Roadway debris determination and alerting method, system, device, and storage medium

Abstract

The application discloses a highway throwing object judgment and alarm method, system, device and storage medium, and belongs to the technical field of throwing object detection and identification. The highway throwing object judgment and alarm method comprises the following steps: constructing an associated area based on a dynamic moving vehicle, and performing motion monitoring on a target in the associated area; the target is preliminarily judged as a to-be-throwing object when the difference between the motion of the target in the associated area and the motion speed of the vehicle exceeds an associated threshold speed; the motion state of the to-be-throwing object is continuously monitored; the to-be-throwing object is judged as a throwing object when the to-be-throwing object is located outside the associated area of the vehicle and the motion speed of the throwing object is reduced to zero; and alarm is performed based on the number of lanes and the lane number occupied by the throwing object. The application identifies the throwing object by detecting the position and speed characteristics of the vehicle and the throwing object target, discards the monitoring method of the visual sensor, eliminates the influence of weather and illumination on the monitoring result, and still obtains a good monitoring effect at a long distance.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of detection and identification of thrown objects, in particular to a highway thrown object determination and alarm method, system, device and storage medium. BACKGROUND

[0002] At present, the identification method of highway thrown objects is generally realized based on visual detection. However, the visual sensor is greatly affected by weather and light. For example, in heavy fog, heavy rain or at night, its detection effect is poor or even invalid. Secondly, when the target distance of the visual sensor is far away, such as more than 500m, its target detection effect will also decrease a lot, especially for the fast-moving target far away, its detection effect is even worse. Therefore, in the highway scene, it is difficult to achieve good results by simply relying on vision to detect thrown objects. SUMMARY

[0003] The purpose of the present application is to provide a highway thrown object determination and alarm method, system, device and storage medium, which aims to solve the technical problem of poor detection effect of highway thrown objects.

[0004] Technical scheme: In a first aspect, the present application provides a highway thrown object determination and alarm method, comprising the following steps:

[0005] Confirming the associated area of the first target;

[0006] In response to the second target being located in the associated area, and the difference between the speed of the first target and the speed of the second target in the second direction being less than the preset associated threshold speed, determining that the second target is a to-be-thrown object, wherein the length direction of the lane is the second direction;

[0007] In response to the to-be-thrown object being located outside the associated area, and the speed of the to-be-thrown object being zero, determining that the to-be-thrown object is a thrown object;

[0008] Based on the lane number and the number of lanes occupied by the thrown object when the speed of the thrown object is zero, an alarm is given.

[0009] In some embodiments, the step of confirming the associated area of the first target comprises:

[0010] The width direction of the lane is the first direction;

[0011] Obtaining the position distribution data of the first target in the first direction and the second direction within a specified period;

[0012] Confirming the attitude angle, center position and distribution size of the first target in the second direction based on the position distribution data;

[0013] Confirming a correlation region of the first target based on the distribution size, the attitude angle and the center position data.

[0014] In some embodiments, the step of acquiring the position distribution data of the first target in the first direction and the second direction within a specified period further comprises:

[0015] Acquiring a point cloud coordinate set associated with the first target in the first direction and the second direction within a scanning period of a radar.

[0016] In some embodiments, the step of confirming the distribution size of the first target in the second direction further comprises:

[0017] Acquiring position data of the first target in the second direction and confirming an average value;

[0018] Acquiring a difference value between each position data of the first target in the second direction and the average value, and confirming a maximum value of the difference value as the distribution size of the first target in the second direction.

[0019] In some embodiments, the step of confirming the attitude angle of the first target comprises:

[0020] Acquiring a radar normal line, and an included angle between the radar normal line and a movement direction of the first target is the attitude angle of the first target;

[0021] Confirming a covariance matrix of the position distribution of the first target in the first direction and the second direction based on the position distribution data of the first target in the first direction and the second direction;

[0022] Performing eigenvalue decomposition on the covariance matrix to acquire a first eigenvector, the first eigenvector pointing to a direction with the largest data variance;

[0023] Calculating a size of the attitude angle based on the first eigenvector.

