Intelligent public security comprehensive management information system and declaration method

Abstract

The invention provides an intelligent public security comprehensive management information system and a declaration method, and relates to the technical field of intelligent public security, and the intelligent public security comprehensive management information system comprises a monitoring collection module which is used for setting a two-dimensional coordinate system on a monitoring road surface image and collecting monitoring road surface image data; a monitor is arranged on a monitored road surface, image data are collected, a right turn of a vehicle is analyzed and calculated, a right turn path of the vehicle is analyzed by setting a coordinate system and is compared with coordinates of pedestrians, and when the coordinates of the pedestrians are located on the upper side of the right turn path of the vehicle, the pedestrians are reminded to avoid through a voice broadcast device at the moment; the method can greatly reduce the accident occurrence probability of traffic security, specifically, the conversion speed, the acceleration and the steering angle of the vehicle are analyzed, the vehicle offset point is generated, the vehicle control point is generated, the method is more practical, the output is more accurate, the Bezier curve is used for analyzing the right turning track of the vehicle, and finally the track related formula is output.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent public security, and specifically to an intelligent public security comprehensive management information system and a reporting method. Background Art

[0002] Intelligent public security is an important field in modern urban management, aiming to improve public safety and traffic safety and ensure the safety of pedestrians. By applying advanced technologies such as big data, artificial intelligence, and the Internet of Things, intelligent public security establishes a comprehensive and real-time public security management system, enabling public security organs to conduct social governance more efficiently. Through technical means such as intelligent transportation systems, real-time monitoring, signal control, and traffic big data analysis, the traffic flow, accident information, and road conditions can be grasped in real time, so as to adjust traffic signals and dredge traffic in a timely manner, reducing congestion and traffic accidents.

[0003] Generally, at the crossroads of public security traffic, there are certain blind spots for right-turning vehicles, which cause drivers to be unable to accurately grasp the position information of pedestrians. When pedestrians enter the right-turn area of the vehicle without noticing, accidents are likely to occur.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and therefore it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent public security comprehensive management information system and a reporting method to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] An intelligent public security comprehensive management information system, comprising:

[0008] A monitoring and acquisition module, which sets a two-dimensional coordinate system on the monitored road surface image, acquires the monitored road surface image data, and performs graying processing on the image data;

[0009] An image data analysis module, which is used to perform correlation analysis on the image data to generate the vehicle speed v, acceleration a, and turning radius R;

[0010] A control point generation module, which is used to perform correlation analysis on the vehicle speed v, acceleration a, and turning radius R to generate vehicle offset points, and perform correlation analysis on the vehicle offset points to generate intermediate control points;

[0011] A trajectory generation module, which is used to perform correlation analysis on the intermediate control points using Bezier curves to generate the vehicle turning trajectory;

[0012] The early warning analysis module is used to collect the pedestrian position coordinates, perform a correlation analysis on the pedestrian position coordinates and the vehicle turning trajectory, output the prediction level of the pedestrian danger state, and output whether to enable voice warning according to the prediction level of the pedestrian danger state.

[0013] Further, a two-dimensional coordinate system is set on the monitored road surface image, where the y-axis is parallel to the road surface after turning, and the x-axis is parallel to the road before turning. The image data is grayscale processed according to the formula: , where I is the grayscale value of the pixel point of the converted image data, R is the red component value of the pixel point of the image data, G is the green component value of the pixel point of the image data, B is the blue component value of the pixel point of the image data. The YOLO algorithm is used to perform real-time object detection on the right boundary of the vehicle, identify the right boundary of the vehicle in each frame of image data and return its boundary coordinates. The boundary coordinates include the tail boundary coordinates and the head boundary coordinates. The Kalman filter is used to track the detected vehicle to update the vehicle position in real time.

