An on-line detection method and device for highway pavement quality

Abstract

The present invention relates to the technical field of image processing, and particularly relates to an on-line detection method and device for highway pavement quality. The method includes: acquiring point cloud data of a highway pavement at each moment within a predetermined time period; determining the degree of change of each point cloud data at each moment within the predetermined time period; determining the occlusion possibility of the current point cloud data at each moment within the predetermined time period; in the case where the occlusion possibility is greater than a first threshold, determining that the current point cloud data is occluded, and in the case where the occlusion possibility is not greater than the first threshold, determining the defect probability of the current point cloud data according to the road surface continuity of the current point cloud data and the occlusion possibility of the current point cloud data at each moment within the predetermined time period; detecting the quality of the position of the highway pavement corresponding to the current point cloud data according to the defect probability. The present invention improves the accuracy of the acquired point cloud data of the highway pavement, and further improves the detection accuracy of the highway pavement quality.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to an on-line detection method and device for highway pavement quality. Background Art

[0002] The quality of a highway pavement refers to the physical condition of the highway surface and its ability to meet traffic demands, which directly affects the safety, comfort and efficiency of driving. Good pavement quality can not only extend the service life of the road, but also reduce vehicle maintenance costs and improve transportation benefits. With the increase in the number of vehicles and the change of transportation demands, the problems of damage and deterioration of highway pavements have become more and more serious, which not only affects traffic flow, but may also lead to traffic accidents. Problems such as uneven pavements, cracks, and potholes may cause vehicles to lose control and increase the risk of traffic accidents. Therefore, it is necessary to monitor and timely maintain the quality of highway pavements.

[0003] In some scenarios, the monitoring of highway pavement quality mainly relies on manual observation, which is slow, prone to missed inspections, and the detection results are highly subjective, making it difficult to achieve large-scale, real-time, and efficient detection. Therefore, the highway pavement can be monitored online by obtaining the point cloud data of the highway pavement in real time. However, for a highway pavement, there may be obstacles and moving vehicles on the pavement, and the acquisition of point cloud data will be affected by the objects on the highway pavement, resulting in inaccurate point cloud data being obtained, that is, the obtained point cloud data may not be the point cloud data of the highway pavement itself. Therefore, the accuracy of the obtained point cloud data of the highway pavement is relatively low, and further the detection accuracy of the highway pavement quality is relatively low. Summary of the Invention

[0004] In order to solve the technical problem of relatively low detection accuracy of highway pavement quality, the purpose of the present invention is to provide an on-line detection method and device for highway pavement quality, and the specific technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides an on-line detection method for highway pavement quality, including: acquiring point cloud data of each moment of a highway pavement within a predetermined time period; determining the degree of change of each point cloud data at each moment within the predetermined time period according to the height and gray value in the point cloud data at each moment within the predetermined time period; determining the relative change speed of the current point cloud data at each moment within the predetermined time period and the speed of the vehicle-mounted radar that acquires the current point cloud data; determining the occlusion possibility of the current point cloud data at each moment within the predetermined time period according to the degree of change, relative change speed and speed of the current point cloud data at each moment within the predetermined time period; in the case where the occlusion possibility is greater than a first threshold, determining that the current point cloud data is occluded, and re-acquiring the point cloud data at the position where the current point cloud data is located; in the case where the occlusion possibility is not greater than the first threshold, determining the defect probability of the current point cloud data according to the pavement continuity of the current point cloud data and the occlusion possibility of the current point cloud data at each moment within the predetermined time period; detecting the quality of the position of the highway pavement corresponding to the current point cloud data according to the defect probability.

[0006] Optionally, determining the degree of change of each point cloud data at each moment within the predetermined time period according to the height and gray value in the point cloud data at each moment within the predetermined time period includes: determining the gray value representation value of the current point cloud data according to the first gray value mean of all the point cloud data in the neighborhood of the current point cloud data and the second gray value mean of all the point cloud data in the neighborhood of other point cloud data; determining the height difference parameter of the current point cloud data according to the first height of the current point cloud data and the second height of the adjacent point cloud data adjacent to the current point cloud data; determining the third height of the point cloud data with the largest gray value representation value; determining the pavement continuity of the current point cloud data according to the height difference parameter, gray value representation value, third height and first height of the current point cloud data; determining the degree of change of the current point cloud data at each moment within the predetermined time period based on the pavement continuity of the current point cloud data at each moment within the predetermined time period, the first duration of the maximum height of the current point cloud data within the predetermined time period, and the second duration of the minimum height of the current point cloud data within the predetermined time period.

[0007] Optionally, determining the gray value representation value of the current point cloud data according to the first gray value mean of all the point cloud data in the neighborhood of the current point cloud data and the second gray value mean of all the point cloud data in the neighborhood of other point cloud data includes: calculating the absolute value of the first difference between the first gray value mean and the second gray value mean of other point cloud data, and superimposing the absolute values of each first difference to obtain a first superimposed value; performing inverse proportional normalization processing on the first superimposed value to obtain the gray value representation value of the current point cloud data.

