box corresponding to the target obstacle convex polygon and the vertex coordinate information corresponding to the target minimum bounding box.

[0083] S350, determining the target cone barrel information corresponding to the target vehicle according to all the target minimum bounding boxes and the vertex coordinate information of each target minimum bounding box.

[0084] Specifically, the target cone barrel information corresponding to the target vehicle is determined by calculating the regular shape corresponding to the target minimum bounding box and the vertex coordinate information of each target minimum bounding box.

[0085] Optionally, in another optional embodiment of the present application, the target cone barrel information corresponding to the target vehicle is determined according to all the target minimum bounding boxes and the vertex coordinate information of each target minimum bounding box, including:

[0086] The center point, direction and coordinate range of each target minimum bounding box are sequentially calculated according to the vertex coordinate information of each target minimum bounding box to determine the center point information, direction information and range information corresponding to each target minimum bounding box.

[0087] The target cone barrel information is determined according to all the direction information, the center point information and the range information.

[0088] Wherein, the center point can be the center of the target minimum bounding box; the direction can be the relative direction of the target minimum bounding box and the driving direction of the target vehicle, and it should be noted that the coordinate system of the vehicle obstacle is the vehicle coordinate system, and the relative direction of the target minimum bounding box and the target vehicle is determined by comparing the vertex coordinate information of the target minimum bounding box with the target vehicle in the vehicle coordinate system. For example, the coordinate calculation is performed on the vertex coordinate information of the target minimum bounding box and the coordinate information corresponding to the target vehicle, if the longitudinal coordinate calculation result of the target minimum bounding box has a positive value, the direction of the target minimum bounding box is forward; if the longitudinal coordinate calculation result of the target minimum bounding box is negative, the direction of the target minimum bounding box is backward; if the horizontal coordinate calculation result of the target minimum bounding box is positive, the direction of the target minimum bounding box is left; if the horizontal coordinate calculation result of the target minimum bounding box is negative, the direction of the target minimum bounding box is right.

[0089] Wherein, the coordinate range can be the range included in the vertex coordinate information of the target minimum bounding box.

[0090] Specifically, for each target minimum bounding box, the specific calculation method is as follows: the center point of the target minimum bounding box is calculated through the vertex coordinate information of the target minimum bounding box, the center point coordinate of the center point of the target minimum bounding box in the vehicle coordinate system is determined, the center point coordinate corresponding to the center point of the target minimum bounding box is determined as the center point information, the relative direction between the target minimum bounding box and the target vehicle is determined according to the vertex coordinate information of the target minimum bounding box and the target vehicle, the range information is taken as the direction information of the target minimum bounding box, and the range information corresponding to the target minimum bounding box is determined according to the vertex coordinate information of the target minimum bounding box. The center point information, direction information and range information of each target minimum bounding box are calculated, and the center point information, direction information and range information of all target minimum bounding boxes are collected and integrated to obtain target cone barrel information.

[0091] Optionally, after obtaining the target cone barrel information, the target cone barrel information is sent to the automatic driving route planning system of the target vehicle, so that the automatic driving route planning system plans a route for the target vehicle.

[0092] The technical scheme of the embodiment of the application acquires the obstacle information of the lane obstacle through the automatic driving perception system of the target vehicle; constructs a cone barrel group through the preset high-precision map and the obstacle information, and determines at least one target cone barrel group; fuses the obstacle corner point information of the lane obstacle in each target cone barrel group one by one, determines the target obstacle convex hull polygon corresponding to each target cone barrel group, identifies the edge of the cone barrel through the obstacle corner point information, and then connects the edge to obtain the target obstacle convex hull polygon, which can effectively determine the range of multiple continuous cone barrels and improve the recognition accuracy of the continuous cone barrels; calculates the minimum bounding box of the target obstacle convex hull polygon one by one, determines the target minimum bounding box corresponding to the target obstacle convex hull polygon and the vertex coordinate information corresponding to the target minimum bounding box; determines the target cone barrel information corresponding to the target vehicle according to all target minimum bounding boxes and the vertex coordinate information of each target minimum bounding box, and further improves the recognition accuracy of the continuous cone barrels of the target vehicle by calculating the target minimum bounding box of the target obstacle convex hull polygon. The technical problem that the continuous cone barrels cannot be recognized in the prior art is solved, and the safety and reliability of vehicle automatic driving are improved.

