Automatic pavement crack wireless detection robot based on combination of ground penetrating radar and vision

Abstract

The invention provides an automatic road surface crack wireless detection robot based on combination of a ground penetrating radar and vision. The automatic road surface crack wireless detection robot comprises a hardware system and a software system. The hardware system comprises a ground penetrating radar and a vehicle body, a camera is installed at the front end of the vehicle body, a first control mainboard is carried on the vehicle body, the ground penetrating radar is separated from the vehicle body, cross scanning detection of cracks is completed under the guidance of the vehicle body through wireless connection, and balance adjustment of stability and responsiveness is carried out according to the density of the cracks; in the software system, a path planning module enables a vehicle body to automatically advance along the crack trend through a first control main board according to an analysis result of a crack recognition module, the pavement crack trend is visually analyzed, crack two-dimensional information is sampled, and a motion path is automatically planned in cooperation with the control main boards; the ground penetrating radar is guided by the vehicle body through wireless connection to sample crack depth information, and a crack three-dimensional model is constructed. The pavement crack can be simply, conveniently and efficiently detected.

Description

Technical Field

[0001] The present invention relates to the technical field of pavement crack detection, and specifically to an automatic pavement crack wireless detection robot based on the combination of ground penetrating radar and vision. Background Art

[0002] With the extension of road usage time and the increase in traffic volume, it is a common phenomenon for cracks to appear on the road surface. Cracks will not only affect the driving smoothness and safety of the road, but may also cause moisture to penetrate into the road base layer, which may in turn lead to more serious road damages such as ruts and potholes. Timely detection and repair of cracks are important measures to extend the service life of roads and ensure traffic safety.

[0003] Traditional road crack detection methods mainly rely on manual inspections, that is, staff drive or walk for inspections, and manually record the type, location, size and severity of cracks. Although this method can detect road crack problems to a certain extent, it has the disadvantages of low efficiency, large manual operation errors, limited detection coverage, inconsistent data records, etc. Automated crack detection equipment can be more time-saving and labor-saving, and improve the detection efficiency.

[0004] Most of the existing pavement crack detection devices are rigidly coupled structures driven or pushed manually. Due to the rigid coupling of the structure of the detection vehicle, when constructing a three-dimensional information scan of the crack, the ground penetrating radar has to scan vertically from the crack direction, so it has to perform high-frequency reciprocating turning operations. However, the manual control accuracy is limited, and it is prone to defects such as mis-scanning and mis-identification. In terms of path planning, the crack detection vehicle with a rigidly coupled structure will increase the difficulty of path planning and increase the computing power consumption. Summary of the Invention

[0005] For the above reasons, the present invention provides an automatic pavement crack wireless detection robot based on the combination of ground penetrating radar and vision, which solves the problems of high-frequency reciprocating turning operations of the rigidly coupled detection vehicle in the prior art, large operation difficulty and low detection accuracy.

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

[0007] In the first aspect of the present invention, an automatic pavement crack wireless detection robot based on the combination of ground penetrating radar and vision is proposed, including a hardware system and a software system. The hardware system includes a ground penetrating radar and a vehicle body. The radar includes a radar antenna, a radar host, and a ranging wheel; a camera is installed at the front end of the vehicle body, a first control main board, an attitude sensor, and a power supply battery are carried on the vehicle body, and mobile wheel assemblies are installed on both sides of the vehicle body; the camera, the mobile wheel assemblies installed on the vehicle body, and the attitude sensor are electrically connected to the first control main board;

[0008] The ground-penetrating radar is separated from the vehicle body. It is equipped with a second control main board, an attitude sensor and a power supply battery. Mobile wheel assemblies are installed on both sides. The radar antenna is installed above the mobile wheel assemblies, the radar main unit is installed above the radar antenna, and the ranging wheel is installed behind the radar antenna. The ranging wheel, the attitude sensor installed on the ground-penetrating radar, the power supply battery, the mobile wheel assemblies are electrically connected to the second control main board. The first control main board communicates wirelessly with the second control main board through a WIFI wireless module. The ground-penetrating radar is guided by the vehicle body to complete the cross-scanning detection of cracks;

[0009] The software system is implanted on the first control main board and includes:

[0010] A camera image acquisition module for acquiring the image data of the camera;

[0011] A crack identification module for identifying and analyzing cracks in the images acquired by the camera;

[0012] A path planning module for analyzing and calculating the travel routes of the vehicle body and the ground-penetrating radar from the image data.