[0024] In some embodiments, the calculation formula of the attitude angle further comprises:

[0025] ;

[0026] wherein, θ is the attitude angle; is a first element of the first eigenvector , indicating a weight of the first eigenvector in the second direction; is a second element of the first eigenvector , indicating a weight of the first eigenvector Weights in the first direction.

[0027] In some embodiments, the calculation formula of the associated region further comprises:

[0028] The points in the associated region satisfy:

[0029] ;

[0030] wherein, Z is the associated region; x is the coordinate in the first direction; y is the coordinate in the second direction; ; θ is the attitude angle; , , is the first target i the coordinate of the center in the first direction at the time t , is the first target i the coordinate of the center in the second direction at the time t , W is the width of the associated region, which is the same as the width of a single lane; L is the length of the associated region, , is the distribution size of the first target i in the second direction.

[0031] In some embodiments, the calculation step of determining the second target as the to-be-sprinkled object in response to the second target being located in the associated region and the difference between the speed of the first target and the speed of the second target in the second direction being less than a preset associated threshold speed, comprises:

[0032] ;

[0033] wherein, is the coordinate of the second target in the first direction at the time j ; is the coordinate of the second target in the second direction at the time j ; is the speed of the first target in the second direction at the time i ; is the speed of the second target in the second direction at the time j ; Va preset associated threshold speed.

[0034] In some embodiments, the step of alarming based on the lane number and the number of lanes occupied by the object when the speed of the object is zero comprises:

[0035] constructing a detection line based on the position data when the speed of the object is zero;

[0036] obtaining a safe lane number occupied by a third target when the third target crosses the detection line;

[0037] obtaining a total number of lanes of the lane, confirming a lane number occupied by the object as an obstacle lane number based on the safe lane number and the total number of lanes, and confirming the obstacle lane number and the number of obstacle lanes;

[0038] alarming based on the obstacle lane number and the number of obstacle lanes.

[0039] In some embodiments, the step of constructing a detection line based on the position data when the speed of the object is zero comprises:

[0040] obtaining position coordinate data when the speed of the object is zero, extracting coordinate data of the second direction from the position coordinate data, and constructing a detection line based on the coordinate data of the second direction:

[0041] ;

[0042] wherein, the coordinate data of the object in the second direction when the speed of the object is zero.

[0043] In a second aspect, embodiments of the present application provide a highway object determination and alarming system, comprising:

[0044] a first module configured to confirm an associated area of a first target;

[0045] a second module configured to determine that a second target is an object to be thrown in response to the second target being located in the associated area and a difference between a speed of the first target and a speed of the second target in a second direction being less than a preset associated threshold speed, wherein a length direction of a lane is the second direction;

[0046] a third module configured to determine that the object to be thrown is an object to be thrown in response to the object to be thrown being located outside the associated area and the speed of the object to be thrown being zero;

[0047] a fourth module configured to alarm based on a lane number and a number of lanes occupied by the object when the speed of the object is zero.

[0048] In a third aspect, the embodiments of the present application provide a highway litter determination and warning device, comprising a processor and a memory, wherein the memory stores a computer program executable by the processor, and the processor executes the computer program to implement the steps of the highway litter determination and warning method according to any one of the first aspect.

[0049] In a fourth aspect, a computer program is stored on a computer readable storage medium, and the computer program is run by a processor to execute the steps of the highway litter determination and warning method according to any one of the first aspect.

