Pavement rolling construction whole process identification method based on image identification

Abstract

The invention relates to the technical field of asphalt paving, and discloses a road surface rolling construction whole process identification method based on image identification, and the method comprises the steps: collecting a first three-dimensional diagram of a road before rolling of a road roller and a second three-dimensional diagram of the road after rolling of the road roller; obtaining a first section set of the first three-dimensional diagram and a second section set of the second three-dimensional diagram according to a preset first rule; according to the first section set and the second section set, the compactness and the flatness of the rolled pavement are evaluated; and determining the current construction position according to the compactness and flatness of the rolled pavement. Therefore, the current rolling process can be accurately identified directly through the change of the road surface, data statistical errors caused by position exchange of the road roller are avoided, the road surface rolling process is carried out in order, the possibility of pressure leakage or excessive pressure is reduced, the road surface rolling efficiency is improved, and the reduction of the road surface rolling effect is prevented.

Description

Technical Field

[0001] This application relates to the technical field of asphalt paving, for example, it relates to a method for identifying the whole process of pavement rolling construction based on image recognition. Background Art

[0002] During the paving process of asphalt pavement, initial compaction, secondary compaction, and final compaction need to be carried out in layers. At the same time, the rolling areas of the rollers for initial compaction, secondary compaction, and final compaction are different. And during the paving process of the same section of the road, due to reasons such as progress and sectional paving, various rollers will appear on the road surface at the same time to roll the road surface. At the same time, there will also be a situation where the roller originally in the initial compaction position and the roller in the final compaction position are swapped, and the rolling order position and work are swapped. Because the initial compaction roller needs continuous rolling operation, while the final compaction does not. The final compaction is an intermittent rolling operation, and it can take a short rest after completing one section. During the long-term rolling operation, the operator of the initial compaction roller is prone to mental fatigue. Therefore, the rollers for final compaction and initial compaction need to swap working positions during the construction operation.

[0003] During the traditional pavement rolling process, the operator remembers to operate the corresponding rollers for initial compaction, secondary compaction, and final compaction respectively, and the acquisition equipment is also pre-programmed in order. However, once the positions are swapped, the collected data is likely to be incorrect, and the collected and statistical data do not meet the operation requirements, and the analysis result of the statistical data shows errors, which reduces the efficiency of pavement rolling and also deteriorates the effect of pavement rolling.

[0004] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of this application. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] To have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a general review, nor is it intended to identify key / important constituent elements or delineate the protection scope of these embodiments. Instead, it serves as a preface to the subsequent detailed description.

[0006] In some embodiments, a method for identifying the whole process of pavement rolling construction based on image recognition includes:

[0007] Collect a first 3D map of the road before the roller compaction and a second 3D map of the road after the roller compaction;

[0008] Obtain a first cross-section set of the first 3D map and a second cross-section set of the second 3D map according to a preset first rule;

[0009] Evaluate the compactness and flatness of the roller-compacted road surface based on the first set of cross-sections and the second set of cross-sections;

[0010] Determine the current construction position based on the compactness and flatness of the roller-compacted road surface.

[0011] In some embodiments, obtaining the first set of cross-sections of the road surface image before rolling and the second set of cross-sections of the road surface image after rolling according to a preset first rule includes:

[0012] Intercept cross-sectional views of the first three-dimensional diagram and the second three-dimensional diagram respectively according to a preset first plane, where the first plane is vertically arranged and the length direction is the same as the length direction of the road;

[0013] Set the cross-sectional plane of the first three-dimensional diagram as the first cross-section and the cross-sectional plane of the second three-dimensional diagram as the second cross-section;

[0014] Continuously intercept the first cross-section and the second cross-section multiple times along the width direction of the road according to a preset first precision to generate the first set of cross-sections and the second set of cross-sections; wherein, the positions of intercepting the first cross-section and the second cross-section each time are the same, and the first cross-section and the second cross-section at the same position are set as a group of cross-sections.

[0015] In some embodiments, after obtaining the first set of cross-sections of the first three-dimensional diagram and the second set of cross-sections of the second three-dimensional diagram according to the preset first rule, it further includes:

[0016] Obtain the contour lines at the tops of the first cross-section and the second cross-section to generate the first contour line of the first cross-section and the second contour line of the second set of cross-sections;

[0017] Differentiate the first contour line and the second contour line respectively according to a preset second precision to generate the first set of differential points of the first contour line and the second set of differential points of the second contour line;

[0018] Record the longitudinal height of each differential point in the first set of differential points and the second set of differential points.