[0013] Preferably, the ground-penetrating radar is guided by the vehicle body to complete the cross-scanning detection of cracks, and the cross-scanning direction is perpendicular to the head direction of the vehicle body.

[0014] Preferably, the path planning module makes the vehicle body automatically travel along the trend of the crack through the first control main board according to the analysis result of the crack identification module. The crack identification module frames the crack in the figure with a rectangular box, constructs the x-axis zero point with the central axis of the picture. The path planning module analyzes the x-axis coordinate of the center point of the box in the image. If the coordinate is positive, it is judged that the crack trend is to the right, and the vehicle body turns right until the center point of the crack frame diagram is located at the x-axis zero point. If the coordinate is negative, it is judged that the crack trend is to the left, and the vehicle body turns left until the center point of the crack frame diagram is located at the x-axis zero point.

[0015] Based on the above-mentioned road surface crack wireless detection robot, the second aspect of the present invention proposes a road surface crack detection method, including the following steps:

[0016] S1: The camera acquires road surface image information;

[0017] S2: The road surface image information is transmitted to the crack identification module;

[0018] S3: When a crack is recognized, the crack identification module obtains the length and width information of the crack, and analyzes and plans the travel route of the vehicle body through the path planning module;

[0019] S4: When the vehicle body is traveling, the ground-penetrating radar always cross-scans the crack in a direction perpendicular to the head direction of the vehicle body;

[0020] S5: When the vehicle encounters an inflection point during driving, when the inflection point disappears from the camera image, the ground penetrating radar fixedly memorizes the orientation of the vehicle head at this time, continues to scan for cracks along this direction, the vehicle head turns according to the inflection point direction and starts to record the driving distance;

[0021] S6: When the driving distance reaches the distance L between the camera and the ground penetrating radar, the ground penetrating radar continuously updates the orientation of the vehicle head at this time until the next time the vehicle head reaches the inflection point;

[0022] S7: When the next inflection point has disappeared from the camera image before reaching the distance L, it is determined that the inflection point area is too small, and the ground penetrating radar can directly scan and cover it, which is simplified to a straight crack, and step S4 is repeated;

[0023] S8: Integrate the three-dimensional information of the cracks to form a three-dimensional model corresponding to the cracks.

[0024] Preferably, in step S6, the cross-scanning of the ground penetrating radar adopts cascade PID control combined with road surface crack information. The road surface crack information is collected by the camera, the crack image information is obtained through image processing, the crack density coefficient b is obtained through calculation, b is mapped to the dynamic adjustment factor k of the control parameter, and k is brought into each link of the double-loop PID for adjustment. When b increases, k decreases, reducing the cross-travel amplitude and slowing down the response, reducing the error rate of misidentifying adjacent cracks; when b decreases, k increases, allowing a larger cross-travel amplitude and faster response.

[0025] Preferably, the crack density coefficient b = s -6 , where s is the ratio of the crack skeleton pixel points to the total pixel points of the image, and the dynamic adjustment factor where t is the adjustment coefficient of the dynamic adjustment factor, which is selected according to the order of magnitude of each parameter of the actual PID and is used to adjust the order of magnitude of the dynamic adjustment factor k;

[0026] Bring the obtained k into each operation of the inner and outer loops of the PID for adjustment. The basic single-loop PID algorithm is as follows:

[0027]

[0028] Among them:

[0029] u(k): The calculation result of the PID algorithm, that is, the control quantity; K p : The adjustment coefficient of the proportional term, which adjusts the performance of the PID proportional link; K i : The adjustment coefficient of the integral term, which adjusts the performance of the PID integral link; K d : The adjustment coefficient of the differential term, which adjusts the performance of the PID differential link; e(k) is the error, that is, the target value - the current state value of the controlled object; [e(k) - e(k - 1)] is the current error minus the previous error;