[0014] Further, the Kalman filter is used to track the detected vehicle to update the vehicle position in real time, and the vehicle boundary coordinates of two consecutive frames are extracted from the result of the target tracking and , for the vehicle boundary coordinates of two consecutive frames and perform a correlation analysis to generate the vehicle speed v according to the formula:

[0015]

[0016] where is the time interval between two frames, and the vehicle speed v is used to reflect the vehicle speed;

[0017] Perform a correlation analysis on the vehicle speed to generate the vehicle acceleration a according to the formula:

[0018]

[0019] where and are two consecutive speed values generated by the vehicle speed v formula in the image data of three consecutive frames respectively. The vehicle acceleration a is used to reflect the vehicle acceleration;

[0020] Perform a correlation analysis on the vehicle speed v and the vehicle steering angle to generate the turning radius R according to the formula:

[0021]

[0022] where the vehicle steering angle Generated by analyzing the angle of the vehicle's front wheel in the image data through OpenCV software, where g is the acceleration due to gravity, and the turning radius R is used to reflect the size of the vehicle's turning profile.

[0023] Further, a correlation analysis is performed on the vehicle speed v, acceleration a, and turning radius R to generate the vehicle offset point d. The formula is as follows:

[0024]

[0025] where k is the offset proportionality coefficient, and its value range is [0.33, 0.25], where is the maximum safe driving speed of the vehicle under the current road conditions, is the maximum safe acceleration of the vehicle under the current road conditions.

[0026] Further, the intermediate control points include control point and control point , and a correlation analysis is performed on the vehicle offset point d, the vehicle steering angle , and the starting point coordinates to generate control point . The formula is as follows:

[0027]

[0028] where the starting point coordinates are the coordinates of the vehicle at the front end of the turning area;

[0029] A correlation analysis is performed on the vehicle offset point d, the vehicle steering angle , and the ending point coordinates to generate control point . The formula is as follows:

[0030]

[0031] where the ending point coordinates are the coordinates of the vehicle at the end of the turning area.

[0032] Further, a correlation analysis is performed on the intermediate control points, the starting point coordinates , and the ending point coordinates using the Bezier curve to generate the vehicle turning trajectory . The formula is as follows:

[0033]

[0034] where the vehicle turning trajectory Denote the coordinate points of the trajectory under the parameter t, simulate the vehicle turning path, set the total length to 1, and the parameter t is used to index the position points of the vehicle turning trajectory at the t length.

[0035] Furthermore, collect the pedestrian position coordinates, perform a correlation analysis on the pedestrian position coordinates and the vehicle turning trajectory, output the predicted level of the pedestrian danger state, and output whether to enable voice warning according to the predicted level of the pedestrian danger state. Collect the pedestrian position coordinates and compare them with the vehicle turning trajectory When the pedestrian position coordinates are on the upper side of the vehicle turning trajectory Output the predicted level of the pedestrian danger state as level one. At this time, the pedestrian is on the vehicle turning trajectory and is in a certain degree of danger. Enable voice warning to remind the pedestrian to stay away. When the pedestrian position coordinates are on the lower side of the vehicle turning trajectory Output the predicted level of the pedestrian danger state as level two. At this time, the pedestrian is not on the vehicle turning trajectory and the voice warning is not enabled.

[0036] The present invention also provides a method for reporting intelligent public security comprehensive management information, which is used to execute an intelligent public security comprehensive management information system, and specifically includes the following steps:

[0037] S1. Set up a two-dimensional coordinate system on the monitored road surface image, collect the monitored road surface image data, and perform gray-scale processing on the image data;

[0038] S2. Perform a correlation analysis on the image data to generate the vehicle speed v, acceleration a, and turning radius R;

[0039] S3. Perform a correlation analysis on the vehicle speed v, acceleration a, and turning radius R to generate vehicle offset points, and perform a correlation analysis on the vehicle offset points to generate intermediate control points;

[0040] S4. Use the Bezier curve to perform a correlation analysis on the intermediate control points to generate the vehicle turning trajectory;

[0041] S5. Collect the pedestrian position coordinates, perform a correlation analysis on the pedestrian position coordinates and the vehicle turning trajectory, output the predicted level of the pedestrian danger state, and output whether to enable voice warning according to the predicted level of the pedestrian danger state.

