Ramp speed limit identification method and device, and storage medium

Abstract

This application provides a method, device, and storage medium for identifying speed limits on ramps. The method includes: acquiring a target road image and extracting a first set of speed limit signs and a first lane line; determining a second lane line based on a target pre-aiming point, wherein the target pre-aiming point is determined based on a fitting model of a pre-aiming distance and the first lane line, the pre-aiming distance is determined based on the vehicle's current speed and a preset pre-aiming time reference value, and the second lane line is a portion of the lane line extracted from the first lane line based on the target pre-aiming point; in response to the lane line curvature of the second lane line being greater than or equal to a preset curvature threshold, identifying a target speed limit sign as a speed limit sign of a target ramp, and identifying the speed limit value corresponding to the target speed limit sign as the speed limit value of the target ramp, wherein the target speed limit sign is a first speed limit sign in the first set of speed limit signs whose distance from the second lane line is within a preset distance range, and the target ramp is the ramp corresponding to the second lane line.

Description

Technical Field

[0001] This application relates to the field of automotive technology, and more specifically, to a method, device, and storage medium for identifying speed limits on ramps. Background Technology

[0002] Ramp speed limit recognition technology relies on features such as the lateral distance between the vehicle and the speed limit sign, the vehicle speed, navigation map fusion, or recognition of ramp text to make a judgment. The information collected is complex and easily interfered with in different scenarios. When some information cannot be collected successfully or is inaccurate, misidentification or omission can easily occur, resulting in a poor user experience for drivers and poor system availability.

[0003] It is evident that the ramp speed limit recognition method in the relevant technology suffers from low recognition accuracy. Summary of the Invention

[0004] This application provides a method, apparatus, and storage medium for identifying ramp speed limits, in order to at least solve the technical problem of low accuracy in ramp speed limit identification methods.

[0005] According to one aspect of the embodiments of this application, a method for identifying speed limits on ramps is provided, comprising: acquiring a target road image and extracting a first set of speed limit signs and a first lane line from the target road image; determining a second lane line based on a target aiming point, wherein the target aiming point is determined based on a fitting model of an aiming distance and the first lane line, the aiming distance is determined based on the current speed of the vehicle and a preset aiming time reference value, and the second lane line is a portion of the lane line extracted from the first lane line based on the target aiming point; in response to a lane line curvature of the second lane line being greater than or equal to a preset curvature threshold, determining a target speed limit sign in the first set of speed limit signs as a speed limit sign of a target ramp, and identifying the speed limit value corresponding to the target speed limit sign as the speed limit value of the target ramp, wherein the target speed limit sign is a first speed limit sign in the first set of speed limit signs whose distance from the second lane line is within a preset distance range, and the target ramp is the ramp corresponding to the second lane line.

[0006] According to another aspect of the embodiments of this application, a ramp speed limit recognition device is also provided, comprising: a first execution unit, configured to acquire a target road image and extract a first set of speed limit signs and a first lane line from the target road image; a first determination unit, configured to determine a second lane line based on a target pre-aiming point, wherein the target pre-aiming point is determined based on a fitting model of a pre-aiming distance and the first lane line, the pre-aiming distance is determined based on the current speed of the vehicle and a preset pre-aiming time reference value, and the second lane line is a portion of the lane line extracted from the first lane line based on the target pre-aiming point; and a second execution unit, configured to, in response to a lane line curvature of the second lane line being greater than or equal to a preset curvature threshold, determine a target speed limit sign in the first set of speed limit signs as a speed limit sign of a target ramp, and identify the speed limit value corresponding to the target speed limit sign as the speed limit value of the target ramp, wherein the target speed limit sign is a first speed limit sign in the first set of speed limit signs whose distance from the second lane line is within a preset distance range, and the target ramp is a ramp corresponding to the second lane line.

[0007] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed by a processor.

[0008] According to another aspect of the embodiments of this application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform the steps in any of the method embodiments described above.

[0009] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to perform the steps of any of the above method embodiments through the computer program.

[0010] This application acquires a target road image and extracts a first set of speed limit signs and a first lane line from the target road image; a second lane line is determined based on a target preview point, wherein the target preview point is determined based on a fitting model of the preview distance and the first lane line, the preview distance is determined based on the vehicle's current speed and a preset preview time reference value, and the second lane line is a portion of the lane line extracted from the first lane line based on the target preview point; in response to the lane line curvature of the second lane line being greater than or equal to a preset curvature threshold, the target speed limit signs in the first set of speed limit signs are determined as the speed limit signs of the target ramp. The system identifies the speed limit value corresponding to the target speed limit sign as the speed limit value of the target ramp. The target speed limit sign is the first speed limit sign in the first set of speed limit signs whose distance from the second lane line is within a preset distance range. The target ramp is the ramp corresponding to the second lane line. Since the real-time dynamic distance from the speed limit sign to the lane line can be determined by calculating the coordinates of the pre-aiming point, and combined with distance threshold filtering, the ramp speed limit in the curve scenario can be accurately identified. Therefore, it can solve the problem of low recognition accuracy of ramp speed limit recognition methods in related technologies and improve the accuracy of ramp speed limit recognition. Attached Figure Description

[0011] Figure 1 This is a schematic diagram illustrating an application scenario of a ramp speed limit recognition method according to an embodiment of this application;

[0012] Figure 2 This is a flowchart illustrating an optional ramp speed limit recognition method according to an embodiment of this application;

[0013] Figure 3 This is a schematic diagram of an optional ramp speed limit recognition method according to an embodiment of this application;

[0014] Figure 4 This is a schematic diagram of another optional ramp speed limit recognition method according to an embodiment of this application;

[0015] Figure 5 This is a structural block diagram of an optional ramp speed limit recognition device according to an embodiment of this application;

[0016] Figure 6 This is a computer system architecture block diagram of an optional electronic device according to an embodiment of this application. Detailed Implementation

[0017] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0018] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0019] According to one aspect of the embodiments of this application, a speed control method for a mobile device is provided. Optionally, in this embodiment, the speed control method for the mobile device may be applied to, but is not limited to, [examples of other methods]. Figure 1 The hardware environment shown includes vehicle 102 and server 104. Server 104 can be connected to vehicle 102 via a network and can be used to provide services (e.g., application services, etc.) to vehicle 102 or clients installed on vehicle 102. A database can be set up on or independently of server 104 to provide data storage services for server 104.

