Method, device and equipment for detecting lane edge line change and storage medium

Abstract

The application provides a lane edge line change detection method, device, equipment and storage medium. The method comprises the following steps: acquiring a lane edge line corresponding to a current position of a vehicle in a high-precision map and point clouds of a road area where the lane edge line is located; determining a first height value and a first intensity value of a point cloud of interest, the point cloud of interest being point clouds located inside a surface buffer area, the surface buffer area being a surface area constructed according to the lane edge line; determining a second height value and a second intensity value of a non-point cloud of interest, the non-point cloud of interest being point clouds located outside the surface buffer area; if a difference between the first height value and the second height value is less than a preset height difference value, and a difference between the first intensity value and the second intensity value is less than a preset intensity difference value, sending a detection result of a current time to a server, the detection result comprising a position of the vehicle and information that the lane edge line at the position of the vehicle has changed. The method improves the map updating efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the automatic driving technology, and in particular to a lane edge line change detection method and device, equipment and storage medium. BACKGROUND

[0002] The high-precision map is mainly used for path planning of automatic driving, and the accuracy of the high-precision map affects the control of the automatic driving vehicle. When the road and lane boundary change with construction, isolation fence, or encounter the tidal lane, it is necessary to detect such changes in time and update the high-precision map to guide the safe driving of the vehicle.

[0003] At present, the lane edge line change discovery technology mainly relies on the operation personnel or the automatic driving safety officer to find the signs of the vehicle driving to the lane boundary during driving or monitoring the vehicle, or to find the changes according to the comparison between the monitoring map and the actual road, and then record the position of the abnormal driving and manually check the abnormal reason to the position of the abnormal driving, and then report to the background, and the map operator adjusts the high-precision map according to the reported information.

[0004] The above process takes a long time, which causes the update of the high-precision map to be not timely, and thus the update efficiency of the high-precision map is low, thereby affecting the safety of the vehicle driving. SUMMARY

[0005] The present application provides a lane edge line change detection method, device, equipment and storage medium to solve the problem of not timely updating the high-precision map, which makes the update efficiency of the high-precision map low, thereby affecting the safety of the vehicle driving.

[0006] In a first aspect, the present application provides a lane edge line change detection method, comprising: acquiring a lane edge line corresponding to a current position of a vehicle in a high-precision map; acquiring a point cloud of a road area where the lane edge line is located; determining a first height value and a first intensity value of a point cloud of interest, the point cloud of interest being a point cloud located inside a surface buffer area, the surface buffer area being a surface area constructed according to the lane edge line; determining a second height value and a second intensity value of a non-point cloud of interest, the non-point cloud of interest being a point cloud located outside the surface buffer area; if the difference between the first height value and the second height value is less than a preset height difference value, and the difference between the first intensity value and the second intensity value is less than a preset intensity difference value, sending a detection result of the current time to a server, the detection result including the position of the vehicle and information that the lane edge line at the position of the vehicle has changed.

[0007] In some possible implementations, the method further comprises: performing geometric intersection on the surface buffer area and the point cloud to obtain the point cloud of interest and the non-point cloud of interest.

[0008] In some possible implementation manners, the determining the height value of the point cloud of the point of interest obtains a first height value, and the determining the intensity value of the point cloud of the point of interest obtains a first intensity value, including: determining an average value of the height values of all points in the point cloud of the point of interest to obtain the first height value; and determining an average value of the intensity values of all points in the point cloud of the point of interest to obtain the first intensity value.

[0009] In some possible implementation manners, the determining the height value of the point cloud of the point of interest obtains a first height value, and the determining the intensity value of the point cloud of the point of interest obtains a first intensity value, including: determining an average value of the height values of all points in the point cloud of the point of interest to obtain the first height value; and determining an average value of the intensity values of all points in the point cloud of the point of interest to obtain the first intensity value.

[0010] In some possible implementation manners, the lane edge line includes a first lane line and a second lane line, and the first lane line and the second lane line are both lane lines based on a map coordinate system, and the method further includes: performing coordinate system conversion on the first lane line and the second lane line according to a conversion relationship between the map coordinate system and a vehicle coordinate system, to obtain a first target lane line based on the vehicle coordinate system and a second target lane line based on the vehicle coordinate system; performing processing on the first target lane line and the second target lane line to obtain a first lane marking and a second lane marking, and a width between the first lane marking and the second lane marking is a preset width; and performing face buffer zone construction according to the first lane marking and the second lane marking to obtain the face buffer zone.

