Curve overspeed early warning method and device, electronic equipment and medium

Abstract

The embodiment of the invention provides a curve overspeed early warning method and device, electronic equipment and a medium, and relates to the technical field of vehicles, and the method comprises the steps: obtaining at least two types of lane center line information obtained according to information collected by at least two types of sensors of a vehicle, the at least two types of sensors comprise a map sensor and a camera sensor, the map sensor comprises a positioning sensor and a module for acquiring map information, and each kind of lane center line information comprises a plurality of position points and the curvature of each position point; according to the at least two kinds of lane center line information, obtaining target lane center line information used for describing the lane center line of the road section in front of the vehicle, wherein the target lane center line information comprises a plurality of position points and the curvature of each position point; and if it is determined that a set curve overspeed early warning condition is established according to the center line information of the target lane and the vehicle speed of the vehicle, executing curve overspeed early warning processing. According to the embodiment of the invention, the occurrence rate of curve overspeed accidents can be reduced.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method, device, electronic equipment and medium for warning of speeding on a curve. Background Art

[0002] With the rapid development of the automobile industry, road traffic safety issues have received more and more attention, especially when driving on curves. Due to the driver's misjudgment of the curve conditions, speeding on curves and other reasons, the incidence of speeding accidents on curves is relatively high.

[0003] In order to reduce the incidence of speeding accidents on curves, a speeding warning on curves can be issued through the driving assistance system. Summary of the invention

[0004] The embodiments of the present application provide a curve speeding warning method, device, electronic equipment and medium, which can reduce the occurrence rate of curve speeding accidents.

[0005] In a first aspect, an embodiment of the present application provides a method for warning speeding on a curve, comprising: obtaining at least two types of lane centerline information, wherein the at least two types of lane centerline information are obtained based on information collected by at least two sensors of the vehicle, the at least two sensors include a map sensor and a camera sensor, the map sensor includes a positioning sensor and a module for obtaining map information, and each type of lane centerline information includes multiple position points and the curvature of each position point; obtaining target lane centerline information based on the at least two types of lane centerline information, the target lane centerline information includes multiple position points and the curvature of each position point, and the target lane centerline information is used to describe the lane centerline of the road section ahead of the vehicle; determining whether a set speeding warning condition for curve is met based on the target lane centerline information and the vehicle speed; and executing speeding warning processing for curve when the speeding warning condition for curve is met.

[0006] In an embodiment of the present application, the lane centerline information of the road section ahead of the vehicle is obtained based on the vehicle's multi-channel sensor information (including information from map sensors and camera sensors), and the lane centerline information and the vehicle's speed are combined to determine whether a curve speeding warning is needed, and then the curve speeding warning processing is performed as needed.

[0007] Compared with the curve speeding warning implementation method based on a single sensor (such as a camera or IMU gyroscope), the curve speeding warning implementation method based on multi-sensor fusion has better warning effect and better user experience.

[0008] By providing on-demand warnings for speeding on curves, the driver can be assisted in driving the vehicle safely, thereby reducing the probability of accidents caused by speeding on curves and improving driving safety in curve scenarios.

[0009] Optionally, based on the target lane centerline information and the vehicle speed, determining whether the set curve overspeed warning condition is met, including: when the target lane centerline information meets the set curve restriction condition, obtaining the safe speed information based on the curvature of the position point in the target lane centerline information; determining whether the vehicle speed meets the set curve overspeed condition based on the safe speed information; when the vehicle speed meets the curve overspeed condition, determining whether the set curve overspeed warning condition is met.

[0010] In the embodiment of the present application, it is determined whether the vehicle is traveling in a preset curve scene according to the lane centerline information, and when the vehicle is traveling in the curve scene, it is determined whether the vehicle is speeding on the curve. If the vehicle is speeding on the curve, it is further determined whether a curve overspeed warning is required, so that the curve overspeed warning can be executed on demand. By performing curve overspeed warning on demand, it can play an auxiliary guiding role for the driver to drive the vehicle safely, so as to reduce the probability of accidents caused by speeding on the curve and improve the driving safety of the curve scene.

[0011] Optionally, target lane centerline information is obtained based on at least two types of lane centerline information, including: obtaining a lane centerline length corresponding to each type of lane centerline information based on a position point in each type of lane centerline information obtained; obtaining a time distance corresponding to each type of lane centerline information based on a vehicle speed and a lane centerline length corresponding to each type of lane centerline information; fusing at least two types of lane centerline information based on the time distance corresponding to each type of lane centerline information, the priority of each type of lane centerline information and a set time distance threshold to obtain fused lane centerline information, the fused lane centerline information being one of the at least two types of lane centerline information; and obtaining target lane centerline information based on the fused lane centerline information.

[0012] When integrating multiple lane centerline information, by combining the time intervals corresponding to the various lane centerline information, the priorities of the various lane centerline information, and the preset time interval threshold, the current relatively optimal lane centerline information can be screened out from the multiple lane centerline information as the integrated lane centerline information. By always using the relatively optimal lane centerline information for curve overspeed warning, the curve overspeed warning effect is good.

[0013] Optionally, the priority of the first lane centerline information is higher than the priority of the second lane centerline information, the first lane centerline information is obtained according to information collected by the camera sensor, and the second lane centerline information is obtained according to information collected by the map sensor; the first time distance is the time distance corresponding to the first lane centerline information; the second time distance is the time distance corresponding to the second lane centerline information; at least two types of lane centerline information are fused according to the time distance corresponding to each type of lane centerline information, the priority of each type of lane centerline information and the set time distance threshold to obtain the fused lane centerline information, including: when the first time distance is greater than or equal to the time distance threshold, the first lane centerline information is used as the fused lane centerline information.

[0014] When fusing the camera perception results and the positioning perception results, by combining the time intervals corresponding to the two perception results, the high priority of the camera perception results and the preset time interval threshold, the better perception result can be determined from the two perception results as the fusion result according to different situations, and the fusion effect meets actual needs.

[0015] Optionally, acquiring target lane centerline information based on the fused lane centerline information includes: when the time distance corresponding to the fused lane centerline information is greater than the time distance threshold, intercepting the fused lane centerline information according to the time distance threshold to obtain intercepted lane centerline information; wherein the starting position point in the intercepted lane centerline information is the starting position point in the fused lane centerline information; acquiring target lane centerline information based on the intercepted lane centerline information, the time distance between adjacent position points in the target lane centerline information being the set time distance interval.

[0016] Compared with directly using the fused lane centerline information as the target lane centerline information, by intercepting and reshaping the fused lane centerline information as needed to obtain the target lane centerline information, accurate and timely curve overspeeding warnings can be achieved, avoiding unnecessary curve overspeeding false warnings during normal vehicle driving, and providing users with a better driving experience.

[0017] Optionally, determining whether a set curve overspeeding warning condition is met includes: determining whether a situation satisfying the curve overspeeding condition exists continuously, and whether the number of consecutive existences reaches a set number threshold.

[0018] This implementation method can serve the purpose of filtering to avoid frequent false warnings caused by errors in the link transmission process, fluctuations in the current vehicle speed, etc.

[0019] Optionally, determining whether the situation that satisfies the speeding condition on a curve exists continuously and the number of consecutive occurrences reaches a set number threshold includes: determining whether the count value of a counter reaches the number threshold; the speeding warning method on a curve also includes: when the vehicle speed meets the speeding condition on a curve, controlling the count value of the counter to increase by one; when the centerline information of the target lane does not meet the curve restriction condition, controlling the count value of the counter to be cleared; when the vehicle speed does not meet the speeding condition on a curve, controlling the count value of the counter to be cleared.