[0020] The aforementioned network may include, but is not limited to, at least one of the following: wired network and wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network (WAN), metropolitan area network (MAN), and local area network (LAN). The aforementioned wireless network may include, but is not limited to, at least one of the following: Wireless Fidelity (WIFI) and Bluetooth. Vehicle 102 may be, but is not limited to, a personal computer (PC), mobile phone, tablet computer, etc. Server 104 may be, but is not limited to, a cloud server, server cluster, or other server types.

[0021] The ramp speed limit recognition method of this application embodiment can be executed by server 104, by vehicle 102, or by both server 104 and vehicle 102. Alternatively, the ramp speed limit recognition method of this application embodiment can be executed by a client installed on vehicle 102.

[0022] Taking the ramp speed limit recognition method in this embodiment, executed by vehicle 102, as an example, Figure 2 This is a flowchart illustrating an optional ramp speed limit recognition method according to an embodiment of this application, as shown below. Figure 2 As shown, the process of this method may include the following steps:

[0023] Step S202: Obtain the target road image, and extract the first speed limit sign set and the first lane line from the target road image;

[0024] Step S204: Determine the second lane line based on the target aiming point, wherein the target aiming point is determined based on the fitting model of the aiming distance and the first lane line, the aiming distance is determined based on the current speed of the vehicle and the preset aiming time reference value, and the second lane line is a portion of the lane line extracted from the first lane line based on the target aiming point.

[0025] Step S206: In response to the curvature of the second lane line being greater than or equal to a preset curvature threshold, the target speed limit sign in the first speed limit sign set is determined as the speed limit sign of the target ramp, and the speed limit value corresponding to the target speed limit sign is identified as the speed limit value of the target ramp. Here, the target speed limit sign is the first speed limit sign in the first speed limit sign set whose distance from the second lane line is within a preset distance range, and the target ramp is the ramp corresponding to the second lane line.

[0026] The ramp speed limit recognition method in this embodiment can be applied to the automotive field, specifically to scenarios where a car is driving on a curve and ramp speed limit recognition is required.

[0027] Ramp speed limit recognition can be based solely on lateral distance and vehicle speed. This involves calculating the lateral distance between the vehicle and the speed limit sign, and then combining this with the difference between the vehicle's real-time speed and the speed limit value for a comprehensive judgment. For example, if the lateral distance between a suspected ramp speed limit sign and the image acquisition device is greater than a preset threshold, and the difference between the current vehicle speed and the speed limit value represented by the sign is greater than a preset parameter, the current environment is determined to contain a ramp speed limit sign. However, the placement of speed limit signs may be inaccurate, such as deviations from standard installation positions or changes in road width, causing the actual lateral distance to deviate from the preset threshold. This judgment logic based on a fixed threshold cannot adapt to non-standard installation scenarios, leading to misidentification or missed identification. In congested traffic scenarios, vehicle speed decreases, potentially falling below normal driving speed. In this case, the difference between the vehicle speed and the speed limit value may not meet the preset parameter conditions, causing the system to fail to correctly identify the ramp speed limit. Furthermore, if a vehicle travels at low speed due to congestion at the end of a straight road and then enters a ramp, the speed limit sign before the ramp entrance may be misjudged as a main road speed limit or ignored, causing a delay in the control logic.

[0028] Furthermore, in curved scenarios, due to the curvature of the road, the lateral geometric relationship between the vehicle and the lane lines changes dynamically with the vehicle's position, and this distance cannot accurately reflect the spatial relationship between the speed limit sign and the lane lines.

[0029] Alternatively, recognition can be based on navigation and vision fusion, that is, acquiring speed limit information from visual recognition and speed limit information from the navigation trajectory separately, and using the navigation trajectory or the vehicle's motion status to determine whether to filter or issue ramp speed limit values. This solution relies on high-precision map data or real-time navigation route planning. However, this increases the cost of use and limits its promotion and application. Moreover, navigation map data has an update lag. For temporarily set speed limit signs, the map data cannot be synchronized in time, causing the system to fail to recognize or output incorrect speed limit values. In addition, in areas with weak signals such as tunnels and under overpasses, navigation positioning may drift or be lost, resulting in positioning failure and making it impossible to accurately determine the vehicle's location, thus causing a delay in issuing ramp speed limit prompts.

[0030] It is evident that the information collection process is complex and susceptible to interference in different scenarios. In cases where some information cannot be successfully collected or is inaccurate, misidentification or omission may occur. In other words, the ramp speed limit recognition method in related technologies suffers from low recognition accuracy.

[0031] To at least partially solve the aforementioned technical problems, in this embodiment, a target road image is acquired, and a first set of speed limit signs and a first lane line are extracted from the target road image; a second lane line is determined based on a target aiming point, wherein the target aiming point is determined based on a fitting model of the aiming distance and the first lane line, the aiming distance is determined based on the vehicle's current speed and a preset aiming time reference value, and the second lane line is a portion of the lane line extracted from the first lane line based on the target aiming point; in response to the lane line curvature of the second lane line being greater than or equal to a preset curvature threshold, the target speed limit sign in the first set of speed limit signs is determined as the target lane line. The method identifies the speed limit signs of ramps and recognizes the speed limit value corresponding to the target speed limit sign as the speed limit value of the target ramp. The target speed limit sign is the first speed limit sign in the first set of speed limit signs whose distance from the second lane line is within a preset distance range. The target ramp is the ramp corresponding to the second lane line. Since the real-time dynamic distance between the speed limit sign and the lane line can be determined by calculating the coordinates of the pre-aiming point and combined with distance threshold filtering, the speed limit of ramps in the curve scenario can be accurately identified. Therefore, it can solve the problem of low recognition accuracy of ramp speed limit recognition methods in related technologies and improve the accuracy of ramp speed limit recognition.

[0032] Optionally, a target road image can be acquired. This can be a road image recorded by a vehicle-mounted forward-facing camera. It can be image data of the front of the vehicle collected at a fixed frame rate (e.g., 30 or 60 frames per second), or it can be a video continuously recorded by the vehicle-mounted forward-facing camera and the road image at the current moment extracted from the video. Alternatively, it can be an image obtained by combining data collected by multiple sensors on the vehicle. This embodiment does not limit this.

[0033] To ensure the accuracy of subsequent processing, the target road image can be preprocessed, including but not limited to: noise reduction, distortion correction (to eliminate distortion caused by wide-angle lens) and illumination equalization (to deal with tunnel entry and exit or strong backlight scenes).

