Curve identification methods, devices, equipment and storage media

Abstract

This application discloses a curve recognition method, apparatus, device, and storage medium, relating to the field of autonomous driving technology. The curve recognition method includes: acquiring the coordinates of data points of the lane virtual centerline within a preset distance in front of the vehicle in the vehicle's coordinate system; determining the filtered curvature radius dataset of the lane virtual centerline based on the coordinates in the vehicle's coordinate system; traversing the filtered curvature radius dataset to obtain the sampling point index information and the filtered curvature radius of the current sampling point, and determining the curve segment start point information and curve segment end point information based on the sampling point index information and the filtered curvature radius of the sampling point; and determining the target curve segment information based on the curve segment start point information and curve segment end point information to complete curve recognition. The solution of this application can achieve real-time recognition of continuous curve information within a certain range in front of the vehicle.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to curve recognition methods, devices, equipment and storage media. Background Technology

[0002] Autonomous driving technology is rapidly developing, enabling vehicles to intelligently perceive roads, traffic, and the environment while driving, thereby improving driving safety and comfort. Curves are a challenging aspect of driving, especially at high speeds or in complex road conditions; navigating curves is crucial for driving safety.

[0003] Existing autonomous driving or advanced driver assistance systems (ADAS) typically monitor road conditions ahead of the vehicle in real time using sensors such as cameras and lidar. Although some systems can detect changes in curvature before entering a curve and trigger speed adjustments, their reaction time is limited, and their ability to anticipate curve characteristics is insufficient, making it impossible to implement optimal early deceleration and passage strategies. Therefore, how to identify continuous curve information within a certain range ahead of the vehicle in real time has become an unsolved problem.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a curve recognition method, device, equipment, and storage medium, aiming to solve the technical problem of how to identify continuous curve information within a certain range in front of a vehicle in real time.

[0006] To achieve the above objectives, this application proposes a curve recognition method, the method comprising:

[0007] Obtain the coordinates of the data points of the virtual center line of the lane within a preset distance in front of the vehicle in the vehicle's coordinate system;

[0008] The filtered curvature radius dataset of the lane virtual centerline is determined based on the coordinates in the vehicle coordinate system.

[0009] Traverse the filtered curvature radius dataset to obtain the sampling point index information and the filtered curvature radius of the current sampling point, and determine the starting point information and ending point information of the curve segment based on the sampling point index information and the filtered curvature radius of the sampling point;

[0010] The target curve segment information is determined based on the curve segment start point information and the curve segment end point information to complete curve identification.

[0011] In one embodiment, the step of determining the start point information and end point information of the curve segment based on the sampling point index information and the sampling point filter curvature radius includes:

[0012] When the filter curvature radius is less than the set curve curvature radius threshold, the current sampling point is determined as the curve starting point, and the first longitudinal distance and the first sampling point index of the curve starting point are obtained to obtain the curve segment starting point information, and the curve segment curvature radius dataset is initialized based on the curve segment starting point information.

[0013] The next sampling point is updated to the current sampling point, and the filtered curvature radius of the current sampling point is stored in the curve segment curvature radius dataset. This process continues until the filtered curvature radius is greater than or equal to the set curve curvature radius threshold. The previous sampling point of the current sampling point is determined as the curve termination point, and the second longitudinal distance and the second sampling point index of the curve termination point are obtained to get the curve segment termination point information.

[0014] In one embodiment, the step of determining the target curve segment information based on the curve segment start point information and the curve segment end point information to complete curve identification includes:

[0015] The length of the curve segment is determined based on the starting point information and ending point information of the curve segment.

[0016] When the length of the curve segment is greater than or equal to the curve length threshold, the curve segment is designated as the target curve segment.

[0017] Obtain the curve information of the target curve segment to complete the curve identification.

[0018] In one embodiment, the step of acquiring the curve information of the target curve segment to obtain the target curve segment information and complete the curve identification includes:

[0019] Obtain the curvature radius dataset of the target curve segment;

[0020] The target radius of curvature of the curve segment is determined based on the curve segment radius of curvature dataset.

[0021] The starting point information of the curve segment, the ending point information of the curve segment, and the target radius of curvature of the curve segment are stored in the curve segment dataset to obtain the target curve segment information, thereby completing the curve identification.

[0022] In one embodiment, the step of determining the filtered curvature radius dataset of the lane virtual centerline based on the coordinates in the vehicle coordinate system includes:

[0023] The lane curvature radius of the sampling point of the virtual center line of the lane is determined based on the coordinates in the vehicle coordinate system.

[0024] The lane curvature radius of the sampling points is smoothed and filtered to obtain a filtered curvature radius dataset, which includes sampling point index information and filtered curvature radius.

[0025] In one embodiment, the step of determining the lane curvature radius of the sampling point of the lane virtual centerline based on the coordinates in the vehicle coordinate system includes:

[0026] The lane curvature radius of the sampling point of the virtual center line of the lane is determined based on the coordinates in the vehicle coordinate system.

[0027] The lane virtual centerline is uniformly sampled according to the lane line fitting equation to obtain the rectangular coordinates of the sampling points;

[0028] The radius of curvature of the lane at the sampling point is determined based on the rectangular coordinates of the sampling point.