[0030] Preferably, the obtained k is brought into each operation of the inner and outer loops of the PID for adjustment, where:

[0031] The process of outer loop adjustment is as follows:

[0032] 1) Generate a reference lateral displacement according to the path planning and multiply it by k to dynamically adjust the target:

[0033] target 1 = target × k, where target1 is the target value of the outer loop PID and target is the reference value of the outer loop PID target value;

[0034] 2) Add dynamic amplitude limiting to the output of the outer loop PID to adjust the target speed of the speed loop PID:

[0035] output 1 ∈ [-V max × k, V max × k];

[0036] where output is the output value of the outer loop PID and serves as the target value of the inner loop PID; Vmax is the limit value of the target speed of the inner loop speed loop PID, which is used to limit the range of the target speed of the inner loop PID;

[0037] The process of inner loop adjustment is as follows:

[0038] Adjust the aggressiveness of the response according to the density of the cracks,

[0039] K p _speed = k p × k;

[0040] K i _speed = k i × k;

[0041] where: Kp_speed is the coefficient of the proportional adjustment term of the inner loop PID, kp is the reference value of the coefficient of the proportional adjustment term of the inner loop PID, Ki_speed is the coefficient of the integral adjustment term of the inner loop PID, and ki is the reference value of the coefficient of the integral adjustment term of the inner loop PID.

[0042] Preferably, in step S6, the cross-scanning of the ground penetrating radar segments the cracks through the inflection points of the cracks, and performs delayed cross-scanning according to the distance L between the inflection point position and the ground penetrating radar at the front camera. Specifically:

[0043] When the inflection point with a curvature greater than the threshold value l appears in the crack in the camera image, it is identified and recorded. When the vehicle body approaches the inflection point and the inflection point disappears from the camera image, the ground penetrating radar fixedly memorizes the orientation of the front of the vehicle body at this time, and continues to cross-scan the crack in the vertical direction of this direction. The front of the vehicle body turns according to the inflection point direction and starts to record the traveling distance; when the traveling distance reaches the distance L between the camera and the ground penetrating radar, the ground penetrating radar continuously updates and memorizes the orientation of the front of the vehicle body at this time until the next time the front of the vehicle reaches the inflection point. If the next inflection point has disappeared from the camera image before traveling the distance L, it is determined that the inflection point area is too small, and the ground penetrating radar can directly scan and cover it, which is simplified to a straight crack, and immediately continuously updates the orientation of the front of the vehicle body at this time, and scans the next crack in the vertical direction of the orientation of the front of the vehicle body.

[0044] Beneficial effects: Compared with the prior art, the present invention innovatively adopts the "dynamic path decoupling control technology", constructs an intelligent collaborative operation system through the electromechanical separation architecture of the vehicle body navigation unit and the ground penetrating radar module, completely revolutionizes the traditional road crack identification mode, and reconstructs the space-time dimension of road crack detection: through space decoupling control, the traveling direction of the vehicle body and the crack scanning direction form decoupled degrees of freedom, and the vehicle body only needs to automatically travel along the crack direction and guide the route for the ground penetrating radar, which simplifies the traveling route and improves the detection efficiency. Brief Description of the Drawings

[0045] Figure 1 It is a schematic diagram of an automatic road crack wireless detection robot based on the combination of ground penetrating radar and vision according to the present invention;

[0046] Figure 2 It is a schematic diagram of the control flow of the automatic road crack wireless detection robot according to the present invention;

[0047] Figure 3 It is a flowchart of a detection method for an automatic road crack wireless detection robot based on the combination of ground penetrating radar and vision according to the present invention;

[0048] Figure 4 It is the ratio of the pixel value of the relatively sparse crack after image processing to the total pixel value of the picture in the embodiment of the present invention;

[0049] Figure 5 It is the ratio of the pixel value of the relatively dense crack after image processing to the total pixel value of the picture in the embodiment of the present invention;

[0050] Figure 6 It is the longitudinal section image transmitted in real time by the ground penetrating radar during the camera shooting process.