[0050] The present application has the beneficial effects that, compared with the prior art, the present application provides a highway litter determination and warning method, system, device and storage medium, comprising first confirming an associated area of a first target, in the associated area of the first target, if the speed of the first target and the speed of a second target in a second direction are less than an associated threshold speed, then determining that the second target is a litter to be thrown, monitoring the position of the litter to be thrown, if the litter to be thrown is located outside the associated area and the speed of the litter to be thrown is zero, then determining that the litter to be thrown is a litter; then warning based on the lane number and the number of lanes occupied by the litter; the present application constructs an associated area based on a dynamically moving vehicle, and monitors the motion of the target in the associated area, after the difference between the motion of the target in the associated area and the motion speed of the vehicle exceeds the associated threshold speed, the target is preliminarily determined to be a litter to be thrown, and the motion state of the litter to be thrown is continuously monitored, after the litter to be thrown is located outside the associated area of the vehicle and the motion speed of the litter to be thrown is reduced to zero, the litter to be thrown is determined to be a litter, and warning is performed based on the number of lanes and the lane number occupied by the litter; the present application identifies the litter by detecting the position and speed characteristics of the vehicle and the litter target, discards the monitoring method of the visual sensor, eliminates the influence of weather and light on the monitoring result, and still obtains good monitoring effect at a long distance. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0052] Figure 1 A step flowchart of a highway litter determination and warning method provided by the embodiments of the present application;

[0053] Figure 2 A module connection schematic diagram of a highway litter determination and warning system provided by the embodiments of the present application;

[0054] Figure 3A state diagram of a trajectory and a speed direction of a second target after the second target leaves an associated region of a first target in a highway litter determination and warning method provided by an embodiment of the present application;

[0055] Figure 4 A state diagram when a second target speed is zero in a highway litter determination and warning method provided by an embodiment of the present application;

[0056] Figure 5 A position diagram of an associated region and a posture angle of a first target in a highway litter determination and warning method provided by an embodiment of the present application;

[0057] Figure 6 A process diagram when a third target crosses a detection line in a highway litter determination and warning method provided by an embodiment of the present application;

[0058] Reference signs: 100, first module; 200, second module; 300, third module; 400, fourth module; x , first direction; y , second direction. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0060] As Figure 1 , Figures 3 to 6As shown, embodiments of this application provide a method for determining and alerting on road spills, including firstly identifying the associated area of ​​a first target; within the associated area of ​​the first target, if the speeds of the first target and the second target in the second direction y are both less than an associated threshold speed, then the second target is determined to be a spill; monitoring the position of the spill; if the spill is located outside the associated area and its speed is zero, then the spill is determined to be a spill; then issuing an alert based on the lane number and lane number occupied by the spill; this application constructs the associated area based on dynamically moving vehicles and monitors the movement of targets within the associated area. The method involves detecting the difference between the speed of a target and the speed of a vehicle within the associated area, which exceeds an associated threshold speed. The target is initially identified as an object to be disposed of, and the movement of the object is continuously monitored. Once the object is outside the associated area of ​​the vehicle and its speed drops to zero, it is determined to be a disposed object, and an alarm is triggered based on the number of lanes and lane number occupied by the disposed object. This application identifies disposed objects by detecting the position and speed characteristics of vehicles and disposed object targets, abandoning the monitoring method of visual sensors and eliminating the influence of weather and lighting on the monitoring results. It can still achieve good monitoring results at a relatively long distance.

[0061] like Figure 1 As shown in the embodiments of this application, the method for determining and alarming about road spills specifically includes:

[0062] Step 1: Identify the associated region of the first target.

[0063] In some embodiments, the length direction of the lane is defined as the first direction x, and the width direction of the lane is defined as the second direction y, wherein the first direction x and the second direction y are orthogonal. In this application, the first target includes, but is not limited to, moving objects such as vehicles traveling on the lane. This application uses a vehicle as an example of the first target to describe the application in detail, but it does not mean that the first target of this application refers only to vehicles.

[0064] Step 1.1: Acquire the position distribution data of the first target in the first direction x and the second direction y within a specified period.

[0065] In some embodiments, radar is used to monitor the trajectory and speed of the target, and the projectiles are identified based on the monitoring results. This eliminates the need for visual sensor monitoring methods, removes the influence of weather and lighting on the monitoring results, and still achieves good monitoring results at a greater distance.

[0066] In some embodiments, during the radar's scanning cycle, a set of point cloud coordinates of the first target in the first direction x and the second direction y is acquired.