[0008] Optionally, determining the height difference parameter of the current point cloud data based on the first height of the current point cloud data and the second height of the adjacent point cloud data adjacent to the current point cloud data includes: calculating a second difference between the first height of the current point cloud data and the second height of the previous adjacent point cloud data adjacent to the current point cloud data, and a third difference between the first height of the current point cloud data and the second height of the next adjacent point cloud data adjacent to the current point cloud data; calculating a fourth difference between the second difference and the third difference, and performing inverse normalization processing on the fourth difference to obtain the height difference parameter of the current point cloud data.

[0009] Optionally, determining the road surface continuity of the current point cloud data based on the height difference parameter, grayscale performance value, third height, and first height of the current point cloud data includes: calculating the absolute value of a fifth difference between the third height and the first height, and a first sum value of the absolute value of the fifth difference and a predetermined value; calculating a first ratio between the height difference parameter and the first sum value; determining that a first product between the grayscale performance value and the first ratio is the road surface continuity of the current point cloud data.

[0010] Optionally, determining the degree of change of the current point cloud data at each moment within a predetermined time period based on the road surface continuity of the current point cloud data at each moment within the predetermined time period, the first duration of the maximum height of the current point cloud data within the predetermined time period, and the second duration of the minimum height of the current point cloud data within the predetermined time period includes: calculating the average continuity of the road surface continuity of the current point cloud data at each moment within the predetermined time period, a second ratio between the average continuity and the road surface continuity of the current point cloud data at each moment within the predetermined time period, and a sixth difference between a predetermined value and the second ratio; performing inverse normalization on the sixth difference to obtain a normalized value; calculating a third ratio between the second duration and the first duration; determining that a second product between the normalized value and the third ratio is the degree of change of the current point cloud data at each moment within the predetermined time period.

[0011] Optionally, determining the occlusion possibility of the current point cloud data at each moment within a predetermined time period based on the degree of change, relative change speed, and speed of the current point cloud data at each moment within the predetermined time period includes: calculating a seventh difference between the relative change speed and the speed, and rounding up the seventh difference to obtain a rounded-up value; determining that a third product between the degree of change of the current point cloud data at each moment within the predetermined time period and the rounded-up value is the occlusion possibility of the current point cloud data at each moment within the predetermined time period.

[0012] Optionally, determining the defect probability of the current point cloud data according to the road surface continuity of the current point cloud data and the occlusion possibility of the current point cloud data at each moment within a predetermined time period includes: superimposing the occlusion possibilities of the current point cloud data at each moment within a predetermined time period to obtain a second superimposed value; calculating a second sum value between the second superimposed value and the road surface continuity of the current point cloud data; performing inverse proportional normalization processing on the second sum value to obtain the defect probability of the current point cloud data.

[0013] Optionally, detecting the quality of the position of the road surface corresponding to the current point cloud data according to the defect probability includes: determining that there is a road surface defect at the position of the road surface corresponding to the current point cloud data when the defect probability is greater than a second threshold.

[0014] In a second aspect, an embodiment of the present invention provides an on-line road surface quality detection device for a highway, including: a processor and a memory; wherein, the memory is used to store a computer program that can run on the processor; the processor is used to execute the program stored on the memory to implement the steps of the on-line road surface quality detection method as mentioned in the first aspect.

[0015] The present invention has the following beneficial effects: First, obtain the point cloud data of the road surface at each moment within a predetermined time period; then determine the degree of change of each point cloud data at each moment within the predetermined time period according to the height and gray value in the point cloud data at each moment within the predetermined time period; then determine the relative change speed of the current point cloud data at each moment within the predetermined time period and the speed of the vehicle-mounted radar that collects the current point cloud data; secondly, determine the occlusion possibility of the current point cloud data at each moment within the predetermined time period according to the degree of change, relative change speed and speed of the current point cloud data at each moment within the predetermined time period; when the occlusion possibility is greater than a first threshold, determine that the current point cloud data is occluded, and re-collect the point cloud data at the position where the current point cloud data is located, and when the occlusion possibility is not greater than the first threshold, determine the defect probability of the current point cloud data according to the road surface continuity of the current point cloud data and the occlusion possibility of the current point cloud data at each moment within the predetermined time period; finally, detect the quality of the position of the road surface corresponding to the current point cloud data according to the defect probability.

[0016] Thus, in the embodiment of the present invention, the point cloud data of the highway pavement is acquired, and the performance characteristics of the point cloud data on the highway pavement are analyzed. According to the change of the point cloud data at different times, the influence of the vehicles passing through on the point cloud data under different traffic conditions on the road surface is analyzed, and the possibility that each point cloud data belongs to the road surface point cloud data is obtained, that is, the occlusion possibility of each point cloud data at each moment is obtained. When the occlusion possibility is greater than the first threshold, it is determined that the current point cloud data is occluded, indicating that the point cloud data may not be the point cloud data of the road surface. When the occlusion possibility is not greater than the first threshold, it indicates that the point cloud data is the point cloud data of the road surface. Thus, the defect probability that a defect may occur at the position corresponding to the point cloud data is calculated using the effective point cloud data, and the road surface quality is detected based on the defect probability. In this way, the accuracy of the point cloud data of the highway pavement obtained by the present invention is improved, and further the detection accuracy of the highway pavement quality is improved, and the road surface defects and flatness problems can be accurately identified, and the interference of other influencing factors on the road surface quality detection can be excluded. Brief Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions and advantages 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, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of an on-line detection method for highway pavement quality provided by an embodiment of the present invention;