[0029] In one embodiment, the step of obtaining the coordinates of the data points of the virtual center line of the lane within a preset distance in front of the vehicle in the vehicle's coordinate system includes:

[0030] Obtain the vehicle's latitude and longitude coordinates, vehicle's heading angle information, and the latitude and longitude coordinates of the shape point of the virtual center line of the lane within a preset distance in front of the vehicle;

[0031] The latitude and longitude coordinates of the shape point are converted into coordinates in the vehicle coordinate system based on the vehicle's latitude and longitude coordinates and the vehicle's heading angle information.

[0032] Furthermore, to achieve the above objectives, this application also proposes a curve recognition device, which includes:

[0033] The information acquisition module is used to acquire the coordinates of the data points of the virtual center line of the lane within a preset distance in front of the vehicle in the vehicle's coordinate system;

[0034] The curvature calculation module determines the filtered curvature radius dataset of the lane virtual centerline based on the coordinates in the vehicle coordinate system.

[0035] The information recognition module is used to traverse the filtered curvature radius dataset, obtain the sampling point index information and the filtered curvature radius of the current sampling point, and determine the starting point information and ending point information of the curve segment based on the sampling point index information and the filtered curvature radius of the sampling point.

[0036] The curve determination module is used to determine the target curve segment information based on the curve segment start point information and the curve segment end point information, so as to complete the curve identification.

[0037] In addition, to achieve the above objectives, this application also proposes a curve recognition device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the curve recognition method as described above.

[0038] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the curve recognition method described above.

[0039] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the curve recognition method described above.

[0040] One or more technical solutions proposed in this application have at least the following technical effects:

[0041] The system acquires the coordinates of data points representing the virtual centerline of the lane within a preset distance ahead of the vehicle in the vehicle's coordinate system; determines the filtered curvature radius dataset of the virtual centerline based on these coordinates; iterates through the filtered curvature radius dataset to obtain the sampling point index information and the filtered curvature radius of the current sampling point, and determines the start and end points of the curve segment based on these information; finally, it determines the target curve segment information based on the start and end points of the curve segment. Curve recognition involves processing the coordinates of virtual lane centerline data points within a preset distance (e.g., 200 meters) ahead of the vehicle in the vehicle's coordinate system to obtain a filtered curvature radius dataset of the virtual lane centerline. Based on this dataset, the starting and ending points of multiple curve segments within the preset distance (e.g., 200 meters) can be determined. These curve segments are then filtered to identify target curve segments that meet the criteria, enabling early identification of continuous curves. Real-time identification of continuous curves within a certain range ahead of the vehicle during autonomous driving allows for early detection of key curve characteristics. This, combined with the autonomous driving control module and vehicle dynamic stability module, enables appropriate deceleration control before entering a curve, reducing safety hazards caused by excessive speed and improving the availability and reliability of the autonomous driving system. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart illustrating an embodiment of the curve recognition method of this application.

[0045] Figure 2 This is a flowchart of curve judgment provided in Embodiment 1 of the curve recognition method of this application;

[0046] Figure 3 This is a flowchart of the final curve processing provided in Embodiment 1 of the curve recognition method of this application;

[0047] Figure 4 This is a flowchart illustrating Embodiment 2 of the curve recognition method of this application;

[0048] Figure 5 This is a schematic diagram of the module structure of the curve recognition device according to an embodiment of this application;

[0049] Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in the curve recognition method in this application embodiment.

[0050] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0051] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0052] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0053] The main solution of this application embodiment is as follows: Obtain the coordinates of data points of the virtual centerline of the lane within a preset distance in front of the vehicle in the vehicle's coordinate system; determine the filtered curvature radius dataset of the virtual centerline of the lane based on the coordinates in the vehicle's coordinate system; traverse the filtered curvature radius dataset to obtain the sampling point index information and the filtered curvature radius of the current sampling point, and determine the starting point information and ending point information of the curve segment based on the sampling point index information and the filtered curvature radius of the sampling point; determine the target curve segment information based on the starting point information and the ending point information of the curve segment, thereby completing curve recognition.

[0054] In this embodiment, for ease of description, the following description will focus on the vehicle identification end as the execution subject.

[0055] Autonomous driving technology is rapidly developing, enabling vehicles to intelligently perceive roads, traffic, and the environment while driving, thereby improving driving safety and comfort. Curves are a challenging aspect of driving, especially at high speeds or in complex road conditions; navigating curves is crucial for driving safety.

[0056] Existing autonomous driving or advanced driver assistance systems (ADAS) typically monitor road conditions ahead of the vehicle in real time using sensors such as cameras and lidar. Although some systems can detect changes in curvature before entering a curve and trigger speed adjustments, their reaction time is limited, and their ability to anticipate curve characteristics is insufficient, making it impossible to implement optimal early deceleration and passage strategies. Therefore, how to identify continuous curve information within a certain range ahead of the vehicle in real time has become an unsolved problem.

[0057] This application provides a solution that can identify continuous curves within a certain range in front of a vehicle in real time. For multiple curves within a set distance range in front, it can identify them sequentially and provide parameter information for each curve, updating the curve information in real time as the vehicle is driving.

[0058] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or vehicle terminal capable of performing the above functions. The following description uses a vehicle terminal as an example to illustrate this embodiment and the subsequent embodiments.

[0059] Based on this, the embodiments of this application provide a curve recognition method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the curve recognition method of this application.