[0067] Step 1.2: Confirm the center position of the first target based on the location distribution data.

[0068] In some embodiments, the center coordinate of the first target at the time t when the first target is detected in the radar scanning period is set as , the velocity is , and the point cloud coordinate set associated with the first target is , wherein represents the coordinate set of the point cloud in the first direction x, represents the coordinate set of the point cloud in the second direction y.

[0069] Step 1.3: Confirm the distribution size of the first target in the second direction y based on the position distribution data.

[0070] Step 1.3.1: Obtain the position data of the first target in the second direction y and determine the average value.

[0071] In some embodiments, the point cloud coordinate data of each point in the second direction y is obtained using the point cloud coordinate set associated with the first target , the average value of the point cloud coordinate data in the second direction y is solved ;

[0072] Step 1.3.2: Obtain the difference between each position data of the first target in the second direction y and the average value, and confirm that the maximum value of the difference is the distribution size of the first target in the second direction y.

[0073] In some embodiments, the point cloud coordinate data of each point in the second direction y is solved using the average value of the point cloud coordinate data in the second direction y and the point cloud coordinate data of each point in the second direction y , and the maximum value of the difference is selected as the distribution size of the first target in the second direction y . .

[0074] Step 1.4: Confirm the attitude angle of the first target based on the position distribution data.

[0075] Step 1.4.1: Obtain the radar normal line, and the included angle between the radar normal line and the motion direction of the first target is the attitude angle of the first target;

[0076] Step 1.4.2: Based on the position distribution data of the first target in the first direction x and the second direction y, confirm the covariance matrix of the position distribution of the first target in the first direction x and the second direction y.

[0077] In some embodiments, the covariance matrix of the coordinate set of the point cloud in the first direction x and the coordinate set of the point cloud in the second direction y is calculated​​​ .

[0078] Step 1.4.3: Perform eigen decomposition on the covariance matrix to obtain a first eigenvector corresponding to the first direction x.

[0079] In some embodiments, perform eigen decomposition on the covariance matrix to obtain a first eigenvector , the first eigenvector points to the direction with the largest variance of data in the Euclidean space.

[0080] Step 1.4.4: Calculate the size of the pose angle based on the first eigenvector.

[0081] As shown in FIG. 1.4.4, in some embodiments, the first element Figure 5 and the second element of the first eigenvector are obtained. represents the weight of the first eigenvector in the second direction y; represents the weight of the first eigenvector in the first direction x. Based on the first element and the second element , the size of the pose angle is solved.

[0082] Step 1.5: Confirm the associated region of the first target based on the distribution size, the pose angle, and the center position data.

[0083] As shown in FIG. 1.5, in some embodiments, the associated region Figure 5 of the first target is determined by the distribution size , the pose angle , and the center coordinate :

[0084] ;

[0085] wherein, l 1, l 2, l 3 and l 4 are four line segments successively intersecting to form the associated region of the first target, x is the coordinate in the first direction x; y is the coordinate in the second direction y; ; θ is the pose angle; , , is the first target i in​​t The center coordinate at time t is the x-coordinate value in the first direction. For the primary goal i exist t The center coordinate at that moment is the coordinate value of the second direction y; W The width of the associated area is the same as the width of a single lane. In this application, the lane width is set to... ; L The length of the associated region, , For the primary goal i The distribution size in the second direction y.

[0086] That is, the points in the associated region of the first target satisfy:

[0087] ;

[0088] Step 2: In response to the second target being located in the associated area, and the difference between the velocity of the first target and the velocity of the second target in the second direction y being less than a preset associated threshold velocity, the second target is determined to be the object to be disposed of, wherein the length direction of the lane is the second direction y.

[0089] In some embodiments, the radar targets the first target. i During the continuous tracking period At all times, the primary goal i Related regions A second target appears inside. j And in Second goal at all times j The coordinates are The speed is If the first goal i Second objective j If the following conditions are met, then the second objective is... j Marked as items to be disposed of:

[0090] ;

[0091] in, for Second goal at all times j The coordinates in the first direction x; for Second goal at all times j The coordinates in the second direction y; for Always the first goal i The velocity in the second direction y; for Second goal at all times j The velocity in the second direction y;V The preset associated threshold speed.