[0019] In some embodiments, the evaluating the compactness of the roller-compacted road surface according to the first set of cross-sections and the second set of cross-sections includes;

[0020] For each group of cross-sections, calculate the average height h of the first differential points in the first set of differential points 1 and the average height h of the second differential points in the second set of differential points 2 ;

[0021] Obtain the change amount h between the average height h 1 of the same group of cross-sections and the average height h 2 ; a ;

[0022] Take the change amount h aCompare with the preset compaction amount to generate the degree of compaction.

[0023] In some embodiments, the evaluating the flatness of the rolled road surface according to the first set of cross-sections and the second set of cross-sections includes:

[0024] Calculate the variance of the longitudinal heights of the first differential points in the first differential point set and the second differential points in the second differential point set in each group of cross-sections respectively and calculate the difference m;

[0025] Calculate the variance of the longitudinal heights of multiple differential points at the same position of consecutive first cross-sections and second cross-sections respectively along the width direction of the road surface and calculate the difference n;

[0026] Compare the difference m and the difference n with a preset range respectively to generate the flatness of the road surface.

[0027] In some embodiments, before determining the current construction position according to the degree of compaction and flatness of the rolled road surface, it further includes:

[0028] Divide the road along the width direction into multiple regions according to the width of the roller tire;

[0029] Record the number of times and intervals of roller compaction in each region;

[0030] If the interval is less than or equal to the set interval, record the compaction before and after the interval as the same compaction; if the interval is greater than the set interval, record the compaction before and after the interval as different compactions;

[0031] Judge the category of the first compaction in the same compaction according to the degree of compaction and flatness.

[0032] In some embodiments, determining the current construction position according to the degree of compaction and flatness of the rolled road surface further includes:

[0033] If the degree of compaction is within the set first compaction range, the difference m is within the set first longitudinal flatness range, and the difference n is within the set first transverse flatness range, then determine that the current construction position is the initial compaction;

[0034] If the degree of compaction is within the set second compaction range, the difference m is within the set second longitudinal flatness range, and the difference n is within the set second transverse flatness range, then determine that the current construction position is the re-compaction;

[0035] If the degree of compaction is within the set third compaction range, the difference m is within the set third longitudinal flatness range, and the difference n is within the set third transverse flatness range, then determine that the current construction position is the final compaction;

[0036] Wherein, the first compaction range, the second compaction range and the third compaction range are continuous.

[0037] In some embodiments, after determining the current construction position according to the compactness and flatness of the rolled road surface, it further includes:

[0038] Dividing the second contour point set of each second cross-section according to a preset third precision to generate multiple point sets;

[0039] Calculating the variance of each point set and judging the flatness of the current point set according to the variance of each point set;

[0040] If the flatness of the current point set is lower than the set flatness, a reminder is issued.

[0041] The method for identifying the whole process of road surface rolling construction based on image recognition provided by the embodiments of the present disclosure can achieve the following technical effects:

[0042] It can directly identify the current rolling process through the changes in the road surface, avoid data statistical errors caused by the replacement of the roller position, make the road surface rolling process proceed in an orderly manner, reduce the possibility of missed rolling or over-rolling, improve the efficiency of road surface rolling, and help prevent the decline of the road surface rolling effect.

[0043] The above general description and the following description are only exemplary and explanatory, and are not used to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] One or more embodiments are exemplarily illustrated by corresponding drawings. These exemplary illustrations and the drawings do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation, and among them:

[0045] Figure 1 is a schematic diagram of a method for identifying the whole process of road surface rolling construction based on image recognition provided by an embodiment of the present disclosure;

[0046] Figure 2 is a schematic diagram of another method for identifying the whole process of road surface rolling construction based on image recognition provided by an embodiment of the present disclosure;

[0047] Figure 3 is a schematic diagram of another method for identifying the whole process of road surface rolling construction based on image recognition provided by an embodiment of the present disclosure;

[0048] Figure 4 is a schematic diagram of another method for identifying the whole process of road surface rolling construction based on image recognition provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] In order to understand the features and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are only for reference and explanation, and are not used to limit the embodiments of the present disclosure. In the following technical description, for the sake of explanation, a sufficient understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, well-known structures and devices can be shown in a simplified manner to simplify the drawings.

[0050] In the description of the embodiments of the present disclosure, the terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so as to implement the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion.

[0051] Unless otherwise specified, the term "plurality" means two or more.