[0034] Optionally, a first lane line can be extracted from the target road image. This can refer to identifying the lane boundary in the image using a lane line detection algorithm, such as a deep learning-based segmentation network or a traditional image processing-based directional gradient method. This embodiment does not limit the specific method used.

[0035] Optionally, the lane lines extracted from the target road image may include a sequence of pixel coordinates of the lane lines, or coordinates transformed from pixel coordinates to vehicle coordinates or camera coordinates.

[0036] Optionally, lane line tracking algorithms can also predict unobstructed lane line segments to fill in detection gaps caused by occlusion or changes in lighting.

[0037] Optionally, a first set of speed limit signs can also be extracted from the target road image. In this embodiment, no specific image recognition algorithm is limited.

[0038] Optionally, the first set of speed limit signs may include one or more speed limit signs.

[0039] Optionally, after extracting the first set of speed limit signs, the corresponding information of the first speed limit signs can be obtained, which may include, but is not limited to: the pixel coordinates of the speed limit signs, the three-dimensional spatial position of the speed limit signs, and the three-dimensional spatial position of the speed limit signs. The three-dimensional spatial position of the speed limit signs may be obtained by monocular ranging algorithm or calibration-based geometric projection algorithm, etc. This embodiment does not limit this. The calibration of the position may be in the same coordinate system as the calibration of the first lane line. For example, they may both be located in the vehicle coordinate system.

[0040] Optionally, a unique identifier can be assigned to each identified speed limit sign to track the same speed limit sign in consecutive frames.

[0041] Optionally, speed limit signs can be filtered based on confidence level. Only when the confidence level output by the detection algorithm is higher than a preset threshold will the sign be included in the first speed limit sign set, thereby excluding false detection targets such as billboards and graffiti.

[0042] Optionally, the first set of speed limit signs may include all detected speed limit signs located within the vehicle's forward field of vision. The first lane lines may include the boundary lines of the lane the vehicle is currently in and the adjacent lanes.

[0043] Optionally, it can be determined whether the lane line curvature of the second lane line is greater than or equal to a preset curvature threshold, which can be the second lane line determined based on the target aiming point.

[0044] Here, the curvature of the lane lines can be used to determine whether a vehicle is in a curve or ramp scenario, thus influencing the subsequent speed limit recognition logic. If the curvature of the second lane line is less than a preset curvature threshold, it can be classified as a straight road scenario, and conventional ramp speed limit recognition filtering methods can be used. However, if the curvature of the second lane line is greater than or equal to the preset curvature threshold, then a pre-aiming point can be used to recognize the subsequent ramp speed limit.

[0045] For example, such as Figure 3 As shown, at this time, the vehicle may be in a curve scenario and needs to recognize the speed limit sign of the ramp ahead (e.g., a speed limit sign with a speed limit value of 40).

[0046] In a curved driving scenario, due to curvature, the vehicle's future trajectory deviates from its current direction of travel. To accurately determine whether a speed limit sign belongs to the lane the vehicle is about to enter, a target aiming point can be identified to assist in the determination. Here, the aiming point can be the position the vehicle will reach at a specific time in the future. The aiming point can be determined based on a fitting model of the aiming distance and the first lane line, while the aiming distance can be determined based on the vehicle's current speed and a preset aiming time reference value.

[0047] Optionally, the preview time can be a time window set according to road design specifications and driving behavior. This time window needs to be designed to allow the driver to detect emergency or nearby speed limits at high speeds, and to lock onto speed limit information a sufficiently far distance in advance, providing ample reaction time for vehicle deceleration, especially in low-speed or complex curve scenarios. For example, the preview time can range from 0.5 seconds to 5.0 seconds.

[0048] Optionally, the preview time can also be positively correlated with the current vehicle speed. At higher speeds, the braking distance increases, requiring a longer preview time to detect speed limits earlier; at lower speeds, the preview time can be appropriately shortened to avoid misidentifying signs in other lanes ahead due to excessive preview distance. The preview time value can be dynamically adjusted based on a preset mapping table or a linear / nonlinear function model.

[0049] Optionally, the aiming time can be determined based on the vehicle's current speed and a preset aiming time reference value, and then the aiming distance can be determined. For example, the product of the vehicle's current speed and the aiming time can be determined as the aiming distance.

[0050] Alternatively, after determining the aiming distance, it can be input into the fitting model of the first lane line to obtain the target aiming point.

[0051] Optionally, based on the target aiming point, a second lane line can be extracted from the first lane line. That is, the second lane line can be a local road segment extracted from the first lane line and associated with the target aiming point. The second lane line can be a lane line segment extending a certain length forward and backward from the aiming point, or a reference line segment with the aiming point as the reference point. The specific extraction length can be preset or related to the lane line curvature.

[0052] Optionally, the first speed limit sign in the first set of speed limit signs whose distance from the second lane line is within a preset distance range can be identified as the target speed limit sign, and the speed limit value corresponding to the target speed limit sign can be identified as the target ramp speed limit value.

[0053] Here, the first speed limit sign whose distance from the second lane line is not within the preset distance range, for example, a first speed limit sign whose distance exceeds the upper limit of the preset distance range, can be considered to be too far from the ramp lane line, and may be a sign of an adjacent lane or the main road.

[0054] Optionally, for a first speed limit sign whose distance to the second lane line is less than the lower limit of a preset distance range, its corresponding speed limit value can be directly confirmed as the speed limit value of the target ramp and output to the transmission unit without further verification or filtering.

[0055] Optionally, if there are multiple first speed limit signs whose distance from the second lane line is within a preset distance range, only one speed limit sign can be retained as the target speed limit sign. It can be the speed limit sign with the smallest distance from the second lane line, or the speed limit sign with the largest corresponding speed limit value, or other determining conditions. This embodiment does not limit this.

[0056] Optionally, the speed limit value corresponding to the target speed limit sign can be identified as the speed limit value of the target ramp, where the target ramp can be the ramp corresponding to the second lane line. Here, since the second lane line can be determined based on the aiming point, the second lane line can be the predicted trajectory of the ramp that the vehicle is about to enter, and the speed limit sign located near this lane line can be the speed limit sign associated with the second lane line. Since the lane lines change dynamically during vehicle travel, after the speed limit value of the target ramp is identified, the vehicle may enter the target ramp or may not enter the target ramp; neither of these situations affects the current identification of the speed limit value of the target ramp. In response to the determination of the vehicle's subsequent driving intention, the identification of future speed limit values ​​can be dynamically updated and adjusted; this embodiment does not limit this.