[0020] This can achieve the purpose of multi-layer filtering, so that the count value of the counter can accurately reflect whether the speeding situation on the curve exists continuously and the number of times it exists continuously. According to the count value, it can be quickly and accurately determined whether the speeding warning condition on the curve is met.

[0021] Optionally, the curve speeding warning method also includes: determining whether the target lane centerline information meets the curve restriction condition by determining whether there are at least i consecutive position points in the target lane centerline information, and the curvature of each of the at least i consecutive position points is within a set curvature range; wherein i represents a first preset number threshold.

[0022] By determining whether at least i continuous position points exist in the target lane centerline information, it is possible to accurately determine whether the vehicle is in the expected curve scene, providing support for accurate curve speeding warning.

[0023] Optionally, the curvature range is a range defined by a maximum curvature threshold and a minimum curvature threshold.

[0024] By setting the curvature range limited by the maximum curvature threshold and the minimum curvature threshold, false triggering of the curve speeding warning in scenarios such as straight road scenarios, near-straight road scenarios, U-turn scenarios, and intersection scenarios can be avoided, so that users have a better driving experience.

[0025] Optionally, the safe speed information includes the safe speed of each position point in the target group of position points; wherein, the position points in the target group of position points are continuous and the number is not less than n, and the curvature of each position point in the target group of position points is within the curvature range; determining whether the vehicle speed meets the set curve overspeeding condition, including: by determining whether there are at least n consecutive position points in the target group of position points, and the safe speed of each position point in at least n consecutive position points is not greater than the vehicle speed, to determine whether the vehicle speed meets the curve overspeeding condition; wherein n represents a second preset number threshold, and n≤i.

[0026] By judging whether there are at least n consecutive position points in the target group of position points, it is possible to accurately judge whether the vehicle is speeding on a curve, thereby providing support for accurate curve speeding warning.

[0027] In a second aspect, an embodiment of the present application provides a curve overspeed warning device, including: a first acquisition module, used to obtain at least two types of lane centerline information, wherein the at least two types of lane centerline information are obtained according to information collected by at least two sensors of the vehicle, the at least two sensors include a map sensor and a camera sensor, the map sensor includes a positioning sensor and a module for obtaining map information, and each type of lane centerline information includes multiple position points and the curvature of each position point; a second acquisition module, used to obtain target lane centerline information based on at least two types of lane centerline information, the target lane centerline information includes multiple position points and the curvature of each position point, and the target lane centerline information is used to describe the lane centerline of the road section ahead of the vehicle; a determination module, used to determine whether the set curve overspeed warning condition is met based on the target lane centerline information and the vehicle speed; a processing module, used to perform curve overspeed warning processing when the curve overspeed warning condition is met.

[0028] In a third aspect, an embodiment of the present application provides an electronic chip, comprising: a processor, which is used to execute computer program instructions stored in a memory, wherein when the computer program instructions are executed by the processor, the electronic chip is triggered to execute any method as in the first aspect.

[0029] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising at least one processor, wherein the processor and a memory are coupled, the memory is used to store computer program instructions, and the processor is used to execute the computer program instructions, wherein when the computer program instructions are executed by the processor, the electronic device is triggered to execute a method as described in any one of the first aspects.

[0030] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes any method in the first aspect.

[0031] In a sixth aspect, an embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is run on a computer, the computer executes any method in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1A schematic diagram of a process flow of a method for early warning of speeding on a curve provided by an embodiment of the present application;

[0034] Figure 2 A schematic diagram of a planned trajectory point string provided for an embodiment of the present application;

[0035] Figure 3 A schematic diagram of a driving assistance system provided by an embodiment of the present application;

[0036] Figure 4 A schematic diagram of a flow chart of a method for speeding warning on a curve based on multi-sensor fusion technology provided in one embodiment of the present application;

[0037] Figure 5 A block diagram of a curve speeding warning device provided in one embodiment of the present application;

[0038] Figure 6 A schematic diagram of the structure of a computer device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to better understand the technical solution of the present application, the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0040] It should be clear that the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0041] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0042] It should be understood that the term "at least one" used in this article refers to one or more, and "plurality" refers to two or more. The term "and / or" used in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. Among them, A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b and c can be represented by: a, b, c, ab, ac, bc, or abc, wherein a, b, c can be single or multiple.

[0043] It should be understood that, although the terms first, second, etc. may be used to describe the set thresholds in the embodiments of the present application, these set thresholds should not be limited to these terms. These terms are only used to distinguish the set thresholds from each other. For example, without departing from the scope of the embodiments of the present application, the first set threshold may also be referred to as the second set threshold, and similarly, the second set threshold may also be referred to as the first set threshold.

[0044] like Figure 1 As shown, an embodiment of the present application provides a method for warning of speeding on a curve, which may include the following steps 101 to 104. In one embodiment, Figure 1 The execution subject of the illustrated embodiment may be a vehicle.

[0045] Step 101, obtaining at least two types of lane centerline information, wherein the at least two types of lane centerline information are obtained based on information collected by at least two sensors of the vehicle, the at least two sensors include a map sensor and a camera sensor, the map sensor includes a positioning sensor and a module for obtaining map information, and each type of lane centerline information includes multiple position points and the curvature of each position point.

[0046] Step 102, obtaining target lane centerline information based on at least two types of lane centerline information, wherein the target lane centerline information includes multiple position points and the curvature of each position point, and the target lane centerline information is used to describe the lane centerline of the road section ahead of the vehicle.

[0047] In one embodiment, steps 101 to 104 may be periodically executed based on information collected in real time by vehicle sensors to ensure that the vehicle can safely pass through a curve at a low speed when passing through the curve.

[0048] In one embodiment, there may be multiple vehicle sensors for obtaining lane centerline information, such as camera sensors (i.e., visual perception sensors), map sensors (including positioning sensors and modules for obtaining map information), IMU (Inertial Measurement Unit) gyroscopes, laser radars, etc. These vehicle sensors can sense information about the actual scene in which the vehicle is located. In this way, the lane centerline information of the road ahead of the vehicle can be obtained in real time based on the information collected in real time by these vehicle sensors.

[0049] In one embodiment, the multiple position points included in the lane centerline information (or lane centerline point string information) may be a continuous series of position points. The position points may reflect information of corresponding positions (such as position coordinates).

[0050] In one embodiment of the present application, the camera sensor can capture the original image of the road section ahead of the vehicle in real time. By performing image analysis and processing on the original image, visual lane centerline information can be obtained. Since the information collected by the camera is affected by factors such as whether the camera is blocked and the degree of blockage, and the road conditions of the road section ahead of the vehicle, the lane centerline length corresponding to the lane centerline information obtained by the camera sensor may not be fixed.

[0051] In one embodiment of the present application, the positioning sensor can collect the positioning position of the vehicle in real time, and the positioning position can reflect the historical driving trajectory of the vehicle. According to the collected positioning position and the preset map information (the map information may include the position information of the road where the vehicle is located), the lane centerline information of the road where the vehicle is located can be determined. Unlike the camera sensor, the lane centerline length corresponding to the lane centerline information obtained by the map sensor can be a fixed length.