[0019] Figure 2 It is a schematic structural diagram of an on-line detection device for highway pavement quality provided by an embodiment of the present invention;

[0020] Figure 3 It is a schematic structural diagram of an on-line detection device for highway pavement quality provided by another embodiment of the present invention. Detailed Description of the Embodiment

[0021] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following will, in conjunction with the accompanying drawings and preferred embodiments, describe in detail the specific implementation manner, structure, characteristics and effects of an on-line detection method and device for highway pavement quality proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs.

[0023] The following specifically describes the specific solutions of a method and device for on-line detection of highway pavement quality provided by the present invention in conjunction with the accompanying drawings.

[0024] Embodiment 1:

[0025] Please refer to Figure 1 , which shows a flowchart of a method for on-line detection of highway pavement quality provided by an embodiment of the present invention, including:

[0026] S101, Obtain the point cloud data of each moment of the highway pavement within a predetermined time period.

[0027] Specifically, in the embodiment of the present invention, on-vehicle lidar can be used to obtain the point cloud data of the highway pavement. Among them, point cloud data (Point Cloud Data) is a set composed of a large number of three-dimensional coordinate points. Each point represents a measurement position on the surface of an object. Each point contains x, y, z coordinate information, grayscale value, and other information, defining the position and color characteristics of the point in three-dimensional space. Lidar is a commonly used device for obtaining point cloud data. It can work under different lighting and weather conditions, is suitable for long-distance scanning, and can cover a large area. By emitting laser beams and measuring the time required for them to reflect back, the point cloud data of each moment can be obtained, thereby generating three-dimensional point cloud data, generating a road surface height model, recording the precise height information of different points, and obtaining the grayscale value of each point cloud data, and performing three-dimensional modeling on all point cloud data.

[0028] S102, Determine the change degree of each point cloud data at each moment within the predetermined time period according to the height and grayscale value in the point cloud data at each moment within the predetermined time period.

[0029] Specifically, since highway pavements are usually paved with asphalt, their surface colors show a close-to-gray tone and are relatively uniform. The large-area gray tone of the highway pavement has a consistent texture. The uniformity of the asphalt surface forms an obvious contrast with roadside buildings, green belts, traffic signs, or other road surface objects. These objects on the highway pavement usually have different colors, textures, or materials. Therefore, when collecting point cloud data, it will cause obvious differences from the point cloud data on the asphalt pavement. The uniform surface of asphalt often makes the grayscale values of the point cloud data relatively close and stable in this area, making the point cloud data of the highway pavement visually show a relatively uniform distribution. Therefore, it is possible to determine whether the point cloud data is effective point cloud data of the highway pavement by the change degree of each point cloud data at different moments.

[0030] Further, when determining the degree of change, as an alternative embodiment of the present invention, first, according to the first gray value mean of all the point cloud data within the neighborhood of the current point cloud data and the second gray value mean of all the point cloud data within the neighborhood of other point cloud data, determine the gray value performance value of the current point cloud data; then, according to the first height of the current point cloud data and the second height of the adjacent point cloud data adjacent to the current point cloud data, determine the height difference parameter of the current point cloud data; and determine the third height of the point cloud data with the maximum gray value performance; determine the road surface continuity of the current point cloud data according to the height difference parameter, gray value performance, third height and first height of the current point cloud data; finally, based on the road surface continuity of the current point cloud data at each moment within a predetermined time period, the first duration of the maximum height of the current point cloud data within the predetermined time period, and the second duration of the minimum height of the current point cloud data within the predetermined time period, determine the degree of change of the current point cloud data at each moment within the predetermined time period.

[0031] Specifically, the neighborhood of the point cloud data can be the area where the surrounding 8 point cloud data centered on the point cloud data are located. Of course, according to the actual situation, the neighborhood range of the point cloud data can also be in other ways, which is not limited in the embodiments of the present invention. Because of the possible influence of sunlight, taking the direction of the road extension as the analysis direction, at the current moment, the gray value performance value of the i-th point cloud data is calculated in the following way: First, calculate the absolute value of the first difference between the first gray value mean and the second gray value mean of other point cloud data, and superimpose the absolute values of each first difference to obtain the first superimposed value; then, perform inverse proportional normalization processing on the first superimposed value to obtain the gray value performance value of the current point cloud data.