[0011] In some possible implementation manners, the point cloud is a point cloud based on a vehicle coordinate system, and the method further includes: acquiring a point cloud collected by a laser radar; and performing coordinate system conversion on the point cloud collected by the laser radar according to a conversion relationship between a laser radar coordinate system and the vehicle coordinate system, to obtain the point cloud.

[0012] In some possible implementation manners, the acquiring the lane edge line corresponding to the current position of the vehicle in the high-precision map includes: acquiring the current position of the vehicle; and extracting, from the high-precision map, a lane edge line of a lane in which the current position of the vehicle is located, according to the current position of the vehicle.

[0013] In some possible implementation manners, the method includes: receiving an updated high-precision map, the updated high-precision map being a map obtained by updating a high-precision map according to a current detection result by the server, the detection result including information that a position of the vehicle and a lane edge line at the position of the vehicle have changed; and controlling the vehicle according to the updated high-precision map.

[0014] In a second aspect, the present application provides a lane edge line change detection device, comprising: an acquisition module configured to acquire a lane edge line corresponding to a current position of a vehicle in a high-precision map; the acquisition module is further configured to acquire point clouds of a road region where the lane edge line is located; a determination module configured to determine a height value of a point cloud of interest to obtain a first height value, and determine an intensity value of the point cloud of interest to obtain a first intensity value, the point cloud of interest being a point cloud located inside a surface buffer region, the surface buffer region being a surface region constructed according to the lane edge line; the determination module is further configured to determine a height value of a non-point cloud of interest to obtain a second height value, and determine an intensity value of the non-point cloud of interest to obtain a second intensity value, the non-point cloud of interest being a point cloud located outside the surface buffer region; and a sending module configured to send a current detection result to a server if a difference between the first height value and the second height value is less than a preset height difference value, and a difference between the first intensity value and the second intensity value is less than a preset intensity difference value, the detection result including a position of the vehicle and information that a lane edge line at the position of the vehicle has changed.

[0015] In a third aspect, the present application provides a control device of a vehicle, comprising: a memory, a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to implement the method of the first aspect.

[0016] In a fourth aspect, the present application provides a vehicle, comprising: the control device of the vehicle of the third aspect; an inertial navigation system configured to collect a position of the vehicle; and a laser radar configured to collect point clouds of an environment around the vehicle.

[0017] In a fifth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium storing computer-executable instructions, the computer-executable instructions being executed by a processor to implement the method of the first aspect.

[0018] In a sixth aspect, the present application provides a computer program product, comprising a computer program, the computer program being executed by a processor to implement the method of the first aspect.

[0019] The application provides a lane edge line change detection method, device, equipment and storage medium, which comprises the following steps: acquiring a lane edge line corresponding to a current position of a vehicle and a point cloud of a road region where the lane edge line is located in a high-precision map; constructing a face buffer zone according to the lane edge line, performing geometric intersection on the face buffer zone and the point cloud, so as to determine a point cloud of interest and a non-point cloud of interest; and in the case that a difference between a first height value and a second height value is less than a preset height difference value, and a difference between a first intensity value and a second intensity value is less than a preset intensity difference value, sending a detection result of the current time to a server, so that the server updates the high-precision map according to the detection result, and the detection result comprises the position of the vehicle and information that the lane edge line at the position of the vehicle changes. Since the data collected by the vehicle sensor in real time is used for calculation, whether the lane edge line changes is determined, therefore, the problem that the update delay of the high-precision map caused by manual change discovery is avoided, the high-precision map is updated in time, and the effect of improving the map update efficiency is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0020] The accompanying drawings, which are incorporated herein and form part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the application.

[0021] Figure 1 An application scenario diagram provided by the embodiment of the application;

[0022] Figure 2 A flowchart of the lane edge line change detection method provided by the embodiment of the application;

[0023] Figure 3 A control logic diagram of the vehicle provided by the embodiment of the application;

[0024] Figure 4 An example diagram of the lane edge line change detection method provided by the embodiment of the application;

[0025] Figure 5 A schematic diagram of lane line widening provided by the embodiment of the application;

[0026] Figure 6 A schematic diagram of constructing a face buffer zone provided by the embodiment of the application;

[0027] Figure 7 A schematic diagram of a geometric intersection result provided by the embodiment of the application;

[0028] Figure 8 A schematic diagram of the lane edge line change detection device provided by the embodiment of the application;

[0029] Figure 9 A structural schematic diagram of the electronic device provided by the embodiment of the application.

[0030] The specific embodiments of the present application have been shown and described in the above drawings and text. These drawings and text are not meant to limit the scope of the present application in any way but are merely meant to illustrate the present application to one of ordinary skill in the art by reference to certain embodiments. DETAILED DESCRIPTION

[0031] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The same reference numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments are not meant to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0032] Figure 1 An application scenario is provided for the embodiments of the present application. As shown in Figure 1 The application scenario includes a vehicle 1 and a server 2. The vehicle 1 is in communication connection with the server 2.

