A curb detection method and device, a terminal device and a storage medium

Abstract

The application relates to the technical field of environment sensing, and discloses a road edge detection method, a road edge detection device, a terminal device and a storage medium. The method comprises the following steps: when a vehicle is driving on a to-be-detected road, first road edge marking points of the to-be-detected road detected at N time points before a current time are acquired, and second road edge marking points of the to-be-detected road detected at the current time are acquired, wherein N is greater than or equal to 1; the first road edge marking points are projected into a second vehicle body coordinate system in which the second road edge marking points are located according to the motion parameters of the vehicle, so as to obtain target road edge marking points; the second vehicle body coordinate system is a coordinate system corresponding to the current time and constructed by taking a point on the vehicle as an origin; and curve fitting processing is performed on the target road edge marking points and the second road edge marking points, so as to obtain a road edge marking curve of the to-be-detected road. The method can supplement the number of road edge marking points, improve the curve fitting effect of the road edge marking points, and further improve the accuracy of road edge detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of environmental perception, and particularly relates to a road edge detection method and device, a terminal device and a storage medium. BACKGROUND

[0002] A road edge refers to a road boundary. Vehicles such as unmanned sweeping vehicles need to detect the road edge to achieve functions such as edge sweeping. At present, a conventional road edge detection method usually acquires point cloud data of a road by using a laser radar, performs rasterization on the point cloud data, identifies a road edge candidate region according to height differences between grids, finds road edge marker points from the road edge candidate region, and finally obtains road edge information by fitting the road edge marker points. However, the number of detected road edge marker points may be too small at some time, which may result in poor curve fitting effect of the road edge marker points and reduce the accuracy of road edge detection. SUMMARY

[0003] Therefore, the embodiments of the present application provide a road edge detection method and device, a terminal device and a storage medium, which can improve the accuracy of road edge detection.

[0004] A first aspect of the embodiments of the present application provides a road edge detection method, comprising:

[0005] When a vehicle is driving on a to-be-detected road, a first road edge marker point of the to-be-detected road detected at N time instants before a current time instant is acquired, and a second road edge marker point of the to-be-detected road detected at the current time instant is acquired, N≥1;

[0006] According to a motion parameter of the vehicle, the first road edge marker point is projected into a second vehicle body coordinate system in which the second road edge marker point is located, to obtain a target road edge marker point, wherein the second vehicle body coordinate system is a coordinate system corresponding to the current time instant and constructed by taking a point on the vehicle as an origin;

[0007] Curve fitting processing is performed on the target road edge marker point and the second road edge marker point to obtain a road edge marker curve of the to-be-detected road.

[0008] In the embodiment of the present application, first, the first road edge marking points detected at the previous N time points and the second road edge marking points detected at the current time point are acquired; then, according to the motion parameters of the vehicle, such as the speed, position and heading angle and the like, the first road edge marking points can be projected into the vehicle body coordinate system in which the second road edge marking points are located, and the projected road edge marking points are denoted as target road edge marking points; finally, the second road edge marking points and the target road edge marking points are combined, and curve fitting processing is performed on the combined road edge marking points to obtain the final road edge marking curve. Through such a setting, even if the number of road edge marking points detected at the current time point is small, the number of marking points can still be supplemented by the road edge marking points detected at the previous time points adjacent to the current time point, so as to improve the curve fitting effect of the road edge marking points and further improve the accuracy of road edge detection.

[0009] In an implementation manner of the embodiment of the present application, the projecting the first road edge marking points into the second vehicle body coordinate system in which the second road edge marking points are located according to the motion parameters of the vehicle to obtain the target road edge marking points can include:

[0010] detecting a first position coordinate of the vehicle in a first global coordinate system and a second position coordinate of the vehicle in a second global coordinate system; wherein the first global coordinate system is a coordinate system corresponding to the N time points and constructed with a starting point of vehicle driving as an origin, and the second global coordinate system is a coordinate system corresponding to the current time and constructed with the starting point of vehicle driving as an origin;

[0011] projecting the first road edge marking points from a first vehicle body coordinate system into the first global coordinate system to obtain third road edge marking points; wherein the first vehicle body coordinate system is a coordinate system corresponding to the N time points and constructed with a point on the vehicle as an origin;

[0012] calculating a fourth road edge marking point corresponding to the third road edge marking point in the second global coordinate system according to the first position coordinate and the second position coordinate;

[0013] projecting the fourth road edge marking point from the second global coordinate system into the second vehicle body coordinate system to obtain the target road edge marking point.