[0060] In this embodiment, the curve recognition method includes steps S10 to S40:

[0061] Step S10: Obtain the coordinates of the data points of the virtual center line of the lane within a preset distance in front of the vehicle in the vehicle's coordinate system;

[0062] It should be noted that the curve recognition method in this application is aimed at scenarios where Intelligent Connected Autonomous Vehicles (ICA) need to decelerate in advance when entering curves. It can identify key curve parameters (such as curve distance, radius of curvature, and length) during vehicle operation, allowing for appropriate deceleration before entering the curve. Existing autonomous driving solutions often rely on real-time lane detection and prediction to handle the complexities of curves. However, this approach, due to insufficient road information, often carries the risk of excessive entry speed into curves, limiting curve passability and vehicle safety. Especially in small-radius or continuous sharp curves, the system is prone to under-adjustment or slow response, affecting vehicle stability. The solution in this application obtains the coordinates of the virtual centerline data points of the lane within a preset distance (e.g., 200 meters) in the vehicle's coordinate system, enabling the sequential identification of multiple curves and providing parameter information for each curve, which is updated in real-time during vehicle operation.

[0063] It should be noted that the virtual centerline of the lane is an idealized centerline for each lane, representing the central trajectory of the vehicle. Data points for the virtual centerline within a preset distance (e.g., 200 meters) in front of the vehicle can be obtained from Lane-level Detail (LD) map information. The data points in the LD map can be converted into coordinates in the vehicle's coordinate system using the vehicle's positioning information. This vehicle coordinate system is the rear axle center coordinate system, with the rear axle center as the origin. The x-axis points forward along the vehicle's length, the y-axis points to the left along the vehicle's width, and the z-axis is perpendicular to the ground and points upward.

[0064] Step S20: Determine the filter curvature radius dataset of the lane virtual centerline based on the coordinates in the vehicle coordinate system;

[0065] It should be noted that the filtered curvature radius dataset contains the filtered curvature radii of the sampled points of the lane's virtual centerline within a preset distance in front of the vehicle. The curvature radius describes the degree of curvature of the lane's virtual centerline; the smaller the curvature radius, the greater the curvature of the lane's virtual centerline at that point. After obtaining the coordinates of the lane's virtual centerline data points in the vehicle's coordinate system, the initial curvature radius data of the lane's virtual centerline can be obtained using a fitting algorithm such as polynomial fitting. Smoothing the initial curvature radius dataset using a filtering algorithm can reduce the influence of noise and errors, resulting in a more accurate filtered curvature radius dataset.

[0066] In one feasible implementation, step S20 may include steps S21 to S22:

[0067] Step S21: Determine the lane curvature radius of the sampling point of the lane virtual centerline based on the coordinates in the vehicle coordinate system;

[0068] It should be noted that a cubic polynomial equation can be used to fit the coordinates of the data points of the virtual center line of the lane in the vehicle coordinate system to obtain the equation of the virtual center line of the lane. Then, the virtual center line of the lane can be uniformly sampled according to the equation to obtain the radius of curvature of the lane line at each sampling point.

[0069] In one feasible implementation, step S21 may include: fitting the virtual center line of the lane to the coordinates in the vehicle coordinate system to obtain a lane line fitting equation; uniformly sampling the virtual center line of the lane to obtain the rectangular coordinates of the sampling points; and determining the lane curvature radius of the sampling points based on the rectangular coordinates of the sampling points.

[0070] It should be noted that the cubic polynomial equation y = C3x is used. 3 +C2x 2 By fitting the coordinates of the data points of the virtual centerline of the lane in the vehicle coordinate system using +C1x+C0, the cubic fitting parameters [C0, C1, C2, C3] of the virtual centerline can be obtained, and the lane fitting equation can be determined. Specifically, based on the coordinates of the data points of the virtual centerline, an objective function can be constructed using the least squares method or other optimization algorithms to measure the sum of the squares of the vertical distances from all data points to the fitted curve. By minimizing this objective function, the optimal cubic fitting parameters [C0, C1, C2, C3] are obtained.

[0071] It should be understood that the lane line fitting equation y = C3x is obtained. 3 +C2x 2 After adding C1x and C0, the virtual centerline of the lane can be uniformly sampled according to the lane line fitting equation. This involves selecting a series of equally spaced points on the virtual centerline to obtain the rectangular coordinates [x0, y0] of each sampling point. The lane line curvature value ρ for each sampling point can be calculated using the following curvature calculation formula:

[0072]

[0073] Where x0 is the X coordinate of the sampling point, and y0 is the Y coordinate calculated by a cubic polynomial equation.

[0074] After obtaining the lane curvature value ρ at each sampling point, the radius of curvature R at each sampling point can be calculated using the following formula:

[0075] R = 1 / ρ

[0076] The larger the radius of curvature, the less curved the virtual center line of the lane is at that point; the smaller the radius of curvature, the more curved the virtual center line of the lane is at that point.

[0077] Step S22: Perform smoothing filtering on the lane curvature radius of the sampling points to obtain a filtered curvature radius dataset, which includes sampling point index information and filtered curvature radius.