[0033] The vehicle 1 can be an autonomous vehicle or a vehicle equipped with an Advanced Driving Assistance System (ADAS).

[0034] The server 2 can be a single server or a server cluster including multiple servers. The server 2 stores a high-precision map. The server 2 can distribute the high-precision map to the vehicle, so that the vehicle can plan a path according to the high-precision map.

[0035] The vehicle 1 obtains its current position in real time during driving and plans a path according to the current position and the high-precision map. In daily life, the lane edge line can change due to road construction, tidal lanes, isolation barriers, etc. If such changes can be detected in time and the high-precision map can be updated, the vehicle can be controlled to drive safely.

[0036] Currently, the above changes are mainly found by manual work. The position where the change occurs is determined manually, and the position where the change occurs is surveyed or confirmed by historical videos recorded by the vehicle end. Then, the specific position and lane information where the change occurs are confirmed and reported to the server. The server updates the high-precision map according to the reported information.

[0037] However, the process from discovering the change to reporting in the above process is completed by manual, which is time-consuming, leading to that the update of the high-precision map is not timely, and further affecting the safe driving of the vehicle. In addition, the driving distance of the autonomous vehicle is long, and if changes occur in multiple places, it is necessary to go to different places for surveying, which is low in updating efficiency and difficult to ensure the safety of the vehicle driving.

[0038] However, the process from discovering the change to reporting in the above process is completed by manual, which is time-consuming, leading to that the update of the high-precision map is not timely, and further affecting the safe driving of the vehicle. In addition, the driving distance of the autonomous vehicle is long, and if changes occur in multiple places, it is necessary to go to different places for surveying, which is low in updating efficiency and difficult to ensure the safety of the vehicle driving.

[0039] In view of the above technical problems, the inventors of the present application propose the following technical concept: in the process of driving the vehicle, the map data of the current position of the vehicle is acquired in real time, the map data is used to represent the lane edge line of the lane where the current position of the vehicle is located; and the point cloud of the lane where the current position of the vehicle is located collected by the laser radar is acquired; for the point cloud, each scanning point has a height value and an intensity value, the height value and the intensity value of different objects are different, according to this characteristic, the height value and the intensity value of the point cloud inside the lane edge line and the point cloud outside the lane edge line are compared, so as to determine whether the lane edge line of the lane where the current position is located changes, and when the change occurs, the current position of the vehicle and the change information are uploaded to the server, and the server updates the high-precision map in time according to the current position of the vehicle and the change information, so as to guide the driving of other vehicles and avoid safety accidents of other vehicles.

[0040] The technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present application will be described below with reference to the drawings.

[0041] Figure 2 The flowchart of the lane edge line change detection method provided for the embodiments of the present application. Figure 3 The control logic diagram of the vehicle provided for the embodiments of the present application. Figure 4 The example diagram of the lane edge line change detection method provided for the embodiments of the present application. As shown in Figure 2 and Figure 4 The lane edge line change detection method comprises the following steps:

[0042] S201, acquiring the lane edge line corresponding to the current position of the vehicle in the high-precision map.

[0043] In this embodiment, the lane edge line is a line used to indicate the edge of the motor lane or to divide the boundary between the motor vehicle and the non-motor vehicle lane, including two kinds of solid edge line and dashed edge line, and the color is white.

[0044] S202, acquire the point cloud of the road area where the lane edge line is located.

[0045] As shown in Figure 3 The vehicle of the embodiment includes a central control system 31, and further includes a vehicle end positioning module 32, a vehicle end sensor driving module 33, and a whole vehicle calibration system 34, etc.

[0046] The vehicle end positioning module 32 can be an inertial navigation (IN) system or a vehicle end algorithm self-positioning module, and is configured to acquire the position of the vehicle. The lane edge line corresponding to the current position of the vehicle in the high-precision map is acquired by: acquiring the current position of the vehicle; and extracting the lane edge line of the lane where the current position of the vehicle is located from the high-precision map according to the current position of the vehicle. The conversion relationship between the map coordinate system and the vehicle coordinate system is stored in the vehicle end positioning module.

[0047] The vehicle end sensor driving module 33 can be a laser radar, and is configured to acquire the point cloud of the surrounding environment of the vehicle during driving, the surrounding environment including the road area where the lane edge line is located and other ground object information around the vehicle. Specifically, the road area including the lane edge line and the ground object information within a preset distance from the outside of the lane edge line.