[0051] Annotations in the figure:

[0052] 1. Ground Penetrating Radar; 1a. Radar Antenna; 1b. Radar Main Unit; 1c. Rangefinder Wheel; 2. Camera; 3. Mobile Wheel Assembly; 4. Vehicle Body; 5a. First Control Mainboard; 5b. Second Control Mainboard; 6. Power Supply Battery; 7. WIFI Wireless Module; 8. Attitude Sensor; 9. Camera Image Acquisition Module; 10. Crack Identification Module; 11. Path Planning Module. Detailed Implementation Manner

[0053] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0054] As Figure 1 、 Figure 2 shown, the present invention proposes an automatic road crack wireless detection robot based on the combination of ground penetrating radar and vision, including a hardware system and a software system. The hardware system includes a ground penetrating radar 1 and a vehicle body 4. A camera 2 is installed at the front end of the vehicle body 4. A first control mainboard 5a, an attitude sensor 8, and a power supply battery 6 are carried on the vehicle body 4. Mobile wheel assemblies 3 are installed on both sides of the vehicle body 4; the camera 2, the mobile wheel assembly 3 installed on the vehicle body 4, and the attitude sensor 8 are electrically connected to the first control mainboard 5a;

[0055] The ground penetrating radar 1 is separated from the vehicle body 4, and is carried with a second control mainboard ⑤b, a radar antenna 1a, a radar main unit 1b, a rangefinder wheel 1c, an attitude sensor 8, and a power supply battery 6. Mobile wheel assemblies 3 are installed on both sides. The rangefinder wheel 1c is connected to the radar antenna 1a through a torsion spring device. The radar antenna 1a is connected to the radar main unit 1b through a coaxial cable. The rangefinder wheel 1c, the attitude sensor 8 installed on the ground penetrating radar 1, the power supply battery 6, and the mobile wheel assembly 3 are electrically connected to the second control mainboard 5b. The first control mainboard 5a and the second control mainboard 5b communicate wirelessly through the WIFI wireless module 7. The ground penetrating radar ① is guided by the vehicle body 4 to complete the cross-scanning detection of cracks;

[0056] Among them, the camera 2 is used to capture images of road cracks. The mobile wheel assembly 3 drives the vehicle body and the ground penetrating radar to move forward. The rangefinder wheel 1c transmits the moving distance of the vehicle body in real time. The power supply battery 6 supplies energy to the device. The WIFI wireless module 7 is used to realize wireless communication between the vehicle body and the ground penetrating radar. The attitude sensor 8 is used to judge the orientation of the vehicle body and the ground penetrating radar.

[0057] In this embodiment, the ground penetrating radar 1 is separated from the vehicle body, and through wireless connection, it is guided by the vehicle head to complete the cross-scanning detection of cracks, and the balance between the stability and responsiveness of the PID is adjusted according to the crack density.

[0058] The software system is implanted on the first control main board (5a) and includes:

[0059] The camera image acquisition module 9 acquires the image data of the camera;

[0060] The crack recognition module 10 recognizes and analyzes the cracks in the image acquired by the camera 2;

[0061] The path planning module 11 analyzes and calculates the traveling routes of the vehicle body 4 and the ground penetrating radar 1 based on the image data.

[0062] In this embodiment, the path planning module 11 enables the vehicle to automatically travel along the trend of the crack through the control main board by analyzing the crack image acquired by the camera image acquisition module 9 by the crack recognition module 10. The crack recognition module 10 frames the crack in the figure with a rectangular box and constructs the x-axis zero point with the central axis of the picture. The path planning module 11 analyzes the x-axis coordinate of the center point of the square box in the image. If the coordinate is positive, it is determined that the crack trend is to the right, and the vehicle turns right until the center point of the crack frame diagram is located at the x-axis zero point. If the coordinate is negative, it is determined that the crack trend is to the left, and the vehicle turns left until the center point of the crack frame diagram is located at the x-axis zero point, realizing that the vehicle can automatically travel along the trend of the crack.

[0063] For example, when the vehicle travels to the inflection point, the coordinate x1 of the center point x of the next crack frame diagram is obtained. If x1>0, the control main board enables the vehicle body to continuously execute the right-turn instruction, and at the same time continuously updates the coordinate of the center point of the total crack frame diagram of the camera image until x1 = 0. The control main board enables the vehicle body to execute the straight-ahead instruction, and the vehicle body stops turning and travels straight.