[0078] It should be noted that, to avoid the noise impact of a few sampling points with large and small curvatures and to reduce the error in curve parameter calculation, it is necessary to perform smoothing filtering on the lane curvature radius of the sampling points on the virtual centerline of the lane within a preset distance (e.g., 200 meters) in front of the vehicle, to obtain a filtered curvature radius dataset. Specifically, a smoothing filtering algorithm can be used to smooth the coordinate points uniformly sampled on the virtual centerline of the lane. The sliding window size is set to 5, and 5 sampling points are taken before and after (including) the sampling point to be processed each time. The curvature radius value of the sampling point to be processed is taken as the average of the curvature radii of these 5 sampling points, and the filtered curvature radius of that sampling point is obtained. After performing the above smoothing filtering process on all sampling points on the virtual centerline of the lane in sequence, the filtered curvature radius dataset is obtained. The filtered curvature radius dataset is stored in the form of an array, including the index of each sampling point (i.e., sampling point index information) and the corresponding filtered curvature radius value (i.e., filtered curvature radius).

[0079] Step S30: Traverse the filtered curvature radius dataset, obtain the sampling point index information and the filtered curvature radius of the current sampling point, and determine the starting point information and ending point information of the curve segment based on the sampling point index information and the filtered curvature radius of the sampling point;

[0080] It should be noted that by traversing the filtered curvature radius dataset, the index information and corresponding filtered curvature radius of each sampling point can be obtained. By comparing the filtered curvature radius of each sampling point with the small curve curvature radius threshold, the start and end points of multiple curve segments in the filtered curvature radius dataset can be determined. Specifically, when the filtered curvature radius decreases from a large value (i.e., a relatively straight road segment) to below the small curve curvature radius threshold, the sampling point below the small curve curvature radius threshold can be determined as the start point of the curve segment, thus obtaining the curve segment start point information. Conversely, when the curvature radius recovers from a small value (i.e., below the small curve curvature radius threshold) to a value not less than the small curve curvature radius threshold, the previous sampling point of the sampling point not less than the small curve curvature radius threshold can be determined as the end point of the curve segment, thus obtaining the curve segment end point information.

[0081] In one feasible implementation, step S30, which determines the curve segment start point information and curve segment end point information based on the sampling point index information and the sampling point filter curvature radius, may include: when the filter curvature radius is less than a set curve curvature radius threshold, determining the current sampling point as the curve start point, and obtaining the first longitudinal distance and the first sampling point index of the curve start point to obtain the curve segment start point information, and initializing the curve segment curvature radius dataset based on the curve segment start point information; updating the next sampling point to the current sampling point, and storing the filter curvature radius of the current sampling point in the curve segment curvature radius dataset, until the filter curvature radius is greater than or equal to the set curve curvature radius threshold, determining the previous sampling point of the current sampling point as the curve end point, and obtaining the second longitudinal distance and the second sampling point index of the curve end point to obtain the curve segment end point information.

[0082] It should be noted that the curve curvature radius threshold is set as a small curve curvature radius threshold to determine whether the lane line has begun to enter the curve. During the curve recognition process, the filtered curvature radius dataset is traversed, and the filtered curvature radius of each sampling point is compared with the set curve curvature radius threshold. When the filtered curvature radius of the first current sampling point is less than the set small curve curvature radius threshold, the sampling point is determined to be the curve starting point, and the longitudinal distance of the starting point is obtained as the first longitudinal distance. The index of the starting point in the filtered sampling point array (i.e., the filtered curvature radius dataset) is obtained to obtain the first sampling point index. At the same time, based on the first sampling point index, the filtered curvature radius of the starting point is obtained from the filtered curvature radius dataset, and the curve segment curvature radius dataset of the current curve segment is initialized.

[0083] It should be understood that after determining a sampling point as the starting point of the curve, the filtered curvature radii of all sampling points starting from that sampling point that are less than the set small curve curvature radius threshold will be recorded sequentially according to the first sampling point index. This will result in a curve segment curvature radius dataset including all curvature radius values ​​of the current curve segment, which will be stored in array form. This process continues until the filtered curvature radius of the current sampling point is greater than or equal to the small curve curvature radius threshold. The previous sampling point of the current sampling point will then be determined as the curve termination point, and the longitudinal distance of the termination point will be obtained as the second longitudinal distance. The index of the termination point in the filtered sampling point array (i.e., the filtered curvature radius dataset) will be obtained to get the second sampling point index.

[0084] Additionally, it should be understood that the first longitudinal distance, i.e., the Y-coordinate of the sampling point determined as the starting point of the curve, is calculated using the lane line fitting equation, and the second longitudinal distance, i.e., the Y-coordinate of the sampling point determined as the ending point of the curve, is calculated using the lane line fitting equation. By traversing each sampling point in the filtered curvature radius dataset, the starting point information, ending point information, and curvature radius dataset of multiple curve segments within a preset distance (e.g., 200 meters) in front of the vehicle can be obtained.

[0085] Step S40: Determine the target curve segment information based on the curve segment start point information and the curve segment end point information to complete curve identification.

[0086] It should be understood that the starting point information of a curve segment includes the longitudinal distance of the starting point and the index of the starting point in the filtered sample point array (i.e., the filtered curvature radius dataset). The ending point information of a curve segment includes the longitudinal distance of the ending point and the index of the ending point in the filtered sample point array (i.e., the filtered curvature radius dataset). Based on the starting and ending point information of the curve segments, the length information of each curve segment can be calculated. Based on the length information of the curve segments, shorter curve segments can be filtered to obtain the curve information of the target curve segment (such as curve distance, radius, and length), so as to complete the identification of multiple curves within a preset distance (e.g., 200 meters) in front of the vehicle.