[0092] like Figure 3 As shown, Second goal at all times j Deviating from the primary goal i The state diagram where the velocity is not zero after the associated region, where, For the primary goal i exist The speed of time; For the second objective j exist The speed of time For the second objective j exist The velocity component in the second direction y at any given moment For the second objective j exist The velocity component in the first direction x at any given moment.

[0093] In some embodiments, in certain highway scenarios, the preset associated threshold speed is related to the initial velocity of the object to be disposed of relative to the vehicle when it detaches from the vehicle. Consider two disposal scenarios: one where the object detaches automatically from the vehicle, in which case the velocity component of the object in the second direction y is very close to the velocity component of the vehicle in the second direction y. Another method involves manually throwing the object from the vehicle. In this case, the object is primarily subjected to a velocity component in the first direction (x). It will also be very small. In summary, the preset correlation threshold speed... In most cases, the speed of the material to be thrown can be successfully correlated.

[0094] Step 3: In response to the fact that the object to be thrown is located outside the associated area and the velocity of the object to be thrown is zero, the object to be thrown is determined to be a thrown object.

[0095] like Figure 4 As shown, in some embodiments, for Second goal at all times j Deviating from the primary goal i The state diagram where the velocity is zero after the associated region, where, For the primary goal i exist The speed of time; For the second objective j exist The speed at which the radar detects the first target i Second objective j During the continuous tracking period At that moment, the second target of the scattered material j speed to zero, and the second target of the to-be-sprinkled object j outside the associated area of the first target i , it is determined that the second target of the to-be-sprinkled object j is the sprinkled object.

[0096] Step 4: warning based on the lane number and the number of lanes occupied when the speed of the sprinkled object is zero.

[0097] Step 4.1: constructing a detection line based on the position data when the speed of the sprinkled object is zero.

[0098] As shown in the Figure 6 , in some embodiments, coordinate position data when the speed of the sprinkled object is zero is obtained , the position coordinate in the second direction y when the speed of the sprinkled object is zero is extracted , and a detection line is constructed based on the position coordinate in the second direction y when the speed of the sprinkled object is zero .

[0099] Step 4.2: obtaining the lane number occupied by the third target when crossing the detection line as the safe lane number.

[0100] In some embodiments, after the detection line is constructed, for the third target crossing the detection line, the third target is other vehicles crossing the detection line, the lane number occupied by the third target when crossing the detection line is detected, and is marked as the safe lane number.

[0101] Step 4.3: obtaining the total number of lanes, confirming the lane number occupied by the sprinkled object as the obstacle lane number based on the safe lane number and the total number of lanes, and confirming the obstacle lane number and the number of obstacle lanes.

[0102] In some embodiments, the total number of lanes on the highway is obtained, and is numbered in turn, the lane number of the safe lane is recorded, then the remaining lanes are all obstacle lanes, and the number of obstacle lanes is obtained based on the lane number of the obstacle lane.

[0103] Step 4.4: warning based on the obstacle lane number and the number of obstacle lanes.

[0104] In some embodiments, the data of the obstacle lane number and the number of obstacle lanes are obtained, and the warning level is divided, the number of lanes on the highway is set as N, and the warning level division is shown in the following table:

[0105]

[0106] As shown in the Figure 2 , in some embodiments, the application also provides a highway sprinkled object determination and warning system, comprising:

[0107] The first module 100 is configured to confirm the associated area of the first target;

[0108] The second module 200 is configured to determine the second target as the to-be-distributed object in response to the second target being located in the associated area and a difference between the speed of the first target and the speed of the second target in the second direction y being less than a preset associated threshold speed, wherein the length direction of the lane is the second direction y.

[0109] The third module 300 is configured to determine the to-be-distributed object as the distributed object in response to the to-be-distributed object being located outside the associated area and the speed of the to-be-distributed object being zero.