[0032] Among them, the embodiments of the present invention use the following formula to calculate the gray value performance value of the current point cloud data:

[0033] ;

[0034] In the above formula, represents the gray value performance value of the i-th point cloud data. represents the mean of the gray values of all the point cloud data within the neighborhood of the i-th point cloud data, that is, the first gray value mean. represents the second gray value mean of all the point cloud data within the neighborhood of the (i + j)-th point cloud data. represents the number of other point cloud data. represents the difference in gray values between the neighborhood around the i-th point cloud data and the neighborhoods of other point cloud data in the direction of the road extension. The smaller the difference, the more likely it is that the point cloud data is the gray feature of the road surface.

[0035] Furthermore, due to the relatively flat surface of the asphalt pavement, the spatial distribution of the point cloud data is usually relatively regular. The point cloud data scanned by the lidar usually shows relatively small height changes. Different from the asphalt pavement, there are usually steps, road signs, road edge strips or other structures beside the road, and the heights of these objects are significantly higher than the surrounding road surface. During lidar scanning, when these steps or objects are scanned, the height values of their point cloud data usually show significant mutations or contrasts. For example, the height of the road edge strip is usually higher than that of the asphalt pavement, while the edges of the steps or road facilities may show sharp height changes, generating obvious discrete point cloud data. For the point cloud data on the asphalt pavement, there is usually a relatively continuous and regular height change. Due to the smooth and flat surface of the asphalt, when the point cloud data scanned by the lidar is distributed on the road surface, the height differences between them are small, and the height of each point cloud data shows a certain continuity with the changes of the surrounding point cloud data. Therefore, in the embodiments of the present invention, the continuity shown by each point cloud data on the highway pavement is obtained according to the gray scale and height performance.

[0036] Furthermore, when obtaining the height difference parameter between the point cloud data in the embodiments of the present invention, as an optional embodiment of the present invention, first calculate the second difference between the first height of the current point cloud data and the second height of the previous adjacent point cloud data adjacent to the current point cloud data, and the third difference between the first height of the current point cloud data and the second height of the next adjacent point cloud data adjacent to the current point cloud data; then calculate the fourth difference between the second difference and the third difference, and perform inverse proportional normalization on the fourth difference to obtain the height difference parameter of the current point cloud data.

[0037] Specifically, the embodiments of the present invention specifically use the following formula to calculate the height difference parameter of the current point cloud data:

[0038] ;

[0039] In the above formula, represents the height difference parameter of the i-th point cloud data. represents the first height of the i-th point cloud data. represents the second height of the (i + 1)-th point cloud data adjacent to the i-th point cloud data, that is, the second height of the next adjacent point cloud data adjacent to the i-th point cloud data. represents the second height of the (i - 1)-th point cloud data adjacent to the i-th point cloud data, that is, the second height of the previous adjacent point cloud data adjacent to the i-th point cloud data. (-) represents the inverse proportional normalization function, which is used to perform inverse proportional normalization on represents the difference between adjacent point cloud data. The smaller the difference, the higher the continuity of the road surface.

[0040] Further, when calculating the road surface continuity, as an optional embodiment of the present invention, first calculate the absolute value of the fifth difference between the third height and the first height, and the first sum value of the absolute value of the fifth difference and a predetermined value; then calculate the first ratio of the height difference parameter to the first sum value; finally, determine that the first product between the grayscale performance value and the first ratio is the road surface continuity of the current point cloud data.

[0041] Specifically, the predetermined value can be taken as 1, and the present invention embodiment specifically uses the following formula to calculate the road surface continuity of the current point cloud data:

[0042] ;

[0043] In the above formula, represents the road surface continuity of the i-th point cloud data. represents the grayscale performance value of the i-th point cloud data. represents the height difference parameter of the i-th point cloud data. represents the first height of the i-th point cloud data. represents the third height of the point cloud data with the largest grayscale performance value. represents the height difference between the i-th point cloud data and the point cloud data with the largest grayscale performance value. Problems such as defects on the road surface are based on the road surface. In most point cloud data, the road surface accounts for the vast majority, and the grayscale performance values of most point cloud data are almost the same because they are based on a plane. Therefore, the smaller the height difference, the greater the road surface continuity of the i-th point cloud data.

[0044] Furthermore, when a vehicle is traveling on a road surface, its physical volume and position may obscure or interfere with a part of the road surface area, especially defects on the road surface such as potholes, cracks, and damages. These obstructions may cause the defects in the relevant area to not be fully or accurately captured during the data acquisition process, affecting the integrity and quality of the point cloud data. Therefore, when conducting road surface defect detection and analysis, once a vehicle is identified on the road surface, it may be necessary to suspend the acquisition process or re-perform data acquisition to ensure that the defects in the vehicle-obscured area can be clearly recorded. In addition, the presence of the vehicle may also cause distortion of the scanned data. The signals reflected by the vehicle surface may be confused with the reflection signals of the ground or other objects, thereby affecting the accuracy of the point cloud. The affected point cloud data on the road surface may be missing or mis-identified as point cloud data on the vehicle. If the point cloud data changes at different times, it is very likely due to the influence of a moving vehicle passing by or through, which affects the acquisition of the point cloud data, and the road surface continuity will also be affected to a certain extent. Therefore, the embodiments of the present invention can analyze the degree of change of the point cloud data that may be obscured on the road surface to determine the impact on the point cloud data.

