Heading angle confidence judgment method, device, electronic device and storage medium

Abstract

The present invention provides a heading angle confidence determination method, device, electronic device, and storage medium, belonging to the field of intelligent driving technology. The method includes: obtaining first lane line data and second lane line data of a vehicle's road; the first lane line data and the second lane line data are collected in different ways; constructing a first set of lane line fitting points based on the first lane line data, and constructing a second set of lane line fitting points based on the second lane line data; performing point cloud registration on the first and second fitting point sets to determine a rotation matrix that meets preset registration requirements; calculating the deviation angle of the vehicle's heading angle based on the rotation matrix, and determining the confidence level of the vehicle's heading angle based on the deviation angle. The present invention can more accurately calculate the deviation angle of the vehicle's heading angle and determine the confidence level of the vehicle's heading angle based on the deviation angle, thereby ensuring the accuracy of the confidence level and providing safer parameter collection for intelligent driving.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a heading angle confidence judgment method, device, electronic device and storage medium. Background Art

[0002] With the development of science and technology, intelligent driving technology has been widely used. The heading angle confidence of intelligent driving vehicles is related to the safety of vehicle driving and is a very important intelligent driving parameter.

[0003] In the existing technology, the method for determining the vehicle heading angle confidence is to collect lane line images of the road in front of the vehicle, compare different lane line segments through multiple lane line images, and then determine the lane line confidence to judge the vehicle heading angle confidence. This method relies too much on the image features of the actual road and only makes judgments based on the road images collected by the vehicle. It requires high precision of the vehicle image acquisition device and the judgment of the vehicle heading angle confidence is inaccurate.

[0004] This shows that the existing technology has technical problems such as over-reliance on image features of actual roads and inaccurate judgment of the confidence level of vehicle heading angles. Summary of the Invention

[0005] In view of this, it is necessary to provide a heading angle confidence judgment method, device, electronic device and storage medium to solve the technical problems of high cost and low efficiency in optimizing magnetic resonance images in the prior art.

[0006] In order to solve the above technical problems, on the one hand, the present invention provides a heading angle confidence determination method, comprising:

[0007] Acquire first lane line data and second lane line data of a road on which the vehicle is located; the first lane line data and the second lane line data are collected in different ways;

[0008] constructing a first fitting point set for lane lines based on the first lane line data, and constructing a second fitting point set for the lane lines based on the second lane line data; performing point cloud registration on the first fitting point set and the second fitting point set to determine a rotation matrix that meets preset registration requirements;

[0009] A deviation angle of the vehicle heading angle is calculated based on the rotation matrix, and a confidence level of the vehicle heading angle is determined based on the deviation angle.

[0010] As a possible implementation manner of the present invention, in this implementation manner, acquiring first lane line data of the road on which the vehicle is located, acquired by the vehicle-mounted image acquisition device, includes:

[0011] Acquire a target lane line segment image of the road where the vehicle is located, captured by an on-board image acquisition device;

[0012] The target lane line segment is sampled in a vehicle plane rectangular coordinate system based on the target lane line segment image to obtain a first lane line coordinate set.

[0013] As a possible implementation manner of the present invention, in this implementation manner, obtaining the second lane line data of the road includes:

[0014] Taking the vehicle as the origin, obtain the station center coordinate set of the target lane segment in the high-precision map;

[0015] The station center coordinate set is converted into a second lane line coordinate set in the vehicle plane rectangular coordinate system.

[0016] As a possible implementation manner of the present invention, in this implementation manner, constructing a first lane line fitting point set based on the first lane line data, and constructing a second lane line fitting point set based on the second lane line data, includes:

[0017] Constructing a first fitting function between the distance from each first lane line point in the first lane line coordinate set to the starting point of the target lane line segment and the coordinates of each first lane line point; constructing a second fitting function between the distance from each second lane line point in the second lane line coordinate set to the starting point of the target lane line segment and the coordinates of each second lane line point;

[0018] Calculating a first fitting curve of the target lane segment based on the first fitting function, and calculating a second fitting curve of the target lane segment based on the second fitting function;

[0019] The first fitting curve is sampled to obtain a first fitting point set, and the second fitting curve is sampled to obtain a second fitting point set.