[0087] In one feasible implementation, step S40 may include steps S41 to S43:

[0088] Step S41: Determine the length of the curve segment based on the starting point information and ending point information of the curve segment.

[0089] It should be understood that the longitudinal distance from the starting point of the curve segment can be determined based on the information of the starting point of the curve segment, and the longitudinal distance from the ending point of the curve segment can be determined based on the information of the ending point of the curve segment. The simplified representation of the curve segment length can be obtained by calculating the difference in longitudinal distance between the ending point and the starting point.

[0090] Step S42: When the length of the curve segment is greater than or equal to the curve length threshold, the curve segment is designated as the target curve segment.

[0091] It should be understood that after obtaining the lengths of multiple curve segments, the curve segments are filtered based on their lengths to remove curves that are too short and have little impact on driving. This reduces the amount of data that the vehicle needs to process during autonomous driving, improving the system's response speed and real-time performance. The curve length threshold is the minimum curve length threshold. Curve segments with a length greater than or equal to the minimum curve length threshold are considered eligible curves, i.e., target curve segments. Curve segments with a length less than the minimum curve length threshold are considered too short and need to be filtered.

[0092] Step S43: Obtain the curve information of the target curve segment to complete the curve identification.

[0093] It should be noted that the curve information of the target curve segment includes the curve segment start point information, curve segment end point information, minimum radius of curvature, and average radius of curvature.

[0094] In one feasible implementation, step S43 may include: acquiring a curve segment curvature radius dataset of the target curve segment; determining the target curvature radius of the curve segment based on the curve segment curvature radius dataset; storing the curve segment start point information, the curve segment end point information, and the target curvature radius of the curve segment into the curve segment dataset to obtain the target curve segment information, thereby completing curve identification.

[0095] It should be understood that the average radius of curvature of the target curve segment can be calculated based on the curve segment curvature radius dataset, and the minimum radius of curvature of the current curve segment can be determined from this dataset to obtain the target radius of curvature of the curve segment. By storing the curve segment start point information, curve segment end point information, and target radius of curvature of the target curve segment in the curve segment dataset as an array, the target curve segment information can be obtained. During autonomous driving, the curve information of the target curve segment can be identified and updated in real time. Before the vehicle enters the curve segment, key parameters such as the curve distance, radius of curvature, and length of the upcoming curve segment can be obtained based on the pre-updated and stored target curve segment information. Combining the curve radius and length information, the vehicle speed can be dynamically adjusted. Before the vehicle approaches the curve, it can be gradually decelerated to ensure that the vehicle enters the curve at a safe speed, making the driving process smoother and improving passenger comfort.

[0096] For example, refer to Figure 2 , Figure 2 This is a flowchart illustrating the curve recognition method provided in Embodiment 1 of the present application. Figure 2As shown, after smoothing the curvature radius of the sampling points along the virtual centerline of the lane to obtain the filtered curvature radius array (i.e., the filtered curvature radius dataset), the curvature radius array is traversed to obtain the curvature radius of the current sampling point. It is then determined whether the curvature radius of the sampling point is less than the curve curvature radius threshold. If the curvature radius of the sampling point is less than the small curve curvature radius threshold, the curvature radius of the sampling point is stored in the curvature radius array (i.e., the curvature radius dataset) to which the current curve segment belongs. If the curve flag in_curve is not true (indicating that the current sampling point is the curve starting point), the longitudinal distance and index information of the new curve starting point are stored, and in_curve is set to true to start recording the information of the new curve segment. If the curve flag in_curve is true (indicating that the current sampling point is a continuously recorded sampling point less than the small curve curvature radius threshold), the next sampling point is traversed. If the radius of curvature of the sampling point is not less than the small curve radius of curvature threshold, and the curve flag in_curve is true, store the longitudinal distance and index information of the current curve segment termination point, calculate the curve segment length, end the curve information recording of the current curve segment, set the curve flag in_curve to false, and check whether the radius of curvature array to which the current curve segment belongs is empty. If the radius of curvature array to which the current curve segment belongs is not empty, calculate and store the minimum and average radii of curvature of the current curve segment (i.e., the target radius of curvature of the curve segment). When the length of the current curve segment is not less than the minimum curve length, take the current curve segment as the target curve segment and store the current curve segment information in the curve segment array.

[0097] Additionally, it should be noted that the solution in this application will identify all curves within a preset distance (e.g., 200 meters) ahead of the vehicle. If the sampling point at the end of the identification distance is located within a curve, meaning the current curve has not yet ended, that section of the curve needs to be processed separately, referring to... Figure 3 , Figure 3 This is a flowchart illustrating the final curve processing steps provided in Embodiment 1 of the curve recognition method of this application. Figure 3 As shown, for each sampling point in the filtered radius of curvature array, it checks whether the curve flag `in_curve` is true and whether the radius of curvature array to which the current curve segment belongs is not empty. If the curve flag `in_curve` is true and the radius of curvature array to which the current curve segment belongs is not empty, it stores the longitudinal distance and index information of the current curve segment's termination point, calculates the curve length, minimum and average radius of curvature, ends the recording of the curve information for the current curve segment, and checks whether the length of the current curve segment is not less than the minimum curve length. If the length of the current curve segment is not less than the minimum curve length, it determines the current curve segment as the target curve segment, stores the current curve segment information in the curve segment array, and ends the curve detection.