[0093] Fig. 4 is a structural schematic view of a vehicle lane cone barrel recognition device provided by an embodiment of the application. As shown in Fig. 4, the device comprises a perception module 410, an information processing module 420 and a recognition module 430, wherein;

[0094] The perception module 410 is configured to collect information through an automatic driving perception system of the target vehicle to obtain obstacle information of a lane obstacle; wherein the obstacle information comprises obstacle coordinates, obstacle categories and obstacle corner point information;

[0095] The information processing module 420 is configured to construct a cone barrel group through a preset high-precision map and the obstacle information, and determine at least one target cone barrel group;

[0096] The identification module 430 is configured to perform fusion identification on the target cone barrel groups one by one to determine target cone barrel information corresponding to the target vehicle.

[0097] The technical scheme of the embodiment of the application collects information through an automatic driving perception system of the target vehicle to obtain obstacle information of a lane obstacle, determines a recognized cone barrel through the obstacle information, and then processes the cone barrel, thereby realizing accurate identification of the cone barrel and improving the safety of automatic driving; the cone barrel group is constructed through a preset high-precision map and the obstacle information, at least one target cone barrel group is determined, the lane of the vehicle is identified through the high-precision map, and the lane is identified according to the information corresponding to the cone barrel, thereby constructing an effective cone barrel group of the cone barrel, effectively reducing the number of identifications, and improving the efficiency and accuracy of identification; the target cone barrel groups are identified one by one to determine target cone barrel information corresponding to the target vehicle, the target cone barrel groups are identified one by one, continuous cone barrels in the road can be accurately identified, the safety and reliability of vehicle automatic driving are improved, and the technical problem that continuous cone barrels cannot be identified in the prior art is solved, thereby improving the safety and reliability of vehicle automatic driving.

[0098] Optionally, the information processing module is specifically configured to:

[0099] construct a target cone barrel cluster according to the high-precision map and the obstacle information;

[0100] determine at least one target cone barrel group based on the target cone barrel cluster and the obstacle coordinates.

[0101] Optionally, the information processing module is specifically configured to:

[0102] in a case where the obstacle category of the lane obstacle is a cone barrel type, merge according to the high-precision map and the obstacle coordinates of the lane obstacle to determine the target cone barrel cluster.

[0103] Optionally, the information processing module is specifically configured to:

[0104] perform position identification according to the high-precision map and the obstacle coordinates to determine an obstacle lane corresponding to the lane obstacle;

[0105] sequentially calculate the distance of each of the lane obstacles according to the obstacle coordinates, and determine the obstacle distance corresponding to each of the lane obstacles;

[0106] merge according to the obstacle lane and the obstacle distance of the lane obstacle, and determine the target cone cluster.

[0107] Optionally, the information processing module is specifically configured to:

[0108] According to the preset cone group division rule, the lane obstacles in the target cone cluster are divided according to the obstacle coordinates, and at least one target cone group is determined; wherein the target cone group includes a transverse cone group and a longitudinal cone group.

[0109] Optionally, the identification module is specifically configured to:

[0110] The obstacle corner point information of the lane obstacles in each of the target cone groups is fused one by one, and a target obstacle convex hull polygon corresponding to each of the target cone groups is determined.

[0111] The target obstacle convex hull polygon is calculated one by one, and a target minimum bounding box corresponding to the target obstacle convex hull polygon and vertex coordinate information corresponding to the target minimum bounding box are determined.

[0112] According to all the target minimum bounding boxes and the vertex coordinate information of each of the target minimum bounding boxes, target cone information corresponding to the target vehicle is determined.