[0014] Further, the second position coordinate can be detected according to the following manner:

[0015] acquiring inertial measurement unit data and vehicle speed of the vehicle at the current time point;

[0016] calculating the second position coordinate according to the inertial measurement unit data and the vehicle speed.

[0017] Further, the inertial measurement unit data comprises acceleration and gyroscope data of the vehicle, and the second position coordinate is calculated according to the inertial measurement unit data and the vehicle speed, which can comprise:

[0018] A heading angle of the vehicle is calculated according to the acceleration and the gyroscope data.

[0019] The second position coordinate is calculated according to the heading angle and the vehicle speed.

[0020] In an implementation form of the embodiment, the value of N can be determined by the following method:

[0021] The number of marking points contained in the second road edge marking points is detected.

[0022] The value of N is determined according to the number of marking points, wherein the number of marking points and the value of N are inversely proportional.

[0023] In an implementation form of the embodiment, the second road edge marking points of the road to be measured detected at the current time can comprise:

[0024] Point cloud data of the road to be measured at the current time is obtained.

[0025] Grid processing is performed on the point cloud data.

[0026] For each grid obtained after the grid processing, a ground reference height value of the grid is calculated according to the point cloud contained in the grid, and ground points in the point cloud contained in the grid are filtered according to the ground reference height value, wherein the difference between the height of the ground points and the ground reference height value is less than a set threshold.

[0027] The second road edge marking points are detected according to the point cloud after the ground points are filtered from the point cloud contained in each grid.

[0028] In an implementation form of the embodiment, the vehicle is provided with a sweeping device, and after the road edge marking curve of the road to be measured is obtained, the method can further comprise:

[0029] The sweeping device is controlled to perform a telescopic action according to the road edge marking curve.

[0030] The second aspect of the embodiment provides a road edge detection device, comprising:

[0031] The road edge marker point acquisition module is configured to acquire first road edge marker points of the road to be detected, which are detected at N time instants before a current time instant, and acquire second road edge marker points of the road to be detected, which are detected at the current time instant, when the vehicle is driving on the road to be detected, where N≥1;

[0032] The road edge marker point projection module is configured to project the first road edge marker points into a second vehicle body coordinate system in which the second road edge marker points are located, to obtain target road edge marker points, according to the motion parameters of the vehicle, where the second vehicle body coordinate system is a coordinate system corresponding to the current time instant, and is constructed with a point on the vehicle as an origin.

[0033] The road edge marker point fitting module is configured to perform curve fitting processing on the target road edge marker points and the second road edge marker points, to obtain a road edge marker curve of the road to be detected.

[0034] The third aspect of the embodiment of the present application provides a terminal device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the road edge detection method provided in the first aspect of the embodiment of the present application when executing the computer program.

[0035] The fourth aspect of the embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the road edge detection method provided in the first aspect of the embodiment of the present application.

[0036] The fifth aspect of the embodiment of the present application provides a computer program product, which, when executed on a terminal device, causes the terminal device to perform the road edge detection method provided in the first aspect of the embodiment of the present application.

[0037] It can be understood that the beneficial effects of the second aspect to the fifth aspect described above can be referred to the related description in the first aspect described above, and will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 is a flowchart of a road edge detection method provided by the embodiment of the present application;

[0039] Figure 2 is a schematic diagram of a vehicle body coordinate system and a global coordinate system of a vehicle provided by the embodiment of the present application;

[0040] Figure 3 is a structural schematic diagram of an unmanned cleaning vehicle provided by the embodiment of the present application;

[0041] Figure 4 is a structural diagram of a road edge detection device provided by the embodiment of the present application;

[0042] Figure 5 is a schematic diagram of a terminal device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0043] In the following description, for the purpose of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail. Moreover, descriptions of well-known systems, devices, circuits, and methods are often simplified to the extent that process flow management circuits and processes are neither specifically described nor necessarily implied where such processes are well-understood and commonly used.

[0044] The embodiment of the present application provides a road edge detection method, which is suitable for environment perception in automatic driving process. For example, in the driving process of a driverless cleaning vehicle, the road edge can be accurately identified by using the road edge detection method, so that the driverless cleaning vehicle can realize the function of edge cleaning. For more specific technical implementation details of the embodiment of the present application, please refer to the method embodiment described below.

[0045] It should be understood that the execution subject of each method embodiment of the present application is various types of terminal devices or servers, for example, a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a large-screen television, etc. The specific type of the terminal device and the server is not limited in the embodiments of the present application.