[0052] In the embodiments of the present disclosure, the character " / " indicates that the objects before and after are in an "or" relationship. For example, A / B means: A or B.

[0053] The term "and / or" is a description of the association relationship of an object, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B these three relationships.

[0054] The term "corresponding" may refer to an association relationship or a binding relationship. A corresponding to B means that there is an association relationship or a binding relationship between A and B.

[0055] It should be noted that, without conflict, the embodiments in the embodiments of the present disclosure and the features in the embodiments can be combined with each other.

[0056] Referring to Figure 1 , the method for identifying the whole process of pavement rolling construction based on image recognition provided by the embodiments of the present disclosure includes:

[0057] S101, collecting a first three-dimensional map of the road before the roller compaction and a second three-dimensional map of the road after the roller compaction.

[0058] S102, obtaining a first cross-section set of the first three-dimensional map and a second cross-section set of the second three-dimensional map according to a preset first rule.

[0059] S103, evaluating the compactness and flatness of the compacted road surface according to the first cross-section set and the second cross-section set.

[0060] S104. Determine the current construction position according to the compactness and flatness of the rolled road surface.

[0061] Before and after the roller compaction, the three-dimensional map of the road surface is collected by using three-dimensional acquisition technology, and the first three-dimensional map of the road surface before compaction and the second three-dimensional map of the road surface after compaction are generated respectively. Among them, in the process of generating the first three-dimensional map and the second three-dimensional map, the accuracy of the three-dimensional map of the road surface is mainly considered. Then, according to the preset first rule, the first three-dimensional map and the second three-dimensional map are cut respectively, and the cut cross-section is set as the cross-section of the corresponding three-dimensional map, and the corresponding first interface set and second cross-section set are generated. Evaluate the compactness and flatness of the road surface according to the first cross-section and the second cross-section corresponding to the contour line of the road surface in the first cross-section set and the second cross-section set, and determine the construction position according to the compactness and flatness.

[0062] In this way, the current rolling process can be accurately identified directly through the change of the road surface, avoiding the data statistical error caused by the position exchange of the roller, making the road surface rolling process proceed in an orderly manner, reducing the possibility of missed compaction or over-compaction, improving the efficiency of road surface compaction, and helping to prevent the decline of road surface compaction effect.

[0063] Optionally, obtaining the first cross-section set of the road surface image before compaction and the second cross-section set of the road surface image after compaction according to the preset first rule includes:

[0064] Intercept the cross-sectional views of the first three-dimensional map and the second three-dimensional map according to the preset first plane. The first plane is vertically arranged and the length direction is the same as the length direction of the road; set the cross-sectional plane of the first three-dimensional map as the first cross-section and the cross-sectional plane of the second three-dimensional map as the second cross-section.

[0065] The first plane can be a regular rectangular plane with a length greater than the length of the road; move the first plane vertically from top to bottom to cut the first three-dimensional map and the second three-dimensional map, and set the cut cross-sectional planes as the first cross-section and the second cross-section respectively.

[0066] Continuously intercept the first cross-section and the second cross-section along the width direction of the road according to the preset first precision to generate the first cross-section set and the second cross-section set; among them, the positions of intercepting the first cross-section and the second cross-section are the same each time, and the first cross-section and the second cross-section at the same position are set as a group of cross-sections.

[0067] When intercepting the first cross-section set and the second cross-section set, the higher the first precision, the more the number of the first cross-section and the second cross-section collected, and the more accurate the estimation of the compactness and flatness.

[0068] Refer to Figure 2 , the method for identifying the whole process of road surface rolling construction based on image recognition provided by the embodiments of the present disclosure further includes:

[0069] S201, collect the first 3D map of the road before the roller compaction and the second 3D map of the road after the roller compaction.

[0070] S202, obtain the first cross-section set of the first 3D map and the second cross-section set of the second 3D map according to a preset first rule.

[0071] S203, obtain the contour lines at the tops of the first cross-section and the second cross-section, and generate the first contour line of the first cross-section and the second contour line of the second cross-section set.

[0072] The contour lines at the tops of the first cross-section and the second cross-section are the contour lines of the corresponding road surface.

[0073] S204, perform differentiation on the first contour line and the second contour line respectively according to a preset second precision, and generate the first differential point set of the first contour line and the second differential point set of the second contour line.

[0074] S205, record the longitudinal height of each differential point in the first differential point set and the second differential point set. The longitudinal height of each differential point is used to evaluate the compactness and flatness of the compacted road surface.

