Automatic detection and early warning system for hidden intrusion of two-wheeled vehicle in highway toll station

Abstract

The invention belongs to the technical field of expressway intelligent traffic safety, and particularly relates to an expressway toll station two-wheeled vehicle hidden intrusion automatic detection and early warning system which comprises an environment sensing unit, a processing control unit and an early warning execution unit. The processing control unit is connected with the early warning execution unit; the environment sensing unit is used for collecting vehicle information on a highway toll station square and transmitting the vehicle information to the processing control unit; the processing control unit judges whether a hidden two-wheeled vehicle exists behind the current vehicle or not according to the received vehicle information, if the hidden two-wheeled vehicle exists behind the current vehicle, the processing control unit sends an early warning instruction to the early warning execution unit, and the early warning execution unit carries out early warning; otherwise, the processing control unit does not send out the instruction. According to the invention, the detection result is accurate, and the two-wheeled vehicle can be fundamentally prevented from entering the highway.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent traffic safety on expressways, and particularly relates to an automatic detection and early warning system for the concealed intrusion of two-wheel vehicles at expressway toll stations, and more particularly to an automatic detection and early warning system for two-wheel vehicles in the blind spot of vision following large vehicles at toll stations. Background Art

[0002] In recent years, researchers have proposed numerous methods to continuously iterate, upgrade, and optimize the existing facilities at expressway toll stations, and the problem of traffic efficiency has been greatly alleviated. However, these methods have all overlooked the problem of preventing the concealed intrusion of two-wheel vehicles onto expressways.

[0003] Through investigation, it has been found that there is still a phenomenon where motorcycles and bicycles (hereinafter collectively referred to as "two-wheel vehicles" or "two-wheeled vehicles") will secretly pass through toll stations following behind cars (especially behind large vehicles) and enter the expressway. For expressway toll stations where two-wheeled vehicles are prohibited from entering, this not only violates the management regulations but also greatly increases the possibility of traffic accidents. In response to this problem, several domestic invention patents have proposed different vehicle and vehicle type detection methods. Most of these patents detect two-wheeled vehicles following behind small vehicles through radar and cameras. However, due to the influence of the downward and obliquely fixed cameras and lidar on the mounting brackets and their coverage ranges, the existing monitoring means cannot effectively capture two-wheeled vehicles in the blind spot of vision following behind large vehicles, and the existing systems and methods are not perfect.

[0004] In view of this, the present invention is specifically proposed. Summary of the Invention

[0005] The purpose of the present invention is to overcome the above-mentioned shortcomings of the prior art and propose an automatic detection and early warning system for the concealed intrusion of two-wheel vehicles at expressway toll stations. This system can fundamentally prevent two-wheel vehicles from entering the expressway and solves the problem of poor identification of two-wheel vehicles by existing methods.

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

[0007] The present invention provides an automatic detection and early warning system for the concealed intrusion of two-wheel vehicles at expressway toll stations, including an environmental perception unit, a processing and control unit, and an early warning execution unit. The environmental perception unit is connected to the processing and control unit, and the processing and control unit is connected to the early warning execution unit;

[0008] The environmental perception unit is used to collect vehicle information on the square of the expressway toll station and transmit the vehicle information to the processing and control unit;

[0009] The processing control unit determines whether there is a hidden two-wheeled vehicle behind the current vehicle according to the received vehicle information. If it is determined that there is a hidden two-wheeled vehicle behind the current vehicle, the processing control unit issues a warning instruction to the warning execution unit, and the warning execution unit gives a warning; otherwise, the processing control unit does not issue an instruction.

[0010] Further, the environment perception unit includes a plurality of motors connected to the mounting frame at the toll station entrance. A fixed base is connected above each lane through a corresponding motor, and each of the fixed bases is connected with a lidar.

[0011] The lidar is connected to the processing control unit.

[0012] Further, each of the lidars uses a multi-line wide-angle lidar, and the detection mode of each of the multi-line wide-angle lidars includes a downward oblique view mode and a vertically downward mode.

[0013] Further, the processing control unit includes a processor and a controller connected thereto. A target detection algorithm for determining whether there is a hidden two-wheeled vehicle behind the current vehicle is stored on the processor.