[0052] In one embodiment of the present application, the information collected by multiple sensors of the vehicle can be fused by multi-sensor fusion, and then the target lane centerline information can be obtained based on the fusion result, that is, the purpose of speeding warning on a curve can be achieved based on the multi-sensor fusion result. In the case where the lane centerline information is the lane centerline point string information, the obtained target lane centerline information is also called the planning trajectory point string.

[0053] Compared with the curve speeding warning implementation method based on a single sensor (such as a camera or IMU gyroscope), the curve speeding warning implementation method based on multi-sensor fusion has better warning effect and better user experience.

[0054] For example, when a single sensor such as a camera is used to achieve the purpose of speeding warning on a curve, the camera is easily blocked and cannot sense the center line of the lane at a long distance. For another example, when a single sensor such as an IMU gyroscope is used to achieve the purpose of speeding warning on a curve, there is a problem that the IMU gyroscope has a delayed warning. Although a single sensor can avoid the occurrence of speeding through a curve to a certain extent, it still has limitations. The speeding warning effect on a curve is not good, and the user experience is poor.

[0055] The multi-sensor fusion method does not use the perception results of sensors with poor current perception results, but uses the perception results of sensors with better current perception results. In this way, the purpose of speeding warning on curves can always be achieved based on the relatively optimal perception results, which can provide better speeding warning effects on curves.

[0056] In one feasible implementation, the lane centerline information obtained from the information collected by the map sensor and the lane centerline information obtained from the information collected by the camera sensor can be obtained, and the lane centerline information of the dual input sources can be fused, and then the target lane centerline information can be obtained based on the fused lane centerline information. This implementation can not only solve the problem of poor speeding warning effect on curves when using a single sensor, but also reduce the types of sensors set and simplify the solution processing flow.

[0057] In one embodiment of the present application, the step of acquiring target lane centerline information based on at least two types of lane centerline information may include: acquiring a lane centerline length corresponding to each type of lane centerline information based on a position point in each type of lane centerline information acquired; acquiring a time distance corresponding to each type of lane centerline information based on a vehicle speed and a lane centerline length corresponding to each type of lane centerline information; fusing at least two types of lane centerline information based on the time distance corresponding to each type of lane centerline information, the priority of each type of lane centerline information, and a set time distance threshold to obtain fused lane centerline information, the fused lane centerline information being one of the at least two types of lane centerline information; and acquiring target lane centerline information based on the fused lane centerline information.

[0058] The position points in the lane centerline information can form a trajectory point string, the length of the trajectory point string can be used as the lane centerline length, and then the lane centerline time distance can be calculated according to the lane centerline length and the vehicle speed. The time distance can be the quotient of the lane centerline length divided by the vehicle speed.

[0059] In one embodiment, please refer to Figure 2 The current speed of the vehicle may be Vc, and the direction is toward the front. The center line of the road where the vehicle is located may be shown as a dotted line between the road boundary lines on both sides.

[0060] For different types of lane centerline information, the longer the corresponding lane centerline length, the larger the calculated time distance. In addition, the same type of sensor can perceive different lane centerline lengths at different times. Taking a camera sensor as an example, the smaller the degree of occlusion of the camera sensor, the larger the shooting field of view, the more position points in the lane centerline information obtained based on the captured image, the longer the corresponding lane centerline length, and the larger the calculated time distance, the better the camera sensor's perception of the lane centerline, and thus a more timely and accurate judgment of speeding on a curve can be obtained. In this way, the current relatively optimal lane centerline information can be screened out based on the comparison results of the time distances and time distance thresholds corresponding to various lane centerline information.

[0061] Taking into account the possibility that there may be more than one lane centerline information corresponding to a time distance that is not less than the time distance threshold, in order to achieve a better multi-sensor fusion effect, in addition to the time distance corresponding to various lane centerline information and the preset time distance threshold, the current relatively optimal lane centerline information can also be screened out from multiple lane centerline information according to the priority of various lane centerline information.

[0062] For example, based on the visual accurate perception characteristics of the camera sensor, the priority of the lane centerline information of the corresponding camera sensor can be the highest, for example, higher than the priority of the lane centerline information of the corresponding map sensor. If the time distance calculated based on the lane centerline information of the corresponding camera sensor and the time distance calculated based on the lane centerline information of the corresponding map sensor are both greater than the time distance threshold, then based on the priority sorting, the lane centerline information of the corresponding camera sensor can be determined as the current relatively optimal lane centerline information.

[0063] When integrating multiple lane centerline information, by combining the time intervals corresponding to the various lane centerline information, the priorities of the various lane centerline information, and the preset time interval threshold, the current relatively optimal lane centerline information can be screened out from the multiple lane centerline information as the integrated lane centerline information. By always using the relatively optimal lane centerline information for curve overspeed warning, the curve overspeed warning effect is good.

[0064] Considering that if multiple lane centerline information is fitted into one lane centerline information as the fused lane centerline information, the fused lane centerline information always contains lane centerline information obtained based on poor perception results, resulting in poor fusion effect. In this way, unlike the implementation method of fitting multiple lane centerline information to obtain the fused lane centerline information, by combining the comparison results of the time distance corresponding to the lane centerline information and the time distance threshold, and combining priority sorting, the relatively optimal lane centerline information can always be used as the fused lane centerline information, and the multi-sensor fusion effect is better.

[0065] Among different types of lane centerline information, the lane centerline information with a longer lane centerline length is not necessarily the current optimal lane centerline information. In this way, unlike the implementation method of directly comparing the lane centerline lengths to determine the optimal lane centerline information, by combining the comparison results of the time distance corresponding to the lane centerline information and the time distance threshold, and combining priority sorting, the optimal lane centerline information determined can be more accurate and more in line with actual needs.

[0066] For the dual sensor fusion processing of the camera sensor and the map sensor, in one embodiment of the present application, the priority of the centerline information of the first lane is higher than the priority of the centerline information of the second lane, the centerline information of the first lane is obtained based on the information collected by the camera sensor, and the centerline information of the second lane is obtained based on the information collected by the map sensor; the first time distance is the time distance corresponding to the centerline information of the first lane; the second time distance is the time distance corresponding to the centerline information of the second lane.

[0067] Based on this, at least two types of lane centerline information are fused according to the time distance corresponding to each type of lane centerline information, the priority of each type of lane centerline information and the set time distance threshold to obtain fused lane centerline information, including: when the first time distance is greater than or equal to the time distance threshold, the first lane centerline information is used as the fused lane centerline information.

[0068] In one embodiment, if the time interval of the camera perception result is less than the time interval threshold, it can be considered that the camera sensor is blocked to a certain extent, or the road ahead of the vehicle is relatively curved.

[0069] Based on the limiting effect of the time interval threshold, if more than one perception result meets the time interval threshold limit, the time interval limit is weakened and the priority limit is strengthened. In this way, when more than one perception result meets the time interval threshold limit, a perception result with a relatively higher priority is selected.

[0070] Exemplarily, if the time intervals of the camera perception result and the positioning perception result both exceed the time interval threshold, even if the time interval of the positioning perception result is greater than the time interval of the camera perception result, the camera perception result with a higher priority is still taken as the fusion result.

[0071] Similarly, based on the limiting effect of the time interval threshold, if there are not at least two perception results that both meet the time interval threshold, the time interval size limitation is strengthened and the priority limitation is weakened. In this way, if there are not at least two perception results that both meet the time interval threshold, the perception result with a relatively larger time interval is selected.