[0075] There is a standard plane preset at the bottom of the road surface. The longitudinal height of the differential point is the distance between the differential point and the standard plane.

[0076] S206, evaluate the compactness and flatness of the compacted road surface according to the first cross-section set and the second cross-section set.

[0077] The actual evaluation process in this step is to evaluate the compactness and flatness of the compacted road surface according to the longitudinal heights of the differential points corresponding to the first cross-section set and the second cross-section set.

[0078] S207, determine the current construction position according to the compactness and flatness of the compacted road surface.

[0079] When judging the compactness of the road surface, it is mainly determined by the overall change in the height of the road surface, that is, the overall change in the height of the road surface in the vertical direction; when judging the flatness of the road surface, it is mainly determined by the height change of a continuous section of the road surface within a certain width range, that is, the curve change of the road surface within a certain width range. The overall change in the height of the road surface in the vertical direction and the curve change of the road surface within a certain width range can both be reflected by the longitudinal height of the differential points. Therefore, the change in the longitudinal height of the differential points of the road surface contour line can accurately reflect the compactness and flatness of the road surface, improving the accuracy of the evaluation.

[0080] Optionally, evaluating the compactness of the compacted road surface according to the first cross-section set and the second cross-section set includes: for each group of cross-sections, calculate the average height h of the first differential points in the first differential point set 1 and the average height h of the second differential points in the second differential point set2 ; Obtain the average height h of the same group of cross-sections 1 and the average height h 2 The change amount h between them a ; Compare the change amount h a with the preset compaction amount to generate the compaction degree.

[0081] The average height reflects the overall height within the set range of the current road surface. When the change amount h a is large, it indicates that the compaction degree before rolling is low. When the change amount h a is small, it indicates that the compaction degree before rolling is high. When generating the compaction degree, estimate the overall road surface change amount from the asphalt paving to the completion of rolling, and set the overall road surface change amount as the preset compaction amount. Then the compaction degree is:

[0082] where X is the compaction degree; H is the preset compaction amount; ∑h a is the sum of the current change amount ha and all previous change amounts ha.

[0083] Optionally, evaluate the flatness of the rolled road surface according to the first cross-section set and the second cross-section set, including:

[0084] Calculate the variance of the longitudinal heights of the first differential points in the first differential point set and the second differential points in the second differential point set in each group of cross-sections and calculate the difference m; calculate the variance of the longitudinal heights of multiple differential points at the same position of the continuous first cross-section and the second cross-section along the width direction of the road surface and calculate the difference n; compare the difference m and the difference n with the preset range respectively to generate the flatness of the road surface.

[0085] The variance represents the degree of dispersion or deviation of the current data. The variance of the differential point set is used to represent the flatness of the current differential point set. If the variance is larger, it indicates that the corresponding differential point set is more unstable, and the flatness is lower. If the variance is smaller, it indicates that the corresponding differential point set is more stable, and the flatness is higher. The difference in variance indicates the change amount of flatness.

[0086] In this way, using the variance to represent the flatness of the current differential point set can accurately reflect the flatness information of the current road surface, thus facilitating the accurate real-time monitoring of the road construction process.

[0087] Refer to Figure 3 , The method for identifying the whole process of road surface rolling construction based on image recognition provided by the embodiments of the present disclosure further includes:

[0088] S301, Collect the first 3D map of the road before the roller compaction and the second 3D map of the road after the roller compaction.

[0089] S302. Obtain the first cross-section set of the first 3D map and the second cross-section set of the second 3D map according to a preset first rule.

[0090] S303. Evaluate the compactness and flatness of the rolled road surface according to the first cross-section set and the second cross-section set.

[0091] S304. Divide the road into multiple regions along the width direction according to the width of the roller tire.

[0092] S305. Record the number of times and intervals of roller rolling in each region.

[0093] S306. If the interval is less than or equal to the set interval, record the rolling before and after the interval as the same rolling; if the interval is greater than the set interval, record the rolling before and after the interval as different rolling.

[0094] S307. Determine the category of the first rolling in the same rolling according to the compactness and flatness.

[0095] S308. Determine the current construction position according to the compactness and flatness of the rolled road surface.

[0096] During the processes of initial compaction, intermediate compaction, and final compaction, in each category of rolling, the change amount of the road surface before and after the first rolling is relatively large. Therefore, the first rolling is selected as a typical feature for identification.