[0014] Each of the multi-line wide-angle lidars is connected to the processor, and each of the motors is connected to the controller.

[0015] Further, the target detection algorithm specifically includes:

[0016] According to the vehicle information collected when the multi-line wide-angle lidar is in the downward oblique view mode, determine the type of the current vehicle. If it is determined that the vehicle is a large vehicle, further determine whether there is a hidden two-wheeled vehicle behind the large vehicle. If it is determined that the vehicle is a small vehicle, it is considered that there is no hidden two-wheeled vehicle behind the small vehicle.

[0017] Further, determining the type of the current vehicle is to compare the 3D size of the appearance of the current vehicle with a pre-stored 3D threshold. If the 3D size of the appearance of the current vehicle exceeds the 3D threshold, it is considered that the current vehicle is a large vehicle; otherwise, it is considered that the current vehicle is a small vehicle.

[0018] Further, the pre-stored 3D threshold is the 3D size of a small passenger car. If any two of the length, width, and height of the current vehicle exceed the corresponding length, width, and height of the 3D threshold, it is determined that the current vehicle is a large vehicle.

[0019] Further, the process of determining whether there is a hidden two-wheeled vehicle behind a large vehicle is as follows:

[0020] a. Calculate the 3D size of the blind spot behind a large vehicle, and then compare the 3D size of the blind spot with the pre-stored 3D size of a two-wheeler. If the 3D size of the blind spot is smaller than the pre-stored 3D size of the two-wheeler, it is determined that there is no hidden two-wheeler behind the current large vehicle; otherwise, mark the current large vehicle.

[0021] b. After the marked large vehicle enters the two-wheeler detection area, the controller controls the motor of the corresponding lane to adjust the multi-line wide-angle lidar to the vertical downward measurement mode. The multi-line wide-angle lidar re-collects the information data of the current large vehicle and uploads it to the processor. The processor compares the information data with the set conditions of the target detection algorithm. If it meets the set conditions, it is considered that there is a hidden two-wheeler behind the current large vehicle; otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle.

[0022] Further, the set conditions of the target detection algorithm are as follows:

[0023] 1) If the length of the large vehicle detected in the vertical downward mode is within the range of ±1 m of the length of the large vehicle detected in the top-down diagonal mode, then determine whether there is a focal point cloud at the tail of the current large vehicle. If so, enter condition 2); otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle.

[0024] 2) Determine whether the 3D contour size of the focal point cloud meets within ±30% of the 3D size of the two-wheeler. If it meets, enter condition 3); otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle.

[0025] 3) Determine whether the distance between the focal point cloud and the tail of the current large vehicle does not exceed 1.5 m. If so, enter condition 4); otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle.

[0026] 4) Determine whether the difference between the combined moving speed of the focal point cloud and the moving speed of the current large vehicle is within ±20%. If so, it is considered that there is a hidden two-wheeler behind the current large vehicle; otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle.

[0027] Further, the warning execution unit (3) includes a toll gate rod (31), a front screen (32), and a broadcast speaker (33) respectively connected to the controller (22).

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] An automatic detection and early warning system for two-wheelers secretly breaking into highway toll stations proposed by the present invention includes an environmental perception unit, a processing and control unit, and an early warning execution unit. The processing and control unit processes the vehicle information collected by the environmental perception unit and determines whether there is a two-wheeler hidden in the visual blind area behind the current large vehicle through the stored target detection algorithm. Through experiments, it is obtained that the detection result of the system is accurate, which can prevent two-wheelers from entering the highway at the source and solve the problem of poor recognition effect of two-wheelers in the existing methods. Brief Description of the Drawings

[0030] The accompanying drawings here are incorporated into the specification and form a part of this specification, and are used together with the specification to explain the principles of the present invention.

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0032] Figure 1 It is a structural composition diagram of the automatic detection and early warning system of the present invention;

[0033] Figure 2 It is a scene schematic diagram of the automatic detection and early warning system of the present invention;

[0034] Figure 3 It is a geometric relationship diagram of the top-down oblique measurement mode of the lidar of the present invention;

[0035] Figure 4 It is a principle flowchart of the automatic detection and early warning system of the present invention.