[0045] Furthermore, when determining the degree of change of the current point cloud data at each moment within a predetermined time period, as an optional embodiment of the present invention, first calculate the average continuity of the road surface continuity of the current point cloud data at each moment within the predetermined time period, the second ratio between the average continuity and the road surface continuity of the current point cloud data at each moment within the predetermined time period, and the sixth difference between the predetermined value and the second ratio; then perform inverse proportional normalization on the sixth difference to obtain a normalized value, and calculate the third ratio between the second duration and the first duration; finally, determine that the second product between the normalized value and the third ratio is the degree of change of the current point cloud data at each moment within the predetermined time period.

[0046] Specifically, the embodiments of the present invention specifically use the following formula to calculate the degree of change:

[0047] ;

[0048] In the above formula, represents the degree of change of the i-th point cloud data at the t-th moment within the predetermined time period. represents the first duration of the maximum height of the i-th point cloud data within the predetermined time period at the t-th moment. represents the second duration of the minimum height of the i-th point cloud data within the predetermined time period at the t-th moment. represents the road surface continuity of the i-th point cloud data at the t-th moment within the predetermined time period. represents the mean value of the road surface continuity of the i-th point cloud data at the t-th moment within the predetermined time period, that is, the average continuity. It represents the ratio of the duration of the minimum height to the maximum height within a predetermined time period. Since the vehicle is driving on the road surface, the height of the point cloud data that may cause errors will be higher than the height of the road surface. Under normal circumstances, the vehicle will pass by quickly within the predetermined time period, so the duration is short. Therefore, the larger the ratio, the shorter the duration, and the more likely it is that the change in the point cloud data is caused by the passing of the vehicle, and the greater the degree of change. It represents the change situation of the road surface continuity. If a vehicle passes by, the road surface continuity will also change. The greater the difference from other continuities within the predetermined time period, the greater the degree of change of the i-th point cloud data at this time. (-) represents the inverse proportional normalization function, which is used to perform inverse proportional normalization processing.

[0049] S103. Determine the relative change speed of the current point cloud data at each moment within the predetermined time period and the speed of the vehicle-mounted radar that collects the current point cloud data.

[0050] Specifically, on the road, the driving vehicle is a common dynamic object, which will have a certain impact on the acquisition of point cloud data. Since lidar or other sensors usually obtain three-dimensional data of the surrounding environment by emitting laser beams and receiving the reflected signals, the movement of the driving vehicle will cause changes in the collected point cloud data, resulting in uneven distribution of the density of the point cloud data, changes in the position of the point cloud, and even abnormal points that do not conform to the surrounding environment may appear. When the vehicle passes by, the reflection intensity of the point cloud data may increase or decrease, or the point cloud data from the vehicle and its attached objects, while the point cloud data obtained from the defects on the road surface will not change accordingly. As the vehicle-mounted radar moves forward, since the defects on the road surface are moving in the opposite direction relative to the vehicle-mounted radar, the relative speed of the point cloud data of the defects on the road surface is the same as the speed of the vehicle-mounted radar. However, other driving vehicles may be moving in the same direction or in the opposite direction and all have a certain speed, so their speeds will not always be the same as that of the vehicle-mounted radar. Therefore, in the embodiment of the present invention, the occlusion possibility at each moment is calculated by obtaining the relative change speed of the current point cloud data at each moment within the predetermined time period and the speed of the vehicle-mounted radar that collects the current point cloud data. The relative change speed refers to the speed of the vehicle causing occlusion relative to the ground.

[0051] S104. Determine the occlusion possibility of the current point cloud data at each moment within the predetermined time period according to the degree of change, relative change speed, and speed of the current point cloud data at each moment within the predetermined time period.

[0052] Specifically, when determining the occlusion possibility of the current point cloud data at each moment within a predetermined time period, as an optional embodiment of the present invention, first calculate the seventh difference between the relative change speed and the speed, and round up the seventh difference to obtain a rounded value; then determine that the third product between the change degree of the current point cloud data at each moment within the predetermined time period and the rounded value is the occlusion possibility of the current point cloud data at each moment within the predetermined time period.

[0053] Among them, the embodiment of the present invention uses the following formula to calculate the occlusion possibility of the current point cloud data at each moment within a predetermined time period:

[0054] ;

[0055] In the above formula, represents the occlusion possibility of the i-th point cloud data at the t-th moment within the predetermined time period. represents the change degree of the i-th point cloud data at the t-th moment within the predetermined time period. represents the relative change speed of the i-th point cloud data at the t-th moment within the predetermined time period. represents the speed of the vehicle-mounted radar. When the change degree is larger, the occlusion possibility of the i-th point cloud data at this time is greater. represents the rounding up of the difference between the relative change speed and the speed of the radar. The larger the difference, the greater the possibility that it may not be a defect on the road surface.

[0056] S105. When the occlusion possibility is greater than the first threshold, determine that the current point cloud data is occluded, and re-collect the point cloud data at the position where the current point cloud data is located. When the occlusion possibility is not greater than the first threshold, determine the defect probability of the current point cloud data according to the road surface continuity of the current point cloud data and the occlusion possibility of the current point cloud data at each moment within the predetermined time period.