[0042] Compared with the prior art, the beneficial effects of the present invention are:

[0043] The present invention analyzes and calculates the right turn of a vehicle by collecting image data through a monitor set on a monitored road surface. By setting up a coordinate system, the right turn path of the vehicle is analyzed and compared with the coordinates of pedestrians. When the pedestrian coordinates are above the right turn path of the vehicle, a voice broadcast device is used to remind pedestrians to avoid and remind the driver to pay attention, which can greatly reduce the probability of traffic security accidents. Specifically, by analyzing the conversion speed, acceleration, and steering angle of the vehicle, a vehicle offset point is generated, and a vehicle control point is generated, which is more in line with the actual situation, the output is more accurate, the Bezier curve is used to analyze the right turn trajectory of the vehicle, and finally the relevant formula of the trajectory is output. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the overall system module of the present invention;

[0045] Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to specific embodiments.

[0047] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meaning understood by those of ordinary skill in the field to which the present invention belongs. The "first", "second", and similar terms used in the present invention do not represent any order, quantity, or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0048] Embodiment:

[0049] Please refer to Figure 1 , the present invention provides a technical solution:

[0050] An intelligent public security comprehensive management information system is applicable to cross-shaped intersections and analyzes the trajectories of right-turning vehicles at cross-shaped intersections. A voice broadcast reminder device installed beside the intersection is used to remind pedestrians to stay away from the trajectory route of right-turning vehicles, including:

[0051] The monitoring and acquisition module sets up a two-dimensional coordinate system on the monitored road surface image, acquires the monitored road surface image data, and performs grayscale processing on the image data;

[0052] A two-dimensional coordinate system is set up on the monitored road surface image, where the y-axis is parallel to the road surface after turning, and the x-axis is parallel to the road before turning. Perspective transformation and coordinate system drawing are realized through OpenCV, and grayscale processing is performed on the image data. The formula is as follows: , where I is the grayscale value of the pixel point of the converted image data. The unified color representation of the converted image can improve the accuracy of recognition and discrimination. R is the red component value of the pixel point of the image data, G is the green component value of the pixel point of the image data, and B is the blue component value of the pixel point of the image data. The YOLO algorithm is used to perform real-time object detection on the right boundary of the vehicle. OpenCV is used to read the image data, and each frame of image data is input into the YOLO model for object detection. The model output is parsed, and the detected right boundary box of the vehicle is drawn. The right boundary of the vehicle is recognized in each frame of image data and its boundary coordinates are returned. The boundary coordinates include the rear boundary coordinates and the front boundary coordinates of the vehicle. The Kalman filter is used to track the detected vehicle to update the vehicle position in real time.

[0053] The image data analysis module is used to perform correlation analysis on the image data and generate the vehicle speed v, acceleration a, and turning radius R;

[0054] The Kalman filter is used to track the detected vehicle to update the vehicle position in real time. The vehicle boundary coordinates of two consecutive frames are extracted from the result image data of target tracking and , where and are the coordinate points of the same point on the same vehicle in the image data of two consecutive frames. Correlation analysis is performed on the vehicle boundary coordinates and of two consecutive frames to generate the vehicle speed v. The formula is as follows:

[0055]

[0056] where is the time interval between two frames. The vehicle speed v is used to reflect the speed of the vehicle. This speed is not the actual vehicle speed. Strictly speaking, it is the moving speed of the vehicle boundary in the image data and is only used for subsequent calculation and analysis;

[0057] Correlation analysis is performed on the vehicle speed to generate the vehicle acceleration a. The formula is as follows:

[0058]

[0059] Among them, and are respectively two consecutive speed values generated by the vehicle speed v formula in the image data of three consecutive frames. The vehicle acceleration a is used to reflect the vehicle acceleration and is obtained by calculating based on the speed v.

