Speed limit sign information screening method and system based on coordinate transformation

Through the speed limit sign information screening method based on coordinate transformation, the problem of the speed limit sign being unable to judge the effectiveness when it exceeds the camera's field of view is solved, the speed limit sign recognition rate is improved, the risk of missed and false alarms is reduced, and the driving experience is improved .

CN119007430APending Publication Date: 2024-11-22SHENZHEN HANGSHENG ELECTRONICS
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410936246.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-12
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

In the prior art, the speed limit sign cannot be judged when it exceeds the camera's field of view, resulting in an increase in the risk of missed and false alarms.

Method used

The speed limit sign information screening method based on coordinate transformation is used to predict the position through vehicle status information and speed limit sign information, and compare it with lane line information to judge the effectiveness of the speed limit sign.

Benefits of technology

It improves the recognition rate of effective speed limiting signs, reduces the risk of missed and false alarms, and makes the driving experience of drivers and passengers more comfortable.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119007430A_ABST
    Figure CN119007430A_ABST
Patent Text Reader

Abstract

The invention provides a speed limit sign information screening method and system based on coordinate transformation, and relates to the technical field of intelligent driving, firstly, vehicle state information is obtained through a vehicle sensor, speed limit sign information and lane line information are obtained through a sensing camera, and the speed limit sign information is filtered; after the speed limit sign exceeds the visual field range of the sensing camera, carrying out transformation calculation on the speed limit sign coordinate of the previous frame, and predicting the speed limit sign coordinate of the current frame; the transverse effective distance is set based on the lane line information, the predicted speed limit sign coordinates are compared with the transverse effective distance, whether the speed limit sign is effective or not is judged, and finally the speed limit value of the effective speed limit sign is output. And the defect that the visual field of a camera is limited in visual perception is overcome, so that the recognition rate of the effective speed limit board is improved, the risk of missing report and false report is reduced, and the driving experience of a driver and passengers is more comfortable.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent driving, and more specifically, to a method and system for screening speed limit sign information based on coordinate transformation. Background Art

[0002] In autonomous driving or assisted driving systems, speed limit sign recognition technology can provide real-time road speed limit information and remind drivers to adjust their speed, thereby reducing the risk of traffic accidents. Accurate and effective speed limit sign recognition can effectively curb speeding, reduce traffic violation rates, and maintain road traffic order.

[0003] At present, the method of speed limit recognition mainly relies on the combination of navigation information and visual perception information. However, when the network signal is poor and the navigation information cannot be obtained in time, the judgment of the road type by visual perception alone is not very accurate. Therefore, the prior art discloses a vehicle speed limit prompt method. When a speed limit sign is detected, the speed limit sign information corresponding to the speed limit sign is obtained, and the vehicle information corresponding to the target vehicle is obtained; the number of speed limit signs of the speed limit sign is determined according to the speed limit sign information, the speed limit sign working condition is determined according to the speed limit sign number, and the current speed limit information is determined according to the speed limit sign working condition. Finally, the driver of the target vehicle is given a speed limit prompt according to the current speed limit information to improve the speed limit sign recognition effect. However, due to the limited field of view of the visual perception camera, when the vehicle is close to the speed limit sign, the speed limit sign exceeds the field of view of the camera, and the vehicle cannot receive the visual perception information, so it is impossible to judge the validity of the speed limit sign. Summary of the invention

[0004] In order to solve the problem that the validity of the current speed limit sign cannot be determined after it exceeds the field of view of the camera, the present invention proposes a speed limit sign information screening method and system based on coordinate transformation, which predicts the position and screens the validity of speed limit signs at close range through coordinate transformation calculation, thereby reducing the risk of missed reports and false reports.

[0005] In order to achieve the above technical effects, the technical solution of the present invention is as follows:

[0006] A method for screening speed limit sign information based on coordinate transformation, comprising:

[0007] S1. Obtain vehicle status information through the vehicle's own sensors, and obtain speed limit sign information and lane line information through perception cameras;

[0008] S2. Filter the speed limit sign information;

[0009] S3. Determine whether the speed limit sign exceeds the field of view of the perception camera. If so, predict the position of the speed limit sign. Based on the vehicle status information and the speed limit sign information, transform and calculate the speed limit sign coordinates of the previous frame to predict the speed limit sign coordinates of the current frame. Otherwise, return to step S2;

[0010] S4. Setting a lateral effective distance based on the lane line information, comparing the predicted speed limit sign coordinates with the lateral effective distance, and determining whether the speed limit sign is valid;

[0011] S5. Output the speed limit value of the effective speed limit sign.