[0072] There is no situation where at least two perception results both meet the time distance threshold limit. It may be a situation where the time distance of only one perception result meets the time distance threshold limit, or it may be a situation where the time distance of any perception result does not meet the time distance threshold limit.

[0073] When the time interval of only one perception result meets the time interval threshold limit, the perception result with a time interval exceeding the time interval threshold is selected (that is, the perception result with a relatively larger time interval is selected), even if the priority of the perception result is lower than the priority of the unselected perception result.

[0074] For example, if the time interval of the positioning perception result exceeds the time interval threshold, but the time interval of the camera perception result does not exceed the time interval threshold, even if the priority of the camera perception result is higher than the positioning perception result, the positioning perception result is still taken as the fusion result.

[0075] In the case where the time interval of any perception result does not satisfy the time interval threshold limit, a perception result with a relatively larger time interval is selected, even if the priority of the perception result is lower than the priority of the unselected perception result.

[0076] Exemplarily, if the time interval of the camera perception result and the positioning perception result does not exceed the time interval threshold, and the time interval of the positioning perception result is greater than the time interval of the camera perception result, even if the priority of the camera perception result is higher than the positioning perception result, the positioning perception result is still taken as the fusion result.

[0077] In this way, when only the camera perception results and the positioning perception results are fused, if the time intervals of the two perception results are both greater than the time interval threshold, the camera perception result will be used as the fusion result because the camera perception result has a higher priority; if the time interval of only one of the two perception results is greater than the time interval threshold, the perception result will be used as the fusion result; if the time intervals of the two perception results are both less than the time interval threshold, the perception result with the larger time interval will be used as the fusion result.

[0078] That is, compared with the perception results that do not meet the time interval threshold limit, the perception results that meet the time interval threshold limit will be used. If there is more than one perception result that meets the time interval threshold limit, the perception result with a relatively higher priority will be used. If there is no perception result that meets the time interval threshold limit, the perception result with a relatively larger time interval will be used.

[0079] Based on multiple limitations such as priority, time interval threshold, and time interval size, it supports the judgment of speeding warning on curves based on the overall relatively optimal perception results, which helps to improve the judgment accuracy of speeding warning on curves.

[0080] In one embodiment of the present application, when the second time distance is greater than the time distance threshold and the first time distance is less than the time distance threshold, the second lane centerline information is used as the fused lane centerline information.

[0081] In one embodiment of the present application, when the second time distance is less than the first time distance and the first time distance is less than the time distance threshold, the first lane centerline information is used as the fused lane centerline information.

[0082] In one embodiment of the present application, when the first time distance is less than the second time distance and the second time distance is less than a time distance threshold, the second lane centerline information is used as the fused lane centerline information.

[0083] When fusing the camera perception results and the positioning perception results, by combining the time intervals corresponding to the two perception results, the high priority of the camera perception results and the preset time interval threshold, the better perception result can be determined from the two perception results as the fusion result according to different situations, and the fusion effect meets actual needs.

[0084] In one embodiment of the present application, the step of acquiring target lane centerline information based on the fused lane centerline information may include: when the time distance corresponding to the fused lane centerline information is greater than the time distance threshold, intercepting the fused lane centerline information according to the time distance threshold to obtain intercepted lane centerline information; wherein the starting position point in the intercepted lane centerline information is the starting position point in the fused lane centerline information; acquiring the target lane centerline information based on the intercepted lane centerline information, the time distance between adjacent position points in the target lane centerline information being the set time distance interval.

[0085] In one embodiment, the product of the time interval threshold and the vehicle speed can be used as the lane centerline length required to implement the current curve speeding warning. Figure 2 In the driving situation shown, the vehicle speed is Vc, and the product of the headway threshold and Vc can be as follows Figure 2 The length indicated by the middle label s2. By using the time distance threshold and the vehicle speed to obtain the target lane centerline information, if there is a curve at a relatively long distance from the vehicle, the vehicle can temporarily ignore the speeding judgment for the curve, so as to avoid unnecessary speeding warnings during normal driving of the vehicle and reduce the user's driving experience.

[0086] In this way, if the time distance corresponding to the fused lane centerline information is greater than the time distance threshold, it can be considered that the lane centerline length corresponding to the fused lane centerline information is greater than the lane centerline length required for the curve overspeed warning. In order to avoid false warnings of curve overspeeding, the fused lane centerline information can be intercepted and processed according to the time distance threshold.

[0087] In one embodiment, the time distance corresponding to the intercepted lane centerline information may be equal to the time distance threshold, so that the required accurate judgment of speeding on a curve can be achieved.

[0088] By controlling the starting position point in the intercepted lane centerline information to be the starting position point in the fused lane centerline information, the intercepted lane centerline information can be made the lane centerline information of the road section ahead of the vehicle, providing support for timely and accurate judgment of speeding on curves.

[0089] In one embodiment, the starting position point may be the current position point of the vehicle.

[0090] If the time distance corresponding to the fused lane centerline information is less than the time distance threshold, no interception processing is required, that is, the fused lane centerline information is used as the intercepted lane centerline information.

[0091] In one embodiment, after interception processing is performed as needed, the intercepted lane centerline information can be used as the target lane centerline information.

[0092] In another embodiment, after interception processing is performed as needed, the intercepted lane centerline information can also be reshaped to obtain target lane centerline information. After the reshaping processing, the time distance between adjacent position points in the target lane centerline information can be made to be the set time distance interval, so as to provide support for subsequent accurate judgment of curve scenes and accurate judgment of speeding on curves based on the target lane centerline information.

[0093] In one embodiment, the number of position points in the target lane centerline information can be made larger than the number of position points in the intercepted lane centerline information through reshaping, so as to increase the number of position points. In this way, the number of position points in the lane centerline information obtained based on the information collected by the sensor can be smaller, so that the data processing volume is smaller and does not affect the accurate judgment of subsequent speeding on the curve.

[0094] In one embodiment, the position information and curvature of the newly supplemented position points can be calculated based on the position points and curvatures in the intercepted lane centerline information in combination with interpolation or bisection, thereby obtaining the position points and curvatures in the target lane centerline information.

[0095] Compared with directly using the fused lane centerline information as the target lane centerline information, by intercepting and reshaping the fused lane centerline information as needed to obtain the target lane centerline information, accurate and timely curve overspeeding warnings can be achieved, avoiding unnecessary curve overspeeding false warnings during normal vehicle driving, and providing users with a better driving experience.

[0096] Step 103, determining whether the set curve speeding warning condition is met according to the target lane centerline information and the vehicle speed.

[0097] It is feasible to determine whether the vehicle is traveling on a curve based on the target lane centerline information.

[0098] It is feasible to determine whether the vehicle is speeding on a curve based on the vehicle's speed.

[0099] It is feasible that if the vehicle is traveling on a curve, the safe speed of the vehicle in the current curve can be further obtained based on the target lane centerline information, and based on the comparison between the safe speed and the current speed of the vehicle, it can be determined whether the vehicle is speeding on the curve.

[0100] Thus, in one embodiment of the present application, step 103 may include: when the target lane centerline information satisfies the set curve restriction condition, obtaining safe speed information according to the curvature of the position point in the target lane centerline information; determining whether the vehicle speed satisfies the set curve overspeeding condition according to the safe speed information; and when the vehicle speed satisfies the curve overspeeding condition, determining whether the set curve overspeeding warning condition is established.