[0048] The conversion relationship between the laser radar coordinate system and the vehicle coordinate system is stored in the whole vehicle calibration system 34.

[0049] The execution subject of the embodiment can be the central control system of the vehicle. In an optional implementation, the central control system 31 of the vehicle can acquire the current position of the vehicle and the point cloud of the road area where the lane edge line is located from the vehicle end positioning module 32 and the vehicle end sensor driving module 33, respectively. Further, the central control system of the vehicle can further acquire the lane edge line of the lane where the vehicle is currently located from the high-precision map according to the current position of the vehicle.

[0050] It should be noted that the execution order of steps S201 and S202 is not limited, and step S201 can be executed first, then step S202 can be executed, or step S202 can be executed first, then step S201 can be executed, or steps S201 and S202 can be executed simultaneously.

[0051] S203, construct a face buffer for the lane edge line.

[0052] S204, perform geometric intersection on the face buffer and the point cloud, determine the point cloud located inside the face buffer as the point cloud of interest, and determine the point cloud located outside the face buffer as the non-point cloud of interest.

[0053] In this embodiment, the first lane line and the second lane line are both lane lines based on a map coordinate system, and the point cloud collected by the laser radar is a point cloud based on a laser radar coordinate system. The data in the two coordinate systems cannot be directly geometrically intersected. Therefore, before the geometric intersection of the face buffer and the point cloud is performed, the point cloud and the face buffer need to be converted to the same coordinate system. In this embodiment, the point cloud and the face buffer are both converted to the vehicle coordinate system. It should be understood that the point cloud and the face buffer can also be converted to other coordinate systems, such as the world coordinate system, as long as the data in the point cloud and the face buffer are in the same coordinate system.

[0054] In this embodiment, the point cloud collected by the laser radar is converted to the vehicle coordinate system according to the conversion relationship between the laser radar coordinate system and the vehicle coordinate system, to obtain the point cloud of the road region where the lane edge line is located.

[0055] In this embodiment, the point cloud collected by the laser radar is converted to the vehicle coordinate system according to the conversion relationship between the laser radar coordinate system and the vehicle coordinate system, to obtain the point cloud of the road region where the lane edge line is located.

[0056] Specifically, the conversion of the first lane line and the second lane line to the vehicle coordinate system includes:

[0057] S2031, according to the conversion relationship between the map coordinate system and the vehicle coordinate system, the first lane line and the second lane line are converted to the vehicle coordinate system, to obtain the first target lane line based on the vehicle coordinate system and the second target lane line based on the vehicle coordinate system.

[0058] The lane edge line located on the left side of the vehicle driving direction in the lane edge line obtained from the high-precision map is the first original lane line, and the lane edge line located on the right side of the vehicle driving direction is the second original lane line. By fitting the first original lane line, the first lane line can be obtained. And by fitting the second original lane line, the second lane line can be obtained.

[0059] S2032, the first target lane line and the second target lane line are processed to obtain the first lane marking and the second lane marking, and the width between the first lane marking and the second lane marking is a preset width.

[0060] In this embodiment, the point cloud collected by the laser radar is converted to the vehicle coordinate system according to the conversion relationship between the laser radar coordinate system and the vehicle coordinate system, to obtain the point cloud of the road region where the lane edge line is located.

[0056] Specifically, the conversion of the first lane line and the second lane line to the vehicle coordinate system includes:

[0057] S2031, according to the conversion relationship between the map coordinate system and the vehicle coordinate system, the first lane line and the second lane line are converted to the vehicle coordinate system, to obtain the first target lane line based on the vehicle coordinate system and the second target lane line based on the vehicle coordinate system.

[0058] The lane edge line located on the left side of the vehicle driving direction in the lane edge line obtained from the high-precision map is the first original lane line, and the lane edge line located on the right side of the vehicle driving direction is the second original lane line. By fitting the first original lane line, the first lane line can be obtained. And by fitting the second original lane line, the second lane line can be obtained.

[0059] S2032, the first target lane line and the second target lane line are processed to obtain the first lane marking and the second lane marking, and the width between the first lane marking and the second lane marking is a preset width.

[0060] In this embodiment, the point cloud collected by the laser radar is converted to the vehicle coordinate system according to the conversion relationship between the laser radar coordinate system and the vehicle coordinate system, to obtain the point cloud of the road region where the lane edge line is located.

[0061] The embodiment is to respectively widen the lane area formed by the first target lane line and the second target lane line on the left side and the right side, to obtain a standard lane area formed by the first lane marking and the second lane marking.