[0046] Please refer to Figure 1 , which shows a road edge detection method provided by an embodiment of the present application, comprising:

[0047] 101. When a vehicle is driving on a to-be-detected road, a first road edge marker point of the to-be-detected road detected at N time instants before a current time instant is acquired, and a second road edge marker point of the to-be-detected road detected at the current time instant is acquired, N≥1;

[0048] The to-be-detected road is any type of road that needs to be detected for a road edge. When a vehicle such as an unmanned sweeper travels on the to-be-detected road, a device such as a laser radar installed on the vehicle body can collect point cloud data of the to-be-detected road, and a road edge marker point can be detected through the collected point cloud data. Since the vehicle is traveling on the to-be-detected road, the point cloud data collected at each moment is different, that is, the road edge marker point detected at each moment is also different. For example, assuming that the current moment is T5, one aspect of an embodiment of the present application obtains a road edge marker point of the to-be-detected road detected at the moment T5, denoted as a second road edge marker point; and another aspect obtains road edge marker points of the to-be-detected road detected at N moments before the moment T5, denoted as first road edge marker points. Wherein, N is an integer greater than or equal to 1, for example, if N = 1, the first road edge marker point is a road edge marker point of the to-be-detected road detected at the moment T4; if N = 2, the first road edge marker point is a road edge marker point of the to-be-detected road detected at the moment T4 and a road edge marker point of the to-be-detected road detected at the moment T3, and so on.

[0049] In an implementation manner of the embodiment of the present application, the value of N can be determined in the following manner:

[0050] (1) detecting the number of marker points contained in the second road edge marker point;

[0051] (2) determining the value of N according to the number of marker points; wherein the number of marker points and the value of N are inversely proportional.

[0052] The basic idea of the embodiment of the present application is to supplement the road edge marker point detected at the current moment with the road edge marker points detected at adjacent historical moments, so as to solve the problem of too few road edge marker points detected at the current moment. Based on the basic idea, if the number of road edge marker points detected at the current moment is relatively large, too many road edge marker points do not need to be supplemented, so only a few road edge marker points detected at historical moments need to be obtained, for example, N = 1; and if the number of road edge marker points detected at the current moment is relatively small, too many road edge marker points need to be supplemented, so more road edge marker points detected at historical moments need to be obtained, for example, N = 3.

[0053] In an implementation manner of the embodiment of the present application, the obtaining of the second road edge marker point of the to-be-detected road detected at the current moment can include:

[0054] (1) obtaining point cloud data of the to-be-detected road at the current moment;

[0055] (2) performing rasterization processing on the point cloud data;

[0056] (3) For each grid obtained after the rasterization processing, a ground reference height value of the grid is calculated according to the point cloud contained in the grid, and a ground point in the point cloud contained in the grid is filtered according to the ground reference height value, wherein the difference between the height of the ground point and the ground reference height value is less than a set threshold value;

[0057] (4) The second road edge marker point is detected according to the point cloud after the ground point is filtered from each grid.

[0058] After obtaining the point cloud data of the road to be detected, the point cloud data is subjected to rasterization processing, that is, the point cloud in the point cloud data is divided into a plurality of corresponding grids according to regions. After the grids are divided, the following operations are performed for each grid: a ground reference height value corresponding to the grid is calculated according to the point cloud contained in the grid, and a ground point in the point cloud contained in the grid is filtered according to the ground reference height value. The ground reference height value is used to represent the true ground height corresponding to a grid. The height of each point of the point cloud contained in the grid can be compared with the ground reference height value respectively, and if the difference (absolute value can be added) between the two is less than a set threshold value, the corresponding point can be determined as a ground point in the point cloud. The ground point may cause interference in the road edge detection process, so the ground point needs to be filtered out. Finally, the detection of the road edge marker point is completed according to the point cloud after the ground point is filtered out, which can exclude the interference of the ground point, thereby improving the accuracy of the detection of the road edge marker point. When detecting the road edge marker point according to the point cloud, the road edge candidate area can be found by the height difference between the grids first, then the road edge candidate points can be found in the road edge candidate area by the height difference of the point cloud, and finally the road edge candidate points whose difference between the height and the ground reference height value of the corresponding grid is greater than a set threshold value and which are not in the detection frame of the pedestrian or vehicle (which can be obtained by performing target detection on the image of the road to be detected) are determined as the detected road edge marker point. It should be understood that the road edge marker point at each time can be detected by the above method.

[0059] For example, for grid 1, the ground reference height value H1 corresponding to the grid is first calculated based on the points contained in grid 1. Then, points in the point cloud of grid 1 with heights close to H1 are treated as ground points and filtered out. For grid 2, the ground reference height value H2 corresponding to the grid is first calculated based on the points contained in grid 2. Then, points in the point cloud of grid 2 with heights close to H2 are treated as ground points and filtered out. It can be seen that since different grids contain different point clouds, the ground reference height values ​​corresponding to different grids may also be different. In other words, the ground reference height value of a certain grid is an adapted value calculated based on the features of the point cloud contained in that grid, which can accurately represent the true ground height of the area corresponding to that grid. Therefore, this method can accurately identify and filter out ground points in the point cloud contained in each grid, thereby improving the accuracy of subsequent curb marker detection.