[0110] The fourth module 400 is configured to perform an alarm based on the lane number and the number of lanes occupied by the distributed object when the speed of the distributed object is zero.

[0111] In some embodiments, the present application further provides a highway distributed object determination and alarm device, comprising a processor and a memory, the memory storing a computer program executable by the processor, and the processor executes the steps of the highway distributed object determination and alarm method when executing the computer program.

[0112] In some embodiments, the present application further provides a computer readable storage medium, the computer readable storage medium storing a computer program, and the computer program executes the steps of the highway distributed object determination and alarm method when executed by a processor.

[0113] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0114] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0115] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. For example, the division of the units is only a logical function division. There can be another division manner for the 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. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0116] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0117] In addition, each functional unit in the embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0118] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts of the technical solutions that make contributions to the prior art, or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the embodiments of the present application.

[0119] The aforementioned storage medium includes: a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0120] The above is merely specific embodiments 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 replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of highway debris determination and warning, comprising: The method comprises the following steps: Confirming the associated area of the first target; In response to the second target being located in the associated area and the difference between the speed of the first target and the speed of the second target in the second direction (y) being less than a preset associated threshold speed, determining that the second target is a to-be-sprinkled object, wherein the length direction of the lane is the second direction (y); In response to the to-be-sprinkled object being located outside the associated area and the speed of the to-be-sprinkled object being zero, determining that the to-be-sprinkled object is a sprinkled object; Based on the lane number and the lane number occupied by the sprinkled object when the speed of the sprinkled object is zero, an alarm is given; The step of confirming the associated area of the first target comprises: The width direction of the lane is the first direction (x); In a specified period, the position distribution data of the first target in the first direction (x) and the second direction (y) is obtained; Based on the position distribution data, the attitude angle, the center position and the distribution size of the first target in the second direction (y) are confirmed; Based on the distribution size, the attitude angle and the center position data, the associated area of the first target is confirmed; The calculation formula of the associated area further comprises: The associated region The points in the associated region satisfy: ； wherein Z is a relevant area; x is a coordinate in the first direction (x); y is a coordinate in the second direction (y); θ is a posture angle; and , , , is a coordinate value of a center coordinate of the first target i in the first direction (x) at time t, is a coordinate value of a center coordinate of the first target i in the second direction (y) at time t; W is a width of the relevant area, which is the same as the width of a single lane; and L is a length of the relevant area, , is a distribution size of the first target i in the second direction (y). The step of giving an alarm based on the lane number and the lane number occupied by the sprinkled object when the speed of the sprinkled object is zero comprises: Based on the position data of the sprinkled object when the speed of the sprinkled object is zero, a detection line is constructed; The lane number occupied by the third target when crossing the detection line is obtained as a safe lane number; The total number of lanes is obtained, and based on the safe lane number and the total number of lanes, the lane number occupied by the sprinkled object is confirmed as an obstacle lane number, and the obstacle lane number and the number of obstacle lanes are confirmed; Based on the obstacle lane number and the number of obstacle lanes, an alarm is given.

2. The highway debris determination and warning method of claim 1, wherein The step of obtaining the position distribution data of the first target in the first direction (x) and the second direction (y) in a specified period further comprises: In the scanning period of the radar, the point cloud coordinate set associated with the first target in the first direction (x) and the second direction (y) is obtained.

3. The highway debris determination and warning method of claim 1, wherein The step of confirming the distribution size of the first target in the second direction (y) further comprises: The position data of the first target in the second direction (y) is obtained, and the average value is confirmed; The difference between each position data of the first target in the second direction (y) and the average value is obtained, and the maximum value of the difference is confirmed as the distribution size of the first target in the second direction (y).

4. The highway debris determination and warning method of claim 2, wherein The step of confirming the attitude angle of the first target comprises: The normal line of the radar is obtained, and the included angle between the normal line of the radar and the motion direction of the first target is the attitude angle of the first target; Based on the position distribution data of the first target in the first direction (x) and the second direction (y), the covariance matrix of the position distribution of the first target in the first direction (x) and the second direction (y) is confirmed; The covariance matrix is subjected to eigenvalue decomposition, and the first eigenvector corresponding to the first direction (x) is obtained; Based on the first eigenvector, the size of the attitude angle is calculated.