[0057] Specifically, road surface defects usually manifest as irregularities or local fractures of point cloud data. If the road surface continuity of the same point cloud data is small and the occlusion possibility at multiple moments is low, this indicates the discontinuity of the point cloud data in space and the lack of errors or incompleteness caused by perspective occlusion. Therefore, this type of point cloud data is very likely to be caused by road surface defects. To ensure the accuracy and reliability of detection, it is necessary to re-collect these possible defect points to exclude misjudgments caused by external factors such as occlusion.

[0058] Further, within the captured time range, the occlusion possibility of the same point cloud data at each moment is statistically analyzed, and a first threshold is set. When the occlusion possibility is greater than the first threshold, it indicates that the point cloud data collected at this time may be occluded, and it is necessary to re-collect the data at this position. For other normal moments, the point cloud data at this time can better reflect the actual road surface conditions and is suitable for further road surface quality detection and analysis. Among them, the first threshold can be determined according to the actual situation, and in the embodiment of the present invention, the value is 0.8.

[0059] Further, when determining the defect probability of the current point cloud data, as an optional embodiment of the present invention, first, the occlusion possibilities of the current point cloud data at each moment within a predetermined time period are superimposed to obtain a second superimposed value; then, the second sum value between the second superimposed value and the road surface continuity of the current point cloud data is calculated; finally, the second sum value is subjected to inverse proportional normalization processing to obtain the defect probability of the current point cloud data.

[0060] Specifically, the embodiment of the present invention specifically uses the following formula to calculate the road surface continuity of the current point cloud data:

[0061] ;

[0062] In the above formula, represents the defect probability of the i-th point cloud data at the t-th moment within the predetermined time period. represents the occlusion possibility of the i-th point cloud data at the t-th moment within the predetermined time period. represents the road surface continuity of the i-th point cloud data. T represents the number of moments within the predetermined time period. If the road surface continuity of the same point cloud data is small and the occlusion possibilities at multiple moments are small, it indicates that the point cloud data is more likely to belong to a road surface defect, and the defect probability is greater. (-) represents the inverse proportional normalization function, which is used to perform inverse proportional normalization processing on

[0063] S106. Detect the quality of the position of the highway road surface corresponding to the current point cloud data according to the defect probability.

[0064] Specifically, after the embodiment of the present invention calculates the defect probability, when the defect probability is greater than the second threshold, it is determined that there is a road surface defect at the position of the highway road surface corresponding to the current point cloud data.

[0065] Among them, in the embodiment of the present invention, by setting a second threshold, if the defect probability of the position corresponding to the collected point cloud data is greater than the second threshold, it means that the possibility of a road surface defect occurring at this position is relatively high, and the point cloud data is marked. If there is also marked point cloud data in the surrounding or extended direction area of the point cloud data, further on-site inspection is required at this place. During the inspection, key attention should be paid to whether there are cracks, potholes, unevenness or other road surface quality problems that may affect driving safety and comfort. For main roads or key traffic hub areas with large traffic flow and frequent vehicle passage, for sections where defects often occur, in addition to timely repair, regular monitoring and maintenance should also be considered.

[0066] Furthermore, the second threshold can be determined according to the actual situation, and the value in the embodiment of the present invention is 0.85.

[0067] In the embodiment of the present invention, the point cloud data of the highway road surface is obtained, and the performance characteristics of the point cloud data on the highway road surface are analyzed. According to the change situation of the point cloud data at different times, the influence of vehicles passing through on the point cloud data under different traffic conditions on the road surface is analyzed, and the possibility that each point cloud data belongs to the point cloud data of the road surface is obtained, that is, the occlusion possibility of each point cloud data at each moment is obtained. When the occlusion possibility is greater than the first threshold, it is determined that the current point cloud data is occluded, indicating that the point cloud data may not be the point cloud data of the road surface. When the occlusion possibility is not greater than the first threshold, it indicates that the point cloud data is the point cloud data of the road surface. Thus, the defect probability that a defect may occur at the position corresponding to the point cloud data is calculated using the effective point cloud data, and the road surface quality is detected based on this defect probability. In this way, the accuracy of the obtained point cloud data of the highway road surface is improved in the present invention, and further the detection accuracy of the highway road surface quality is improved, and road surface defects and flatness problems can be accurately identified, and the interference of other influencing factors on the road surface quality detection can be excluded.