[0020] As a possible implementation manner of the present invention, in this implementation manner, constructing a first fitting function between the distance from each first lane line point in the first lane line coordinate set to the starting point of the target lane segment and the coordinates of each first lane line point includes:

[0021] A first abscissa fitting function and a first ordinate fitting function are constructed by taking the distance from each first lane line point in the first lane line coordinate set to the starting point of the target lane line segment as the independent variable and the abscissa and ordinate of the first lane line point as the dependent variable.

[0022] As a possible implementation manner of the present invention, in this implementation manner, constructing a second fitting function of the distance from each second lane line point in the second lane line coordinate set to the starting point of the target lane segment and the coordinates of each second lane line point includes:

[0023] A second abscissa fitting function and a second ordinate fitting function are constructed by taking the distance from each second lane line point in the second lane line coordinate set to the starting point of the target lane line segment as the independent variable and the abscissa and ordinate of the second lane line point as the dependent variables.

[0024] As a possible implementation manner of the present invention, in this implementation manner, calculating the deviation angle of the vehicle heading angle based on the rotation matrix, and determining the confidence level of the vehicle heading angle based on the deviation angle include:

[0025] Performing Euler angle conversion on the rotation matrix to determine the deviation angle of the vehicle heading angle;

[0026] When the deviation angle is greater than a preset angle threshold for a consecutive preset number of times, determining that the confidence level of the vehicle heading angle is in an abnormal state;

[0027] When the deviation angle is less than or equal to a preset angle threshold for a consecutive preset number of times, it is determined that the confidence level of the vehicle heading angle is in a normal state.

[0028] On the other hand, the present invention also provides a heading angle confidence judgment device, comprising:

[0029] A data acquisition module, configured to acquire data of a first lane line and a second lane line of a road on which the vehicle is located; the data of the first lane line and the data of the second lane line are acquired in different ways;

[0030] a fitting module, configured to construct a first fitting point set for lane lines based on the first lane line data, and to construct a second fitting point set for the lane lines based on the second lane line data; perform point cloud registration on the first fitting point set and the second fitting point set to determine a rotation matrix that meets preset registration requirements;

[0031] A judgment module is used to calculate a deviation angle of the vehicle heading angle based on the rotation matrix, and determine a confidence level of the vehicle heading angle based on the deviation angle.

[0032] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein:

[0033] The memory is used to store programs;

[0034] The processor is coupled to the memory and is configured to execute the program stored in the memory to implement the steps of the heading angle confidence determination method described in any of the above implementations.

[0035] On the other hand, the present invention also provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the heading angle confidence judgment method described in any of the above-mentioned implementation methods.

[0036] The present invention has the following beneficial effects: The heading angle confidence determination method provided by the present invention obtains first lane line data and second lane line data of the road on which the vehicle is located, wherein the first lane line and second lane line data are collected in different ways, constructs two fitting point sets based on the two lane line data, performs point cloud registration on the fitting point sets, determines a rotation matrix, calculates the deviation angle of the vehicle heading angle based on the rotation matrix, and determines the confidence level of the vehicle heading angle based on the deviation angle. By comparing the two lane line data, the deviation angle of the vehicle heading angle can be more accurately calculated, and the confidence level of the vehicle heading angle can be determined based on the deviation angle, thereby ensuring the accuracy of the confidence level and providing safer parameter collection for intelligent driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 A schematic diagram of a flow chart of a heading angle confidence determination method provided by an embodiment of the present invention;

[0039] Figure 2 A schematic diagram of a flow chart of a method for collecting first lane line data provided by an embodiment of the present invention;

[0040] Figure 3 A schematic diagram of a flow chart of a method for obtaining second lane line data provided by an embodiment of the present invention;

[0041] Figure 4 A schematic diagram of a flow chart of a method for constructing a fitting point set provided by an embodiment of the present invention;

[0042] Figure 5 A flowchart of a possible implementation method of S103 provided in an embodiment of the present invention;

[0043] Figure 6A schematic structural diagram of a heading angle confidence determination device provided by an embodiment of the present invention;

[0044] Figure 7 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0046] The terms "first," "second," and so on, used in the embodiments of the present invention are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, technical features designated as "first" or "second" may explicitly or implicitly include at least one such feature.