[0101] The target lane centerline information may include a plurality of position points and the curvature of each position point, and the plurality of position points may be a continuous series of position points. In this way, it may be determined whether the vehicle is traveling in the expected curve scene according to the target lane centerline information.

[0102] Considering that the vehicle can be in the pre-curve stage or in the mid-curve stage, the trajectory corresponding to the target lane centerline information is not always a curve line, that is, the curvature of the position points in the target lane centerline information is not always large. As long as at least a part of the trajectory is a curve line, it can be considered that the vehicle is currently in a curve scene, that is, the vehicle is about to or is passing through the curve.

[0103] Thus, in one embodiment of the present application, the curve speeding warning method also includes: determining whether there are at least i continuous position points in the target lane centerline information, and the curvature of each of the at least i continuous position points is within the set curvature range, to determine whether the target lane centerline information meets the curve restriction condition; wherein i represents a first preset number threshold.

[0104] In a feasible implementation, if the target lane centerline information contains curvatures {k n ,k n+1 …k n+i} of multiple consecutive positions, and satisfy x≤{k n ,k n+1 …k n+i}≤y, x is the minimum curvature threshold, y is the maximum curvature threshold, it can be determined that the target lane centerline information meets the curve restriction condition.

[0105] If there are at least i continuous position points as mentioned above, it can be considered that the trajectory line corresponding to the target lane centerline information has an expected curve line, and it can be confirmed that the vehicle is currently in a curve scene. Otherwise, it can be confirmed that the vehicle is not currently in a curve scene.

[0106] If the number of continuous position points within the set curvature range determined at adjacent time points increases, it may indicate that the vehicle is about to enter a curve. If the number of continuous position points within the set curvature range determined at adjacent time points decreases, it may indicate that the vehicle is about to exit a curve.

[0107] Please refer to Figure 2 The driving situation shown in FIG. 1 can determine that there are at least i continuous position points, which can be Figure 2 The dashed line shown is a series of position points on a curve at the front of the vehicle. The length of the curve is as follows: Figure 2 As shown in the label s1.

[0108] It can be seen that by judging whether there are at least i continuous position points mentioned above in the target lane centerline information, it is possible to accurately judge whether the vehicle is in the expected curve scene, providing support for the accurate implementation of curve speeding warning.

[0109] In one embodiment of the present application, the curvature range is a range defined by a minimum curvature threshold. In this way, those straight road scenes or nearly straight road scenes with a small curvature can be excluded, and the curve overspeed warning processing is not performed in these scenes to avoid the false triggering of the curve overspeed warning, which meets the actual needs.

[0110] Considering that in special curve scenarios such as U-turn scenarios and intersection driving scenarios, the curvature of the curve is high and the required safe speed at the curve is too low, it is easy to have multiple consecutive speeding situations on the curve, resulting in frequent speeding warnings on the curve and poor user experience. Based on this, it is not necessary to judge the speeding situation on the curve in this special curve scenario, so the maximum curvature threshold can be set to exclude these special curve scenarios.

[0111] In one embodiment of the present application, the curvature range is a range defined by a maximum curvature threshold and a minimum curvature threshold. In this way, those straight road scenes or nearly straight road scenes with a small curvature can be excluded, and those U-turn scenes and intersection driving scenes with a large curvature can be excluded. In these scenes, the curve speeding warning processing is not performed to avoid the frequent triggering of the curve speeding warning, which meets the actual needs.

[0112] By setting the curvature range limited by the maximum curvature threshold and the minimum curvature threshold, false triggering of the curve speeding warning in scenarios such as straight road scenarios, near-straight road scenarios, U-turn scenarios, and intersection scenarios can be avoided, so that users have a better driving experience.

[0113] If the target lane centerline information does not meet the curve restriction conditions, it can be said that the vehicle is not in the preset curve scene, which means that the vehicle is not currently speeding on the curve.

[0114] When it is determined that the vehicle is in an expected curve scenario, the safe speed information can be obtained based on the curvature of the position point in the target lane centerline information, so that it can be further determined whether the vehicle is speeding on the curve based on the safe speed information.

[0115] In one embodiment, the safe vehicle speed information can be obtained based on the curvature of the position points at the curve in the target lane centerline information (i.e., some or all of the position points that meet the curve restriction conditions). In this way, the safe vehicle speed information can include the safe vehicle speed of each position point at the curve.

[0116] Compared with calculating the safe speed information based on the curvature of each position point in the target lane centerline information, calculating the safe speed information based on the curvature of the position point at the curve can not only achieve accurate judgment of speeding on the curve, but also make the data volume of the safe speed information smaller and more targeted, thus reducing the amount of data processing.

[0117] In one embodiment, the safe vehicle speed at any position point can be obtained based on the curvature of the position point.

[0118] In one feasible implementation, the safe speed at a location point can be calculated according to the following formula:

[0119]

[0120] Wherein, V represents the safe vehicle speed at the position point, a represents the preset comfort / safety lateral acceleration (which can be obtained through calibration or experience), and k represents the curvature of the position point.

[0121] It can be seen that the greater the curvature of a position point, the more curved the corresponding position is, the smaller the safe speed at the position point is, and the more likely the current speed of the vehicle is to exceed the safe speed.

[0122] In one embodiment of the present application, the safe speed information includes the safe speed of each position point in the target group of position points; wherein the position points in the target group of position points are continuous and the number is not less than n, and the curvature of each position point in the target group of position points is within the curvature range. For example, if there are 50 continuous position points in the target lane centerline information, and the curvature is within the curvature range, and the first preset number threshold (i.e., i) is less than 50, such as i=30, then the target group of position points can be the 50 continuous position points, or can be a portion of the 50 continuous position points that is not less than n.

[0123] Based on the above content, determining whether the vehicle speed meets the set curve overspeeding condition includes: determining whether the vehicle speed meets the curve overspeeding condition by determining whether there are at least n consecutive position points in the target group of position points, and the safe speed of each of the at least n consecutive position points is not greater than the vehicle speed; wherein n represents a second preset number threshold, and n≤i.

[0124] In one embodiment, the curvature of the position points adjacent to the target group position points in the target lane centerline information is not within the curvature range, that is, the target group position points are all the position points on the curve rather than some of the position points. By calculating the safe speed of each position point on the curve, accurate judgment of speeding on the curve can be achieved.

[0125] If there are at least n consecutive position points, it can be considered that the vehicle speed is greater than the safe speed specified at the curve, that is, there is speeding on the curve. If there are no at least n consecutive position points, there is no speeding on the curve. By judging whether there are at least n consecutive position points in the target lane centerline information, it is possible to accurately judge whether the vehicle is speeding on the curve, providing support for accurate speeding warning on the curve.

[0126] Taking into account the possibility of false alarms in information such as vehicle speed and curvature, which may lead to the possibility of misjudgment of speeding on a curve, in order to avoid the false warning caused by this situation and affect the user's driving experience, the speeding warning on a curve is not issued when the speeding on a curve is detected. Instead, after the speeding on a curve is detected, it is further judged whether the conditions for the speeding warning on a curve are met, and the speeding warning on a curve is executed on demand based on the judgment result.

[0127] In one embodiment, whether the curve overspeeding warning condition is met can be determined by judging whether the number of times the curve overspeeding condition is met within a set time period reaches a corresponding number threshold.