[0097] Optionally, determining the current construction position according to the compactness and flatness of the rolled road surface includes: if the compactness is within a set first compactness range, the difference m is within a set first longitudinal flatness range, and the difference n is within a set first transverse flatness range, then determine that the current construction position is initial compaction; if the compactness is within a set second compactness range, the difference m is within a set second longitudinal flatness range, and the difference n is within a set second transverse flatness range, then determine that the current construction position is intermediate compaction; if the compactness is within a set third compactness range, the difference m is within a set third longitudinal flatness range, and the difference n is within a set third transverse flatness range, then determine that the current construction position is final compaction; where the first compactness range, the second compactness range, and the third compactness range are continuous.

[0098] For example, during the initial compaction process, the overall height change of the road surface is large; in the width direction of the road, assuming that the first region is under initial compaction and the second region has not been initially compacted, there will be a height difference in the width direction of the road, so the difference n is large. And during the first initial compaction of a region, the change amount of the road is large, while the change amount of the road during the second initial compaction becomes smaller, but overall, the overall height change amount during initial compaction is greater than that during intermediate compaction, that is, the compactness is different and the compactness change amount is also different.

[0099] For example, after the multi-pass compaction is completed and before the final compaction starts, there are some ruts on the road surface, and the ruts disappear after the final compaction. The change in the degree of compaction is less than that before the initial compaction and before and after the multi-pass compaction; the flatness becomes higher, but the change in flatness is less than that before and after the initial compaction and the multi-pass compaction; among them, the change amounts of the difference m and the difference n of the road surface before and after the final compaction are both relatively small.

[0100] In the process of judging the initial compaction, multi-pass compaction, and final compaction, not only can the construction sequence be judged by the degree of compaction, the difference m, and the difference n, but also the variance of the longitudinal height of the first differential point set in the first differential point concentration and the second differential point set in the second differential point concentration, as well as the variance of the longitudinal height of multiple differential points at the same position of the first cross-section and the second cross-section, and the changes in the road surface before and after the overall completion of the initial compaction, multi-pass compaction, and final compaction can be combined for comprehensive judgment.

[0101] Refer to Figure 4 , the method for identifying the whole process of road surface rolling construction based on image recognition provided by the embodiments of the present disclosure further includes:

[0102] S401, collect the first 3D map of the road before the roller compaction and the second 3D map of the road after the roller compaction.

[0103] S402, obtain the first cross-section set of the first 3D map and the second cross-section set of the second 3D map according to the preset first rule.

[0104] S403, evaluate the degree of compaction and flatness of the compacted road surface according to the first cross-section set and the second cross-section set.

[0105] S404, determine the current construction sequence according to the degree of compaction and flatness of the compacted road surface.

[0106] S405, divide the second contour point set of each second cross-section according to the preset third precision to generate multiple point sets.

[0107] S406, calculate the variance of each point set and judge the flatness of the current point set according to the variance of each point set.

[0108] S407, if the flatness of the current point set is lower than the set flatness, send a reminder.

[0109] For the set segment point set, the variance is used to judge the flatness of the current point set after compaction, so as to facilitate the system to detect whether the road surface in the current segment has been compacted. If there is a situation where the variance is large and the flatness is low, a reminder will be sent to the relevant person in charge, indicating that the current road surface has not been compacted according to the expected target. In this way, it is possible to automatically guide and monitor the whole process of on-site construction and remind relevant defective parts.

[0110] When calculating the variance of the current point set after compaction, the average height is calculated using the average height of the entire second contour point set.

[0111] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure, enabling those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. The embodiments only represent possible variations. Unless explicitly required, the individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terms used in this application are only for describing the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to also include the plural forms. Similarly, as used in this application, the term "and / or" refers to any and all possible combinations of one or more of the associated listed items. Additionally, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" etc. mean the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups of these. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, or apparatus comprising the element. In this document, what each embodiment focuses on may be the differences from other embodiments, and the same or similar parts between the embodiments may be referred to each other. For the methods and the like disclosed in the embodiments, if they correspond to the method parts disclosed in the embodiments, the relevant parts may refer to the description of the method parts.

[0112] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner may depend on the specific application and design constraints of the technical solution. The technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the embodiments of the present disclosure.

[0113] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of systems that can be implemented according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. Each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for identifying the entire process of road rolling construction based on image recognition, comprising: Collecting a first three-dimensional image of the road before the roller is rolled and a second three-dimensional image of the road after the roller is rolled; Acquire a first cross-section set of the first three-dimensional image and a second cross-section set of the second three-dimensional image according to a preset first rule; evaluating the compaction degree and smoothness of the rolled pavement according to the first cross-section set and the second cross-section set; The current construction position is determined based on the compaction and flatness of the rolled road surface.