[0060] On the other hand, after determining the ground reference height value corresponding to each grid, obstacle points in the point cloud contained in each grid can be detected using the ground reference height value. Specifically, points in the point cloud whose height is greater than the ground reference height value by a certain value (e.g., 20cm or 10cm) can be identified as obstacles on the road surface. When outputting the curb detection information, the obstacle point information can also be output to enable the vehicle to perform obstacle avoidance planning and other operations.

[0061] 102. Based on the vehicle's motion parameters, project the first curb marker point onto the second vehicle coordinate system where the second curb marker point is located to obtain the target curb marker point;

[0062] The second road edge marker point is in a second vehicle body coordinate system, which is a coordinate system corresponding to the current time and constructed with a point on the vehicle as an origin. The first road edge marker point is in a first vehicle body coordinate system, which is a coordinate system corresponding to the N time points and constructed with a point on the vehicle as an origin. It should be understood that the first road edge marker point includes road edge marker points detected at the N time points, and the first vehicle body coordinate system includes vehicle body coordinate systems at the N time points. For example, if N = 2 and the current time is T5, the N time points are T3 and T4. Since the vehicle is in a moving state, each time point has a corresponding vehicle body coordinate system, that is, T3 has a corresponding vehicle body coordinate system Lp3, T4 has a corresponding vehicle body coordinate system Lp4, and T5 has a corresponding vehicle body coordinate system Lp5. The road edge marker point detected at T3 is in the vehicle body coordinate system Lp3, the road edge marker point detected at T4 is in the vehicle body coordinate system Lp4, and the road edge marker point detected at T5 is in the vehicle body coordinate system Lp5. According to the motion parameters of the vehicle, such as speed, position and heading angle, the relative position change of the first road edge marker point projected into the second vehicle body coordinate system where the second road edge marker point is located can be calculated, so that each road edge marker point (represented by a target road edge marker point) obtained by projecting into the second vehicle body coordinate system is closer to the real road edge point in the second vehicle body coordinate system.

[0063] In an implementation manner of the embodiment of the present application, the projecting the first road edge marker point into the second vehicle body coordinate system where the second road edge marker point is located according to the motion parameters of the vehicle to obtain a target road edge marker point can include:

[0064] (1) detecting a first position coordinate of the vehicle in a first global coordinate system and a second position coordinate of the vehicle in a second global coordinate system; wherein the first global coordinate system is a coordinate system corresponding to the N time points and constructed with a starting point of the vehicle as an origin, and the second global coordinate system is a coordinate system corresponding to the current time and constructed with the starting point of the vehicle as an origin;

[0065] (2) projecting the first road edge marker point from the first vehicle body coordinate system into the first global coordinate system to obtain a third road edge marker point; wherein the first vehicle body coordinate system is a coordinate system corresponding to the N time points and constructed with a point on the vehicle as an origin;

[0066] (3) according to the first position coordinate and the second position coordinate, the third road following mark point corresponding to the fourth road following mark point in the second global coordinate system is calculated;

[0067] (4) the fourth road following mark point is projected from the second global coordinate system to the second vehicle body coordinate system to obtain the target road following mark point.

[0068] The global coordinate system can be constructed with the starting point of the vehicle as the origin. Among them, the first global coordinate system corresponds to the N moments, and the second global coordinate system corresponds to the current moment. First, the position coordinates of the vehicle in the first global coordinate system (represented by the first position coordinate, which can also be understood as the position of the vehicle at the current moment) and in the second global coordinate system (represented by the second position coordinate, which can also be understood as the position of the vehicle at the N moments) are detected. A position coordinate can be calculated according to the vehicle parameters at the corresponding moment. For example, for the current moment, the second position coordinate can be detected according to the following method:

[0069] (1) obtaining the inertial measurement unit data and the vehicle speed of the vehicle at the current moment;

[0070] (2) calculating the second position coordinate according to the inertial measurement unit data and the vehicle speed.