[0128] In one cycle, a judgment result that the speeding condition on a curve is met or a judgment result that the speeding condition on a curve is not met can be obtained. If it is judged that the curve restriction condition is not met in one cycle, a judgment result that the speeding condition on a curve is not met can also be obtained.

[0129] In one embodiment, the set time period may be m cycles, and the number threshold may be m, that is, it is determined whether the curve overspeeding condition is met for m consecutive times. By setting the number threshold to m rather than a value less than m, filtering can be achieved to avoid frequent false warnings due to factors such as errors in the link transmission process and fluctuations in the current vehicle speed. Thus, in one embodiment of the present application, the step of determining whether the set curve overspeeding warning condition is met may include: determining whether the situation that meets the curve overspeeding condition exists continuously, and the number of consecutive existences reaches the set number threshold.

[0130] In a feasible implementation, the judgment results of whether the curve limitation conditions and the curve overspeeding conditions are met in each cycle can be recorded, and whether the curve overspeeding warning conditions are met can be determined based on the recorded contents of different cycles.

[0131] In another feasible implementation, a counter can be used to determine whether the curve overspeed warning condition is met. Thus, in one embodiment of the present application, the step of determining whether the situation that satisfies the curve overspeed condition exists continuously and the number of consecutive existences reaches a set number threshold can include: determining whether the count value of the counter reaches the number threshold. Based on this, the curve overspeed warning method also includes: when the vehicle speed meets the curve overspeed condition, controlling the count value of the counter to increase by one; when the target lane centerline information does not meet the curve restriction condition, controlling the count value of the counter to be cleared; when the vehicle speed does not meet the curve overspeed condition, controlling the count value of the counter to be cleared.

[0132] On the one hand, if the curve restriction condition is not met, it means that the vehicle is not in the expected curve scene, so there is no curve overspeeding, and the counter can be controlled to be cleared at this time; on the other hand, if the curve overspeeding condition is not met, it means that the vehicle is in the expected curve scene but is not speeding, that is, there is no curve overspeeding, and the counter can also be controlled to be cleared at this time. In this way, the purpose of multi-layer filtering can be achieved, and the count value of the counter can accurately reflect whether the curve overspeeding situation exists continuously and the number of times it exists continuously. According to the count value, it can quickly and accurately determine whether the curve overspeeding warning condition is established.

[0133] By controlling the counter to be cleared when it is determined that the curve restriction conditions are not met, frequent false warnings caused by curvature fluctuations can be avoided, thereby affecting the user's driving experience.

[0134] By limiting the speeding warning on a curve to when the count value reaches a threshold number of times, rather than issuing an immediate warning when speeding on a curve occurs, this can achieve a filtering purpose, thereby avoiding frequent false warnings due to errors in the link transmission process, fluctuations in the current vehicle speed, and other factors, thereby affecting the user's driving experience.

[0135] Step 104: When the curve overspeed warning condition is met, execute the curve overspeed warning process.

[0136] In one embodiment of the present application, the curve overspeed warning process can be performed by outputting a warning signal. The warning signal can prompt the driver through sound, image, vibration, etc. that the current curve speed is too high, there is danger, and the speed needs to be reduced.

[0137] Figure 1The curve speeding warning method provided in the embodiment obtains the lane centerline information of the road section ahead of the vehicle based on the vehicle's multi-channel sensor information (including information from map sensors and camera sensors), and determines whether a curve speeding warning is needed in combination with the lane centerline information and the vehicle's speed, and then performs the curve speeding warning processing as needed. Compared with the curve speeding warning implementation method based on a single sensor, the curve speeding warning implementation method based on multi-sensor fusion has a better warning effect and a better user experience. By performing curve speeding warning on demand, it can play an auxiliary guiding role in the driver's safe driving of the vehicle, thereby reducing the probability of accidents caused by speeding on curves and improving driving safety in curve scenarios.

[0138] Please refer to Figure 3 An embodiment of the present application provides a driving assistance system, which may include a sensor module 310, a controller 320, and an actuator 330. The driving assistance system may be used as a curve speed warning system (Curve Speed ​​Warning, CSW) to implement on-demand curve speed warning.

[0139] Among them, the sensor module 310 may include a positioning sensor 311, a camera sensor 312, a vehicle speed sensor 313 and a processing module 321; the controller 320 may include a perception module 322, a multi-sensor fusion module 323 and a curve speeding detection module 324; the actuator 330 may include a warning signal output module 331.

[0140] Please refer to Figure 3 The positioning sensor 311 can output the real-time collected positioning position to the processing module 321, and the processing module 321 can obtain the first lane centerline information according to the input positioning position and the pre-acquired map information. The first lane centerline information can be used to describe the lane centerline of the road section ahead of the vehicle. The first lane centerline information can be a lane centerline point string including a series of position points on the lane centerline and their curvatures.

[0141] The camera sensor 312 can output the original image captured in real time to the perception module 322, and the perception module 322 can perform image analysis processing on the input original image to obtain the second lane centerline information. The second lane centerline information can be used to describe the lane centerline of the road section ahead of the vehicle, and the second lane centerline information can be a lane centerline point string including a series of position points on the lane centerline and their curvatures.

[0142] In one feasible implementation, the perception module 322 can perform image analysis processing on the input original image through a built-in visual deep learning model to obtain a forward visual lane centerline point string with curvature information and position coordinates.

[0143] The multi-sensor fusion module 323 can fuse the two lane centerline point strings input according to the current vehicle speed collected and input in real time by the vehicle speed sensor 313 to obtain the target lane centerline information (or referred to as the planning trajectory point string herein). The target lane centerline information can be used to describe the lane centerline of the road ahead of the vehicle, and the target lane centerline information can be a lane centerline point string including a series of position points and their curvatures.

[0144] The curve overspeed detection module 324 can determine whether the vehicle is in the expected curve scene according to the input planning trajectory point string. If so, it further determines whether the vehicle is currently in a curve overspeed situation (i.e., the vehicle will overspeed through the curve if it does not slow down) according to the current vehicle speed collected and input in real time by the vehicle speed sensor 313 and the preset curve overspeed condition. If the vehicle is currently in a curve overspeed situation, it further determines whether the curve overspeed warning condition is met, and if so, a warning signal can be output.

[0145] In one embodiment, a counter may be built into the curve overspeed detection module 324 to determine whether the curve overspeed warning condition is met by comparing the count value of the counter with the number threshold.

[0146] The warning signal output module 331 can issue a curve overspeed warning reminder based on the input warning signal to remind the driver to reduce the speed and pass the curve scene at a low speed.

[0147] Figure 3 For the specific technical implementation of each unit module in the driving assistance system shown, reference may be made to the relevant technical descriptions of other embodiments of the present application, which will not be elaborated in this embodiment.

[0148] Figure 3 The sensors of the system shown integrate two types of sensors: positioning perception and visual perception. This can solve the limitations of the characteristics of a single sensor and the problem of false alarms, thereby enhancing the security, redundancy and robustness of the system from a hardware level.

[0149] Figure 3 A multi-sensor fusion module and a curve overspeed detection module are deployed in the controller of the system shown. A reasonable multi-layer fusion algorithm is used in the multi-sensor fusion module, and a reasonable filtering algorithm is used in the curve overspeed detection module. The false alarm problem caused by fluctuations in input data or errors in the calculation process can be solved. Therefore, the redundancy and robustness of the system are enhanced from the software level, and the false alarm rate of the system is reduced.