[0036] Among them: 1 is the environmental perception unit; 2 is the processing and control unit; 3 is the early warning execution unit; 11 is the motor; 12 is the fixed base; 13 is the lidar; 21 is the processor; 22 is the controller; 31 is the toll gate rod of the toll station; 32 is the front screen; 33 is the broadcast speaker. Detailed Embodiments

[0037] Here, the exemplary embodiments will be described in detail. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are only examples consistent with some aspects of the present invention detailed in the appended claims.

[0038] Please refer to Figures 1 to 4, an embodiment of the present invention provides an automatic detection and early warning system for the concealed intrusion of two-wheel vehicles at highway toll stations, including an environmental perception unit 1, a processing and control unit 2, and an early warning execution unit 3. The environmental perception unit 1 is connected to the processing and control unit 2, and the processing and control unit 2 is connected to the early warning execution unit 3;

[0039] The environmental perception unit 1 is used to collect vehicle information on the toll station square and transmit the vehicle information to the processing and control unit 2;

[0040] The processing and control unit 2 determines whether there is a concealed two-wheel vehicle behind the current vehicle according to the received vehicle information. If it is determined that there is a concealed two-wheel vehicle behind the current vehicle, the processing and control unit 2 issues a warning instruction to the early warning execution unit 3, and the early warning execution unit 3 gives a warning; otherwise, the processing and control unit 2 does not issue an instruction.

[0041] In this embodiment, the environmental perception unit 1 includes 4 motors 11 connected to the mounting frame at the toll station entrance. Each motor 11 corresponds to 1 lane. All 4 lanes are connected with fixed bases 12 through the corresponding motors 11, and each fixed base 12 is connected with a lidar 13;

[0042] The lidar 13 is connected to the processing and control unit 2.

[0043] Further, each lidar 13 adopts a multi-line wide-angle lidar, and the detection mode of each multi-line wide-angle lidar includes a top-down oblique mode and a vertical downward mode.

[0044] Further, the processing and control unit 2 includes a processor 21 and a controller 22 connected thereto. The processor 21 stores a target detection algorithm for determining whether there is a concealed two-wheel vehicle behind the current vehicle;

[0045] Each multi-line wide-angle lidar is connected to the processor 21, and each motor 11 is connected to the controller 22.

[0046] Further, the target detection algorithm specifically includes:

[0047] Determine the type of the current vehicle according to the vehicle information collected when the multi-line wide-angle lidar is in the top-down oblique mode. If it is determined that the vehicle is a large vehicle, further determine whether there is a concealed two-wheel vehicle behind the large vehicle. If it is determined that the vehicle is a small vehicle, it is considered that there is no concealed two-wheel vehicle behind the small vehicle.

[0048] Further, determining the type of the current vehicle is to compare the 3D appearance size of the current vehicle with a pre-stored 3D threshold. If the 3D appearance size of the current vehicle exceeds the 3D threshold, the current vehicle is considered a large vehicle; otherwise, the current vehicle is considered a small vehicle.

[0049] Further, the pre-stored 3D threshold is set according to the characteristics of the appearance 3D dimensions of large vehicles and small vehicles. If any two of the length, width, and height values of the current vehicle exceed the corresponding length, width, and height of the 3D threshold, the current vehicle is determined to be a large vehicle.

[0050] Specifically, in this embodiment, the multi-line wide-angle lidar detects the point cloud of the target vehicle, and then calculates the length, width, and height of the target vehicle. The 3D threshold is based on GB 1589-2016. For small passenger cars (number of passengers ≤ 9), the vehicle length ≤ 6m, the vehicle width ≤ 2m, and the vehicle height ≤ 4m. If any two of the length, width, and height values of the target vehicle do not conform to the size values of small passenger cars, the target vehicle is determined to be a large vehicle. The 3D threshold can be pre-stored according to the actual situation, which is not limited here. Only one example is listed in this embodiment.

[0051] Further, the process of determining whether there is a hidden two-wheeler behind the large vehicle is as follows:

[0052] a. Calculate the 3D dimensions of the field of vision blind area behind the large vehicle, and then compare the 3D dimensions of the field of vision blind area with the pre-stored 3D dimensions of two-wheelers. If the 3D dimensions of the field of vision blind area are smaller than the pre-stored 3D dimensions of two-wheelers, it is determined that there is no hidden two-wheeler behind the current large vehicle; otherwise, mark the current large vehicle.