[0060] Perform a correlation analysis on the vehicle speed v and the vehicle steering angle to generate the turning radius R. The formula relied on is:

[0061]

[0062] Among them, the vehicle steering angle is generated by analyzing the angle of the vehicle's front wheels in the image data through the OpenCV software. g is the acceleration due to gravity. The turning radius R is used to reflect the size of the vehicle's turning contour.

[0063] Use the Bezier curve to analyze the vehicle's motion trajectory. During the analysis process, limit the vehicle's motion trajectory through the vehicle speed v, acceleration a, and turning radius R, so as to accurately analyze the vehicle offset point. Specifically, the analysis is carried out through the following modules:

[0064] The control point generation module is used to perform a correlation analysis on the vehicle speed v, acceleration a, and turning radius R to generate the vehicle offset point, and perform a correlation analysis on the vehicle offset point to generate the intermediate control point;

[0065] The offset point refers to a point that is offset through a certain algorithm based on the Bezier curve, thereby forming a new curve path, that is, the vehicle's motion trajectory. The offset point can be used as a constraint condition for the vehicle's motion trajectory.

[0066] Perform a correlation analysis on the vehicle speed v, acceleration a, and turning radius R to generate the vehicle offset point d. The formula relied on is:

[0067]

[0068] Among them, k is the offset proportionality coefficient, and its value range is [0.33, 0.25]. Among them is the maximum safe driving speed of the vehicle under the current road conditions, is the maximum safe acceleration of the vehicle under the current road conditions, which is obtained through experimental analysis and measurement. The offset proportionality coefficient k is a parameter used to describe the deflection degree of the Bezier curve and is set , The offset ratio coefficient, as the offset, can ensure the smoothness of turning and is closer to the actual situation. The maximum safe driving speed and maximum safe acceleration of the vehicle affect the lateral force and dynamic stability borne by the vehicle during turning. During the turning process, the dynamic characteristics of the vehicle are significantly affected by speed and acceleration. When turning, the vehicle not only needs to overcome the centripetal force but also manage the centrifugal force caused by speed and acceleration. When the vehicle speed approaches the maximum safe driving speed, the centrifugal force increases, and the vehicle requires a larger offset distance to maintain its stability during turning. That is, the closer the vehicle speed and acceleration are to the maximum safe driving speed and maximum safe acceleration of the vehicle, the greater the degree of deflection, resulting in a larger offset point d.

[0069] Further, the intermediate control points include control point and control point , perform a correlation analysis on the vehicle offset point d, the vehicle steering angle , and the starting point coordinates to generate control point , and the formula is:

[0070]

[0071] where the starting point coordinates are the coordinates of the vehicle at the front end of the turning area;

[0072] Perform a correlation analysis on the vehicle offset point d, the vehicle steering angle , and the end point coordinates to generate control point , and the formula is:

[0073]

[0074] where the end point coordinates are the coordinates of the vehicle at the end of the turning area.

[0075] The intermediate control points are key parameters in the Bezier curve generation algorithm. They determine the shape and bending degree of the vehicle trajectory curve. By analyzing the vehicle offset point and using trigonometric functions to obtain the positions of the control points in the coordinate system, the offset and direction can be converted into specific coordinate values. Through the setting of the control points, the bending degree and direction of the curve can be precisely controlled.

[0076] The trajectory generation module is used to perform a correlation analysis on the intermediate control points using the Bezier curve to generate the vehicle turning trajectory;

[0077] Perform a correlation analysis on the intermediate control points, the starting point coordinates , and the end point coordinates using the Bezier curve to generate the vehicle turning trajectory , and the formula is as follows:

[0078]

[0079] where the vehicle turning trajectory represents the coordinate point of the trajectory at parameter t. The vehicle turning path is simulated, and the total length is set to 1. The parameter t is used to index the position of the vehicle turning trajectory at length t. For example, when t = 0, it is the starting point of the vehicle turning trajectory, and when t = 1, it is the ending point of the vehicle turning trajectory.

[0080] An early warning analysis module, which is used to collect the pedestrian position coordinates, perform a correlation analysis on the pedestrian position coordinates and the vehicle turning trajectory, output the predicted level of the pedestrian danger state, and output whether to enable voice warning according to the predicted level of the pedestrian danger state.