[0062] Figure 5 The schematic diagram provided by the embodiment of the present application for widening the lane line is shown in the figure. Figure 5 As shown in the figure, in the transverse direction of the vehicle driving direction, the first target lane line 41 is increased by a preset distance d to the outside of the lane area to obtain the first lane marking 42, and the second target lane line 43 is increased by a preset distance d to the outside of the lane area to obtain the second lane marking 44.

[0063] After converting the first lane line and the second lane line to data in the same coordinate system as the point cloud, the following step S2033 can be performed to construct a face buffer, and then the geometric intersection between the face buffer and the point cloud is performed.

[0064] Specifically, the geometric intersection refers to determining the intersection of the face buffer and the point cloud.

[0065] S2033, constructing a face buffer according to the first lane marking and the second lane marking, to obtain the face buffer.

[0066] Specifically, the face buffer is constructed according to the region within the preset length range from the current position of the vehicle and including the first lane marking and the second lane marking.

[0067] Figure 6 The schematic diagram provided by the embodiment of the present application for constructing the face buffer is shown in the figure. Figure 6 As shown in the figure, after obtaining the first lane marking 42 and the second lane marking 44, the lane area within the L length range from the current position of the vehicle can be intercepted, and a buffer is constructed for the intercepted region to obtain the face buffer (as shown by the rectangular frame in the figure). Figure 5

[0068] Figure 7 The schematic diagram of the geometric intersection result provided by the embodiment of the present application is shown in the figure.

[0069] As shown in the figure, the rectangular frame is the face buffer, the point cloud located inside the rectangular frame is the point cloud of interest (the point set inside the solid line rectangular frame in the figure), and the point cloud located outside the rectangular frame is the non-point cloud of interest (the point set inside the dashed line frame in the figure). Figure 7

[0070] S205, determining the first height value and the first intensity value of the point cloud of interest, and the second height value and the second intensity value of the non-point cloud of interest.

[0071] ​​The laser radar emits a beam of light, which forms a reflected light after encountering an object and is received by the laser radar. After obtaining the spatial coordinates of each sampling point on the surface of the object, a set of points, referred to as a point cloud, can be obtained. The point cloud of interest includes a plurality of points, each having three-dimensional coordinates (x, y, z) and laser reflection intensity (Intensity).

[0072] For the point cloud of interest, the z-axis coordinate values of all points in the point cloud of interest are averaged to obtain a first height value. Similarly, the laser reflection intensities of all points in the point cloud of interest are averaged to obtain a first intensity value.

[0073] For the point cloud of interest, the z-axis coordinate values of all points in the point cloud of interest are averaged to obtain a first height value. Similarly, the laser reflection intensities of all points in the point cloud of interest are averaged to obtain a first intensity value.

[0074] In this embodiment, after the geometric intersection of the point cloud and the face buffer is performed, the original point cloud of interest is obtained, which includes outliers and needs to be filtered. The point cloud formed by the remaining points is determined as the point cloud of interest. Specifically, the points in the original point cloud of interest whose height values are outside the preset height range and whose intensity values are outside the preset intensity range are filtered, and the remaining points are determined as the point cloud of interest.

[0075] In addition, in this embodiment, part of the point cloud outside the face buffer is randomly selected as the point cloud of non-interest.

[0076] S206, determine whether the difference between the first height value and the second height value is less than a preset height difference value.

[0077] S207, if the difference between the first height value and the second height value is less than the preset height difference value, determine whether the difference between the first intensity value and the second intensity value is less than a preset intensity difference value.

[0078] If there is a significant difference in height value, it indicates that there are still point clouds in the face buffer that represent ground objects with significant height changes from the road itself. These ground objects can be road curbs or isolation barriers, and there is no change in the lane edge line, so the intensity value needs to be further determined.

[0079] S208, if the difference between the first intensity value and the second intensity value is less than the preset intensity difference value, send the detection result of the current time to the server, and the detection result includes the position of the vehicle and the information that the lane edge line at the position of the vehicle has changed.

[0080] If the height values do not have obvious differences, the intensity contrast value is further compared with the intensity reference value in the boundary range. Since the intensity information of the scanned point cloud is only related to the material of the scanned object, there is a large difference between the asphalt road surface and the marking sprayed material. Therefore, if the intensity values are small, it is considered that the lane edge line at this position has changed, that is, it has been adjusted or moved.

[0081] Specifically, after receiving the detection result of the current time, the server changes the lane information at the position of the vehicle in the high-precision map according to the position of the vehicle in the detection result of the current time and the information that the lane edge line at the position of the vehicle has changed, so as to be consistent with the real environment.

[0082] In S209, if the difference between the first height value and the second height value is greater than or equal to a preset height difference value, or the difference between the first intensity value and the second intensity value is greater than or equal to a preset intensity difference value, the process ends.