[0053] b. When the marked large vehicle enters the two-wheeler detection area, the controller 22 controls the motor 11 in the corresponding lane to adjust the multi-line wide-angle lidar to the vertical downward measurement mode. The multi-line wide-angle lidar re-collects the information data of the current large vehicle and uploads it to the processor 21. The processor 21 compares the information data with the set conditions of the target detection algorithm. If it meets the set conditions, it is considered that there is a hidden two-wheeler behind the current large vehicle; otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle.

[0054] In this embodiment, the pre-stored 3D dimensions of two-wheelers are the 3D dimensions of conventional motorcycles, bicycles and other two-wheel vehicles. Specifically, the 3D dimensions of two-wheelers can be: according to GB 7258-2017, the length, width, and height of motorcycles should not exceed 2.5m, 1m, and 1.4m respectively. According to GB 17761-2018, the length, width, and height of electric bicycles should not exceed 2m, 0.65m, and 1.2m respectively. The 3D dimensions of two-wheelers can be pre-stored according to the actual situation, which is not limited here. Only one example is listed in this embodiment.

[0055] Specifically, the set conditions of the target detection algorithm are as follows:

[0056] 1) When the current length of the large vehicle detected in the vertical downward mode is within the range of the current length of the large vehicle detected in the overlooking diagonal mode ± 1 m (length - 1 to length + 1), it is determined whether there is a focused point cloud at the tail of the current large vehicle. If there is, proceed to condition 2); otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle;

[0057] 2) Determine whether the 3D contour size of the focused point cloud is within plus or minus 30% of the 3D size of the two-wheeler. If it is, proceed to condition 3); otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle;

[0058] 3) Determine whether the distance between the focused point cloud and the tail of the current large vehicle does not exceed 1.5 m. If so, proceed to condition 4); otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle;

[0059] 4) Determine whether the difference between the combined moving speed of the focused point cloud and the moving speed of the current large vehicle is within plus or minus 20%. If so, it is considered that there is a hidden two-wheeler behind the current large vehicle; otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle.

[0060] Furthermore, the warning execution unit 3 includes a toll gate rod 31, a front screen 32, and a broadcast speaker 33 that are respectively connected to the controller 22.

[0061] The working principle of the warning system of the present invention is specifically as follows:

[0062] Step 1, as Figure 1 shown, the multi-line wide-angle lidar of the environment perception unit 1 is installed on the fixed base 12 and is used to collect vehicle information on the highway toll station square; the fixed base 12 can be rotated up and down by the motor 11 and is fixed on the mounting frame above each lane at the toll station entrance, so that the lidar 13 can achieve two measurement modes: overlooking diagonal and vertical downward. In this step, the lidar 13 is in the conventional overlooking diagonal measurement mode, and the installation height and maximum detection angle are determined. In this mode, the lidar can measure the three-dimensional (3D) dimensions of the object, such as Figure 2 shown in lanes 1, 2, and 4.

[0063] Step 2, after the vehicle enters the detection area, the lidar 13 transmits the collected vehicle information to the processor 21, and judges the vehicle type on the lane through the target detection algorithm. If the 3D size of the current vehicle does not exceed the pre-stored 3D threshold, it is considered that the current vehicle is a small vehicle, and the current algorithm ends, and the next vehicle is judged continuously; otherwise, it is considered a large vehicle, and proceed to the next step;

[0064] Step 3: After determining that the current vehicle is a large vehicle, calculate the 3D size of the visual blind area behind the large vehicle based on geometric relationships such as the distance and angle between the lidar 13 and the large vehicle.

[0065] Specifically, as Figure 3 shown, OA is the installation height of the lidar 13, with a value of h; θ is the maximum detection angle of the lidar 13; AB is the distance from the lidar 13 to the large vehicle, denoted as m; AC is the farthest detection distance of the lidar 13, with a value of k, and k = m + m'. All the above parameters are known quantities. According to mathematical geometric relationships, obviously, ΔAOC and ΔBO′C are similar triangles, that is

[0066] According to the properties of similar triangles, it is easy to know that ∠OAC = ∠O'BC = α; l is a fixed value; based on the above geometric relationships, the length n' and height h' of the visual blind area behind the large vehicle can be calculated. The specific calculation process is shown in the following formula:

[0067]

[0068] In the right triangle BO′C, both m′ and n′ have been obtained, and n′ can be obtained through the Pythagorean theorem, that is

[0069]

[0070] For the three-dimensional space, based on similar triangles at different angles, the width of the visual blind area can be obtained in the same way. So far, the 3D size (length, width, height) of the visual blind area has been calculated through a specific algorithm, and then the algorithm proceeds to the next step.