[0098] This embodiment provides a curve recognition method, which acquires the coordinates of data points of the virtual centerline of the lane within a preset distance in front of the vehicle in the vehicle's coordinate system; determines the filtered curvature radius dataset of the virtual centerline of the lane based on the coordinates in the vehicle's coordinate system; traverses the filtered curvature radius dataset to acquire the sampling point index information and the filtered curvature radius of the current sampling point, and determines the curve segment start point information and curve segment end point information based on the sampling point index information and the filtered curvature radius of the sampling point; and determines the target based on the curve segment start point information and curve segment end point information. Curve segment information is used to complete curve recognition. By processing the coordinates of data points of the lane virtual centerline within a preset distance (e.g., 200 meters) in the vehicle's coordinate system, a filtered curvature radius dataset of the lane virtual centerline is obtained. Based on the filtered curvature radius dataset, the start and end points of multiple curve segments within the preset distance (e.g., 200 meters) can be determined. Then, based on the start and end point information of the curve segments, multiple curve segments are filtered to obtain the curve information of target curve segments that meet the conditions, realizing the early recognition of continuous curves. In the process of autonomous driving, real-time recognition of continuous curve information within a certain range in front of the vehicle can detect the key characteristics of curves in advance. Combined with the autonomous driving control module and the vehicle dynamic stability module, appropriate deceleration control can be implemented before entering the curve, reducing safety hazards caused by excessive speed and improving the availability and reliability of the autonomous driving system.

[0099] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 4 Step S10 may include steps S11 to S12:

[0100] Step S11: Obtain the latitude and longitude coordinates of the vehicle, the heading angle of the vehicle, and the latitude and longitude coordinates of the shape point of the virtual center line of the lane within a preset distance in front of the vehicle;

[0101] It should be noted that the data acquisition in this application relies on map positioning technology. Lane-level positioning and map road topology relationships allow for the acquisition of LD map information within a preset distance (e.g., 200 meters) in front of the vehicle. Based on the LD map information, the vehicle's lane can be located, the virtual centerline of the lane can be identified, and the latitude and longitude coordinates of the virtual centerline within the preset distance in front of the vehicle can be obtained. The LD map information includes map data with detailed road and lane information, such as lane topology data (e.g., lane connections, intersection information, etc.).

[0102] Specifically, based on the vehicle's current Global Positioning System (GPS) coordinates and lane-level positioning systems such as high-precision maps combined with Inertial Measurement Unit (IMU) sensors and LiDAR, the specific lane information of the vehicle can be determined. Combined with the topological data in the LD map information, the shapepoint latitude and longitude coordinates of the lane's virtual centerline within a preset distance ahead of the vehicle can be obtained. Shapepoints are data points on the lane's virtual centerline obtained from the LD map information, used to fit the shape of the lane's virtual centerline, thus describing the lane's specific shape and location. The shapepoint latitude and longitude coordinates represent the longitude and latitude positions of the corresponding data points on the lane's virtual centerline in the geographic coordinate system within the LD map. The vehicle's latitude and longitude coordinates represent the vehicle's current position in the geographic coordinate system, which can be obtained through GPS, indicating the vehicle's geographical location. The vehicle heading angle information includes the direction angle information of the vehicle relative to geographic north (or the Earth coordinate system), which describes the orientation of the vehicle's forward direction, that is, the orientation or driving direction of the vehicle, and can be measured by the vehicle's sensors such as IMU.

[0103] Step S12: Convert the latitude and longitude coordinates of the shape point into coordinates in the vehicle coordinate system based on the vehicle's latitude and longitude coordinates and the vehicle's heading angle information.

[0104] It should be noted that, based on the vehicle's latitude and longitude coordinates and heading angle information, mathematical algorithms (such as rotation matrices or coordinate transformation formulas) can be used to convert the latitude and longitude coordinates of each point on the virtual centerline of the lane into coordinates in the vehicle's coordinate system. Specifically, the relative position difference between the vehicle's latitude and longitude coordinates and the latitude and longitude coordinates of each point can be calculated to obtain the horizontal and vertical distances of the point relative to the vehicle. Based on the vehicle's heading angle, the relative positions of the points are rotated according to this angle to match the orientation of the vehicle's coordinate system, thus obtaining the coordinates of the data points on the virtual centerline of the lane in the vehicle's coordinate system.

[0105] This embodiment provides a curve recognition method, which obtains the latitude and longitude coordinates of the vehicle, the heading angle information of the vehicle, and the latitude and longitude coordinates of the shape point of the virtual center line of the lane within a preset distance in front of the vehicle; based on the latitude and longitude coordinates of the vehicle and the heading angle information, the latitude and longitude coordinates of the shape point are converted into coordinates in the vehicle coordinate system. By accurately obtaining the geographical location (latitude and longitude coordinates) and direction (heading angle information) of the vehicle, and combining them with the latitude and longitude coordinates of the shape point of the virtual center line of the lane within a preset distance in front of the vehicle, the precise positioning of the virtual center line of the lane in the vehicle coordinate system can be achieved.

[0106] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the curve recognition method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0107] This application also provides a curve recognition device, please refer to... Figure 5 The curve recognition device includes:

[0108] Information acquisition module 10 is used to acquire the coordinates of data points of the virtual center line of the lane within a preset distance in front of the vehicle in the vehicle coordinate system;

[0109] Curvature calculation module 20 determines the filtered curvature radius dataset of the lane virtual centerline based on the coordinates in the vehicle coordinate system;

[0110] The information recognition module 30 is used to traverse the filtered curvature radius dataset, obtain the sampling point index information and the filtered curvature radius of the current sampling point, and determine the starting point information and ending point information of the curve segment based on the sampling point index information and the filtered curvature radius of the sampling point.