[0083] After updating the high-precision map according to the above-mentioned embodiments, the server will distribute the updated high-precision map to all vehicles, so that these vehicles plan paths according to the updated high-precision map.

[0084] The embodiment obtains the point cloud of the lane edge line corresponding to the current position of the vehicle in the high-precision map and the road area where the lane edge line is located; constructs a face buffer area according to the lane edge line, and performs geometric intersection on the face buffer area and the point cloud to determine the point cloud of interest and the point cloud of non-interest; and in the case that the difference between the first height value and the second height value is less than a preset height difference value, and the difference between the first intensity value and the second intensity value is less than a preset intensity difference value, the detection result of the current time is sent to the server, so that the server updates the high-precision map according to the detection result. The detection result includes the position of the vehicle and the information that the lane edge line at the position of the vehicle has changed. Since the data collected by the vehicle sensor in real time is used for calculation to determine whether the lane edge line has changed, the problem of long update delay of the high-precision map caused by manual change detection can be avoided, the high-precision map can be updated in time, and the map update efficiency is improved.

[0085] On the basis of the above-mentioned method embodiments, Figure 8 The schematic diagram of the lane edge line change detection device provided by the embodiment of the application is as follows. Figure 8As shown, the apparatus comprises: an acquisition module 801, a determination module 802 and a sending module 803; the acquisition module 801 is configured to acquire a lane edge line corresponding to a current position of a vehicle in a high-precision map; the acquisition module 801 is further configured to acquire a point cloud of a road region where the lane edge line is located; the determination module 802 is configured to determine a height value of a point cloud of interest to obtain a first height value, and determine an intensity value of the point cloud of interest to obtain a first intensity value, the point cloud of interest being a point cloud located inside a surface buffer region, the surface buffer region being a surface region constructed according to the lane edge line; the determination module 802 is further configured to determine a height value of a non-point cloud of interest to obtain a second height value, and determine an intensity value of the non-point cloud of interest to obtain a second intensity value, the non-point cloud of interest being a point cloud located outside the surface buffer region; and the sending module 803 is configured to send a detection result of a current time to a server if a difference between the first height value and the second height value is less than a preset height difference value, and a difference between the first intensity value and the second intensity value is less than a preset intensity difference value, the detection result comprising a position of the vehicle and information that a lane edge line at the position of the vehicle has changed.

[0086] In some possible implementation manners, the apparatus further comprises a geometric intersection module 804 configured to perform geometric intersection on the surface buffer region and the point cloud to obtain the point cloud of interest and the non-point cloud of interest.

[0087] In some possible implementation manners, the determination module 802 determines a height value of the point cloud of interest to obtain a first height value, and determines an intensity value of the point cloud of interest to obtain a first intensity value, specifically comprising: determining an average value of height values of all points in the point cloud of interest to obtain the first height value; and determining an average value of intensity values of all points in the point cloud of interest to obtain the first intensity value.

[0088] In some possible implementation manners, the determination module 802 determines a height value of the non-point cloud of interest to obtain a second height value, and determines an intensity value of the non-point cloud of interest to obtain a second intensity value, comprising: determining an average value of height values of all points in the non-point cloud of interest to obtain the second height value; and determining an average value of intensity values of all points in the non-point cloud of interest to obtain the second intensity value.

[0089] In some possible implementation manners, the lane edge line includes a first lane line and a second lane line, and the first lane line and the second lane line are both lane lines based on a map coordinate system, and the method further includes: a first conversion module 805, configured to perform coordinate system conversion on the first lane line and the second lane line according to a conversion relationship between the map coordinate system and a vehicle coordinate system, to obtain a first target lane line based on the vehicle coordinate system and a second target lane line based on the vehicle coordinate system; a processing module 806, configured to process the first target lane line and the second target lane line to obtain a first lane marking and a second lane marking, and a width between the first lane marking and the second lane marking is a preset width; and a face buffer area construction module 707, configured to perform face buffer area construction according to the first lane marking and the second lane marking to obtain the face buffer area.

[0090] In some possible implementation manners, the point cloud is a point cloud based on a vehicle coordinate system, and the acquisition module 801 is specifically configured to: acquire a point cloud collected by a laser radar; and perform coordinate system conversion on the point cloud collected by the laser radar according to a conversion relationship between a laser radar coordinate system and the vehicle coordinate system, to obtain the point cloud.

[0091] In some possible implementation manners, the device further includes: a second conversion module 808; and the acquisition module 801 is further configured to acquire a current position of the vehicle, and the second conversion module 808 is configured to extract, from the high-precision map, a lane edge line of a lane in which the vehicle is currently located according to the current position of the vehicle.