[0081] Furthermore, collect the pedestrian position coordinates, perform a correlation analysis on the pedestrian position coordinates and the vehicle turning trajectory, output the predicted level of the pedestrian danger state, output whether to enable voice warning according to the predicted level of the pedestrian danger state, collect the pedestrian position coordinates, and compare them with the vehicle turning trajectory When the pedestrian position coordinates are above the vehicle turning trajectory , that is, the pedestrian may coincide with the vehicle turning trajectory, output the predicted level of the pedestrian danger state as level one. At this time, the pedestrian is on the vehicle turning trajectory and has a certain degree of danger. Enable voice warning to remind the pedestrian to stay away. When the pedestrian position coordinates are below the vehicle turning trajectory , output the predicted level of the pedestrian danger state as level two. At this time, the pedestrian is not on the vehicle turning trajectory, and voice warning is not enabled.

[0082] Referring to Figure 2 , the present invention also provides a method for reporting intelligent public security comprehensive management information, which is used to execute an intelligent public security comprehensive management information system, and specifically includes the following steps:

[0083] Step 1: Set a two-dimensional coordinate system on the monitored road surface image, collect the monitored road surface image data, and perform grayscale processing on the image data;

[0084] Step 2: Perform a correlation analysis on the image data to generate the vehicle speed v, acceleration a, and turning radius R;

[0085] Step 3: Perform a correlation analysis on the vehicle speed v, acceleration a, and turning radius R to generate vehicle offset points, and perform a correlation analysis on the vehicle offset points to generate intermediate control points;

[0086] Step 4: Use the Bezier curve to perform a correlation analysis on the intermediate control points to generate the vehicle turning trajectory;

[0087] Step 5: Collect the pedestrian position coordinates, perform a correlation analysis on the pedestrian position coordinates and the vehicle turning trajectory, output the predicted level of the pedestrian's dangerous state, and output whether to enable voice warning according to the predicted level of the pedestrian's dangerous state.

[0088] All the above formulas are dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0089] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0090] 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. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0091] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all of them should be covered by the protection scope of the present application.

Claims

1. A smart public security integrated management information system, characterized in that: include: The monitoring acquisition module sets a two-dimensional coordinate system on the monitored road surface image, collects the monitored road surface image data, and performs grayscale processing on the image data; An image data analysis module is used to perform correlation analysis on the image data and generate vehicle speed v, acceleration a, and turning radius R; A control point generation module is used to perform correlation analysis on the vehicle speed v, acceleration a, and turning radius R to generate vehicle offset points, and to perform correlation analysis on the vehicle offset points to generate intermediate control points; The trajectory generation module is used to perform correlation analysis on the intermediate control points using Bezier curves to generate the vehicle turning trajectory; The warning analysis module is used to collect the pedestrian position coordinates, perform correlation analysis on the pedestrian position coordinates and the vehicle turning trajectory, output the pedestrian danger state prediction level, and output whether to enable voice warning based on the pedestrian danger state prediction level.

2. According to claim 1, the intelligent public security integrated management information system is characterized by: A two-dimensional coordinate system is set on the monitored road surface image, where the y-axis is parallel to the road surface after the turn, and the x-axis is parallel to the road before the turn. The image data is grayed out, and the formula is as follows: , where I is the grayscale value of the converted image data pixel, R is the red component value of the image data pixel, G is the green component value of the image data pixel, and B is the blue component value of the image data pixel. The YOLO algorithm is used to perform real-time target detection on the right boundary of the vehicle. The right boundary of the vehicle is identified in each frame of image data and its boundary coordinates are returned. The boundary coordinates include the rear boundary coordinates and the front boundary coordinates. The Kalman filter is used to track the detected vehicle to update the vehicle position in real time.