[0071] The inertial measurement unit data, namely the IMU data, can include vehicle acceleration and gyroscope data, etc. According to the IMU data at the current moment and the speed of the vehicle, the driving trajectory of the vehicle can be predicted, and then the position of the vehicle at the current moment can be calculated, i.e. the second position coordinate is obtained. Similarly, the positions of the vehicle at other moments can also be calculated by the same method. Specifically, the inertial measurement unit data includes the acceleration and gyroscope data of the vehicle, and the second position coordinate is calculated according to the inertial measurement unit data and the vehicle speed, which can include:

[0072] (1) calculating the heading angle of the vehicle according to the acceleration and the gyroscope data;

[0073] (2) calculating the second position coordinate according to the heading angle and the vehicle speed.

[0074] The acceleration and gyroscope data of the vehicle can be obtained from the IMU data. If the gyroscope is installed horizontally, the data of the Z-axis direction of the gyroscope can be time-integrated to obtain the heading angle of the vehicle at the current time. In addition, the attitude angle of the vehicle, which includes the heading angle of the vehicle, can also be obtained by means of complementary filtering or Kalman filtering of the acceleration and gyroscope data. Then, according to the vehicle speed and the heading angle, the position coordinates of the vehicle at the current time in the second global coordinate system can be calculated.

[0075] Then, the first road marking point is projected from the first vehicle body coordinate system to the first global coordinate system, and the point formed in the first global coordinate system is represented by a third road marking point. According to the first position coordinates, the second position coordinates and other vehicle parameters, the road position change of the vehicle when it is converted from the first global coordinate system to the second global coordinate system can be calculated, and the corresponding point of the third road marking point in the second global coordinate system (represented by a fourth road marking point) can be predicted according to the road position change. Finally, the fourth road marking point is projected from the second global coordinate system to the second vehicle body coordinate system, and the point formed in the second vehicle body coordinate system is the target road marking point described above. In this process, the specific method of projecting the marking point from the vehicle body coordinate system to the global coordinate system and projecting the marking point from the global coordinate system to the vehicle body coordinate system can refer to the prior art, which will not be described here.

[0076] The schematic diagram of the vehicle body coordinate system and the global coordinate system is shown in Figure 2 , in which Figure 2 each rectangular block represents the position of the vehicle at each different time, and the dashed line represents the trajectory of the vehicle; the coordinate system X-Y represents the global coordinate system, and the origin is the starting point of the vehicle; the coordinate system x-y represents the vehicle body coordinate system, and the origin is a point on the vehicle. Figure 2 It can be seen that there is a corresponding vehicle body coordinate system at each different time.

[0077] For example, let N=2, assuming the current time is T5, the N time points are T3 and T4; T3 corresponds to the vehicle body coordinate system Lp3, T4 corresponds to the vehicle body coordinate system Lp4, and T5 corresponds to the vehicle body coordinate system Lp5; T3 corresponds to the global coordinate system Gp3, T4 corresponds to the global coordinate system Gp4, and T5 corresponds to the global coordinate system Gp5. First, according to the motion parameters (such as IMU data and vehicle speed) of the vehicle at T3, the position of the vehicle at T3 can be calculated, and the position coordinates of the vehicle in Lp3 can be obtained; according to the motion parameters of the vehicle at T4, the position of the vehicle at T4 can be calculated, and the position coordinates of the vehicle in Lp4 can be obtained; according to the motion parameters of the vehicle at T5, the position of the vehicle at T5 can be calculated, and the position coordinates of the vehicle in Lp5 can be obtained. Then, the road edge marker point detected at T3 is projected from Lp3 to Gp3, and according to the motion parameters and position information of the vehicle at T3 and T5, the predicted position of the road edge marker point projected from Gp3 to Gp5 can be calculated, and finally the road edge marker point formed by the predicted position is projected from Gp5 to Lp5, that is, finally projected into the vehicle body coordinate system of the road edge marker point detected at T5. Similarly, for the road edge marker point detected at T4, it is also projected through the projection path of Lp4-Gp4-Gp5-Lp5, and finally projected into the vehicle body coordinate system of the road edge marker point detected at T5. After this operation, the road edge marker points detected at T3 and T4 (to adapt to the change of road edge position caused by time transformation, the position of the road edge marker point has been adjusted in the steps described in the foregoing) are added to the road edge marker points detected at T5, thereby increasing the number of road edge marker points at T5, so as to facilitate subsequent curve fitting processing of the road edge marker points. In addition, generally, the transmission frequency of vehicle motion parameter data is higher than the sampling frequency of the laser radar, and in the data synchronization process at each time point, the vehicle motion parameter data transmitted at the time point closest to the sampling time can be taken for each frame of radar data. For example, for the radar data of T5 (the road edge marker point of T5 is detected through the radar data), a time point closest to T5 can be found from the transmission time points of a plurality of vehicle motion parameter data near T5, and the vehicle motion parameter transmitted at the time point is taken as the vehicle motion parameter corresponding to T5.