[0064] Such as Figure 3 shown, the road surface crack detection method based on the above detection robot includes the following steps:

[0065] S1: The camera 2 acquires road surface image information;

[0066] S2: The road surface image information is transmitted to the crack recognition module 10;

[0067] S3: When a crack is recognized, the crack recognition module 10 obtains the length and width information of the crack, and analyzes and plans the traveling route of the vehicle body 4 through the path planning module 11;

[0068] S4: When the vehicle body 4 travels, the ground penetrating radar 1 always cross-scans the crack in a direction perpendicular to the front direction of the vehicle body 4, that is, the vehicle body 4 travels along the crack direction, and the ground penetrating radar 1 performs a "z"-shaped reciprocating scan and moves forward on the traveling route of the vehicle body 4;

[0069] S5: When the vehicle encounters an inflection point during travel, when the inflection point disappears from the image of Camera 2, the ground penetrating radar 1 fixedly memorizes the orientation of the front of the vehicle body 4 at this time, continues to scan for cracks along the direction of the vehicle head, the vehicle head turns according to the inflection point direction and starts to record the travel distance;

[0070] S6: When the travel distance reaches the distance L between Camera 2 and the ground penetrating radar 1, the ground penetrating radar 1 continuously updates the orientation of the front of the vehicle body 4 at this time until the next time the vehicle head reaches the inflection point;

[0071] S7: When the next inflection point has disappeared from the image of Camera 2 before reaching the distance L, it is determined that the inflection point area is too small, and the ground penetrating radar 1 can directly scan and cover it, which is simplified to a straight crack, and step S4 is repeated;

[0072] S8: Integrate the three-dimensional information of the cracks to form a three-dimensional model corresponding to the cracks.

[0073] In this embodiment, the cross-scanning of the ground penetrating radar 1 in S6 adopts cascade PID control combined with road surface crack information. The road surface crack information is collected by Camera 2, the crack image information is obtained through image processing, the crack density coefficient b is obtained through calculation, b is mapped to the dynamic adjustment factor k of the control parameter, and is brought into each link of the double-loop PID for adjustment. When b increases (cracks are dense), k decreases, thereby reducing the cross-travel amplitude, slowing down the response, and reducing the error rate of misidentifying adjacent cracks; when b decreases (cracks are sparse), k increases, allowing a larger cross-travel amplitude and faster response. b is the crack density coefficient, which is calculated from the crack pixel ratio after image processing. Specifically, as Figure 4 、 Figure 5 shown, Figure 4 s1 is the ratio of the pixel value of the crack after image processing to the total picture pixel value in the case of relatively sparse cracks Figure 5 s2 is the ratio of the pixel value of the crack after image processing to the total picture pixel value in the case of relatively dense cracks Figure 6 is the longitudinal section image transmitted in real time by the ground penetrating radar 1 during the shooting process of Camera 2.

[0074] The calculation formula of s:

[0075]

[0076] Substitute s1 and s2 into the following operations to obtain the corresponding crack density coefficient b:

[0077] b = s -6

[0078] It can be obtained that: b1 = 0.68^-6 = 10.11, b2 = 0.68^-6 = 2.15

[0079] Then, convert b to the dynamic adjustment factor k using the following formula:

[0080]

[0081] Where:

[0082] k: The dynamic adjustment factor, used to adjust the parameters in each item of PID;

[0083] b: The crack density coefficient, reflecting the density of cracks in the image. The larger it is, the denser the cracks;

[0084] t: The adjustment coefficient of the dynamic adjustment factor, selected according to the order of magnitude of the actual PID parameters, used to adjust the dynamic adjustment factor k to an appropriate order of magnitude.