[0071] Step 4: After obtaining the 3D size of the visual blind area behind the large vehicle, compare it with the 3D size of the two-wheeler stored in advance. If the 3D size of the visual blind area is smaller than the 3D size of the two-wheeler, the system determines that the current visual blind area does not have the possibility of hiding the two-wheeler, the algorithm ends, and continues to detect the next vehicle; otherwise, it proceeds to the next step;

[0072] Step 5: When the system determines that the visual blind area behind the current large vehicle is sufficient to hide at least one two-wheeler, the processor 21 makes a key mark on the large vehicle. After the marked vehicle enters the two-wheeler detection area, the controller 22 sends a rotation instruction to the motor 11, and the motor 11 drives the fixed base 12 to rotate downward. At this time, the lidar 13 enters the vertical downward measurement mode, as Figure 2 shown in lane 3 in the figure, and then proceeds to the next step;

[0073] Step 6. In the vertically downward measurement mode, the lidar 13 can only obtain the two-dimensional length and width dimensions of the current large vehicle. Based on this, the lidar 13 re-measures the length and width dimensions of the marked vehicle and the moving speed of the vehicle, and inputs the collected information data to the processor 21. The processor 21 applies a target detection algorithm to compare the input information data with the pre-stored 3D threshold. When four conditions are simultaneously met (i.e., the set conditions described above), it is determined that there is a hidden two-wheeler in the blind area of the large vehicle's vision; otherwise, the algorithm ends, and the lidar 13 returns to the conventional downward oblique measurement mode to continue detecting the next vehicle.

[0074] Step 7. When it is determined that there is a hidden two-wheeler behind the current large vehicle, the controller 22 sends an instruction to the warning execution unit 3, mainly making the following four aspects of warnings:

[0075] ① Send a warning message to the toll station control center to let the relevant staff know this information;

[0076] ② The front screen 32 of the toll station displays that a two-wheeler has entered, so that the driver of the large vehicle knows this information;

[0077] ③ The toll gate rod 31 of the toll station immediately drops to prevent the two-wheeler from following the large vehicle through the toll station and entering the highway;

[0078] ④ The toll station broadcast speaker 33 starts to broadcast in a loop: warnings such as a two-wheeler has entered, please leave immediately;

[0079] When the system detects that the two-wheeler has left the toll station square, the controller 22 issues a warning cancellation instruction to stop the warning, and the lidar 13 returns to the conventional downward oblique measurement mode, and the above steps are cycled; otherwise, the warning continues until the two-wheeler leaves.

[0080] The above is only the specific implementation manner of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention.

[0081] It should be understood that the present invention is not limited to the content already described above, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. An automatic detection and early warning system for the concealed intrusion of two-wheeled vehicles at highway toll stations, characterized in that, It includes an environment perception unit (1), a processing and control unit (2), and a warning execution unit (3). The environment perception unit (1) is connected to the processing and control unit (2), and the processing and control unit (2) is connected to the warning execution unit (3); The environment perception unit (1) is used to collect vehicle information on the toll station square and transmit the vehicle information to the processing and control unit (2); The processing and control unit (2) determines whether there is a concealed two-wheeler behind the current vehicle based on the received vehicle information. If it is determined that there is a concealed two-wheeler behind the current vehicle, the processing and control unit (2) issues a warning instruction to the warning execution unit (3), and the warning execution unit (3) gives a warning; otherwise, the processing and control unit (2) does not issue an instruction.

2. The two-wheeler concealed intrusion automatic detection and early warning system for highway toll stations according to claim 1, characterized in that, The environment perception unit (1) includes a plurality of motors (11) connected to the mounting frame at the toll station entrance. A fixed base (12) is connected above each lane through the corresponding motor (11), and each fixed base (12) is connected with a lidar (13); The lidar (13) is connected to the processing and control unit (2).