[0012] This technical solution predicts the position of the speed limit sign in real time based on coordinate transformation, and then judges the validity of the speed limit sign, which solves some drawbacks of information that relies solely on visual perception and improves the recognition rate of effective speed limit signs.

[0013] Preferably, the vehicle state information acquired by the vehicle's own sensor includes the vehicle's own speed VehSpd and the yaw angular velocity ω.

[0014] Preferably, the speed limit sign information acquired by the perception camera includes the coordinates (X, Y) and the speed limit value of the speed limit sign in the VCS coordinate system, and the lane line information includes the lane line type and the intercept of the lane line in the VCS coordinate system, the lane line types include curb, solid line, dotted line and other types, and the intercept includes left intercept and right intercept.

[0015] Preferably, in step S2, the speed limit sign coordinates are smoothed by filtering, and the formula is as follows:

[0016] filter X =(1-K Gain )*Ob X +K Gain *Ma X

[0017] filter Y =(1-K Gain )*Ob Y +K Gain *Ma Y

[0018] Among them, (filter X ,filter Y ) is the filtered speed limit sign coordinate, K Gain is the filter coefficient to be calibrated, (Ob X ,Ob Y ) is the coordinate observation value calculated according to the coordinate transformation, (Ma x ,Ma Y) is the coordinate measurement value input by the perception camera; the coordinate transformation calculation process is shown in the coordinate transformation calculation formula in step S33.

[0019] Preferably, the process of step S3 includes:

[0020] S31 determines whether the speed limit sign information input signal disappears, if so, proceeds to step S32, otherwise, returns to step S2;

[0021] S32. Define static variables (Predict X ,Predict Y ) is used to store the position of the speed limit sign, and the static variable is initialized with the speed limit sign coordinates of the last frame before the speed limit sign information input signal disappears;

[0022] S33. Perform coordinate transformation on the speed limit sign coordinates of the last frame to obtain the speed limit sign coordinates of the current frame. The coordinate transformation calculation formula is as follows:

[0023] Predict X =Predict Y *sin(ω*dt)+Predic X *cos(ω*dt)+Coord X

[0024] Predict Y =Predict Y *cos(ω*dt)-Predict X *sin(ω*dt)+Coord Y

[0025] Where dt is the discrete sampling time, (Coord x ,Coord Y ) is the coordinate of the origin of the coordinate system of the previous frame in the coordinate system of the current frame; suppose the vehicle moves in a circle within the discrete sampling time dt, (Coord x ,Coord Y ) is calculated as follows:

[0026] (Coord x ,Coord Y )=(R*(1-cos(ω*dt)),R*sin(ω*dt))

[0027]

[0028] Among them, R is the radius of the circular motion of the vehicle in the discrete sampling time.

[0029] Preferably, in step S4, based on the lane line information, a lateral effective distance is set, and it is determined whether the speed limit sign is valid. The process is as follows:

[0030] According to the lane line type, set the lateral effective distances Dis1 to Dis4;

[0031] If the lane line type on one side of the speed limit sign is a curb, when and only when |Coord Y | < Dis1, it is determined that the speed limit sign is valid; otherwise, the speed limit sign is invalid;

[0032] If the lane line type on one side of the speed limit sign is a solid line, when and only when |Coord Y | < Dis2, it is determined that the speed limit sign is valid; otherwise, the speed limit sign is invalid;

[0033] If the lane line type on one side of the speed limit sign is a dotted line, when and only when |Coord Y | < Dis3, it is determined that the speed limit sign is valid; otherwise, the speed limit sign is invalid;

[0034] If the lane line type on one side of the speed limit sign is other types, when and only when |Coord Y | < Dis4, it is determined that the speed limit sign is valid; otherwise, the speed limit sign is invalid.

[0035] Preferably, according to the lane line type, setting the lateral effective distance includes the following process:

[0036] Calculate the current lane width LaneWidth according to the left lane line intercept LC0 and the right lane line intercept RC0. The calculation formula is as follows:

[0037] LaneWidth = |LC0| + |RC0|

[0038] The setting formula for the lateral effective distance is as follows:

[0039] Dis i = num i * LaneWidth + |C0|

[0040] where num i is the calibrated quantity to be marked with the lane line type, i = 1, 2, 3, 4; C0 is the lane line type on one side of the speed limit sign.