[0113] Optionally, the identification module is specifically configured to:

[0114] According to the vertex coordinate information of each of the target minimum bounding boxes, the center point, orientation and coordinate range of the target minimum bounding box are calculated one by one, and the center point information, direction information and range information corresponding to each of the target minimum bounding boxes are determined.

[0115] According to all the direction information, the center point information and the range information, the target cone information is determined.

[0116] The vehicle lane cone recognition device provided by the embodiment of the application can execute the vehicle lane cone recognition method provided by any embodiment of the application, and has the corresponding function modules and beneficial effects of the execution method.

[0117] FIG. 5 shows a structural diagram of an electronic device 10 that can be used to implement embodiments of the present application. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their modes of operation, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0118] As shown in FIG. 5, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., connected to the at least one processor 11 in communication, where the memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0119] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, speakers, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer grid, such as the Internet, and / or various telecommunications grids.

[0120] The processor 11 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the vehicle-to-lane-cone bucket recognition method.

[0121] In some embodiments, the vehicle-to-lane-cone bucket recognition method can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 18. In some embodiments, parts or all of the computer program can be loaded and / or installed onto electronic device 10 via, e.g., ROM 12 and / or communication unit 19. When the computer program is loaded onto RAM 13 and executed by processor 11, one or more steps of the vehicle-to-lane-cone bucket recognition method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the vehicle-to-lane-cone bucket recognition method by other any suitable means, e.g., by way of firmware.

[0122] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0123] Computer programs used to implement the processes of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed, implements the methods / operations specified in the flow charts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as part of a standalone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0124] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0125] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0126] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0127] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. Servers can be cloud servers, also known as cloud computing servers or cloud hosts, which are host products in the cloud computing service system to solve the defects of large management difficulty and weak business scalability in traditional physical hosts and VPS services.

[0128] It should be understood that the various forms of flow shown above can be reordered, added to, or have steps deleted. For example, the steps described in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, and the present application does not limit this.

[0129] The embodiment provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the steps of the vehicle lane cone barrel identification method provided by any embodiment of the present application, and the method comprises the following steps:

[0130] Information is collected by an automatic driving perception system of a target vehicle to obtain obstacle information of a lane obstacle; wherein the obstacle information comprises obstacle coordinates, obstacle categories and obstacle corner point information;

[0131] A cone barrel group is constructed by a preset high-precision map and the obstacle information, and at least one target cone barrel group is determined;

[0132] The target cone barrel groups are fused and identified one by one to determine target cone barrel information corresponding to the target vehicle.

[0133] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples (non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or component.

[0134] Computer readable signal media can include a propagated data signal with computer readable program code embodied therein. For example, a propagated signal can be an electromagnetic signal, an optical signal, and / or any other suitable type of signal. Such a propagated signal can carry computer readable program code in the form of electrical signals, optical signals, and / or magnetic

[0135] Program code embodied on a computer readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0136] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0137] Those skilled in the art will appreciate that the various modules or steps of the present application described above can be implemented in a general purpose computer, and they can be centralized in a single computer or distributed over a network of computers, and optionally, they can be implemented in computer executable program code, which can be stored in a storage device and executed by a computer, or they can be implemented as individual integrated circuit modules, or a plurality of modules or steps can be implemented in a single integrated circuit module. Thus, the present application is not limited to any particular combination of hardware and software.

[0138] It should be understood that the various forms of flow shown in the figures can be re-ordered, added to, or deleted from, without departing from the scope of the present application. For example, the steps recited in the present application can be performed in parallel, in series, or in a different order, and the present application is not limited in this regard.

[0139] The above detailed description does not limit the scope of the application. Various modifications, combinations, sub-combinations and alternatives can be made to the detailed description. Any modification, equivalent replacement and improvement etc. made within the spirit and principle of the application shall be included in the scope of the application.