[0047] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0048] The present invention provides a heading angle confidence determination method, device, electronic device, and storage medium, which are described below respectively.

[0049] Figure 1 A flow chart of an embodiment of a method for determining heading angle confidence provided by the present invention is shown as follows: Figure 1 As shown, the heading angle confidence judgment method includes:

[0050] S101, obtaining first lane line data and second lane line data of a road on which a vehicle is located; the first lane line data and the second lane line data are collected in different ways;

[0051] S102, constructing a first lane line fitting point set based on the first lane line data, and constructing a second lane line fitting point set based on the second lane line data; performing point cloud registration on the first fitting point set and the second fitting point set to determine a rotation matrix that meets preset registration requirements;

[0052] S103 , calculating a deviation angle of the vehicle heading angle based on the rotation matrix, and determining a confidence level of the vehicle heading angle based on the deviation angle.

[0053] The heading angle confidence judgment method provided in an embodiment of the present invention can be applied to a vehicle that has been equipped with a forward-looking camera that can identify actual road lane lines, to assist the vehicle in intelligent driving. The forward-looking camera can normally output the actual lane lines printed on the left or right side in front of the vehicle.

[0054] In an embodiment of the present invention, the first lane line data may be lane line data of the road surface on which the vehicle is traveling, collected by an on-board image acquisition device, wherein the on-board image acquisition device may be the forward-looking camera of the aforementioned embodiment. Generally speaking, the first lane line data is lane line data located on the left side of the vehicle in front of the vehicle on the road surface on which the vehicle is traveling. In some special cases, such as when the left lane line does not exist or is unclear, lane line data on the right side of the vehicle may be obtained, or lane line data on both sides of the vehicle may be obtained at the same time. The present invention does not impose any restrictions on this.

[0055] In an embodiment of the present invention, the second lane marking data may be lane marking data of the road surface on which the vehicle is traveling as depicted in a high-precision map. Similarly, the lane marking data may be lane marking data on the left side of the vehicle or lane marking data on the right side of the vehicle. To obtain the second lane marking data, a high-precision map sensor device may be installed on the vehicle to obtain real-time lane marking data on the left and / or right side of the vehicle while the vehicle is traveling.

[0056] In an embodiment of the present invention, the first fitting point set refers to a set of shape point data obtained by sampling the first lane line data and capable of roughly describing the shape of the lane line. The second fitting point set refers to a set of shape point data obtained by sampling the second lane line data and capable of roughly describing the shape of the lane line. There should be a corresponding relationship between the first fitting point set and the second fitting point set, that is, the first fitting point set can be obtained by a rotation matrix and a translation matrix to obtain the second fitting point set. Generally, the first fitting point set cannot completely overlap with the second fitting point set after rotation and translation, and therefore only needs to meet the preset registration requirements.

[0057] In an embodiment of the present invention, after the rotation matrix is ​​calculated, the deviation angle of the vehicle heading angle can be obtained based on the rotation matrix. The deviation angle of the heading angle refers to the difference between the heading angle in the vehicle navigation module and the heading angle during the actual driving process of the vehicle. Based on the deviation angle of the heading angle, the confidence of the vehicle heading angle can be determined.