[0041] Preferably, in step S5, if the speed limit sign is valid, it is determined whether the vehicle itself has traveled to directly below the vertical of the speed limit sign. If so, initialize (Predict X , Predict Y ), and output the speed limit value corresponding to the speed limit sign; otherwise, return to step S33;

[0042] If the speed limit sign is invalid, directly (Predict X ,Predict Y )initialization.

[0043] Preferably, the basis for determining whether the vehicle is traveling directly below the speed limit sign is as follows:

[0044]

[0045] Among them, LastMa X is the longitudinal coordinate when the speed limit sign disappears, t k is the disappearance moment of the speed limit sign. When the time variable t satisfies the above inequality, it is determined that the vehicle travels to the vertical position directly below the speed limit sign at this moment.

[0046] A speed limit sign information screening system based on coordinate transformation, comprising:

[0047] An information input module is used to input vehicle status information acquired by the vehicle's own sensors and speed limit sign information and lane line information acquired by the perception camera;

[0048] A filtering module, used for filtering the speed limit sign information;

[0049] The coordinate prediction module is used to determine whether the speed limit sign exceeds the field of view of the perception camera. If so, the position of the speed limit sign is predicted. Based on the vehicle status information and the speed limit sign information, the coordinates of the speed limit sign in the previous frame are transformed and calculated to predict the coordinates of the speed limit sign in the current frame.

[0050] An effective distance judgment module is used to set a lateral effective distance based on lane line information, compare the predicted speed limit sign coordinates with the lateral effective distance, and judge whether the speed limit sign is valid;

[0051] The speed limit value output module is used to output the speed limit value of the effective speed limit sign.

[0052] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0053] The present invention proposes a speed limit sign information screening method and system based on coordinate transformation. Firstly, the vehicle status information is obtained through the vehicle's own sensor, the speed limit sign information and lane line information are obtained through the perception camera, and the speed limit sign information is filtered; after the speed limit sign exceeds the field of view of the perception camera, the position of the speed limit sign is predicted, the speed limit sign coordinates of the previous frame are transformed and calculated, and the speed limit sign coordinates of the current frame are predicted; the lateral effective distance is set based on the lane line information, the predicted speed limit sign coordinates are compared with the lateral effective distance, it is determined whether the speed limit sign is valid, and finally the speed limit value of the effective speed limit sign is output, which not only gets rid of the dependence of the speed limit sign recognition function on navigation information, but also overcomes the defect of limited camera field of view in visual perception, thereby improving the recognition rate of effective speed limit signs, reducing the risk of missed reports and false reports, and making the driving experience of drivers and passengers more comfortable. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic diagram showing a flow chart of a method for screening speed limit sign information based on coordinate transformation proposed in Embodiment 1 of the present invention;

[0055] Figure 2 A schematic diagram showing a flow chart of a speed limit sign coordinate prediction algorithm in Embodiment 2 of the present invention;

[0056] Figure 3 A schematic diagram showing the structure of a speed limit sign information screening system based on coordinate transformation proposed in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0057] The drawings are for illustrative purposes only and should not be construed as limiting the present patent;

[0058] In order to better illustrate the present embodiment, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the actual size;

[0059] It is understandable to those skilled in the art that descriptions of certain well-known contents in the drawings may be omitted.

[0060] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0061] The positional relationships described in the drawings are only for illustrative purposes and should not be construed as limiting the present patent;

[0062] Example 1

[0063] like Figure 1 As shown, this embodiment proposes a speed limit sign information screening method based on coordinate transformation, including:

[0064] S1. Obtain vehicle status information through the vehicle's own sensors, and obtain speed limit sign information and lane line information through perception cameras;

[0065] In this embodiment, the vehicle state information acquired by the vehicle's own sensor includes the vehicle's own speed VehSpd and the yaw angular velocity ω;

[0066] The vehicle status information acquired by the vehicle's own sensor includes the vehicle speed VehSpd and the yaw angular velocity ω; the speed limit sign information acquired by the perception camera includes the coordinates (X, Y) and the speed limit value of the speed limit sign in the VCS coordinate system, and the lane line information includes the lane line type and the intercept of the lane line in the VCS coordinate system, the lane line types include curb, solid line, dashed line and other types, and the intercept includes left intercept and right intercept.

[0067] S2. Filter the speed limit sign information.

[0068] S3. Determine whether the speed limit sign is beyond the field of view of the perception camera. If so, predict the position of the speed limit sign. Based on the vehicle status information and the speed limit sign information, transform and calculate the speed limit sign coordinates of the previous frame to predict the speed limit sign coordinates of the current frame. Otherwise, return to step S2.