[0078] 103. Perform curve fitting processing on the target road edge marker point and the second road edge marker point to obtain a road edge marker curve of the road to be measured.

[0079] After obtaining the target curb marker points, the target curb marker points and the second curb marker points can be merged. Based on the merged curb marker points, curve fitting is performed to obtain the curb marker curve of the road under test. When performing curve fitting, methods such as least squares fitting or RANSAC curve fitting can be used.

[0080] Additionally, the point cloud height distribution near each curb marker can be statistically analyzed. Based on the characteristics of the point cloud height distribution, the type of curb can be determined, such as a standard curb, guardrail, or fence. When outputting curb information, the curb marker curve, the corresponding curb type, and obstacle point information can be output together. For example, the point cloud height distribution characteristics of different types of curbs are as follows: the point cloud height of a standard curb is concentrated between 10-30cm; the point cloud height of a guardrail is greater than 30cm and is concentrated at a certain height; the point cloud height of a fence is distributed between 10-150cm, and point clouds exist in each height range, with a relatively uniform point cloud distribution.

[0081] In one implementation of this application, the vehicle is equipped with a sweeping brush device, and after obtaining the curb marking curve of the road to be tested, it may further include:

[0082] The sweeping brush device is controlled to perform a telescopic movement based on the curb marking curve.

[0083] For vehicles such as unmanned sweepers, they are generally equipped with lidar and sweeping brushes, such as Figure 3 The diagram shown is a structural schematic of an unmanned cleaning vehicle provided in an embodiment of this application. Figure 3 In the unmanned sweeper, a lidar 301 is installed on the roof of the vehicle. The lidar 301 is tilted at a certain angle to detect point cloud data in front of the road. The chassis of the unmanned sweeper is equipped with a retractable sweeping brush 302 for cleaning the road surface. Figure 3 The left side is a top view, and the right side is a side view. Based on the detected curb markings and other curb information, as well as obstacle point information, the vehicle's sweeping equipment can be flexibly controlled to perform extension and retraction movements to achieve functions such as edge cleaning or obstacle avoidance.

[0084] In the embodiments of the present application, first, the first road edge marking points detected at the previous N time instants and the second road edge marking points detected at the current time instant are acquired; then, the first road edge marking points are projected into the second vehicle body coordinate system in which the second road edge marking points are located according to the motion parameters of the vehicle such as the speed, position and heading angle and the like, and the projected road edge marking points are denoted as target road edge marking points; finally, the second road edge marking points and the target road edge marking points are combined, and curve fitting processing is performed on the combined road edge marking points to obtain the final road edge marking curve. Through such a setting, even if the number of road edge marking points detected at the current time instant is small, the number of marking points can still be supplemented by the road edge marking points detected at the previous time instants adjacent to the current time instant, so as to improve the curve fitting effect of the road edge marking points and further improve the accuracy of road edge detection.

[0085] It should be understood that the size of the serial number of each step in the above-mentioned various embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0086] The above mainly describes a road edge detection method, and a road edge detection device will be described below.

[0087] Please refer to Figure 4 An embodiment of a road edge detection device in the embodiments of the present application includes:

[0088] The road edge marking point acquisition module 401 is configured to acquire the first road edge marking points of the to-be-detected road detected at the previous N time instants before the current time instant and acquire the second road edge marking points of the to-be-detected road detected at the current time instant when the vehicle is driving on the to-be-detected road, and N≥1;

[0089] The road edge marking point projection module 402 is configured to project the first road edge marking points into the second vehicle body coordinate system in which the second road edge marking points are located according to the motion parameters of the vehicle, to obtain target road edge marking points; wherein the second vehicle body coordinate system is a coordinate system corresponding to the current time instant constructed with a point on the vehicle as the origin;

[0090] The road edge marking point fitting module 403 is configured to perform curve fitting processing on the target road edge marking points and the second road edge marking points to obtain the road edge marking curve of the to-be-detected road.

[0091] In an implementation manner of the embodiments of the present application, the road edge marking point projection module can include:

[0092] A position coordinate detection unit is configured to detect a first position coordinate of the vehicle in a first global coordinate system and a second position coordinate of the vehicle in a second global coordinate system, wherein the first global coordinate system is a coordinate system corresponding to the N time points and constructed with a starting point of the vehicle as an origin, and the second global coordinate system is a coordinate system corresponding to the current time and constructed with the starting point of the vehicle as an origin;

[0093] A first projection unit is configured to project the first road mark point from a first vehicle body coordinate system into the first global coordinate system to obtain a third road mark point, wherein the first vehicle body coordinate system is a coordinate system corresponding to the N time points and constructed with a point on the vehicle as an origin;

[0094] A mark point calculation unit is configured to calculate a fourth road mark point corresponding to the third road mark point in the second global coordinate system according to the first position coordinate and the second position coordinate;

[0095] A second projection unit is configured to project the fourth road mark point from the second global coordinate system into the second vehicle body coordinate system to obtain the target road mark point.