3. The two-wheeled vehicle concealed intrusion automatic detection and warning system for highway toll stations according to claim 1, characterized in that Each lidar (13) adopts a multi-line wide-angle lidar, and the detection mode of each multi-line wide-angle lidar includes a downward oblique view mode and a vertically downward mode.

4. The two-wheeler concealed intrusion automatic detection and warning system for highway toll stations according to claim 3, characterized in that, The processing and control unit (2) includes a processor (21) and a controller (22) connected thereto. A target detection algorithm for determining whether there is a concealed two-wheeler behind the current vehicle is stored on the processor (21); Each multi-line wide-angle lidar is connected to the processor (21), and each motor (11) is connected to the controller (22).

5. The two-wheeler concealed intrusion automatic detection and early warning system for highway toll stations according to claim 1, characterized in that, The target detection algorithm specifically includes: Based on the vehicle information collected when the multi-line wide-angle lidar is in the downward oblique view mode, determine the type of the current vehicle. If it is determined that the vehicle is a large vehicle, further determine whether there is a concealed two-wheeler behind the large vehicle. If it is determined that the vehicle is a small vehicle, it is considered that there is no concealed two-wheeler behind the small vehicle.

6. The two-wheeler concealed intrusion automatic detection and early warning system for highway toll stations according to claim 5, characterized in that, Determining the type of the current vehicle is to compare the 3D appearance size of the current vehicle with a pre-stored 3D threshold. If the 3D appearance size of the current vehicle exceeds the 3D threshold, the current vehicle is considered a large vehicle; otherwise, the current vehicle is considered a small vehicle.

7. The two-wheeler concealed intrusion automatic detection and early warning system for highway toll stations according to claim 6, characterized in that, The pre-stored 3D threshold is the 3D size of a small passenger car. If any two of the length, width, and height values of the current vehicle exceed the corresponding length, width, and height of the 3D threshold, the current vehicle is determined to be a large vehicle.

8. The two-wheeler stealth intrusion automatic detection and warning system for highway toll stations according to claim 6, wherein The process of determining whether there is a concealed two-wheeler behind a large vehicle is as follows: a. Calculate the 3D size of the visual blind area behind the large vehicle, and then compare the 3D size of the visual blind area with the pre-stored 3D size of a two-wheeler. If the 3D size of the visual blind area is smaller than the pre-stored 3D size of a two-wheeler, it is determined that there is no concealed two-wheeler behind the current large vehicle; otherwise, mark the current large vehicle; b. After the marked large vehicle enters the two-wheeler detection area, the controller (22) controls the motor (11) of the corresponding lane to adjust the multi-line wide-angle lidar to the vertically downward measurement mode. The multi-line wide-angle lidar re-collects the information data of the current large vehicle and uploads it to the processor (21). The processor (21) compares the information data with the set conditions of the target detection algorithm. If it meets the set conditions, it is considered that there is a hidden two-wheeler behind the current large vehicle; otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle.

9. The two-wheeler concealed intrusion automatic detection and early warning system for highway toll stations according to claim 8, characterized in that, The set conditions of the target detection algorithm are as follows: 1) If the length of the large vehicle detected in the vertically downward mode is within the range of ±1 m of the length of the large vehicle detected in the top-down diagonal mode, then it is judged whether there is a focused point cloud at the tail of the current large vehicle. If so, enter condition 2); otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle; 2) Judge whether the 3D contour size of the focused point cloud meets within plus or minus 30% of the 3D size of the two-wheeler. If it meets, enter condition 3); otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle; 3) Judge whether the distance between the focused point cloud and the tail of the current large vehicle does not exceed 1.5 m. If so, enter condition 4); otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle; 4) Judge whether the difference between the combined movement speed of the focused point cloud and the movement speed of the current large vehicle is within plus or minus 20%. If so, it is considered that there is a hidden two-wheeler behind the current large vehicle; otherwise, it is considered that there is no hidden two-wheeler behind the current large vehicle.

10. The two-wheeler concealed intrusion automatic detection and early warning system for highway toll stations according to claim 1, characterized in that, The warning execution unit (3) includes a toll gate rod (31), a front screen (32), and a broadcast speaker (33) respectively connected to the controller (22).

Images