[0069] S4. Set the lateral effective distance based on the lane line information, compare the predicted speed limit sign coordinates with the lateral effective distance, and determine whether the speed limit sign is valid; specifically, preset the lateral effective distances corresponding to the curb, solid line, dashed line and other types, and according to the identified lane line type, compare the predicted speed limit sign coordinates with the lateral effective distance corresponding to the lane line type to determine whether the speed limit sign is valid.

[0070] S5. Output the speed limit value of the effective speed limit sign.

[0071] Example 2

[0072] In this embodiment, see Figure 2 Based on the speed limit sign information screening method based on coordinate transformation proposed in Example 1, steps S2 to S5 are further explained.

[0073] The specific process of step S2 is as follows:

[0074] Smooth the speed limit sign coordinates through filtering:

[0075] filter X =(1-K Gain )*Ob X +K Gain *Ma X

[0076] filter Y =(1-K Gain )*Ob Y +K Gain *Ma Y

[0077] Among them, (filter X ,filter Y ) is the filtered speed limit sign coordinate, K Gain is the filter coefficient to be calibrated, (Ob X ,Ob Y ) is the coordinate observation value calculated according to the coordinate transformation, (Ma x ,Ma Y ) is the coordinate measurement value input by the perception camera; in this embodiment, the coordinate transformation calculation method can refer to step S33, but the coordinate observation value is not the same as the predicted coordinate obtained in S33, (Ob X ,Ob Y ) is calculated during the period when the perception camera can detect the speed limit sign, (Predict X ,Predict Y ) is calculated from the time when the camera senses that it can no longer detect the speed limit sign to the time when it outputs the speed limit value.

[0078] The specific process of step S3 includes:

[0079] S31 determines whether the speed limit sign information input signal disappears, if so, proceeds to step S32, otherwise, returns to step S2;

[0080] S32. Define static variables (Predict X ,Predict Y ) is used to store the position of the speed limit sign, and the static variable is initialized with the speed limit sign coordinates of the last frame before the speed limit sign information input signal disappears;

[0081] S33. Since the speed limit sign is stationary and only the car is moving all the time, the coordinate transformation of the speed limit sign in the previous frame coordinate system to the coordinate transformation of the current frame coordinate system can be calculated, and the coordinate transformation of the speed limit sign in the last frame coordinate system can be performed to obtain the coordinate transformation of the speed limit sign in the current frame. The coordinate transformation calculation formula is as follows:

[0082] Predict X =Predict Y *sin(ω*dt)+Predict X *cos(ω*dt)+Coord X

[0083] Predict Y =Predict Y *cos(ω*dt)-Predict X *sin(ω*dt)+Coord Y

[0084] Where dt is the discrete sampling time, (Coord x ,Coord Y ) is the coordinate of the origin of the coordinate system of the previous frame in the coordinate system of the current frame. In the actual calculation process, since dt is very short, it can be assumed that the vehicle is moving in a circle. Further, (Coord x ,Coord Y ) is calculated as follows:

[0085] (Coord x ,Coord Y )=(R*(1-cos(ω*dt)),R*sin(ω*dt))

[0086]

[0087] Where R is the radius of the circular motion.

[0088] In step S4, it is determined whether the speed limit sign is valid, and the determination process is as follows:

[0089] The current lane width LaneWidth is calculated based on the left lane line intercept LC0 and the right lane line intercept RC0. The calculation formula is as follows:

[0090] LaneWidth=|LC0|+|RC0|

[0091] The setting formula of the horizontal effective distance is as follows:

[0092] Dis i =num i *LaneWidth+|C0|

[0093] Among them, num i is the number of lane line types to be marked, i = 1, 2, 3, 4; C0 is the lane line type on the side of the speed limit sign;

[0094] According to the lane line type, set the lateral effective distance Dis1~Dis4;

[0095] If the lane type on the side of the speed limit sign is curb, then |Coord YWhen <Dis1, it is determined that the speed limit sign is valid; otherwise, the speed limit sign is invalid.

[0096] If the lane line type on one side of the speed limit sign is a solid line, if and only if |Coord Y When <Dis2, it is determined that the speed limit sign is valid; otherwise, the speed limit sign is invalid.

[0097] If the lane line type on one side of the speed limit sign is a dashed line, if and only if |Coord Y When <Dis3, it is determined that the speed limit sign is valid; otherwise, the speed limit sign is invalid.