[0057] Through the embodiments of this application, a target road image is acquired, and a first set of speed limit signs and a first lane line are extracted from the target road image; a second lane line is determined based on a target preview point, wherein the target preview point is determined based on a fitting model of the preview distance and the first lane line, the preview distance is determined based on the vehicle's current speed and a preset preview time reference value, and the second lane line is a portion of the lane line extracted from the first lane line based on the target preview point; in response to the lane line curvature of the second lane line being greater than or equal to a preset curvature threshold, the target speed limit sign in the first set of speed limit signs is determined as the speed limit sign of the target ramp, and the speed limit value corresponding to the target speed limit sign is identified as the speed limit value of the target ramp, wherein the target speed limit sign is a first speed limit sign in the first set of speed limit signs whose distance from the second lane line is within a preset distance range, and the target ramp is the ramp corresponding to the second lane line. This solves the problem of low recognition accuracy in ramp speed limit recognition methods in related technologies and improves the accuracy of ramp speed limit recognition.

[0058] In one exemplary embodiment, before determining the second lane line based on the target aiming point, the method further includes:

[0059] A polynomial fit is performed on the first lane line to determine the fitting model of the first lane line, wherein the fitting model of the first lane line includes polynomial coefficients used to represent the geometric features of the first lane line.

[0060] Visual sensors (such as cameras) typically acquire two-dimensional image data, which can be processed into models that characterize geometric features. Since lane lines are non-linear curves, directly processing pixel coordinates is insufficient to accurately describe the lane's geometry. Therefore, the first lane line can be extracted to construct a model.

[0061] Optionally, the model can be constructed by combining data acquired from other sensors of the vehicle (such as point cloud data).

[0062] In this embodiment, a polynomial fitting can be performed on the first lane line to determine the fitting model of the first lane line, which can be a fitting model of the first lane line that transforms discrete lane line pixels.

[0063] Optionally, after extracting and filtering lane line pixels, the extracted data can be preprocessed. For example, outliers (such as false detections caused by road stains, shadows, or reflections) can be removed to eliminate noise interference.

[0064] Optionally, a vehicle coordinate system can be established. For example, the optical center of the camera or the center of the front axle of the vehicle can be defined as the origin, or the entire vehicle can be used as the origin, with the longitudinal direction of the vehicle as the X-axis and the lateral direction as the Y-axis.

[0065] Alternatively, the filtered pixel coordinates can be transformed into the vehicle coordinate system using the calibration parameters (intrinsic parameter matrix) of the sensor (such as a camera) used to acquire images of the target road, resulting in a series of spatial points, and then polynomial fitting can be performed.

[0066] Since roads typically have smooth curvature changes, a cubic polynomial can be used to construct the lane line model, as shown in formula (1):

[0067] y = ax + bx + cx + d (1)

[0068] Where x and y are the coordinates in the vehicle coordinate system, and a, b, c, and d are the polynomial coefficients used to represent the geometric features of the first lane line.

[0069] Alternatively, a higher-order fitting model can be used. This embodiment does not limit this, but compared to higher-order polynomials (such as sixth degree or higher), cubic polynomials can meet the fitting requirements of most road scenarios while maintaining lower computational complexity, making them suitable for real-time in-vehicle processing.

[0070] This embodiment demonstrates how a fitting model based on lane lines can be effectively built for subsequent identification needs, thereby improving the accuracy of ramp speed limit identification.

[0071] In one exemplary embodiment, extracting a first set of speed limit signs and a first set of lane lines from a target road image includes:

[0072] Lane line recognition is performed on the target road image to obtain the first lane line;

[0073] The target road image is subjected to speed limit sign recognition to obtain a second set of speed limit signs. Then, the second speed limit signs that meet the preset speed limit conditions are selected from the second set of speed limit signs to obtain a first set of speed limit signs.

[0074] The preset speed limit conditions include at least one of the following: the speed limit is located on the first side of the vehicle and the difference between the corresponding speed limit value and the most recently acquired historical valid speed limit value is less than a preset difference threshold; the speed limit is located on the second side of the vehicle and the corresponding speed limit value is within the preset speed limit value range; the first side and the second side are different sides.

[0075] Optionally, lane line recognition can be performed, which can be based on a deep learning semantic segmentation model or an edge detection algorithm, or other algorithms, as described in the foregoing embodiments, and will not be repeated here.

[0076] Optionally, speed limit signs can be identified in the target road image, and the identified speed limit signs can be preliminarily screened. Here, the method for identifying speed limit signs in the target road image is similar to that in the previous embodiments, and will not be described in detail here.

[0077] To eliminate interference and focus on the most likely ramp speed limit signs, a preliminary screening can be performed on the second set of speed limit signs obtained by speed limit sign recognition of the target road image.

[0078] Optionally, different screening criteria can be used for speed limit signs located on the first and second sides of the vehicle, where the first and second sides are different sides.

[0079] Optionally, the first side can be the main road side or the inner side of the road, which can be the left side in the vehicle coordinate system constructed in the aforementioned embodiments. For the speed limit sign located on the first side of the vehicle, it can correspond to the main road speed limit or the main speed limit value of the current driving lane. It is usually relatively stable or the speed limit value is relatively high. In this case, the consistency of speed limit recognition can be ensured by comparing the difference with the historical valid speed limit value, and the sudden change of speed limit value can be filtered out.

[0080] Optionally, the second side can be the outer side of the road, corresponding to a ramp or auxiliary road, which can be the right side in the vehicle coordinate system constructed in the aforementioned embodiments. For the speed limit sign located on the second side of the vehicle, it can correspond to the speed limit of a ramp or a curve. As a connecting road, the speed limit value of a ramp is usually lower and there is a specific speed limit range. In this case, it can be determined whether the speed limit value corresponding to the speed limit sign located on the second side of the vehicle is within the preset speed limit range to eliminate the interference of main road signs, target lane signs or non-target area signs.

[0081] Alternatively, in response to different road conditions, the first side and the second side can also be other designs, for example, the first side is the right side and the second side is the left side. This embodiment does not limit this.

[0082] This embodiment reduces the computational load by performing preliminary screening on speed limit signs located on different sides of the vehicle, thereby improving the accuracy and real-time performance of ramp identification.