[0085] Substitute the obtained k into each operation of the inner and outer loops of PID for adjustment:

[0086]

[0087] Where:

[0088] u(k): The calculation result of the PID algorithm, that is, the control quantity

[0089] K p : The adjustment coefficient of the proportional term, adjusting the performance of the PID proportional link;

[0090] K i : The adjustment coefficient of the integral term, adjusting the performance of the PID integral link;

[0091] K d : The adjustment coefficient of the differential term, adjusting the performance of the PID differential link;

[0092] e(k): The error, that is, the target value - the current state value of the controlled object, [e(k) - e(k - 1)]: the current error minus the previous error.

[0093] The outer loop adjustment includes:

[0094] 1. Generate a reference lateral displacement (crossing amplitude) according to the path planning and multiply it by k to dynamically adjust the target:

[0095] target 1 = target × k

[0096] Where:

[0097] target1: The target value of the outer loop PID;

[0098] target: The reference value of the outer loop PID target value, which can be flexibly adjusted according to application requirements;

[0099] k: A dynamic adjustment factor used to adjust the parameters in each item of PID;

[0100] 2. Add dynamic amplitude limiting to the output of the outer - loop PID to adjust the target speed of the speed - loop PID:

[0101] output 1∈[-V max×k,V max×k]

[0102] Where:

[0103] output: The output value of the outer - loop PID, which serves as the target value of the inner - loop PID;

[0104] Vmax: The limit value of the target speed of the inner - loop speed - loop PID, which restricts the range of the target speed of the inner - loop PID;

[0105] k: A dynamic adjustment factor used to adjust the parameters in each item of PID;

[0106] Inner - loop adjustment:

[0107] Adjust the aggressiveness of the response according to the density of the cracks:

[0108] K p _speed=k p ×k

[0109] Ki_speed=ki×k

[0110] Where:

[0111] Kp_speed: The coefficient of the proportional adjustment term of the inner - loop PID;

[0112] kp: The reference value of the coefficient of the proportional adjustment term of the inner - loop PID;

[0113] Ki_speed: The coefficient of the integral adjustment term of the inner - loop PID;

[0114] ki: The reference value of the coefficient of the integral adjustment term of the inner - loop PID;

[0115] In S6, the cross - scanning of the ground - penetrating radar 1 segments the cracks through the inflection points of the cracks, and performs delayed cross - scanning based on the position of the inflection points and the distance L between the front - end camera and the ground - penetrating radar. Specifically:

[0116] When an inflection point with a crack curvature greater than the set threshold limit appears in the image of camera 2, it is identified and recorded. When the vehicle approaches the inflection point and the inflection point disappears from the image of camera 2, the ground penetrating radar 1 fixedly memorizes the orientation of the vehicle head at this time, and continues to cross-scan the crack in the vertical direction of this direction. The vehicle head turns according to the inflection point direction and starts to record the traveling distance. When the traveling distance reaches the distance L between the vehicle head camera 2 and the ground penetrating radar 1, the ground penetrating radar 1 continuously updates the orientation of the vehicle head at this time until the next vehicle head reaches the inflection point. When the next inflection point has disappeared from the image of camera 2 before traveling the distance L, it is determined that the inflection point area is too small, and the ground penetrating radar can directly scan and cover it, which is simplified to a straight crack, and immediately continuously updates the orientation of the vehicle head at this time, and scans the next section of the crack in the vertical direction of the vehicle head orientation. In this way, the delay of the ground penetrating radar scanning and the vehicle head recognition is realized, and the time difference between the time when camera 2 recognizes the crack and the time when the ground penetrating radar 1 reaches the crack position is compensated.

[0117] The present invention analyzes the road surface crack trend through vision, samples the two-dimensional information of the crack, and cooperates with the control main board to automatically plan the movement path. When the vehicle travels along the crack, the ground penetrating radar samples the crack depth information under the guidance of the vehicle body through wireless connection, and constructs a three-dimensional crack model. The present invention can simplify the vehicle movement path, construct a three-dimensional crack model, and realize simple and efficient detection of road surface cracks.

[0118] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. The above are only the preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included in the protection scope of the claims of the present invention.