3. According to claim 2, the intelligent public security integrated management information system is characterized by: The Kalman filter is used to track the detected vehicle, update the vehicle position in real time, and extract the vehicle boundary coordinates of two consecutive frames from the target tracking results. and , for the vehicle boundary coordinates of two consecutive frames and Correlation analysis is performed to generate the vehicle speed v, based on the formula: in, is the time interval between two frames, and the vehicle speed v is used to reflect the speed of the vehicle; The vehicle speed is correlated and the vehicle acceleration a is generated based on the following formula: in, and They are two consecutive speed values ​​generated by the vehicle speed v formula in three consecutive frames of image data, and the vehicle acceleration a is used to reflect the vehicle acceleration; For vehicle speed v, vehicle steering angle Correlation analysis is performed to generate the turning radius R, based on the formula: The vehicle steering angle The OpenCV software is used to analyze the angle of the front wheel of the vehicle in the image data. g is the acceleration of gravity, and the turning radius R is used to reflect the turning profile size of the vehicle.

4. According to claim 3, the intelligent public security integrated management information system is characterized by: The vehicle speed v, acceleration a, and turning radius R are correlated and the vehicle offset point d is generated based on the following formula: Among them, k is the offset proportional coefficient, and its value range is [0.33, 0.25]. is the maximum safe driving speed of the vehicle under the current road conditions, It is the maximum safe acceleration of the vehicle under the current road conditions.

5. According to claim 4, the intelligent public security integrated management information system is characterized by: The intermediate control points include control points and control points , for the vehicle offset point d, the vehicle steering angle , starting point coordinates Perform correlation analysis and generate control points , the formula based on is: The starting point coordinates is the coordinate of the front end of the vehicle in the turning area; For the vehicle offset point d and the vehicle steering angle , End point coordinates Perform correlation analysis and generate control points , the formula based on is: The ending point coordinates are the coordinates of the vehicle at the end of the turning area.

6. According to claim 5, a smart public security integrated management information system is characterized by: Use Bezier curve to adjust the coordinates of the middle control point and the starting point , End point coordinates Perform correlation analysis to generate vehicle turning trajectories , the formula based on is: The vehicle turning trajectory Represents the coordinate point of the trajectory under parameter t, simulates the vehicle turning path, sets the total length to 1, and the parameter t is used to index the point position of the vehicle turning trajectory under length t.

7. The intelligent public security integrated management information system according to claim 6 is characterized by: Collect the coordinates of pedestrians, analyze the correlation between the coordinates of pedestrians and the turning trajectory of vehicles, output the predicted level of pedestrian danger status, and output whether to enable voice warning according to the predicted level of pedestrian danger status. Compare, when the pedestrian position coordinates are in the vehicle turning trajectory When the pedestrian is on the turning track of the vehicle, the output pedestrian danger state prediction level is level 1. At this time, the pedestrian is on the turning track of the vehicle, which is dangerous. The voice warning is activated to remind the pedestrian to stay away. When the pedestrian position coordinates are on the turning track of the vehicle When it is on the lower side, the output pedestrian danger state prediction level is level 2. At this time, the pedestrian is not on the vehicle turning trajectory and the voice warning is not enabled.

8. A method for reporting smart public security integrated management information, used to implement a smart public security integrated management information system as claimed in claim 1, characterized in that: The specific steps include: S1. Setting a two-dimensional coordinate system on the monitored road surface image, collecting monitored road surface image data, and gray-processing the image data; S2. Perform correlation analysis on the image data to generate vehicle speed v, acceleration a, and turning radius R; S3, performing correlation analysis on the vehicle speed v, acceleration a, and turning radius R to generate a vehicle offset point, performing correlation analysis on the vehicle offset point to generate an intermediate control point; S4, using Bezier curves to perform correlation analysis on the intermediate control points to generate a vehicle turning trajectory; S5. Collect the coordinates of the pedestrian's position, perform correlation analysis on the pedestrian's position coordinates and the vehicle's turning trajectory, output the pedestrian's dangerous state prediction level, and output whether to enable voice warning based on the pedestrian's dangerous state prediction level.

Images