5. The highway debris determination and warning method of claim 4, wherein, The calculation formula of the attitude angle further comprises: ； where θ is the attitude angle; is a first element of the first feature vector is a second element of the first feature vector is a third element of the first feature vector is a fourth element of the first feature vector 6. The highway debris determination and warning method of claim 1, wherein, The calculating step of determining the second target as the object to be scattered in response to the second target being located in the associated region and the difference between the speed of the first target and the speed of the second target in the second direction (y) being less than the preset associated threshold speed, comprises: ； wherein, is the coordinate value of the second target j in the first direction (x) at the instant t; is the coordinate value of the second target j in the second direction (y) at the instant t; is the velocity of the first target i in the second direction (y) at the instant t; is the velocity of the second target j in the second direction (y) at the instant t; V is a preset associated threshold velocity.

7. The highway debris determination and warning method of claim 1, wherein, The step of constructing a detection line based on the position data of the object to be scattered when the speed of the object to be scattered is zero, comprises: obtaining position coordinate data of the object to be scattered when the speed of the object to be scattered is zero, extracting coordinate data of the second direction (y) from the position coordinate data, and constructing a detection line based on the coordinate data of the second direction (y): ； wherein is the coordinate data of the scatter in the second direction (y) when the velocity of the scatter is zero.

8. A highway debris determination and warning system, comprising: comprises: a first module (100) configured to confirm an associated region of a first target; a second module (200) configured to determine the second target as the object to be scattered in response to the second target being located in the associated region and the difference between the speed of the first target and the speed of the second target in the second direction (y) being less than the preset associated threshold speed, wherein the length direction of the lane is the second direction (y); a third module (300) configured to determine the object to be scattered as the object to be scattered in response to the object to be scattered being located outside the associated region and the speed of the object to be scattered being zero; a fourth module (400) configured to alarm based on the lane number and the number of lanes occupied by the object to be scattered when the speed of the object to be scattered is zero; The step of confirming the associated region of the first target, comprises: the width direction of the lane is the first direction (x); obtaining position distribution data of the first target in the first direction (x) and the second direction (y) within a specified period; confirming the attitude angle, the center position and the distribution size of the first target in the second direction (y) based on the position distribution data; confirming the associated region of the first target based on the distribution size, the attitude angle and the center position data; The calculation formula of the associated region further comprises: The associated region The points in the associated region satisfy: ； wherein Z is a relevant area; x is a coordinate in the first direction (x); y is a coordinate in the second direction (y); θ is a posture angle; and , , , is a coordinate value of a center coordinate of the first target i in the first direction (x) at time t, is a coordinate value of a center coordinate of the first target i in the second direction (y) at time t; W is a width of the relevant area, which is the same as the width of a single lane; L is a length of the relevant area, , is a distribution size of the first target i in the second direction (y). The step of alarming based on the lane number and the number of lanes occupied by the object to be scattered when the speed of the object to be scattered is zero, comprises: constructing a detection line based on the position data of the object to be scattered when the speed of the object to be scattered is zero; obtaining the lane number occupied by the third target when the third target crosses the detection line as a safe lane number; obtaining the total number of lanes of the lane, confirming the lane number occupied by the object to be scattered as an obstacle lane number based on the safe lane number and the total number of lanes, and confirming the obstacle lane number and the number of obstacle lanes; alarming based on the obstacle lane number and the number of obstacle lanes.

9. A highway debris determination and warning device, characterized by, comprises a processor and a memory, the memory stores a computer program executable by the processor, and the processor executes the steps of the highway object to be scattered determination and alarm method in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer program is stored on the computer readable storage medium, and the computer program is run by the processor to execute the steps of the highway object to be scattered determination and alarm method in any one of claims 1-7.

Images