[0150] Figure 3The driving assistance system provided in the embodiment can realize the overspeed warning before the curve and the overspeed warning in the curve beyond the visual range, greatly improving the redundancy, safety and comfort of the system. The driving assistance system can play an auxiliary and guiding role for the driver to drive the vehicle safely by providing overspeed warning on the curve as needed, thereby reducing the probability of accidents caused by overspeeding on the curve and improving driving safety in the curve scene.

[0151] Please refer to Figure 4 In one embodiment of the present application, a method for warning speeding on a curve based on multi-sensor fusion technology is provided. The method may include the following steps 401 to 410. In one embodiment, the execution subject of the method may be Figure 3 Driving assistance systems shown.

[0152] Step 401, obtaining first lane centerline information based on information collected by the vehicle's camera sensor, and obtaining second lane centerline information based on information collected by the vehicle's map sensor, each type of lane centerline information includes multiple position points and the curvature of each position point, and each type of lane centerline information is used to describe the lane centerline of the road section ahead of the vehicle.

[0153] Step 402: obtaining a first time distance according to the vehicle speed and the position point in the first lane centerline information, and obtaining a second time distance according to the vehicle speed and the position point in the second lane centerline information.

[0154] Step 403, based on the first time distance, the second time distance, the priority of the first lane centerline information, the priority of the second lane centerline information and the set time distance threshold, the first lane centerline information and the second lane centerline information are fused to obtain fused lane centerline information, and the fused lane centerline information is one of the first lane centerline information and the second lane centerline information.

[0155] Among them, the priority of the center line information of the first lane is higher than the priority of the center line information of the second lane.

[0156] Step 404, determine whether the time distance corresponding to the fused lane centerline information is greater than the set time distance threshold. If so, execute step 405, otherwise use the fused lane centerline information as the intercepted lane centerline information and execute step 406.

[0157] Step 405 , the fused lane centerline information is intercepted and processed according to the time distance threshold to obtain intercepted lane centerline information, and the starting position point in the intercepted lane centerline information is the starting position point in the fused lane centerline information.

[0158] Step 406, reshape the captured lane centerline information to obtain target lane centerline information, wherein the target lane centerline information includes a plurality of position points and the curvature of each position point, and the time distance between adjacent position points in the target lane centerline information is a set time distance interval.

[0159] Step 407, determine whether there are at least i continuous position points in the target lane centerline information, and the curvature of each of the at least i continuous position points is within the set curvature range defined by the maximum curvature threshold and the minimum curvature threshold. If so, execute step 408, otherwise the count value of the control counter is cleared and the current process ends.

[0160] If the judgment result of step 407 is no, it can be indicated that the vehicle is not in the preset curve scene, that is, it can be indicated that the vehicle does not currently have a curve overspeed situation.

[0161] Step 408, obtaining the safe vehicle speed of each position point in the target group of position points; wherein the position points in the target group of position points are continuous and the number is not less than n, n≤i, the curvature of each position point in the target group of position points is within the set curvature range, and the safe vehicle speed of the position point is obtained according to the curvature of the position point.

[0162] Step 409, determine whether there are at least n consecutive position points in the target group of position points, and the safe speed of each position point in at least n consecutive position points is not greater than the speed of the vehicle. If so, the count value of the control counter is increased by one and step 410 is executed, otherwise the count value of the control counter is cleared to zero and the current process ends.

[0163] If the judgment result of step 409 is no, it can be indicated that the vehicle is in the preset curve scene but is not speeding, which can also be indicated that the vehicle is not currently speeding on the curve.

[0164] By controlling the count value of the counter to be incremented or reset as needed, the count value can reflect whether the vehicle continuously exceeds the speed limit on the curve and the number of times the vehicle continuously exceeds the speed limit on the curve.

[0165] Step 410, determine whether the count value of the counter reaches the number threshold, if so, execute the curve overspeed warning processing, otherwise end the current process and do not execute the curve overspeed warning processing.

[0166] In one embodiment, steps 401 to 410 may be executed periodically, and the count value of the counter is cleared or incremented in each execution cycle. When the count value of the counter reaches a threshold number of times, a curve speeding warning may be issued.

[0167] In one embodiment, the count value of the counter may be cleared after the curve speeding warning is performed.

[0168] Figure 4 For the specific technical implementation of each step in the illustrated embodiment, reference may be made to the relevant technical descriptions of other embodiments of the present application, which will not be elaborated in detail in this embodiment.

[0169] Through multi-sensor fusion processing, the fusion of multiple lane centerline information input sources can be achieved (see steps 401 to 406). When a speeding warning on a curve is performed based on the fusion result, the limitations and false alarm problems of speeding warning on a curve based on a single sensor can be solved.

[0170] The multi-layer filtering process (see step 407 and step 409) can solve the problem of false alarms caused by vehicle speed fluctuations and unstable results of the identified lane centerline curvature.

[0171] Figure 4 The curve speeding warning method shown is based on multi-sensor fusion processing and combined with multi-layer filtering processing. It can realize overspeed warning before the curve and overspeed warning in the curve beyond visual range. At the same time, as the vehicle speed increases, the warning distance can also be extended, which greatly improves the redundancy, safety and comfort of the warning system and is applicable to more scenarios.

[0172] like Figure 5 As shown, an embodiment of the present application provides a device 50 for warning speeding on a curve, comprising: a first acquisition module 501, for acquiring at least two types of lane centerline information, wherein the at least two types of lane centerline information are respectively obtained according to information collected by at least two sensors of the vehicle, the at least two sensors include a map sensor and a camera sensor, the map sensor includes a positioning sensor and a module for acquiring map information, and each type of lane centerline information includes a plurality of position points and a curvature of each position point; a second acquisition module 502, for acquiring target lane centerline information according to at least two types of lane centerline information, the target lane centerline information includes a plurality of position points and a curvature of each position point, and the target lane centerline information is used to describe the lane centerline of the road section ahead of the vehicle; a determination module 503, for determining whether a set warning condition for speeding on a curve is met according to the target lane centerline information and the vehicle speed; a processing module 504, for executing a warning process for speeding on a curve when the warning condition for speeding on a curve is met.

[0173] An embodiment of the present application provides an electronic chip, including: a processor, which is used to execute computer program instructions stored in a memory, wherein when the computer program instructions are executed by the processor, the electronic chip is triggered to execute the method described in any embodiment of the present application.

[0174] An embodiment of the present application provides an electronic device, which includes at least one processor, the processor and a memory are coupled, the memory is used to store computer program instructions, and the processor is used to execute the computer program instructions, wherein when the computer program instructions are executed by the processor, the electronic device is triggered to execute the method described in any embodiment of the present application.

[0175] An embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the method described in any embodiment of the present application.

[0176] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program runs on a computer, the computer executes the method described in any embodiment of the present application.

[0177] Figure 6 A schematic diagram of a computer device provided in one embodiment of the present application. Figure 6 As shown, the computer device 20 of this embodiment includes: a processor 21 and a memory 22, the memory 22 is used to store a computer program 23 that can be run on the processor 21, and the computer program 23 is executed by the processor 21 to implement the steps in the method embodiment of the present application. To avoid repetition, they are not described one by one here. Alternatively, when the computer program 23 is executed by the processor 21, the functions of each model / unit in the device embodiment of the present application are implemented. To avoid repetition, they are not described one by one here.