[0058] The heading angle confidence determination method provided by the present invention obtains first lane line data of the vehicle's road, captured by an on-board image acquisition device, and second lane line data of the same road in a high-precision map. Two fitting point sets are constructed using these two lane line data sets. Point cloud registration is performed on the fitting point sets to determine a rotation matrix. The deviation angle of the vehicle's heading angle is calculated based on the rotation matrix, and the confidence level of the vehicle's heading angle is determined based on this deviation angle. By comparing the lane line data captured by the on-board image acquisition device with the lane line data in the high-precision map, the deviation angle of the vehicle's heading angle can be more accurately calculated. The confidence level of the vehicle's heading angle is determined based on the deviation angle, ensuring the accuracy of the confidence level and providing safer parameter collection for intelligent driving.

[0059] As a possible embodiment of the present invention, in this embodiment, Figure 2 As shown, obtaining the first lane line data of the road where the vehicle is located collected by the vehicle-mounted image acquisition device includes:

[0060] S201, acquiring a target lane line segment image of the road where the vehicle is located, captured by a vehicle-mounted image acquisition device;

[0061] S202 : Sampling the target lane line segment in a vehicle plane rectangular coordinate system based on the target lane line segment image to obtain a first lane line coordinate set.

[0062] In the embodiment of the present invention, the target lane line segment image refers to the image of the lane line at a preset distance ahead of the vehicle. Since the acquisition distance of the vehicle-mounted image acquisition device is limited, it is only necessary to acquire the lane line image within a certain distance ahead of the vehicle. For the acquired lane line segment image, a fitting curve of the lane line segment is determined by curve fitting. Optionally, a cubic polynomial can be used to fit the lane line curve, as shown in formula (1):

[0063] (1)

[0064] in, represents the intercept, represents the slope at the starting point, is the curvature of the lane centerline, is the curvature change rate, Y is the vertical coordinate of the lane line point in the vehicle coordinate system, and X is the horizontal coordinate of the lane line point in the vehicle coordinate system.

[0065] In an embodiment of the present invention, for the lane line curve obtained by fitting, 200 shape point data coordinates of the lane line curve can be obtained by downsampling, such as sampling within the range of 0 to 20 meters with a step size of 0.1, to constitute a first lane line coordinate set.

[0066] The embodiment of the present invention performs curve fitting on the lane lines in the lane line image and constructs a first lane line coordinate set of the lane lines based on the fitted curve, thereby acquiring lane line data more accurately.

[0067] As a possible embodiment of the present invention, in this embodiment, Figure 3 As shown, obtaining the second lane line data of the road includes:

[0068] S301, taking the vehicle as the origin, obtaining a set of station center coordinates of the target lane segment in the high-precision map;

[0069] S302: Convert the station center coordinate set into a second lane line coordinate set in the vehicle plane rectangular coordinate system.

[0070] In an embodiment of the present invention, for acquiring the second lane line data, it is necessary to first convert the lane line point data in the high-precision map from latitude and longitude coordinates into vehicle plane coordinate system coordinates. Optionally, it can be based on the conversion relationship between the station-centered coordinate system and the plane coordinate system. The station-centered coordinate system is also called the site coordinate system, the east-north-sky coordinate system ENU, and is a coordinate system used to understand the motion laws of other objects centered on the observer. For example, the vehicle's position is used as the origin of the station-centered coordinate system, and the station-centered coordinates of the lane line points in the high-precision map are obtained, and the station-centered coordinates are converted to obtain the lane line coordinates of the vehicle plane rectangular coordinate system with the vehicle's position as the origin.

[0071] In an embodiment of the present invention, after obtaining the coordinates of the lane line points in the high-precision map in the vehicle rectangular plane coordinate system, the coordinates are downsampled to obtain a second lane line coordinate set. Specifically, the coordinates of the projection point of the vehicle position vertically projected onto the lane edge of the map are first calculated. With the projection point as the starting point, lane line point data is selected with a preset step size to construct the second lane line coordinate set, where the preset step size is the distance between each lane line point data, and is calculated using formula (2):

[0072] (2)

[0073] Among them, S is the distance from the lane linear point to the starting point, is the horizontal coordinate of the lane line point in the vehicle rectangular plane coordinate system, is the horizontal coordinate of the lane line point in the vehicle rectangular plane coordinate system, and N is the number of lane line point data; the coordinates of 200 lane line point data between S=0 and S=20 are sampled to form the second lane line coordinate set.