[0068] Embodiment 2:

[0069] Based on the online highway road surface quality detection method provided in the above embodiment, based on the same technical concept, the embodiment of the present invention also provides an online highway road surface quality detection device. Figure 2 The structural schematic diagram of an online highway road surface quality detection device provided for an embodiment of the present invention is as Figure 2As shown in the figure. The on-line road surface quality detection device 200 includes: an acquisition module 201, configured to acquire point cloud data of the road surface at each moment within a predetermined time period; a determination module 202, configured to determine the change degree of each point cloud data at each moment within the predetermined time period according to the height and gray value in the point cloud data at each moment within the predetermined time period; the determination module 202 is further configured to determine the relative change speed of the current point cloud data at each moment within the predetermined time period and the speed of the vehicle-mounted radar that acquires the current point cloud data; the determination module 202 is further configured to determine the occlusion possibility of the current point cloud data at each moment within the predetermined time period according to the change degree, relative change speed and speed of the current point cloud data at each moment within the predetermined time period; the determination module 202 is further configured to determine that the current point cloud data is occluded and re-acquire the point cloud data at the position where the current point cloud data is located when the occlusion possibility is greater than a first threshold, and determine the defect probability of the current point cloud data according to the road surface continuity of the current point cloud data and the occlusion possibility of the current point cloud data at each moment within the predetermined time period when the occlusion possibility is not greater than the first threshold; a detection module 203, configured to detect the quality of the position of the road surface corresponding to the current point cloud data according to the defect probability.

[0070] In the embodiment of the present invention, by acquiring the point cloud data of the road surface and analyzing the performance characteristics of the point cloud data on the road surface. According to the change of the point cloud data at different moments, the influence of the vehicles passing by on the road surface under different traffic conditions on the point cloud data is analyzed, and the possibility that each point cloud data belongs to the road surface point cloud data is obtained, that is, the occlusion possibility of each point cloud data at each moment is obtained. When the occlusion possibility is greater than a first threshold, it is determined that the current point cloud data is occluded, indicating that the point cloud data may not be the point cloud data of the road surface. When the occlusion possibility is not greater than the first threshold, it indicates that the point cloud data is the point cloud data of the road surface. Thus, the defect probability that a defect may occur at the position corresponding to the point cloud data is calculated using the effective point cloud data, and the road surface quality is detected based on the defect probability. In this way, the accuracy of the acquired point cloud data of the road surface is improved in the present invention, and further the detection accuracy of the road surface quality is improved, and the road surface defects and flatness problems can be accurately identified, and the interference of other influencing factors on the road surface quality detection can be excluded.

[0071] Embodiment 3:

[0072] Corresponding to the on-line road surface quality detection method provided in the above embodiment, based on the same technical concept, the embodiment of the present invention further provides an on-line road surface quality detection device, and the on-line road surface quality detection device is used to execute the above on-line road surface quality detection method. Figure 3 The structural schematic diagram of an on-line road surface quality detection device provided for another embodiment of the present invention is as Figure 3As shown in the figure. The on-line detection device for highway pavement quality may vary greatly due to different configurations or performances, and may include one or more processors 301 and a memory 302. The memory 302 is used to store computer programs that can run on the processor 301. The processor 301 is used to execute the programs stored on the memory 302 to implement the above Figure 1 each step in the method embodiments. Among them, the memory 302 can be transient storage or persistent storage. The application programs stored in the memory 302 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions for the on-line detection device for highway pavement quality.

[0073] Furthermore, the processor 301 can be set to communicate with the memory 302 and execute a series of computer-executable instructions in the memory 302 on the on-line detection device for highway pavement quality. The on-line detection device for highway pavement quality may also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input / output interfaces 305, and one or more keyboards 306.

[0074] Specifically, in this embodiment, the on-line detection device for highway pavement quality includes a processor, a communication interface, a memory, and a communication bus; among them, the processor, the communication interface, and the memory complete mutual communication through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored on the memory to implement the above Figure 1 each step in the method embodiments, and has the beneficial effects of the above method embodiments. To avoid repetition, the embodiments of the present invention will not be described in detail here.

[0075] It should be noted that the on-line detection device for highway pavement quality provided by the embodiments of the present invention and the on-line detection method for highway pavement quality provided by the embodiments of the present invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned on-line detection method for highway pavement quality, and has the same or similar beneficial effects. The repeated parts will not be described again.

[0076] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0077] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. A method for online detection of road pavement quality, characterized in that: The highway pavement quality online detection method comprises: Obtaining point cloud data of the road surface at each time within a predetermined time period; Determine the degree of change of each point cloud data at each moment in the predetermined time period according to the height and grayscale value in the point cloud data at each moment in the predetermined time period; Determine the relative change speed of the current point cloud data at each moment in a predetermined time period and the speed of the vehicle-mounted radar that collects the current point cloud data; Determining the occlusion possibility of the current point cloud data at each moment in the predetermined time period according to the change degree of the current point cloud data at each moment in the predetermined time period, the relative change speed and the speed; When the occlusion possibility is greater than a first threshold, determine that the current point cloud data is occluded, and re-collect the point cloud data at the location where the current point cloud data is located; when the occlusion possibility is not greater than the first threshold, determine the defect probability of the current point cloud data according to the road surface continuity of the current point cloud data and the occlusion possibility of the current point cloud data at each moment within a predetermined time period; The quality of the position of the highway road surface corresponding to the current point cloud data is detected according to the defect probability.