[0178] The computer device 20 includes but is not limited to a processor 21 and a memory 22. Those skilled in the art will appreciate that Figure 6 It is only an example of the computer device 20 and does not constitute a limitation of the computer device 20. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0179] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may be any conventional processor, etc.

[0180] The memory 22 may be an internal storage unit of the computer device 20, such as a hard disk or memory of the computer device 20. The memory 22 may also be an external storage device of the computer device 20, such as a plug-in hard disk, a Smart Media (SM) card, a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device 20. Further, the memory 22 may also include both an internal storage unit of the computer device 20 and an external storage device. The memory 22 is used to store the computer program 23 and other programs and data required by the computer device. The memory 22 may also be used to temporarily store data that has been output or is to be output.

[0181] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0182] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0183] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0184] The integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (Processor) to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program code.

[0185] In the embodiments of the present application, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, method, commodity or device including the element.

[0186] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0187] Those skilled in the art will appreciate that the various units and algorithm steps described in the embodiments of the present application can be implemented by a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0188] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the same or similar parts between the various embodiments in this application can be referred to each other. For example, the specific working process of the system, device and unit described in the embodiments of this application can refer to the corresponding process in the method embodiment of this application, and will not be repeated here.

[0189] The above description is only a specific embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for early warning of speeding on a curve, characterized in that: include: Acquire at least two types of lane centerline information, wherein the at least two types of lane centerline information are obtained based on information collected by at least two sensors of the vehicle, the at least two sensors include a map sensor and a camera sensor, the map sensor includes a positioning sensor and a module for acquiring map information, and each type of lane centerline information includes a plurality of position points and a curvature of each position point; Acquire target lane centerline information according to the at least two types of lane centerline information, wherein the target lane centerline information includes a plurality of position points and a curvature of each position point, and the target lane centerline information is used to describe the lane centerline of the road section ahead of the vehicle; Determining whether a set curve overspeed warning condition is met according to the target lane centerline information and the vehicle speed; When the curve overspeed warning condition is met, a curve overspeed warning process is executed.

2. The method according to claim 1, characterized in that The determining whether a set curve speeding warning condition is met according to the target lane centerline information and the vehicle speed includes: When the target lane centerline information satisfies the set curve restriction condition, obtaining safe vehicle speed information according to the curvature of the position point in the target lane centerline information; Determining whether the vehicle speed satisfies a set speeding condition on a curve according to the safe vehicle speed information; When the vehicle speed satisfies the curve overspeeding condition, it is determined whether the set curve overspeeding warning condition is met.

3. The method according to claim 1, characterized in that The acquiring the target lane centerline information according to the at least two lane centerline information comprises: According to the position point in each type of lane centerline information obtained, the lane centerline length corresponding to each type of lane centerline information is obtained; Obtaining a time distance corresponding to each type of lane centerline information according to the vehicle speed and the lane centerline length corresponding to each type of lane centerline information; According to the time distance corresponding to each type of lane centerline information, the priority of each type of lane centerline information and the set time distance threshold, the at least two types of lane centerline information are fused to obtain fused lane centerline information, where the fused lane centerline information is one of the at least two types of lane centerline information; The target lane centerline information is obtained according to the fused lane centerline information.

4. The method according to claim 3, characterized in that The priority of the centerline information of the first lane is higher than that of the centerline information of the second lane, the centerline information of the first lane is obtained according to the information collected by the camera sensor, and the centerline information of the second lane is obtained according to the information collected by the map sensor; The first time distance is the time distance corresponding to the first lane centerline information; The second time distance is the time distance corresponding to the centerline information of the second lane; The step of fusing the at least two types of lane centerline information according to the time distance corresponding to each type of lane centerline information, the priority of each type of lane centerline information, and the set time distance threshold to obtain the fused lane centerline information includes: When the first time distance is greater than or equal to the time distance threshold, the first lane centerline information is used as the fused lane centerline information.

5. The method according to claim 3, characterized in that: The acquiring the target lane centerline information according to the fused lane centerline information includes: When the time distance corresponding to the fused lane centerline information is greater than the time distance threshold, intercepting the fused lane centerline information according to the time distance threshold to obtain intercepted lane centerline information; Wherein, the starting position point in the intercepted lane centerline information is the starting position point in the fused lane centerline information; The target lane centerline information is acquired according to the intercepted lane centerline information, and the time distance between adjacent position points in the target lane centerline information is a set time distance interval.

6. The method according to any one of claims 1 to 5, characterized in that: The determining whether the set curve overspeed warning condition is met includes: It is determined whether the situation satisfying the curve overspeeding condition exists continuously and the number of times of continuous existence reaches a set number threshold.

7. The method according to claim 6, characterized in that The determining whether the situation satisfying the curve overspeeding condition exists continuously and the number of times of continuous existence reaches a set number threshold includes: Determine whether the count value of the counter reaches the number threshold; The method further includes: controlling the count value of the counter to increase by one when the speed of the vehicle meets the curve overspeeding condition; When the target lane centerline information does not satisfy the curve restriction condition, controlling the count value of the counter to be cleared; When the vehicle speed does not satisfy the curve overspeeding condition, the count value of the counter is controlled to be cleared.

8. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: By determining whether there are at least i continuous position points in the target lane centerline information, and the curvature of each of the at least i continuous position points is within a set curvature range, determining whether the target lane centerline information satisfies the curve restriction condition; Wherein, i represents the first preset number threshold.

9. The method according to claim 8, characterized in that The curvature range is a range defined by a maximum curvature threshold and a minimum curvature threshold.

10. The method according to claim 8, characterized in that The safe vehicle speed information includes the safe vehicle speed of each position point in the target group of position points; The position points in the target group of position points are continuous and the number is not less than n, and the curvature of each position point in the target group of position points is within the curvature range; The determining whether the vehicle speed satisfies a set curve overspeeding condition includes: Determining whether the speed of the vehicle satisfies the curve overspeeding condition by determining whether there are at least n consecutive position points in the target group of position points, and the safe vehicle speed of each of the at least n consecutive position points is not greater than the speed of the vehicle; Wherein, n represents the second preset number threshold, and n≤i.

11. A device for warning speeding on a curve, characterized in that: include: a first acquisition module, configured to acquire at least two types of lane centerline information, wherein the at least two types of lane centerline information are respectively acquired based on information collected by at least two sensors of the vehicle, the at least two sensors include a map sensor and a camera sensor, the map sensor includes a positioning sensor and a module for acquiring map information, and each type of lane centerline information includes a plurality of position points and a curvature of each position point; A second acquisition module is used to acquire target lane centerline information according to the at least two types of lane centerline information, wherein the target lane centerline information includes a plurality of position points and a curvature of each position point, and the target lane centerline information is used to describe the lane centerline of the road section ahead of the vehicle; A determination module, used to determine whether a set curve overspeed warning condition is met according to the target lane centerline information and the vehicle speed; The processing module is used to execute the curve overspeed warning processing when the curve overspeed warning condition is met.

12. An electronic device, characterized in that: The electronic device comprises at least one processor, the processor is coupled to a memory, the memory is used to store computer program instructions, and the processor is used to execute computer program instructions, wherein when the computer program instructions are executed by the processor, the electronic device is triggered to execute the method as described in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the method according to any one of claims 1 to 10.

Images