[0092] In some possible implementation manners, the device further includes: a receiving module 809, configured to receive an updated high-precision map, the updated high-precision map being a map obtained by updating a high-precision map according to a current detection result, and the detection result including a position of the vehicle and information that a lane edge line at the position of the vehicle has changed; and a control module 810, configured to control the vehicle according to the updated high-precision map.

[0093] The lane edge line change detection device provided by the embodiments of the present application can be used to execute the technical solutions of the lane edge line change detection method in the above embodiments, and has similar implementation principles and technical effects, which will not be described herein again.

[0094] The embodiment obtains the point cloud of the lane edge line corresponding to the current position of the vehicle in the high-precision map and the road area where the lane edge line is located, constructs a face buffer area according to the lane edge line, performs geometric intersection on the face buffer area and the point cloud to determine the point cloud of interest and the point cloud of non-interest, and in the case that the difference between the first height value and the second height value is less than a preset height difference value and the difference between the first intensity value and the second intensity value is less than a preset intensity difference value, sends the detection result of the current time to the server to enable the server to update the high-precision map according to the detection result, and the detection result includes the position of the vehicle and information that the lane edge line at the position of the vehicle changes. Since the data collected by the vehicle sensor in real time is used for calculation to determine whether the lane edge line changes, the problem that the update of the high-precision map is delayed for a long time due to manual change discovery can be avoided, the high-precision map can be updated in time, and the effect of improving the map update efficiency is achieved.

[0095] It should be noted that the division of each module of the above device is only a logical division of functions, and all or part of the modules can be integrated into one physical entity, or physically separated. And these modules can all be implemented in the form of software called by a processing element; all can be implemented in the form of hardware; some modules can be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. For example, the determination module 802 can be a separate processing element, or can be integrated into a chip of the above device, and in addition, the function of the determination module 802 can be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The implementation of other modules is similar. In addition, all or part of the modules can be integrated together or independently implemented. The processing element here can be an integrated circuit with signal processing capability. In the implementation process, each step of the above method or each module can be completed by the integrated logic circuit of hardware or the instruction of software in the processing element.

[0096] Figure 9 The structure schematic diagram of the electronic device provided by the embodiment of the application is shown in the figure. Figure 9 As shown in the figure, the computer device can include a receiver 900, a transmitter 901, a processor 902, and a memory 903.

[0097] The processor 902 executes computer-executed instructions stored in the memory to cause the processor 902 to perform the solutions in the above embodiments. The processor 902 can be a general-purpose processor, including a central processing unit CPU, a network processor NP, etc.; can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0098] The memory 903 is connected with the processor 902 through the system bus and completes mutual communication, and the memory 903 is used for storing computer program instructions.

[0099] The transceiver 901 can be used to receive operation instructions.

[0100] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The transceiver is used to realize the communication between the database access device and other computers (such as clients, read-write libraries and read-only libraries). The memory can contain random access memory (RAM), and can also include non-volatile memory.

[0101] The electronic device provided by the embodiments of the present application can be the terminal device or the server of the above embodiments.

[0102] The electronic device provided by the embodiments of the present application can be used to execute the technical solutions of the lane edge line change detection method in the above embodiments, and the implementation principles and technical effects are similar, which will not be repeated here.

[0103] The embodiments of the present application also provide a chip for running instructions, which is used to execute the technical solutions of the lane edge line change detection method in the above embodiments.

[0104] The embodiments of the present application also provide a computer readable storage medium, which stores computer instructions, and when the computer instructions run on a computer, the computer executes the technical solutions of the lane edge line change detection method in the above embodiments.

[0105] The embodiment of the present application further provides a computer program product, which comprises a computer program stored in a computer readable storage medium, at least one processor can read the computer program from the computer readable storage medium, and the at least one processor can implement the technical solution of the lane edge line change detection method in the above embodiment when executing the computer program.

[0106] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to 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 or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

[0107] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. The specification and examples given are exemplary only and the true scope and spirit of the application is indicated by the following claims. It will be appreciated by persons skilled in the art that numerous variations and / or modifications can be made to the application as described above without departing from the scope or spirit of the application. It is intended that all such variations and / or modifications be included within the scope of the application. The specification and examples given are exemplary only and the true scope and spirit of the application is indicated by the following claims.

[0108] It should be understood that the application is not limited to the precise construction that has been described and illustrated herein and that various modifications and changes can be made therein without departing from the scope thereof. The scope of the application is indicated by the appended claims rather than by the description.