[0083] In one exemplary embodiment, after identifying the speed limit value corresponding to the target speed limit sign as the speed limit value of the target ramp, the above method further includes:

[0084] Based on driving information, the driving intention of the vehicle is identified, wherein the driving information includes at least one of the following: operation command signal, attitude parameters;

[0085] When the vehicle's driving intention is to enter the target ramp, the speed limit value of the target ramp is transmitted to the vehicle's display unit for display.

[0086] If the vehicle's intention is not to enter the target ramp, the speed limit of the target ramp is discarded.

[0087] In this embodiment, by fusing multimodal sensor data, it is possible to determine whether the vehicle has the actual intention to enter the target ramp and output the final ramp speed limit value.

[0088] Optionally, vehicle driving information can be collected, which can be collected in real time. The aforementioned driving information may include operating command signals and vehicle attitude parameters.

[0089] For example, the operation command signal may include, but is not limited to: turn signal, brake pedal angle signal, gear signal, etc.; vehicle attitude parameters may include, but are not limited to: body roll angle, lateral acceleration, pitch rate, etc.

[0090] Optionally, the driving intention of the vehicle can be identified based on the above driving information. This can be done by building a driving intention recognition model based on historical data or by comprehensively recognizing the driving intention based on preset recognition conditions. This embodiment does not limit this.

[0091] Optionally, if the vehicle's driving intention is to enter the target ramp, the speed limit value of the target ramp can be transmitted to the vehicle's display unit for display, in order to perform speed limit reminders or speed limit control.

[0092] Optionally, if the vehicle's intention is not to enter the target ramp, the speed limit of the target ramp can be discarded. In this case, the current main road speed limit display can continue to be maintained to avoid sending incorrect information to the driver.

[0093] By introducing operation command signals and vehicle attitude information as intent verification in this embodiment, speed limit signs of non-target ramps can be effectively filtered out, reducing the false alarm rate and improving the accuracy of ramp speed limit recognition.

[0094] In an exemplary embodiment, when the driving information includes an operation command signal, the operation command signal includes at least one of the following: a turn signal activation signal, a steering wheel angle change signal;

[0095] When driving information includes attitude parameters, the attitude parameters include at least one of the following: body roll angle and lateral acceleration.

[0096] When driving information includes operation command signals, the operation command signals may include at least one of the following: turn signal activation signal, steering wheel angle change signal, wherein both the turn signal activation signal and the steering wheel angle change signal can indicate the vehicle's steering intention, in order to further confirm whether the vehicle intends to enter the target ramp.

[0097] When driving information includes attitude parameters, the attitude parameters may include at least one of the following: body roll angle, lateral acceleration, wherein when the vehicle enters a curve or ramp, the body will roll due to centrifugal force, and the lateral acceleration may also indicate the vehicle's steering intention, thereby being used to confirm whether the vehicle intends to enter the target ramp.

[0098] Optionally, different methods can be used to verify the vehicle's driving intention for the different types of driving information mentioned above.

[0099] For example, when the steering wheel angle continues to increase to a preset angle (e.g., greater than 15 degrees), and the lateral acceleration stabilizes within a specific range (e.g., 0.2g-0.5g), and the vehicle position deviates from the center line of the main road, it is determined that there is an intention to enter.

[0100] Optionally, different driving information can be given different weights when determining the vehicle's driving intention. For example, the turn signal activation signal can have a higher weight, while attitude parameters, used as auxiliary verification, can have a lower weight. The confidence level of the driving intention can be determined based on the above driving information combined with the weights. Only when the confidence level of the driving intention exceeds a confidence threshold is it confirmed as an intention to enter the target ramp.

[0101] This embodiment improves the accuracy of ramp speed limit recognition and avoids false alarms by comprehensively judging the vehicle's driving intention based on driving information before displaying the reference speed limit value.

[0102] In one exemplary embodiment, before determining the target speed limit sign in the first set of speed limit signs as the speed limit sign of the target ramp, the method further includes:

[0103] Determine the coordinates of each first speed limit sign in the first speed limit sign set;

[0104] Based on the coordinates of each first speed limit sign and the fitting model of the second lane line, the shortest geometric distance between each first speed limit sign and the second lane line is determined, thus obtaining the distance between each first speed limit sign and the second lane line.

[0105] Similar to the previous embodiments, the distance between the first speed limit sign and the second lane line can be determined, which can be the shortest geometric distance between the speed limit sign and the second lane line.

[0106] Optionally, the coordinates of each first speed limit sign can be determined. This can be done by converting the image coordinates of the first speed limit sign identified in the target road image to the vehicle coordinate system. The conversion method is similar to that in the previous embodiments and will not be described in detail here.

[0107] Optionally, for the speed limit sign of the ramp entering the candidate range (i.e., the first speed limit sign), the distance from it to the lane line can be calculated in real time. Assuming the coordinates of the speed limit sign are (m, n), they can be input into the fitting model of the second lane line to obtain the shortest geometric distance between them.

[0108] Here, since the second lane line is a local lane line segment extracted from the first lane line and related to the aiming point, the fitting model of the second lane line can be a representation of the fitting model of the first lane line within a specific interval.

[0109] For example, the fitting model of the first lane line can be a fitting model obtained by performing polynomial fitting, as shown in formula (1). Correspondingly, the fitting model of the second lane line is also shown in formula (1). If the coordinates of any point on the curve are (x, y), then the shortest geometric distance between the speed limit sign and the second lane line can be shown in formula (2):

[0110] (2)

[0111] To reduce computational complexity and improve real-time performance, the squared distance D² can be used for simplified calculation, as shown in formula (3):

[0112] D²=(xm)² + (ax+bx+cx+dn)² (3)

[0113] The distance can be obtained by taking the square root of the square of the above distance, or it can be directly used to filter and judge subsequent distances.

[0114] This embodiment improves the accuracy of subsequent screening of ramp speed limit signs by determining the shortest geometric distance corresponding to each speed limit sign, simplifies calculations, and reduces resource consumption.

[0115] In one exemplary embodiment, after identifying the speed limit value corresponding to the target speed limit sign as the speed limit value of the target ramp, the above method further includes:

[0116] In response to the fulfillment of the exit condition, the identification of the speed limit value of the target ramp is stopped, wherein the exit condition includes at least one of the following: the duration for which the lane line curvature of the second lane is less than a preset curvature threshold is greater than a preset time threshold, and the lateral acceleration of the vehicle is less than a preset acceleration threshold.