Claims

1. An automatic road crack wireless detection robot based on the combination of ground penetrating radar and vision, characterized in that It includes a hardware system and a software system. The hardware system includes a ground penetrating radar (1) and a vehicle body (4). The radar (1) includes a radar antenna (1a), a radar main unit (1b), and a ranging wheel (1c). A camera (2) is installed at the front end of the vehicle body (4). A first control main board (5a), an attitude sensor (8), and a power supply battery (6) are carried on the vehicle body (4). Mobile wheel assemblies (3) are installed on both sides of the vehicle body (4). The camera (2), the mobile wheel assemblies (3) installed on the vehicle body (4), and the attitude sensor (8) are electrically connected to the first control main board (5a). The ground penetrating radar (1) is separated from the vehicle body (4). A second control main board (5b), an attitude sensor (8), and a power supply battery (6) are carried on it. Mobile wheel assemblies (3) are installed on both sides. The radar antenna (1a) is installed above the mobile wheel assemblies (3). The radar main unit (1b) is installed above the radar antenna (1a). The ranging wheel (1c) is installed behind the radar antenna (1a). The ranging wheel (1c), the attitude sensor (8) installed on the ground penetrating radar (1), the power supply battery (6), and the mobile wheel assemblies (3) are electrically connected to the second control main board (5b). The first control main board (5a) and the second control main board (5b) communicate wirelessly through a WIFI wireless module (7). The ground penetrating radar (1) is guided by the vehicle body (4) to complete the cross-scanning detection of cracks. The software system is implanted on the first control main board (5a) and includes: A camera image acquisition module (9) for acquiring the image data of the camera. A crack identification module (10) for identifying and analyzing cracks in the images collected by the camera (2). A path planning module (11) for analyzing and calculating the travel routes of the vehicle body (4) and the ground penetrating radar (1) based on the image data.

2. The automatic road crack wireless detection robot based on the combination of ground penetrating radar and vision according to claim 1, characterized in that: The ground penetrating radar (1) is guided by the vehicle body (4) to complete the cross-scanning detection of cracks. The cross-scanning direction is perpendicular to the head direction of the vehicle body (4).

3. The automatic road crack wireless detection robot based on the combination of ground penetrating radar and vision according to claim 1, characterized in that The path planning module (11) makes the vehicle body (4) automatically travel along the trend of the crack through the first control main board (5a) according to the analysis result of the crack identification module (10). The crack identification module (10) frames the crack in the figure with a rectangular box and constructs the x-axis zero point with the central axis of the picture. The path planning module (11) analyzes the x-axis coordinate of the center point of the box in the image. If the coordinate is positive, it is judged that the crack trend is to the right, and the vehicle body (4) turns right until the center point of the crack frame diagram is located at the x-axis zero point. If the coordinate is negative, it is judged that the crack trend is to the left, and the vehicle body (4) turns left until the center point of the crack frame diagram is located at the x-axis zero point.

4. The road surface crack detection method of the wireless detection robot according to any one of claims 1-3, characterized in that, It includes the following steps: S1: The camera (2) acquires the road surface image information. S2: The road surface image information is transmitted to the crack identification module (10). S3: When a crack is identified, the crack identification module (10) obtains the length and width information of the crack and analyzes and plans the travel route of the vehicle body (4) through the path planning module (11). S4: When the vehicle body (4) is traveling, the ground penetrating radar (1) always cross-scans the crack in a direction perpendicular to the head direction of the vehicle body (4). S5: When the vehicle encounters an inflection point during driving, when the inflection point disappears from the image of the camera (2), the ground penetrating radar (1) fixedly memorizes the orientation of the front of the vehicle body (4) at this time, continues to scan for cracks along this direction, the front of the vehicle turns according to the inflection point direction and starts to record the driving distance; S6: When the driving distance reaches the distance L between the camera (2) and the ground penetrating radar (1), the ground penetrating radar (1) continuously updates the orientation of the front of the vehicle body (4) at this time until the next time the front of the vehicle reaches the inflection point; S7: When the next inflection point has disappeared from the image of the camera (2) before reaching the distance L, it is determined that the inflection point area is too small, and the ground penetrating radar (1) can directly scan and cover it, which is simplified to a straight crack, and step S4 is repeated; S8: Integrate the three-dimensional information of the cracks to form a three-dimensional model corresponding to the cracks.