Claims

1. A method of vehicle-to-lane-cone-barrel recognition, characterized by, The method comprises the following steps: information acquisition is performed by an automatic driving perception system of a target vehicle to obtain obstacle information of a lane obstacle; wherein the obstacle information comprises obstacle coordinates, obstacle categories and obstacle corner point information; a cone barrel group is constructed based on a preset high-precision map and the obstacle information, and at least one target cone barrel group is determined; each of the target cone barrel groups is fused and recognized to determine target cone barrel information corresponding to the target vehicle.

2. The method of claim 1, wherein, The step of constructing a cone barrel group based on the preset high-precision map and the obstacle information, and determining at least one target cone barrel group comprises: a target cone barrel cluster is constructed based on the high-precision map and the obstacle information; at least one target cone barrel group is determined based on the target cone barrel cluster and the obstacle coordinates.

3. The method of claim 2, wherein, The step of constructing a target cone barrel cluster based on the high-precision map and the obstacle information comprises: in a case where the obstacle category of the lane obstacle is a cone barrel type, the high-precision map and the obstacle coordinates of the lane obstacle are merged to determine the target cone barrel cluster.

4. The method of claim 3, wherein, The step of merging the high-precision map and the obstacle coordinates of the lane obstacle to determine the target cone barrel cluster comprises: the position of each lane obstacle is identified based on the high-precision map and the obstacle coordinates to determine an obstacle lane corresponding to the lane obstacle; the distance of each lane obstacle is calculated based on the obstacle coordinates to determine an obstacle distance corresponding to each lane obstacle; the target cone barrel cluster is determined by merging the obstacle lane and the obstacle distance of the lane obstacle.

5. The method of claim 4, wherein, The step of determining at least one target cone barrel group based on the target cone barrel cluster and the obstacle coordinates comprises: the lane obstacles in the target cone barrel cluster are divided based on the obstacle coordinates according to a preset cone barrel group division rule to determine at least one target cone barrel group; wherein the target cone barrel group comprises a horizontal cone barrel group and a vertical cone barrel group.

6. The method of claim 1, wherein, The step of fusing and recognizing each of the target cone barrel groups to determine target cone barrel information corresponding to the target vehicle comprises: the obstacle corner point information of each lane obstacle in each target cone barrel group is fused to determine a target obstacle convex hull polygon corresponding to each target cone barrel group; a minimum bounding box of each target obstacle convex hull polygon is calculated to determine a target minimum bounding box corresponding to the target obstacle convex hull polygon and vertex coordinate information corresponding to the target minimum bounding box; target cone barrel information corresponding to the target vehicle is determined based on all the target minimum bounding boxes and the vertex coordinate information of each target minimum bounding box.

7. The method of claim 6, wherein, The step of determining target cone barrel information corresponding to the target vehicle based on all the target minimum bounding boxes and the vertex coordinate information of each target minimum bounding box comprises: the center point, orientation and coordinate range of each target minimum bounding box are calculated based on the vertex coordinate information of each target minimum bounding box to determine center point information, direction information and range information corresponding to each target minimum bounding box; The target cone barrel information is determined according to the total direction information, the center point information and the range information.

8. A device for identifying a vehicle to a lane cone barrel, characterized by, Comprise: The perception module is used for collecting information through the automatic driving perception system of the target vehicle to obtain obstacle information of a lane obstacle; wherein the obstacle information comprises obstacle coordinates, obstacle categories and obstacle corner point information; The information processing module is used for constructing a cone barrel group through a preset high-precision map and the obstacle information, and determining at least one target cone barrel group; The identification module is used for performing fusion identification on the target cone barrel groups one by one to determine target cone barrel information corresponding to the target vehicle.

9. An electronic device, comprising: The electronic device comprises: At least one processor; and The memory is in communication connection with the at least one processor; wherein The memory stores a computer program which can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the vehicle lane cone barrel identification method in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, and the computer instructions are used to enable the processor to execute the vehicle lane cone barrel identification method in any one of claims 1-7 when executed.

Images