[0117] In this embodiment, the speed limit value of the ramp can be output only when the vehicle is actually driving on the ramp. Once the vehicle leaves the ramp or it is confirmed that it has not entered the ramp, the cached speed limit value can be cleared to prevent false alarms caused by signal residue.

[0118] Optionally, it is possible to monitor whether the exit conditions are met. The exit conditions may include multiple monitoring indicators, such as road geometry and vehicle driving characteristics.

[0119] Optionally, it can monitor whether the duration for which the lane line curvature of the second lane is less than a preset curvature threshold is greater than a preset time threshold. Since ramps usually have significant curvature characteristics, their curvature is greater than that of the straight line or gentle curvature of the main road. When the duration for which the lane line curvature of the second lane is less than the preset curvature threshold is greater than the preset time threshold, it can be determined that the road segment where the vehicle is currently located tends to be straight and no longer conforms to the geometric characteristics of the ramp.

[0120] Optionally, the lateral acceleration of the vehicle can be monitored to be less than a preset acceleration threshold. During the driving process on the ramp, the vehicle usually maintains a certain steering angle, generating a continuous non-zero lateral acceleration. The preset acceleration threshold can be used to determine whether the vehicle is still making significant lateral movements. When the lateral acceleration of the vehicle is less than the preset acceleration threshold, it indicates that the vehicle has returned to the correct direction or is in a straight driving state. At this time, the vehicle may have exited the curve or ramp.

[0121] Optionally, for lateral acceleration, it can also be monitored whether it is continuously lower than a preset acceleration threshold. For example, if the duration of the vehicle's lateral acceleration being less than the preset acceleration threshold is greater than a second preset time threshold, it can be determined that the exit condition is met.

[0122] Optionally, in response to the exit condition being met, the identification of the speed limit value of the target ramp can be stopped. At this time, the target ramp speed limit value and related sign information temporarily stored in memory can be deleted, and the speed limit reference value of the vehicle controller can be restored to the current effective speed limit value of the main road (such as the speed limit value of the main road visually identified, or the historical effective speed limit value obtained last time), and the ramp speed limit prompt can be removed from the display unit.

[0123] This embodiment improves the accuracy of ramp speed limit recognition and the safety of vehicle control by stopping the display of the target ramp speed limit value when the vehicle exits the ramp.

[0124] The following explanation, using optional examples, illustrates the ramp speed limit recognition method in this application. In this optional example, a pre-aiming technique is used to determine the distance between the speed limit sign and the lane lines in advance, achieving optimization solely based on visual perception without relying on the word "ramp".

[0125] Figure 4 This is a flowchart illustrating the ramp speed limit recognition method in this optional example, as shown below. Figure 4 As shown, the process of this ramp speed limit recognition method may include the following steps:

[0126] Step S402, Curvature Classification and Filtering Strategy Selection: After the system obtains the lane line curvature k in real time, it first performs scene classification determination: set the curvature threshold k1 = 0.002m. -1 (This threshold can be calibrated and optimized based on the computing power resources of the onboard processor and the actual performance of different road types.) When k < k1, it is determined to be a low curvature scenario, and conventional ramp speed limit recognition filtering methods are used; when k ≥ k1, it is determined to be a high curvature scenario, and subsequent methods are used to ensure the accuracy of speed limit recognition in curved scenarios.

[0127] Step S404, Preview Point Coordinate Calculation: After the vision sensor acquires the image and completes lane line detection, it outputs the parameters of the cubic polynomial lane line equation, as shown in the above formula (1) (x is the vertical axis of the vehicle coordinate system, y is the horizontal axis, positive on the left and negative on the right). The system combines the current vehicle speed v and sets the preview time window according to the standard requirement of advance display of road speed limit signs. The preview distance x is calculated by x=vt (t is the preview time, which can be adjusted adaptively according to the speed, with a value range of 610.5-5.0s). Substituting the preview distance x into the lane line equation, the corresponding preview point coordinates (x,y) are obtained, providing a benchmark for subsequent distance calculation.

[0128] Step S406, Speed ​​Limit Range Filtering and Candidate Range Entry: The vision sensor synchronously outputs the lateral and longitudinal distance coordinates (m, n) of each speed limit sign relative to the vehicle (m is the longitudinal distance, n is the lateral distance). To avoid signal interference caused by misidentification of speed limit signs, the system first makes a real-time prediction based on the pre-aiming distance, and at the same time distinguishes whether the speed limit sign is located on the left or right side of the vehicle:

[0129] If the speed limit sign is on the left side of the vehicle: extract the recognition value v_limit of the speed limit sign, calculate the difference with the valid speed limit value v_prev output in the previous frame. If v_limit > v_prev + 20kph, it is judged as an abnormal speed limit value and the recognition result is discarded directly; if v_limit ≤ v_prev + 20kph, the speed limit sign is included in the ramp speed limit candidate range.

[0130] If the speed limit sign is on the right side of the vehicle: determine whether the recognition value v_limit falls within the 30-60kph range (this range covers the standard speed limit values ​​of mainstream ramps). If it does, it is included in the ramp speed limit candidate range. If it exceeds this range, it is directly excluded and does not enter the subsequent judgment process.

[0131] Step S408, Distance Function Construction and Simplified Calculation: For the speed limit sign entering the candidate range, the system calculates the distance from it to the lane line in real time. Define the distance function: Let the coordinates of the speed limit sign be (m,n) and the coordinates of any point on the curve be (x,y), then the distance D between the two points is expressed as shown in formula (2). To reduce the computational complexity and improve real-time performance, the squared distance D² can be used for simplified calculation. After substituting into the lane line equation, the above formula (3) is obtained. The distance can be quickly solved through this simplified formula.

[0132] Step S410, Distance Threshold Filtering and Preliminary Determination of Ramp Speed ​​Limits: Based on actual road conditions, two levels of distance thresholds are set: long distance threshold D1 = 10m, and short distance threshold D2 = 3.5m (both thresholds can be calibrated and adjusted according to different road widths and lane layouts). First, speed limit signs with a distance D > D1 from the lane line are filtered out to eliminate long-distance interference targets. Among the retained speed limit signs, if their attribute ID (used to identify consecutive frame matching of the same speed limit sign) remains unchanged, the system calculates the minimum distance D_min from the lane line in real time. If D2 < D_min ≤ D1, the speed limit value is determined to be a candidate value for the ramp speed limit, and this value is retained for subsequent verification processes.