[0111] The curve determination module 40 is used to determine the target curve segment information based on the curve segment start point information and the curve segment end point information, so as to complete the curve identification.

[0112] In one embodiment, the information recognition module 30 is further configured to: determine the current sampling point as the starting point of the curve when the filtered curvature radius is less than a set curve curvature radius threshold; obtain the first longitudinal distance and the first sampling point index of the starting point of the curve to obtain curve segment starting point information; initialize the curve segment curvature radius dataset based on the curve segment starting point information; update the next sampling point to the current sampling point; and store the filtered curvature radius of the current sampling point in the curve segment curvature radius dataset until the filtered curvature radius is greater than or equal to the set curve curvature radius threshold; determine the previous sampling point of the current sampling point as the curve ending point; and obtain the second longitudinal distance and the second sampling point index of the curve ending point to obtain curve segment ending point information.

[0113] In one embodiment, the curve determination module 40 is further configured to determine the curve length of the curve segment based on the curve segment start point information and the curve segment end point information; when the curve length of the curve segment is greater than or equal to a curve length threshold, the curve segment is designated as a target curve segment; and the curve information of the target curve segment is obtained to complete the curve identification.

[0114] In one embodiment, the curve determination module 40 is further configured to acquire a curve segment curvature radius dataset of the target curve segment; determine the target curvature radius of the curve segment based on the curve segment curvature radius dataset; and store the curve segment start point information, the curve segment end point information, and the target curvature radius of the curve segment into the curve segment dataset to obtain the target curve segment information, thereby completing the curve identification.

[0115] In one embodiment, the curvature calculation module 20 is further configured to determine the lane curvature radius of the sampling point of the lane virtual centerline based on the coordinates in the vehicle coordinate system; and to perform smoothing filtering on the lane curvature radius of the sampling point to obtain a filtered curvature radius dataset, wherein the filtered curvature radius dataset includes sampling point index information and filtered curvature radius.

[0116] In one embodiment, the curvature calculation module 20 is further configured to perform lane line fitting on the virtual center line of the lane based on the coordinates in the vehicle coordinate system to obtain a lane line fitting equation; perform uniform sampling on the virtual center line of the lane based on the lane line fitting equation to obtain the rectangular coordinates of the sampling points; and determine the lane curvature radius of the sampling points based on the rectangular coordinates of the sampling points.

[0117] In one embodiment, the information acquisition module 10 is further configured to acquire the latitude and longitude coordinates of the vehicle, the heading angle information of the vehicle, and the latitude and longitude coordinates of the shape point of the virtual center line of the lane within a preset distance in front of the vehicle; and convert the latitude and longitude coordinates of the shape point into coordinates in the vehicle coordinate system according to the latitude and longitude coordinates of the vehicle and the heading angle information of the vehicle.

[0118] The curve recognition device provided in this application, employing the curve recognition method in the above embodiments, can solve the technical problem of how to identify continuous curve information within a certain range in front of a vehicle in real time. Compared with the prior art, the beneficial effects of the curve recognition device provided in this application are the same as those of the curve recognition method provided in the above embodiments, and other technical features in the curve recognition device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0119] This application provides a curve recognition device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the curve recognition method in Embodiment 1 above.

[0120] The following is for reference. Figure 6The diagram illustrates a structural schematic suitable for implementing the curve recognition device of the embodiments of this application. The curve recognition device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The curve recognition device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0121] like Figure 6 As shown, the curve recognition device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the curve recognition device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the cornering identification device to communicate wirelessly or wiredly with other devices to exchange data. Although cornering identification devices with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0122] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0123] The curve recognition device provided in this application, employing the curve recognition method in the above embodiments, can solve the technical problem of how to identify continuous curve information within a certain range in front of a vehicle in real time. Compared with the prior art, the beneficial effects of the curve recognition device provided in this application are the same as those of the curve recognition method provided in the above embodiments, and other technical features of this curve recognition device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0124] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0125] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0126] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the curve recognition method in the above embodiments.

[0127] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0128] The aforementioned computer-readable storage medium may be included in the curve recognition device; or it may exist independently and not assembled into the curve recognition device.

[0129] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the curve recognition device, the curve recognition device: acquires the coordinates of data points of the lane virtual centerline within a preset distance in front of the vehicle in the vehicle's coordinate system; determines the filtered curvature radius dataset of the lane virtual centerline based on the coordinates in the vehicle's coordinate system; traverses the filtered curvature radius dataset, acquires the sampling point index information and the sampling point filtered curvature radius, and determines the curve segment start point information and curve segment end point information based on the sampling point index information and the sampling point filtered curvature radius; and determines the target curve segment information based on the curve segment start point information and the curve segment end point information, thereby completing curve recognition.

[0130] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0131] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0132] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0133] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described curve recognition method, and can solve the technical problem of how to identify continuous curve information within a certain range in front of a vehicle in real time. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the curve recognition method provided in the above embodiments, and will not be repeated here.

[0134] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the curve recognition method described above.