[0074] The embodiment of the present invention transforms the coordinates of the lane lines in the high-precision map to obtain the coordinates of the lane lines in the vehicle plane rectangular coordinate system, and constructs a second lane line coordinate set based on the coordinates to facilitate the calculation of the subsequent vehicle heading angle deviation value.

[0075] As a possible embodiment of the present invention, in this embodiment, Figure 4 As shown, constructing a first lane line fitting point set based on the first lane line data and constructing a second lane line fitting point set based on the second lane line data includes:

[0076] S401, constructing a first fitting function between the distance from each first lane line point to the starting point of the target lane line segment and the coordinates of each first lane line point in the first lane line coordinate set; constructing a second fitting function between the distance from each second lane line point to the starting point of the target lane line segment and the coordinates of each second lane line point in the second lane line coordinate set;

[0077] S402, calculating a first fitting curve of the target lane segment based on the first fitting function, and calculating a second fitting curve of the target lane segment based on the second fitting function;

[0078] S403 : Sampling the first fitting curve to obtain a first fitting point set, and sampling the second fitting curve to obtain a second fitting point set.

[0079] In an embodiment of the present invention, in order to ensure the accuracy of lane line curve fitting, it is necessary to construct a fitting function for the first lane line coordinate set and the second lane line coordinate set. In order to improve the accuracy of vehicle heading angle confidence calculation, it is necessary to use the same independent variable to perform function fitting on the first lane line coordinate set and the second lane line coordinate set. Optionally, the independent variable is the distance from each first lane line point in the first lane line coordinate set to the starting point of the target lane segment and the distance from each second lane line point in the second lane line coordinate set to the starting point of the target lane segment. Specifically, the projection point of the vehicle's current position vertically projected onto the lane edge is used as the starting point of the target lane segment, and the distance from the first lane line point in the first lane line coordinate set to the starting point and the distance from the second lane line point in the second lane line coordinate set to the starting point are used as independent variables to construct a fitting function. Based on the fitting function, a first fitting curve corresponding to the first lane line coordinate set and a second fitting curve corresponding to the second lane line coordinate set are respectively calculated, and then the first fitting curve and the second fitting curve are sampled to obtain a first fitting point set and a second fitting point set.

[0080] As a possible implementation of the present invention, in this implementation, constructing a first fitting function between the distance from each first lane line point to the starting point of the target lane line segment in the first lane line coordinate set and the coordinates of each first lane line point includes:

[0081] The distance from each first lane line point in the first lane line coordinate set to the starting point of the target lane line segment is used as the independent variable, and the horizontal coordinate and vertical coordinate of the first lane line point are used as the dependent variables to construct the first horizontal coordinate fitting function and the first vertical coordinate fitting function.

[0082] As a possible implementation of the present invention, in this implementation, constructing a second fitting function between the distance from each second lane line point to the starting point of the target lane segment in the second lane line coordinate set and the coordinates of each second lane line point includes:

[0083] The distance from each second lane line point in the second lane line coordinate set to the starting point of the target lane line segment is used as the independent variable, and the horizontal coordinate and vertical coordinate of the second lane line point are used as the dependent variables to construct the second horizontal coordinate fitting function and the second vertical coordinate fitting function.