Claims

1. A method for detecting lane edge line changes, characterized in that, include: Obtain the lane edge line corresponding to the current position of the vehicle in the high-precision map; Obtain the point cloud of the road area where the lane edge line is located; Determine the first height value and the first intensity value of the point cloud of interest, wherein the point cloud of interest is a point cloud located inside the surface buffer zone, and the surface buffer zone is generated by adding a preset distance to the outside of the lane area according to the lane edge line, generating the first lane marking and the second lane marking, and constructing the surface buffer zone according to the first lane marking and the second lane marking; Determine the second height value and the second intensity value of the non-interest point cloud, which is a point cloud located outside the surface buffer; If the difference between the first height value and the second height value is less than a preset height difference, and the difference between the first intensity value and the second intensity value is less than a preset intensity difference, then the current detection result is sent to the server. The detection result includes information about the vehicle's position and changes in the lane edge line at the vehicle's position.

2. The method according to claim 1, characterized in that, The method further includes: Geometric intersection is performed on the surface buffer and the point cloud to obtain the point cloud of interest and the point cloud of non-interest.

3. The method according to claim 1 or 2, characterized in that, The determination of the first height value and the first intensity value of the point cloud of interest includes: The average height value of all points in the point cloud of interest is determined to obtain the first height value; The first intensity value is obtained by determining the average value of the intensity values ​​of all points in the point cloud of interest.

4. The method according to claim 1 or 2, characterized in that, The determination of the second height value and second intensity value of the non-interest point cloud includes: The average height value of all points in the non-interest point cloud is determined to obtain the second height value; The average intensity value of all points in the non-interest point cloud is determined to obtain the second intensity value.

5. The method according to claim 1, characterized in that, The lane edge lines include a first lane line and a second lane line, both of which are lane lines based on a map coordinate system. The method further includes: Based on the transformation relationship between the map coordinate system and the vehicle coordinate system, the first lane line and the second lane line are transformed to obtain the first target lane line and the second target lane line based on the vehicle coordinate system. The first target lane line and the second target lane line are processed to obtain the first lane marking and the second lane marking, and the width between the first lane marking and the second lane marking is a preset width; The surface buffer zone is constructed based on the first lane marking and the second lane marking to obtain the surface buffer zone.

6. The method according to claim 1 or 5, characterized in that, The point cloud is a point cloud based on a vehicle coordinate system, and the method further includes: Acquire point clouds collected by lidar; Based on the transformation relationship between the lidar coordinate system and the vehicle coordinate system, the point cloud collected by the lidar is transformed to obtain the point cloud.

7. The method according to claim 1 or 5, characterized in that, The step of obtaining the lane edge line corresponding to the current position of the vehicle in the high-precision map includes: Obtain the current location of the vehicle; Based on the vehicle's current location, the lane edge line of the lane where the vehicle's current location is located is extracted from the high-precision map.

8. The method according to claim 7, characterized in that, The method includes: The system receives an updated high-precision map, which is obtained by the server updating the high-precision map based on the current detection results. The detection results include information about the vehicle's position and changes in the lane edge lines at the vehicle's position. The vehicle is controlled based on the updated high-precision map.

9. A detection device for lane edge line changes, characterized in that, include: The acquisition module is used to acquire the lane edge line corresponding to the current position of the vehicle in the high-precision map; The acquisition module is also used to acquire the point cloud of the road area where the lane edge line is located; The determination module is used to determine the height value of the point cloud of interest to obtain a first height value, and to determine the intensity value of the point cloud of interest to obtain a first intensity value. The point cloud of interest is a point cloud located inside the surface buffer. The surface buffer is generated by adding a preset distance to the outside of the lane area according to the lane edge line, generating a first lane marking and a second lane marking, and constructing the surface buffer according to the first lane marking and the second lane marking. The determining module is further configured to determine the height value of the non-interest point cloud to obtain a second height value, and to determine the intensity value of the non-interest point cloud to obtain a second intensity value, wherein the non-interest point cloud is a point cloud located outside the surface buffer. The sending module is configured to send the current detection result to the server if the difference between the first height value and the second height value is less than a preset height difference, and the difference between the first intensity value and the second intensity value is less than a preset intensity difference. The detection result includes the position of the vehicle and information on changes in the lane edge line at the position of the vehicle.

10. A vehicle control device, characterized in that, include: Memory, processor; Memory; Memory used to store the processor's executable instructions; The processor is configured to implement the method as described in any one of claims 1-8.

11. A vehicle, characterized in that, include: The vehicle control device as described in claim 10; An inertial navigation system is used to acquire the vehicle's position. LiDAR is used to collect point clouds of the environment surrounding the vehicle.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-8.

13. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-8.

Images