5. The pavement crack detection method according to claim 4, characterized in that, In step S6, the cross-scanning of the ground penetrating radar (1) adopts a cascade PID control combined with the road surface crack information. The camera (2) collects the road surface crack information, obtains the crack image information through image processing, calculates the crack density coefficient b, maps b to the dynamic adjustment factor k of the control parameter, and brings it into each link of the double-loop PID for adjustment. When b increases, k decreases, reducing the cross-travel amplitude and slowing down the response, reducing the error rate of misidentifying adjacent cracks; when b decreases, k increases, allowing a larger cross-travel amplitude and a faster response.

6. The pavement crack detection method according to claim 5, wherein The crack density coefficient b = s -6 , where s is the ratio of the crack skeleton pixel points to the total pixel points of the image, and the dynamic adjustment factor where t is the adjustment coefficient of the dynamic adjustment factor, which is selected according to the order of magnitude of the actual PID parameters and is used to adjust the order of magnitude of the dynamic adjustment factor k; Substitute the obtained k into the operations of the inner and outer loops of the PID for adjustment. The basic single-loop PID algorithm is as follows: Where: u(k): The calculation result of the PID algorithm, i.e., the control quantity; K p : The adjustment coefficient of the proportional term, which adjusts the performance of the PID proportional link; K i : The adjustment coefficient of the integral term, which adjusts the performance of the PID integral link; K d : The adjustment coefficient of the differential term, which adjusts the performance of the PID differential link; e(k) is the error, i.e., the target value - the current state value of the controlled object; [e(k) - e(k - 1)] is the current error minus the previous error.

7. The pavement crack detection method according to claim 5, characterized in that, The obtained k is brought into each operation of the inner and outer loops of the PID for adjustment, where: The process of outer loop adjustment is as follows: 1). Generate a reference lateral displacement according to the path planning and dynamically adjust the target by multiplying k: target1 = target × k, where target1 is the target value of the outer loop PID, and target is the reference value of the target value of the outer loop PID; 2). Add a dynamic limit to the output of the outer loop PID to adjust the target speed of the speed loop PID: output1 ∈ [-Vmax × k, Vmax × k]; Where output is the output value of the outer loop PID and serves as the target value of the inner loop PID; Vmax is the target speed limit value of the inner loop speed loop PID, which is used to limit the range of the target speed of the inner loop PID; The process of inner loop adjustment is as follows: Adjust the aggressiveness of the response according to the degree of crack density, K p _speed = k p × k; K i _speed = k i × k; Where: Kp_speed is the coefficient of the proportional adjustment term of the inner loop PID, kp is the reference value of the coefficient of the proportional adjustment term of the inner loop PID, Ki_speed is the coefficient of the integral adjustment term of the inner loop PID, and ki is the reference value of the coefficient of the integral adjustment term of the inner loop PID.

8. The pavement crack detection method according to claim 4, characterized in that In step S6, the cross-scanning of the ground penetrating radar (1) in the middle segments the cracks through the crack inflection points, and performs a delayed cross-scanning based on the inflection point position and the distance L between the front camera and the ground penetrating radar; specifically: When an inflection point with a crack curvature greater than the threshold value l appears in the image of the camera (2), it is identified and recorded. When the vehicle body (4) approaches the inflection point and the inflection point disappears from the image of the camera (2), the ground penetrating radar (1) fixedly memorizes the orientation of the front of the vehicle body (4) at this time, and continues to cross-scan the crack in the vertical direction of this direction. The front of the vehicle body (4) turns according to the inflection point direction and starts to record the traveling distance; when the traveling distance reaches the distance L between the camera (2) and the ground penetrating radar (1), the ground penetrating radar (1) continuously updates and memorizes the orientation of the front of the vehicle body (4) at this time until the next time the front of the vehicle reaches the inflection point; if the next inflection point has disappeared from the image of the camera (2) before traveling the distance L, it is determined that the inflection point area is too small, and the ground penetrating radar can directly scan and cover it, which is simplified to a straight crack, and immediately continuously updates the orientation of the front of the vehicle body (4) at this time, and scans the next crack in the vertical direction of the orientation of the front of the vehicle body (4).

Images