[0084] In the embodiment of the present invention, taking the construction of the first fitting function of the distance from each first lane line point in the first lane line coordinate set to the starting point of the target lane line segment and the coordinates of each first lane line point as an example, the projection point of the vehicle position onto the lane edge is used as the starting point of the target lane line segment, the distance S from the coordinate point in the first lane line coordinate set to the starting point is used as the independent variable, and the horizontal coordinate X and vertical coordinate Y of the coordinate point are used as the dependent variables to construct the first horizontal coordinate fitting function. and the first ordinate fitting function , the specific functions are shown in formulas (3) and (4):

[0085] (3)

[0086] (4)

[0087] The embodiment of the present invention performs curve fitting through a fifth-order polynomial. - are the unknown coefficients of the fifth-order polynomial of the horizontal coordinate fitting function, - It is the unknown coefficient of the quintic polynomial of the vertical coordinate fitting function, which can be calculated and determined based on multiple S-(X,Y) data pairs.

[0088] Similarly, the function fitting method combined with the second lane line coordinates is the same as the principle of the above embodiment and will not be repeated here.

[0089] In an embodiment of the present invention, the function fitting method provided in the aforementioned embodiment can obtain a fitting curve of the first lane line data collected by the vehicle-mounted image acquisition device and a fitting curve of the second lane line data in the high-precision map. By downsampling the first fitting curve and the second fitting curve, a first fitting point set and a second fitting point set can be obtained.

[0090] As a possible embodiment of the present invention, in this embodiment, Figure 5 As shown, the deviation angle of the vehicle heading angle is calculated based on the rotation matrix, and the confidence of the vehicle heading angle is determined based on the deviation angle, including:

[0091] S501, performing Euler angle conversion on the rotation matrix to determine the deviation angle of the vehicle heading angle;

[0092] S502, when the deviation angle is greater than a preset angle threshold for a consecutive preset number of times, determining that the confidence level of the vehicle heading angle is in an abnormal state;

[0093] S503: When the deviation angle is less than or equal to the preset angle threshold for a consecutive preset number of times, it is determined that the confidence level of the vehicle heading angle is normal.

[0094] In the embodiment of the present invention, after obtaining the first fitting point set according to the above embodiment, and the second set of fitting points After that, there is a rotation and translation transformation relationship between the first fitting point set Q and the second fitting point set P. After determining the rotation matrix that meets the preset requirements, the rotation matrix is ​​converted into Euler angles to obtain the deviation angle between the vehicle heading angle and the actual vehicle driving direction. The deviation angle is compared with a preset deviation angle threshold. Optionally, the deviation angle threshold is 0.8 degrees. If the deviation angle between the vehicle heading angle and the actual vehicle driving direction is greater than 0.8 degrees in 5 consecutive frame calculations, it indicates that the vehicle heading angle confidence is unreliable, and the confidence abnormality information is sent to the back end to remind the driver to pay attention. If the deviation angle between the vehicle heading angle and the actual vehicle driving direction is not greater than 0.8 degrees in 5 consecutive frame calculations, it indicates that the vehicle heading angle confidence is credible and driving can be based on the vehicle heading angle.

[0095] The embodiment of the present invention determines the confidence level of the vehicle heading angle by calculating the deviation angle between the vehicle heading angle and the actual vehicle driving direction, and the determination of the confidence level of the vehicle heading angle is more accurate.

[0096] In order to better implement the heading angle confidence determination method in the embodiment of the present invention, based on the heading angle confidence determination method, correspondingly, Figure 6 As shown, an embodiment of the present invention further provides a heading angle confidence determination device, and the heading angle confidence determination device 600 includes:

[0097] The data acquisition module 601 is used to acquire the first lane line data and the second lane line data of the road where the vehicle is located; the first lane line data and the second lane line data are collected in different ways;

[0098] A fitting module 602 is configured to construct a first set of fitting points for lane lines based on the first lane line data and a second set of fitting points for lane lines based on the second lane line data; perform point cloud registration on the first set of fitting points and the second set of fitting points to determine a rotation matrix that satisfies a preset registration requirement;

[0099] The judgment module 603 is configured to calculate a deviation angle of the vehicle heading angle based on the rotation matrix, and determine a confidence level of the vehicle heading angle based on the deviation angle.