[0096] Further, the road mark point projection module can further include:

[0097] A vehicle parameter acquisition module is configured to acquire inertial measurement unit data and a vehicle speed of the vehicle at the current time;

[0098] A position coordinate calculation unit is configured to calculate the second position coordinate according to the inertial measurement unit data and the vehicle speed.

[0099] Further, the inertial measurement unit data includes acceleration and gyroscope data of the vehicle, and the position coordinate calculation unit can include:

[0100] A heading angle calculation sub-unit is configured to calculate a heading angle of the vehicle according to the acceleration and the gyroscope data;

[0101] A position coordinate calculation sub-unit is configured to calculate the second position coordinate according to the heading angle and the vehicle speed.

[0102] In an implementation manner of the embodiment of the present application, the road detection device can further include:

[0103] A mark point number detection module is configured to detect a number of mark points included in the second road mark point;

[0104] A numerical value determination module is configured to determine the numerical value of the N according to the number of the marking points; wherein the number of the marking points and the numerical value of the N are inversely proportional.

[0105] In an implementation form of the embodiment of the application, the road edge marking point acquisition module can comprise:

[0106] A point cloud data acquisition unit is configured to acquire point cloud data of the to-be-detected road at the current time point;

[0107] A gridding processing unit is configured to perform gridding processing on the point cloud data;

[0108] A ground reference height calculation unit is configured to, for each grid obtained after the gridding processing, calculate a ground reference height value of the grid according to the point cloud contained in the grid, and filter out ground points in the point cloud contained in the grid according to the ground reference height value, wherein a difference between a height of the ground points and the ground reference height value is less than a set threshold value;

[0109] A road edge marking point detection unit is configured to detect the second road edge marking point according to the point cloud after the ground points are filtered out from each of the grids.

[0110] In an implementation form of the embodiment of the application, the vehicle is provided with a sweeping device, and the road edge detection apparatus can further comprise:

[0111] A sweeping device control module is configured to control the sweeping device to perform a telescopic action according to the road edge marking curve.

[0112] The embodiment of the application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement any one of the road edge detection methods shown in Figure 1 .

[0113] The embodiment of the application further provides a computer program product, which, when running on a terminal device, causes the terminal device to perform any one of the road edge detection methods shown in Figure 1 .

[0114] Figure 5 is a schematic diagram of a terminal device provided by an embodiment of the application. As shown in Figure 5 , the terminal device 5 of this embodiment comprises a processor 50, a memory 51, and a computer program 52 stored in the memory 51 and executable on the processor 50. The processor 50 implements the steps in the embodiments of the above-mentioned action detection methods when executing the computer program 52, for example Figure 1The steps 101 to 103 are shown. Alternatively, the processor 50 implements the functions of the modules / units in the above-mentioned apparatus embodiments when executing the computer program 52, for example Figure 4 The functions of the modules 401 to 403 are shown.

[0115] The computer program 52 can be segmented into one or more modules / units stored in the memory 51 and executed by the processor 50 to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program 52 in the terminal device 5.

[0116] The processor 50 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0117] The memory 51 can be an internal storage unit of the terminal device 5, such as a hard disk or a memory of the terminal device 5. The memory 51 can also be an external storage device of the terminal device 5, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 51 can include both the internal storage unit and the external storage device of the terminal device 5. The memory 51 is used to store the computer program and other programs and data required by the terminal device. The memory 51 can also be used to temporarily store data that has been output or will be output.