[0098] If the lane line type on one side of the speed limit sign is other types, if and only if |Coord Y When <Dis4, it is determined that the speed limit sign is valid; otherwise, the speed limit sign is invalid.

[0099] As a preferred embodiment, the magnitude relationship of the effective distance satisfies:

[0100] Dis1 < Dis2 < Dis4 < Dis3

[0101] Specifically, its relationship needs to be calibrated according to the specific scenario.

[0102] In step S5, if the speed limit sign is valid, it is determined whether the vehicle itself has traveled to directly below the vertical of the speed limit sign. If so, (Predict X , Predict Y ) is initialized, and the speed limit value corresponding to the speed limit sign is output; otherwise, return to step S33; the judgment basis for whether the vehicle itself has traveled to directly below the vertical of the speed limit sign is as follows:

[0103]

[0104] Among them, LastMa X is the longitudinal coordinate when the speed limit sign disappears, t k is the disappearance time of the speed limit sign. When the time variable t satisfies the above inequality, it is determined that the vehicle itself has traveled to directly below the vertical of the speed limit sign at this moment;

[0105] If the speed limit sign is invalid, directly initialize (Predict X , Predict Y ) and output a prompt "The speed limit sign is invalid".

[0106] Embodiment 3

[0107] As Figure 3 shown, this embodiment proposes a speed limit sign information screening system based on coordinate transformation, including:

[0108] The information input module 101 is used to input the vehicle status information acquired by the vehicle's own sensors and the speed limit sign information and lane line information acquired by the perception camera;

[0109] A filtering module 102, used for filtering the speed limit sign information;

[0110] The coordinate prediction module 103 is used to determine whether the speed limit sign exceeds the field of view of the perception camera. If so, the position of the speed limit sign is predicted. Based on the vehicle state information and the speed limit sign information, the coordinates of the speed limit sign of the previous frame are transformed and calculated to predict the coordinates of the speed limit sign of the current frame.

[0111] The effective distance determination module 104 is used to set the lateral effective distance based on the lane line information, compare the predicted speed limit sign coordinates with the lateral effective distance, and determine whether the speed limit sign is valid;

[0112] The speed limit value output module 105 is used to output the speed limit value of the effective speed limit sign.

[0113] Obviously, the above embodiments of the present invention are only examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for screening speed limit sign information based on coordinate transformation, characterized in that: include: S1. Obtain vehicle status information through the vehicle's own sensors, and obtain speed limit sign information and lane line information through perception cameras; S2. Filter the speed limit sign information; S3. Determine whether the speed limit sign exceeds the field of view of the perception camera. If so, predict the position of the speed limit sign. Based on the vehicle status information and the speed limit sign information, transform and calculate the speed limit sign coordinates of the previous frame to predict the speed limit sign coordinates of the current frame. Otherwise, return to step S2; S4. Setting a lateral effective distance based on the lane line information, comparing the predicted speed limit sign coordinates with the lateral effective distance, and determining whether the speed limit sign is valid; S5. Output the speed limit value of the effective speed limit sign.

2. The method for screening speed limit sign information based on coordinate transformation according to claim 1, characterized in that: The vehicle state information acquired by the vehicle's own sensor includes the vehicle's own speed VehSpd and the yaw angular velocity ω.

3. The method for screening speed limit sign information based on coordinate transformation according to claim 2, characterized in that: The speed limit sign information acquired by the perception camera includes the coordinates (X, Y) and speed limit value of the speed limit sign in the VCS coordinate system, and the lane line information includes the lane line type and the intercept of the lane line in the VCS coordinate system. The lane line types include curb, solid line, dotted line and other types, and the intercept includes left intercept and right intercept.

4. The method for screening speed limit sign information based on coordinate transformation according to claim 1, characterized in that: In step S2, the speed limit sign coordinates are smoothed by filtering, and the formula is as follows: filter X =(1-K Gain )*Ob X +K Gain *Ha X filter Y =(1-K Gain )*Ob Y +K Gain *Ha Y Among them, (filter X ,filter Y ) is the filtered speed limit sign coordinate, K Gain is the filter coefficient to be calibrated, (Ob X ,Ob Y ) is the coordinate observation value calculated according to the coordinate transformation, (Ma x ,Ma Y ) is the coordinate measurement value input by the perception camera.