[0135] The computer program product provided in this application can solve the technical problem of how to identify continuous curves within a certain range in front of a vehicle in real time. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the curve recognition method provided in the above embodiments, and will not be repeated here.

[0136] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A curve recognition method, characterized in that, The curve identification method includes: Obtain the coordinates of the data points of the virtual center line of the lane within a preset distance in front of the vehicle in the vehicle's coordinate system; The filtered curvature radius dataset of the lane virtual centerline is determined based on the coordinates in the vehicle coordinate system. Traverse the filtered curvature radius dataset to obtain the sampling point index information and the filtered curvature radius of the current sampling point, and determine the starting point information and ending point information of the curve segment based on the sampling point index information and the filtered curvature radius of the sampling point; The target curve segment information is determined based on the curve segment start point information and the curve segment end point information to complete the curve identification; The step of determining the starting point information and ending point information of the curve segment based on the sampling point index information and the sampling point filter curvature radius includes: When the filter curvature radius is less than the set curve curvature radius threshold, the current sampling point is determined as the curve starting point, and the first longitudinal distance and the first sampling point index of the curve starting point are obtained to obtain the curve segment starting point information, and the curve segment curvature radius dataset is initialized based on the curve segment starting point information. The next sampling point is updated to the current sampling point, and the filtered curvature radius of the current sampling point is stored in the curve segment curvature radius dataset. This process continues until the filtered curvature radius is greater than or equal to the set curve curvature radius threshold. The previous sampling point of the current sampling point is determined as the curve termination point, and the second longitudinal distance and the second sampling point index of the curve termination point are obtained to get the curve segment termination point information.

2. The method as described in claim 1, characterized in that, The step of determining the target curve segment information based on the curve segment start point information and the curve segment end point information to complete curve identification includes: The length of the curve segment is determined based on the starting point information and ending point information of the curve segment. When the length of the curve segment is greater than or equal to the curve length threshold, the curve segment is designated as the target curve segment. Obtain the curve information of the target curve segment to complete the curve identification.

3. The method as described in claim 2, characterized in that, The step of obtaining the curve information of the target curve segment to complete curve identification includes: Obtain the curvature radius dataset of the target curve segment; The target radius of curvature of the curve segment is determined based on the curve segment radius of curvature dataset. The starting point information of the curve segment, the ending point information of the curve segment, and the target radius of curvature of the curve segment are stored in the curve segment dataset to obtain the target curve segment information, thereby completing the curve identification.

4. The method as described in claim 1, characterized in that, The step of determining the filtered curvature radius dataset of the lane virtual centerline based on the coordinates in the vehicle coordinate system includes: The lane curvature radius of the sampling point of the virtual center line of the lane is determined based on the coordinates in the vehicle coordinate system. The lane curvature radius of the sampling points is smoothed and filtered to obtain a filtered curvature radius dataset, which includes sampling point index information and filtered curvature radius.

5. The method as described in claim 4, characterized in that, The step of determining the lane curvature radius of the sampling point of the lane virtual centerline based on the coordinates in the vehicle coordinate system includes: Based on the coordinates in the vehicle coordinate system, the lane virtual centerline is fitted to obtain the lane line fitting equation. The lane virtual centerline is uniformly sampled according to the lane line fitting equation to obtain the rectangular coordinates of the sampling points; The radius of curvature of the lane at the sampling point is determined based on the rectangular coordinates of the sampling point.

6. The method according to any one of claims 1 to 5, characterized in that, The step of obtaining the coordinates of the data points of the virtual center line of the lane within a preset distance in front of the vehicle in the vehicle's coordinate system includes: Obtain the vehicle's latitude and longitude coordinates, vehicle's heading angle information, and the latitude and longitude coordinates of the shape point of the virtual center line of the lane within a preset distance in front of the vehicle; The latitude and longitude coordinates of the shape point are converted into coordinates in the vehicle coordinate system based on the vehicle's latitude and longitude coordinates and the vehicle's heading angle information.

7. A curve recognition device, characterized in that, The device includes: The information acquisition module is used to acquire the coordinates of the data points of the virtual center line of the lane within a preset distance in front of the vehicle in the vehicle's coordinate system; The curvature calculation module determines the filtered curvature radius dataset of the lane virtual centerline based on the coordinates in the vehicle coordinate system. The information recognition module is used to traverse the filtered curvature radius dataset, obtain the sampling point index information and the filtered curvature radius of the current sampling point, and determine the starting point information and ending point information of the curve segment based on the sampling point index information and the filtered curvature radius of the sampling point. The curve determination module is used to determine the target curve segment information based on the curve segment start point information and the curve segment end point information, so as to complete the curve identification. The information recognition module is further configured to: determine the current sampling point as the curve start point when the filtered curvature radius is less than a set curve curvature radius threshold; obtain the first longitudinal distance and the first sampling point index of the curve start point to obtain curve segment start point information; initialize the curve segment curvature radius dataset based on the curve segment start point information; update the next sampling point to the current sampling point; and store the filtered curvature radius of the current sampling point in the curve segment curvature radius dataset until the filtered curvature radius is greater than or equal to the set curve curvature radius threshold; determine the previous sampling point of the current sampling point as the curve end point; and obtain the second longitudinal distance and the second sampling point index of the curve end point to obtain curve segment end point information.

8. A curve recognition device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the curve recognition method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the curve recognition method as described in any one of claims 1 to 6.

Images