[0133] Step S412, Driver Intent and Vehicle Attitude Verification: For the initially determined candidate ramp speed limit values, the system monitors vehicle operation behavior (such as turn signal on status, steering wheel angle change rate) and vehicle attitude parameters (such as body roll angle, lateral acceleration) through visual sensors or other sensors to comprehensively determine whether the driver has the intention to enter or exit the ramp. If a clear intention to enter or exit the ramp is detected, and the vehicle attitude conforms to ramp driving characteristics (such as continuously increasing steering angle, lateral acceleration stable at 0.2-0.5g), the ramp speed limit value is output to the vehicle controller and displayed; if no relevant intention is detected or the vehicle attitude does not conform, the candidate value is discarded to avoid erroneous triggering of speed limit control.

[0134] Step S414, Ramp Speed ​​Limit Dynamic Update and Exit Mechanism: After the system outputs the ramp speed limit value, it continuously monitors the lane curvature, speed limit sign position, and vehicle status to implement dynamic update and exit logic: If the lane curvature k < k1 (low curvature scenario) and the duration is ≥1.5s, or the vehicle lateral acceleration <0.1g, it is determined that the vehicle has exited the ramp, and the output of the ramp speed limit value is immediately stopped, and the current main road effective speed limit display is restored; if a new ramp speed limit sign (different attribute ID) is detected and meets the judgment conditions of the above steps, the original ramp speed limit value is replaced, and the updated value is output; if the original ramp speed limit sign is recognized and the vehicle passes the ramp entrance, the speed limit value is automatically cleared to avoid invalid signal residue.

[0135] This optional example can help avoid problems such as abnormal vehicle speeds caused by traffic jams, improper placement of ramp speed limit signs, and large lateral distance errors that lead to misidentification of ramp speed limits.

[0136] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0137] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / random access memory (RAM), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0138] According to another aspect of the embodiments of this application, a ramp speed limit recognition device is also provided. This ramp speed limit recognition device can be used to implement the ramp speed limit recognition method provided in the above embodiments, and will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0139] Figure 5 This is a structural block diagram of an optional ramp speed limit recognition device according to an embodiment of this application, such as... Figure 5 As shown, the ramp speed limit recognition device includes:

[0140] The first execution unit 502 is used to acquire a target road image and extract a first set of speed limit signs and a first lane line from the target road image.

[0141] The first determining unit 504 is used to determine the second lane line based on the target aiming point, wherein the target aiming point is determined based on the fitting model of the aiming distance and the first lane line, the aiming distance is determined based on the current speed of the vehicle and the preset aiming time reference value, and the second lane line is a portion of the lane line extracted from the first lane line based on the target aiming point.

[0142] The second execution unit 506 is configured to, in response to the curvature of the second lane line being greater than or equal to a preset curvature threshold, determine the target speed limit sign in the first speed limit sign set as the speed limit sign of the target ramp, and identify the speed limit value corresponding to the target speed limit sign as the speed limit value of the target ramp, wherein the target speed limit sign is the first speed limit sign in the first speed limit sign set whose distance from the second lane line is within a preset distance range, and the target ramp is the ramp corresponding to the second lane line.

[0143] It should be noted that the first execution unit 502 in this embodiment can be used to execute the above step S202, the first determination unit 504 in this embodiment can be used to execute the above step S204, and the second execution unit 506 in this embodiment can be used to execute the above step S206.

[0144] The embodiments provided in this application involve acquiring a target road image and extracting a first set of speed limit signs and a first lane line from the target road image; determining a second lane line based on a target preview point, wherein the target preview point is determined based on a fitting model of the preview distance and the first lane line, the preview distance is determined based on the vehicle's current speed and a preset preview time reference value, and the second lane line is a portion of the lane line extracted from the first lane line based on the target preview point; in response to the lane line curvature of the second lane line being greater than or equal to a preset curvature threshold, the target speed limit sign in the first set of speed limit signs is determined as the speed limit sign of the target ramp, and the speed limit value corresponding to the target speed limit sign is identified as the speed limit value of the target ramp, wherein the target speed limit sign is a first speed limit sign in the first set of speed limit signs whose distance from the second lane line is within a preset distance range, and the target ramp is the ramp corresponding to the second lane line. This solves the problem of low recognition accuracy in ramp speed limit recognition methods in related technologies and improves the accuracy of ramp speed limit recognition.

[0145] In one exemplary embodiment, the above-described apparatus further includes:

[0146] A fitting unit is used to perform polynomial fitting on a first lane line before determining a second lane line based on a target aiming point, to determine a fitting model for the first lane line, wherein the fitting model for the first lane line includes polynomial coefficients for representing the geometric features of the first lane line.

[0147] In one exemplary embodiment, the first execution unit includes:

[0148] The recognition module is used to identify lane lines in the target road image to obtain the first lane line;

[0149] The execution module is used to identify speed limit signs in the target road image, obtain a second set of speed limit signs, and filter out second speed limit signs that meet the preset speed limit conditions from the second set of speed limit signs to obtain a first set of speed limit signs.

[0150] The preset speed limit conditions include at least one of the following: the speed limit is located on the first side of the vehicle and the difference between the corresponding speed limit value and the most recently acquired historical valid speed limit value is less than a preset difference threshold; the speed limit is located on the second side of the vehicle and the corresponding speed limit value is within the preset speed limit value range; the first side and the second side are different sides.

[0151] In one exemplary embodiment, the above-described apparatus further includes:

[0152] The identification unit is used to identify the driving intention of the vehicle based on driving information after identifying the speed limit value corresponding to the target speed limit sign as the speed limit value of the target ramp. The driving information includes at least one of the following: operation command signal, attitude parameters.

[0153] The transmission unit is used to transmit the speed limit value of the target ramp to the vehicle's display unit for display when the vehicle's driving intention is to enter the target ramp.

[0154] The discard unit is used to discard the speed limit value of the target ramp when the vehicle's driving intention is not to enter the target ramp.

[0155] In an exemplary embodiment, when the driving information includes an operation command signal, the operation command signal includes at least one of the following: a turn signal activation signal, a steering wheel angle change signal;

[0156] When driving information includes attitude parameters, the attitude parameters include at least one of the following: body roll angle and lateral acceleration.

[0157] In one exemplary embodiment, the above-described apparatus further includes:

[0158] The second determining unit is used to determine the coordinates of each first speed limit sign in the first speed limit sign set before determining the target speed limit sign in the first speed limit sign set as the speed limit sign of the target ramp.