5. The method for screening speed limit sign information based on coordinate transformation according to claim 4, characterized in that: The process of step S3 includes: S31 determines whether the speed limit sign information input signal disappears, if so, proceeds to step S32, otherwise, returns to step S2; S32. Define static variables (Predict X ,Predict Y ) is used to store the position of the speed limit sign, and the static variable is initialized with the speed limit sign coordinates of the last frame before the speed limit sign information input signal disappears; S33. Perform coordinate transformation on the speed limit sign coordinates of the last frame to obtain the speed limit sign coordinates of the current frame. The coordinate transformation calculation formula is as follows: Predict X =Predict Y *sin(ω*dt)+Predict X *cos(ω*dt)+Coord X Predict Y =Predict Y *cos(ω*dt)-Predict X *sin(ω*dt)+Coord Y Where dt is the discrete sampling time, (Coord x ,Coord Y ) is the coordinate of the origin of the coordinate system of the previous frame in the coordinate system of the current frame; suppose the vehicle moves in a circle within the discrete sampling time dt, (Coord x ,Coord Y ) is calculated as follows: (Coord x ,Coord Y )=(R*(1-cos(ω*dt)),R*sin(ω*dt)) Among them, R is the radius of the circular motion of the vehicle in the discrete sampling time.

6. The method for screening speed limit sign information based on coordinate transformation according to claim 1, characterized in that: In step S4, the lateral effective distance is set based on the lane line information to determine whether the speed limit sign is valid. The process is as follows: According to the lane line type, set the lateral effective distance Dis1~Dis4; If the lane line type on one side of the speed limit sign is a curb, then and only then |Coord Y | < Dis1, it is determined that the speed limit sign is valid; otherwise, the speed limit sign is invalid; If the lane line type on one side of the speed limit sign is a solid line, if and only if |Coord Y | < Dis2, it is determined that the speed limit sign is valid; otherwise, the speed limit sign is invalid; If the lane line type on one side of the speed limit sign is a dotted line, if and only if|Coord Y |<Dis3, it is determined that the speed limit sign is valid; otherwise, the speed limit sign is invalid; If the lane line type on one side of the speed limit sign is of other types, if and only if|Coord Y | < Dis4, it is determined that the speed limit sign is valid; otherwise, the speed limit sign is invalid.

7. The method for screening speed limit sign information based on coordinate transformation according to claim 6, characterized in that: According to the lane line type, set the lateral effective distance. The process includes: The current lane width LaneWidth is calculated based on the left lane line intercept LC0 and the right lane line intercept RC0. The calculation formula is as follows: LaneWidth=|LC0|+|RC0| The setting formula of the horizontal effective distance is as follows: Drive i =number i *LaneWidth+|C0| Among them, num i is the number of lane line types to be marked, i = 1, 2, 3, 4; C0 is the lane line type on the side of the speed limit sign.

8. The method for screening speed limit sign information based on coordinate transformation according to claim 1, characterized in that: In step S5, if the speed limit sign is valid, determine whether the vehicle is traveling directly below the speed limit sign. If so, X ,Predict Y ) initializes and outputs the speed limit value corresponding to the speed limit sign; otherwise, returns to step S33; If the speed limit sign is invalid, directly (Predict X ,Predict Y )initialization.

9. The method for screening speed limit sign information based on coordinate transformation according to claim 8, characterized in that: The basis for judging whether the vehicle is traveling directly below the speed limit sign is as follows: Among them, LastMa X is the longitudinal coordinate when the speed limit sign disappears, t k is the disappearance moment of the speed limit sign. When the time variable t satisfies the above inequality, it is determined that the vehicle travels to the vertical position directly below the speed limit sign at this moment.

10. A speed limit sign information screening system based on coordinate transformation, characterized in that: include: An information input module is used to input vehicle status information acquired by the vehicle's own sensors and speed limit sign information and lane line information acquired by the perception camera; A filtering module, used for filtering the speed limit sign information; The coordinate prediction module is used to determine whether the speed limit sign exceeds the field of view of the perception camera. If so, the position of the speed limit sign is predicted. Based on the vehicle status information and the speed limit sign information, the coordinates of the speed limit sign in the previous frame are transformed and calculated to predict the coordinates of the speed limit sign in the current frame. An effective distance judgment module is used to set a lateral effective distance based on lane line information, compare the predicted speed limit sign coordinates with the lateral effective distance, and judge whether the speed limit sign is valid; The speed limit value output module is used to output the speed limit value of the effective speed limit sign.

Citation Information

Cited By

  • Vehicle information processing method and electronic equipment

    CN121459591A