[0100] The heading angle confidence judgment device 600 provided in the above embodiment can implement the technical solution described in the above heading angle confidence judgment method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above heading angle confidence judgment method embodiment, which will not be repeated here.

[0101] The heading angle confidence determination device provided by the present invention obtains first lane line data of the vehicle's road, captured by an on-board image acquisition device, and second lane line data of the same road in a high-precision map. It then constructs two fitting point sets based on these two lane line data, performs point cloud registration on the fitting point sets, determines a rotation matrix, calculates the deviation angle of the vehicle's heading angle based on the rotation matrix, and determines the confidence level of the vehicle's heading angle based on this deviation angle. By comparing the lane line data captured by the on-board image acquisition device with the lane line data in the high-precision map, it is possible to more accurately calculate the deviation angle of the vehicle's heading angle, and determine the confidence level of the vehicle's heading angle based on the deviation angle. This ensures the accuracy of the confidence level and provides safer parameter collection for intelligent driving.

[0102] like Figure 7 As shown, the present invention also provides an electronic device 700. The electronic device 700 includes a processor 701, a memory 702 and a display 703. Figure 7 Only some of the components of the electronic device 700 are shown, but it should be understood that implementation of all of the shown components is not required, and more or fewer components may be implemented instead.

[0103] In some embodiments, the processor 701 may be a central processing unit (CPU), a microprocessor, or other data processing chip, configured to execute program codes or process data stored in the memory 702, such as the heading angle confidence determination method of the present invention.

[0104] In some embodiments, processor 701 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, processor 701 may be local or remote. In some embodiments, processor 701 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, multiple clouds, or any combination thereof.

[0105] In some embodiments, the memory 702 may be an internal storage unit of the electronic device 700, such as a hard disk or memory of the electronic device 700. In other embodiments, the memory 702 may also be an external storage device of the electronic device 700, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 700.

[0106] Furthermore, the memory 702 may include both an internal storage unit of the electronic device 700 and an external storage device. The memory 702 is used to store application software installed in the electronic device 700 and various data.

[0107] In some embodiments, display 703 can be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 703 is used to display information about electronic device 700 and to display a visual user interface. Components 701-703 of electronic device 700 communicate with each other via a system bus.

[0108] In one embodiment, when the processor 701 executes the heading angle confidence determination program in the memory 702, the following steps may be implemented:

[0109] Acquire the first lane line data and the second lane line data of the road where the vehicle is located; the first lane line and the second lane line data are collected in different ways;

[0110] Constructing a first lane line fitting point set based on the first lane line data, and constructing a second lane line fitting point set based on the second lane line data; performing point cloud registration on the first fitting point set and the second fitting point set to determine a rotation matrix that meets preset registration requirements;

[0111] A deviation angle of the vehicle heading angle is calculated based on the rotation matrix, and a confidence level of the vehicle heading angle is determined based on the deviation angle.

[0112] It should be understood that, when the processor 701 executes the heading angle confidence determination program in the memory 702 , in addition to the above functions, it can also implement other functions. For details, please refer to the description of the corresponding method embodiment above.

[0113] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 700 mentioned. The electronic device 700 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, or the like. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices equipped with IOS, Android, Microsoft, or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 700 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0114] Accordingly, an embodiment of the present invention also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, it can implement the steps or functions of the heading angle confidence judgment method provided in the above-mentioned method embodiments.