2. The method for identifying the entire process of road rolling construction based on image recognition according to claim 1, characterized in that: Acquiring a first cross-section set of the road surface image before rolling and a second cross-section set of the road surface image after rolling according to a preset first rule includes: Cutting out cross-sectional views of the first three-dimensional image and the second three-dimensional image respectively according to a preset first plane, wherein the first plane is vertically arranged and has a length direction that is the same as a length direction of the road; Setting the section plane of the first three-dimensional image as the first section, and setting the section plane of the second three-dimensional image as the second section; The first section and the second section are intercepted multiple times continuously along the width direction of the road according to a preset first accuracy to generate a first section set and a second section set; wherein the positions of the first section and the second section are the same each time, and the first section and the second section at the same position are set as a group of sections.

3. The method for identifying the entire process of road rolling construction based on image recognition according to claim 1, characterized in that: After obtaining the first section set of the first three-dimensional image and the second section set of the second three-dimensional image according to the preset first rule, the method further includes: Acquire the contour lines of the top of the first section and the second section, and generate a first contour line of the first section and a second contour line of the second section set; Differentiate the first contour line and the second contour line respectively according to a preset second precision to generate a first differential point set of the first contour line and a second differential point set of the second contour line; The longitudinal height of each differential point in the first differential point set and the second differential point set is recorded, and the longitudinal height of each differential point is used to evaluate the compaction degree and flatness of the rolled road surface.

4. The method for identifying the entire process of road rolling construction based on image recognition according to claim 3 is characterized in that: The step of evaluating the compaction degree of the rolled pavement according to the first cross-section set and the second cross-section set includes: For each group of cross sections, respectively calculate the average height h1 of the first differential point in the first differential point set and the average height h2 of the second differential point in the second differential point set; Get the change h between the average height h1 and the average height h2 of the same set of sections a ; The change h a Compare with the preset compaction amount to generate the compaction degree.

5. The method for identifying the entire process of road rolling construction based on image recognition according to claim 4 is characterized in that: The step of evaluating the flatness of the rolled road surface according to the first cross-section set and the second cross-section set includes: In each group of cross sections, respectively, the variance of the longitudinal heights of the first differential point in the first differential point set and the second differential point in the second differential point set is calculated, and the difference m is calculated; Calculate the variance of the longitudinal heights of a plurality of differential points at the same position of the continuous first section and the second section along the width direction of the road surface and calculate the difference n; The difference m and the difference n are respectively compared with the preset range to generate the flatness of the road surface.

6. The method for identifying the entire process of road rolling construction based on image recognition according to claim 5 is characterized in that: Before determining the current construction position according to the compaction and flatness of the rolled road surface, it also includes: Divide the road into multiple areas along the width direction according to the tire width of the roller; Record the number and interval of roller rolling in each area; If the interval is less than or equal to the set interval, the rolling before and after the interval will be recorded as the same rolling; if the interval is greater than the set interval, the rolling before and after the interval will be recorded as different rolling; Determine the category of the first rolling in the same rolling according to the compaction degree and flatness.

7. The method for identifying the entire process of road rolling construction based on image recognition according to claim 5 or 6, characterized in that: The current construction position is determined according to the compaction and flatness of the rolled road surface, including: If the compaction degree is within the set first compaction range, the difference m is within the set first longitudinal flattening range, and the difference n is within the set first transverse flattening range, the current construction position is determined to be initial compaction; If the compaction degree is within the set second compaction range, the difference m is within the set second longitudinal flattening range, and the difference n is within the set second transverse flattening range, then the current construction position is determined to be re-compaction; If the compaction degree is within the set third compaction range, the difference m is within the set third longitudinal flattening range, and the difference n is within the set third transverse flattening range, the current construction position is determined to be final compaction; Among them, the first compaction range, the second compaction range and the third compaction range are continuous.

8. The method for identifying the entire process of road rolling construction based on image recognition according to claim 5 or 6, characterized in that: After determining the current construction position according to the compaction and flatness of the rolled road surface, it also includes: Dividing the second contour point set of each second cross section according to a preset third precision to generate a multi-segment point set; Calculate the variance of each segment of the point set and determine the flatness of the current point set based on the variance of each segment of the point set; If the flatness of the current point set is lower than the set flatness, a reminder will be issued.

Images