2. The method for online detection of road pavement quality according to claim 1, characterized in that: Determining the degree of change of each point cloud data at each moment in the predetermined time period according to the height and grayscale value in the point cloud data at each moment in the predetermined time period includes: Determine the grayscale representation value of the current point cloud data according to the first grayscale value average of all point cloud data in the neighborhood of the current point cloud data and the second grayscale value average of all point cloud data in the neighborhood of other point cloud data; Determine a height difference parameter of the current point cloud data according to a first height of the current point cloud data and a second height of adjacent point cloud data adjacent to the current point cloud data; Determine the third height of the point cloud data with the largest grayscale representation value; Determine the road surface continuity of the current point cloud data according to the height difference parameter of the current point cloud data, the grayscale representation value, the third height, and the first height; Based on the road surface continuity of the current point cloud data at each moment within the predetermined time period, the first duration of the maximum height of the current point cloud data within the predetermined time period, and the second duration of the minimum height of the current point cloud data within the predetermined time period, the degree of change of the current point cloud data at each moment within the predetermined time period is determined.

3. The method for online detection of road pavement quality according to claim 2, characterized in that: Determining the grayscale representation value of the current point cloud data according to the first grayscale value mean of all point cloud data in the neighborhood of the current point cloud data and the second grayscale value mean of all point cloud data in the neighborhood of other point cloud data includes: Calculating an absolute value of a first difference between the first grayscale value mean and a second grayscale value mean of other point cloud data, and superimposing the absolute values ​​of the first differences to obtain a first superimposed value; The first superposition value is subjected to inverse proportional normalization processing to obtain a grayscale representation value of the current point cloud data.

4. The method for online detection of road surface quality according to claim 2, characterized in that: The step of determining the height difference parameter of the current point cloud data according to the first height of the current point cloud data and the second height of adjacent point cloud data adjacent to the current point cloud data comprises: Calculating a second difference between a first height of the current point cloud data and a second height of a previous adjacent point cloud data adjacent to the current point cloud data, and a third difference between the first height of the current point cloud data and a second height of a next adjacent point cloud data adjacent to the current point cloud data; A fourth difference between the second difference and the third difference is calculated, and an inverse proportional normalization process is performed on the fourth difference to obtain a height difference parameter of the current point cloud data.

5. The method for online detection of road pavement quality according to claim 2, characterized in that: Determining the road surface continuity of the current point cloud data according to the height difference parameter of the current point cloud data, the grayscale representation value, the third height, and the first height includes: calculating an absolute value of a fifth difference between the third height and the first height, and a first sum of the absolute value of the fifth difference and a predetermined value; Calculating a first ratio of the height difference parameter to the first sum value; A first product between the grayscale representation value and the first ratio is determined as the road surface continuity of the current point cloud data.

6. The method for online detection of road surface quality according to claim 2, characterized in that: Determining the degree of change of the current point cloud data at each moment in the predetermined period based on the road surface continuity of the current point cloud data at each moment in the predetermined period, the first duration of the maximum height of the current point cloud data at the predetermined period, and the second duration of the minimum height of the current point cloud data at the predetermined period includes: Calculating an average continuity of road surface continuity of the current point cloud data at each moment within a predetermined period, a second ratio between the average continuity and the road surface continuity of the current point cloud data at each moment within the predetermined period, and a sixth difference between a predetermined value and the second ratio; Performing inverse proportional normalization on the sixth difference to obtain a normalized value; calculating a third ratio between the second duration and the first duration; A second product between the normalized value and the third ratio is determined as a change degree of the current point cloud data at each moment within a predetermined time period.

7. The method for online detection of road pavement quality according to claim 1, characterized in that: Determining the possibility of occlusion of the current point cloud data at each moment in the predetermined period of time according to the change degree of the current point cloud data at each moment in the predetermined period of time, the relative change speed and the speed includes: Calculating a seventh difference between the relative change speed and the speed, and rounding up the seventh difference to obtain an integer value; Determine a third product between the degree of change of the current point cloud data at each moment in the predetermined time period and the integer value as the occlusion possibility of the current point cloud data at each moment in the predetermined time period.

8. The method for online detection of road surface quality according to claim 1, characterized in that: Determining the defect probability of the current point cloud data according to the road surface continuity of the current point cloud data and the occlusion possibility of the current point cloud data at each moment within a predetermined period of time includes: Superimposing the occlusion possibilities of the current point cloud data at each time within a predetermined time period to obtain a second superposition value; Calculating a second sum value between the second superposition value and the road surface continuity of the current point cloud data; The second sum is subjected to inverse proportional normalization processing to obtain the defect probability of the current point cloud data.

9. The method for online detection of road pavement quality according to claim 1, characterized in that: The detecting the quality of the position of the road surface corresponding to the current point cloud data according to the defect probability comprises: When the defect probability is greater than a second threshold, it is determined that a road surface defect occurs at the position of the highway road surface corresponding to the current point cloud data.

10. An on-line detection device for road surface quality, characterized in that: include: A processor and a memory; wherein the memory is used to store a computer program that can be run on the processor; The processor is used to execute the program stored in the memory to implement the steps of the online detection method of highway pavement quality as described in any one of claims 1 to 9.

Images