[0115] Those skilled in the art will appreciate that all or part of the process flow of the above-described method embodiment can be implemented by instructing related hardware (such as a processor, controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0116] The above describes in detail the heading angle confidence judgment method, device, electronic device, and storage medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A heading angle confidence judgment method, characterized in that: include: Acquire first lane line data and second lane line data of a road on which the vehicle is located; the first lane line data and the second lane line data are collected in different ways; constructing a first fitting point set for lane lines based on the first lane line data, and constructing a second fitting point set for the lane lines based on the second lane line data; performing point cloud registration on the first fitting point set and the second fitting point set to determine a rotation matrix that meets preset registration requirements; Calculating a deviation angle of the vehicle heading angle based on the rotation matrix, and determining a confidence level of the vehicle heading angle based on the deviation angle; The obtaining of first lane line data of the road where the vehicle is located includes: Acquire a target lane line segment image of the road where the vehicle is located, captured by an on-board image acquisition device; Sampling the target lane line segment in a vehicle plane rectangular coordinate system based on the target lane line segment image to obtain a first lane line coordinate set; The obtaining of second lane line data of the road includes: Taking the vehicle as the origin, obtain the station center coordinate set of the target lane segment in the high-precision map; Converting the station center coordinate set into a second lane line coordinate set in a vehicle plane rectangular coordinate system; The step of constructing a first lane line fitting point set based on the first lane line data and constructing a second lane line fitting point set based on the second lane line data includes: Constructing a first fitting function between the distance from each first lane line point in the first lane line coordinate set to the starting point of the target lane line segment and the coordinates of each first lane line point; constructing a second fitting function between the distance from each second lane line point in the second lane line coordinate set to the starting point of the target lane line segment and the coordinates of each second lane line point; Calculate a first fitting curve of the target lane segment based on the first fitting function, and calculate a second fitting curve of the target lane segment based on the second fitting function; The first fitting curve is sampled to obtain a first fitting point set, and the second fitting curve is sampled to obtain a second fitting point set.

2. The heading angle confidence determination method according to claim 1, wherein: The constructing a first fitting function of the distance from each first lane line point in the first lane line coordinate set to the starting point of the target lane line segment and the coordinates of each first lane line point includes: A first abscissa fitting function and a first ordinate fitting function are constructed by taking the distance from each first lane line point in the first lane line coordinate set to the starting point of the target lane line segment as the independent variable and the abscissa and ordinate of the first lane line point as the dependent variable.

3. The heading angle confidence determination method according to claim 1, wherein: The constructing a second fitting function of the distance from each second lane line point in the second lane line coordinate set to the starting point of the target lane line segment and the coordinates of each second lane line point includes: A second abscissa fitting function and a second ordinate fitting function are constructed by taking the distance from each second lane line point in the second lane line coordinate set to the starting point of the target lane line segment as the independent variable and the abscissa and ordinate of the second lane line point as the dependent variables.

4. The heading angle confidence determination method according to claim 1, wherein: Calculating a deviation angle of the vehicle heading angle based on the rotation matrix, and determining a confidence level of the vehicle heading angle based on the deviation angle, includes: Performing Euler angle conversion on the rotation matrix to determine the deviation angle of the vehicle heading angle; When the deviation angle is greater than a preset angle threshold for a consecutive preset number of times, determining that the confidence level of the vehicle heading angle is in an abnormal state; When the deviation angle is less than or equal to a preset angle threshold for a consecutive preset number of times, it is determined that the confidence level of the vehicle heading angle is in a normal state.

5. A heading angle confidence judgment device, applicable to the heading angle confidence judgment method according to any one of claims 1 to 4, characterized in that: include: A data acquisition module, configured to acquire data of a first lane line and a second lane line of a road on which the vehicle is located; the data of the first lane line and the data of the second lane line are acquired in different ways; a fitting module, configured to construct a first fitting point set for lane lines based on the first lane line data, and to construct a second fitting point set for the lane lines based on the second lane line data; perform point cloud registration on the first fitting point set and the second fitting point set to determine a rotation matrix that meets preset registration requirements; A judgment module is used to calculate a deviation angle of the vehicle heading angle based on the rotation matrix, and determine a confidence level of the vehicle heading angle based on the deviation angle.

6. An electronic device, characterized in that: comprising a memory and a processor, wherein, The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the heading angle confidence judgment method described in any one of claims 1 to 4 above.

7. A computer-readable storage medium, characterized in that Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the heading angle confidence judgment method described in any one of claims 1 to 4 above.

Images