[0118] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is taken as an example, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit or module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit or module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0119] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, apparatus and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0120] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0121] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0122] In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0123] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0124] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0125] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the contents included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0126] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A curb detection method characterized by, The method comprises the following steps: obtaining first road edge marker points of the road to be detected detected at N time points before the current time and second road edge marker points of the road to be detected detected at the current time when the vehicle is driving on the road to be detected, N≥1; projecting the first road edge marker points into a second vehicle body coordinate system in which the second road edge marker points are located according to the motion parameters of the vehicle to obtain target road edge marker points, wherein the second vehicle body coordinate system is a coordinate system corresponding to the current time and constructed with a point on the vehicle as the origin; performing curve fitting processing on the target road edge marker points and the second road edge marker points to obtain a road edge marker curve of the road to be detected; the step of projecting the first road edge marker points into the second vehicle body coordinate system in which the second road edge marker points are located according to the motion parameters of the vehicle to obtain target road edge marker points comprises the following steps: detecting a first position coordinate of the vehicle in a first global coordinate system and a second position coordinate of the vehicle in a second global coordinate system, wherein the first global coordinate system is a coordinate system corresponding to the N time points and constructed with a starting point of the vehicle as the origin, and the second global coordinate system is a coordinate system corresponding to the current time and constructed with the starting point of the vehicle as the origin; projecting the first road edge marker points from a first vehicle body coordinate system into the first global coordinate system to obtain third road edge marker points, wherein the first vehicle body coordinate system is a coordinate system corresponding to the N time points and constructed with a point on the vehicle as the origin; calculating a fourth road edge marker point corresponding to the third road edge marker point in the second global coordinate system according to the first position coordinate and the second position coordinate; projecting the fourth road edge marker point from the second global coordinate system into the second vehicle body coordinate system to obtain the target road edge marker point.

2. The method of claim 1, wherein, the second position coordinate is detected according to the following method: obtaining inertial measurement unit data and vehicle speed of the vehicle at the current time; calculating the second position coordinate according to the inertial measurement unit data and the vehicle speed.

3. The method of claim 2, wherein, The inertial measurement unit data includes acceleration and gyroscope data of the vehicle, and the second position coordinate is calculated according to the inertial measurement unit data and the vehicle speed, which comprises the following steps: calculating the heading angle of the vehicle according to the acceleration and the gyroscope data; calculating the second position coordinate according to the heading angle and the vehicle speed.

4. The method of claim 1, wherein, The value of N is determined by the following method: detecting the number of marker points contained in the second road edge marker points; determining the value of N according to the number of marker points, wherein the number of marker points and the value of N are inversely proportional.

5. The method of claim 1, wherein, the step of obtaining the second road edge marker points of the road to be detected detected at the current time comprises the following steps: obtaining point cloud data of the road to be detected at the current time; performing rasterization processing on the point cloud data; For each grid obtained after the rasterization processing, a ground reference height value of the grid is calculated according to the point cloud contained in the grid, and ground points in the point cloud contained in the grid are filtered according to the ground reference height value, a difference between a height of the ground points and the ground reference height value being less than a set threshold value; According to the point cloud after the ground points are filtered from each of the grids, a second road edge marker point is detected.

6. The method of any one of claims 1 to 5, wherein, The vehicle is provided with a sweeping device, and after the road edge marker curve of the to-be-detected road is obtained, the method further comprises: According to the road edge marker curve, the sweeping device is controlled to perform a telescopic action.

7. A curb detection device characterized by comprising: Comprise: A road edge marker point acquisition module is configured to acquire first road edge marker points of the to-be-detected road detected at N time instants before a current time instant and acquire a second road edge marker point of the to-be-detected road detected at the current time instant when the vehicle is driving on the to-be-detected road, N≥1; A road edge marker point projection module is configured to project the first road edge marker points into a second vehicle body coordinate system in which the second road edge marker point is located according to motion parameters of the vehicle, to obtain target road edge marker points; wherein the second vehicle body coordinate system is a coordinate system corresponding to the current time instant and constructed with a point on the vehicle as an origin; A road edge marker point fitting module is configured to perform curve fitting processing on the target road edge marker points and the second road edge marker point, to obtain a road edge marker curve of the to-be-detected road; The road edge marker point projection module comprises: A position coordinate detection unit is configured to detect a first position coordinate of the vehicle in a first global coordinate system and a second position coordinate of the vehicle in a second global coordinate system; wherein the first global coordinate system is a coordinate system corresponding to the N time instants and constructed with a starting point of the vehicle as an origin, and the second global coordinate system is a coordinate system corresponding to the current time instant and constructed with the starting point of the vehicle as an origin; A first projection unit is configured to project the first road edge marker points from a first vehicle body coordinate system into the first global coordinate system, to obtain third road edge marker points; wherein the first vehicle body coordinate system is a coordinate system corresponding to the N time instants and constructed with a point on the vehicle as an origin; A marker point calculation unit is configured to calculate fourth road edge marker points corresponding to the third road edge marker points in the second global coordinate system according to the first position coordinate and the second position coordinate; A second projection unit is configured to project the fourth road edge marker points from the second global coordinate system into the second vehicle body coordinate system, to obtain the target road edge marker points.

8. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the road edge detection method in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. The computer program is executed by the processor to implement the road edge detection method in any one of claims 1 to 6.

Images