[0159] The third determining unit is used to determine the shortest geometric distance between each first speed limit sign and the second lane line based on the coordinates of each first speed limit sign and the fitting model of the second lane line, thereby obtaining the distance between each first speed limit sign and the second lane line.

[0160] In one exemplary embodiment, the above-described apparatus further includes:

[0161] The stop unit is used to stop identifying the speed limit value of the target ramp after identifying the speed limit value corresponding to the target speed limit sign as the speed limit value of the target ramp, in response to the satisfaction of the exit condition, wherein the exit condition includes at least one of the following: the duration for which the lane line curvature of the second lane is less than a preset curvature threshold is greater than a preset time threshold, and the lateral acceleration of the vehicle is less than a preset acceleration threshold.

[0162] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0163] According to another aspect of the embodiments of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein the program executes the steps in any of the above method embodiments when it is run.

[0164] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, ROMs, RAMs, portable hard drives, magnetic disks, or optical disks.

[0165] According to another aspect of the embodiments of this application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor is configured to perform the steps of any of the method embodiments described above via the computer program. In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0166] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0167] According to another aspect of the embodiments of this application, a computer program product is also provided, comprising a computer program / instructions containing program code for performing the methods shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit 601, it performs various functions provided in the embodiments of this application. The sequence numbers of the embodiments of this application above are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0168] Figure 6 A schematic block diagram of a computer system architecture for implementing embodiments of the present application is shown. Figure 6 As shown, the computer system 600 includes a Central Processing Unit (CPU) 601, which performs various appropriate actions and processes based on programs stored in ROM 602 or loaded into RAM 603 from storage section 608. Random access memory 603 also stores various programs and data required for system operation. The CPU 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0169] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card, such as a local area network card or modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0170] Specifically, according to embodiments of this application, the processes described in the various method flowcharts can be implemented as computer software programs. For example, embodiments of 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 communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit 601, it performs various functions defined in the system of this application.

[0171] It should be noted that, Figure 6 The computer system 600 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0172] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0173] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for identifying speed limits on ramps, characterized in that, include: Acquire a target road image, and extract a first set of speed limit signs and a first lane line from the target road image; The second lane line is determined based on a target aiming point, wherein the target aiming point is determined based on a fitting model of the aiming distance and the first lane line, the aiming distance is determined based on the vehicle's current speed and a preset aiming time reference value, and the second lane line is a portion of the lane line extracted from the first lane line based on the target aiming point. In response to the curvature of the second lane being greater than or equal to a preset curvature threshold, a target speed limit sign in the first set of speed limit signs is determined as the speed limit sign of the target ramp, and the speed limit value corresponding to the target speed limit sign is identified as the speed limit value of the target ramp. The target speed limit sign is a first speed limit sign in the first set of speed limit signs whose distance from the second lane is within a preset distance range, and the target ramp is the ramp corresponding to the second lane.

2. The method according to claim 1, characterized in that, Before determining the second lane line based on the target aiming point, the method further includes: A polynomial fit is performed on the first lane line to determine the fitting model of the first lane line, wherein the fitting model of the first lane line includes polynomial coefficients for representing the geometric features of the first lane line.

3. The method according to claim 1, characterized in that, The step of extracting the first set of speed limit signs and the first lane lines from the target road image includes: Lane line recognition is performed on the target road image to obtain the first lane line; The target road image is subjected to speed limit sign recognition to obtain a second speed limit sign set, and second speed limit signs that meet preset speed limit conditions are selected from the second speed limit sign set to obtain the first speed limit sign set. The preset speed limit conditions include at least one of the following: the speed limit value is located on the first side of the vehicle and the difference between the corresponding speed limit value and the most recently acquired historical effective speed limit value is less than a preset difference threshold; the speed limit value is located on the second side of the vehicle and the corresponding speed limit value is within a preset speed limit value range; the first side and the second side are different sides.

4. The method according to claim 1, characterized in that, After identifying the speed limit value corresponding to the target speed limit sign as the speed limit value of the target ramp, the method further includes: Based on driving information, the driving intention of the vehicle is identified, wherein the driving information includes at least one of the following: operation command signal, attitude parameters; If the vehicle's driving intention is to enter the target ramp, the speed limit value of the target ramp is transmitted to the vehicle's display unit for display. If the vehicle's driving intention is not to enter the target ramp, the speed limit value of the target ramp is discarded.

5. The method according to claim 4, characterized in that, When the driving information includes operation command signals, the operation command signals include at least one of the following: turn signal activation signal, steering wheel angle change signal; When the driving information includes attitude parameters, the attitude parameters include at least one of the following: vehicle roll angle and lateral acceleration.

6. The method according to claim 1, characterized in that, Before determining the target speed limit sign in the first set of speed limit signs as the speed limit sign of the target ramp, the method further includes: Determine the coordinates of each first speed limit sign in the first speed limit sign set; Based on the coordinates of each first speed limit sign and the fitting model of the second lane line, the shortest geometric distance between each first speed limit sign and the second lane line is determined, thus obtaining the distance between each first speed limit sign and the second lane line.

7. The method according to claim 1, characterized in that, After identifying the speed limit value corresponding to the target speed limit sign as the speed limit value of the target ramp, the method further includes: In response to the fulfillment of the exit condition, the identification of the speed limit value of the target ramp is stopped, wherein the exit condition includes at least one of the following: the duration for which the lane line curvature of the second lane is less than a preset curvature threshold is greater than a preset time threshold, and the lateral acceleration of the vehicle is less than a preset acceleration threshold.

8. A ramp speed limit recognition device, characterized in that, include: The first execution unit is used to acquire a target road image and extract a first set of speed limit signs and a first lane line from the target road image; The first determining unit is used to determine a second lane line based on a target pre-aiming point, wherein the target pre-aiming point is determined based on a fitting model of the pre-aiming distance and the first lane line, the pre-aiming distance is determined based on the current speed of the vehicle and a preset pre-aiming time reference value, and the second lane line is a portion of the lane line extracted from the first lane line based on the target pre-aiming point. The second execution unit is configured to, in response to the curvature of the second lane line being greater than or equal to a preset curvature threshold, determine the target speed limit sign in the first speed limit sign set as the speed limit sign of the target ramp, and identify the speed limit value corresponding to the target speed limit sign as the speed limit value of the target ramp, wherein the target speed limit sign is a first speed limit sign in the first speed limit sign set whose distance from the second lane line is within a preset distance range, and the target ramp is the ramp corresponding to the second lane line.

9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

Images