Automatic synthesis method for airport cement pavement plate based on intersection rectangle verification

Abstract

The invention discloses an automatic synthesis method for airport cement pavement plates based on intersection rectangle verification. The method comprises the following steps: S1, identifying slab joints in an airport cement pavement image based on a semantic segmentation algorithm; s2, according to the GPS information of the image, converting the board seam line segments to a GPS coordinate system, and merging and removing outlier line segments; s3, calculating an intersection point between the mutually vertical plate seam line sections; s4, combining into quadrangles according to the intersection points, and performing rectangle verification on the quadrangles to merge into plates; and S5, clustering is carried out according to the diagonal length of the plate, and the special-shaped plate is removed. The method has the beneficial effects that the plate drawing efficiency can be greatly improved by identifying the plate joints in the cement pavement image, extracting the plate joint line sections, calculating the intersection points, combining the quadrangles according to the intersection points, and performing rectangle verification on the quadrangles and combining the quadrangles into the plate, compared with manual drawing of the airport cement plate.

Description

Technical Field

[0001] The invention relates to the technical field of plate synthesis, in particular to an automatic synthesis method of airport cement road surface panels based on intersection rectangle verification. Background Art

[0002] As the smallest unit of cement pavement at an airport, cement slabs are generally rectangular and evenly distributed in a grid pattern at the airport. In airport maintenance, it is often necessary to calculate the pavement condition index PCI based on the damage of cement slabs to provide a scientific basis for pavement maintenance. The calculation of PCI requires cement slabs to be the smallest unit to count the disease information within the slabs, but the current division of cement slabs often relies on historical design data or is manually drawn on a spliced ​​airport map. Relying on historical design data, it is difficult to update the changes of on-site slabs in a timely manner; manually drawing slabs of large-scale airports on maps is time-consuming and labor-intensive, and inefficient. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art and provide an automatic synthesis method for airport cement pavement slab blocks based on intersection rectangle verification.

[0004] The purpose of the present invention is achieved by the following technical solution: A method for automatically synthesizing airport cement road panel blocks based on intersection rectangle verification, comprising the following steps:

[0005] S1: Identify board seams in airport cement pavement images based on semantic segmentation algorithm;

[0006] S2: convert the plate seam segments into the GPS coordinate system according to the GPS information of the image, and merge and remove outlier segments;

[0007] S3: Calculate the intersection points between mutually perpendicular plate seam segments;

[0008] S4: Combine the intersection points into quadrilaterals, and perform rectangle verification on the quadrilaterals to merge them into plates;

[0009] S5: Cluster the plates according to their diagonal lengths and remove irregular-shaped plates.

[0010] Preferably, in step S1, the semantic segmentation algorithm is Unet or Deeplabv3.

[0011] Preferably, step S2 further includes the following steps:

[0012] S21: skeletonize the plate seam mask to extract the plate seam centerline, and perform straight line fitting on the plate seam centerline;

[0013] S22: Convert the plate seam line segments to the GPS coordinate system according to the GPS information of the image to obtain the line segment set of all plate seams , calculate the azimuth of all line segments in the GPS coordinate system;

[0014] S23: Calculate the line segment set The Euclidean distance between the line segment vertices in , merge the collinear line segments within the set distance;

[0015] S24: Clustering is performed according to the angles of the plate seam segments, a histogram is performed on the number of categories, and outlier segments with values ​​lower than the histogram mean are removed.

[0016] Preferably, in step S23, collinear line segments within 0.2 meters are merged.

[0017] Preferably, in step S24, the clustering method is DBSCAN or MeanShift.

[0018] Preferably, step S3 further includes the following steps:

[0019] S31: Extend the line segment to both ends by several meters, calculate the angle between every two intersecting line segments, and if the difference between the angle and 90° is less than 2°, calculate the intersection point of the two line segments to obtain the intersection points of all mutually perpendicular line segments;

[0020] S32: Calculate the Euclidean distance between the intersection points and merge the points of the nearest neighbors within a certain distance;

[0021] S33: Calculate the average value of the coordinates of the neighboring points as the coordinates of the merged point to obtain the set of all merged plate seam intersection points .

[0022] Preferably, in step S32, points with the nearest neighbors within 0.2 meters are merged.

[0023] Preferably, step S4 further includes the following steps:

[0024] S41: Set of intersection points of plate seams For each intersection point, find the ten nearest intersection points according to the distance, and combine them into multiple non-repeating point sets in groups of four. Each point set is used as a vertex to construct a quadrilateral, and a quadrilateral set is obtained. ;

[0025] S42: Calculate whether the vector dot product of two adjacent edges is 0 to verify the quadrilateral set For each quadrilateral in the , when the vector dot product of two adjacent edges is 0, the corresponding quadrilateral is constructed as a plate and added to the plate set .

[0026] Preferably, step S5 further includes the following steps:

[0027] S51: Computational Block Collection The diagonal length of each plate rectangle in , and clustering is performed based on the diagonal length;

[0028] S52: Perform histogram statistics on the clustering results, and select the diagonal length of the largest number of categories as the reference length;

[0029] S53: Calculate the difference between the diagonal length of all plates and the reference length. If the difference is greater than 0.5, the corresponding plate is judged as an irregular plate and is removed.

[0030] Preferably, in step S51, the clustering method is DBSCAN or MeanShift.

[0031] The present invention has the following advantages: the present invention identifies the plate seams in the cement pavement image, extracts the plate seam line segments and calculates the intersection points, combines them into quadrilaterals according to the intersection points, and performs rectangular verification on the quadrilaterals to merge them into plates. Compared with manually drawing the airport cement plates, the plate drawing efficiency can be greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 Schematic diagram of the process of automatic plate synthesis method. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0034] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0036] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0037] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, or the positions or positional relationships in which the product of the invention is usually placed when in use, or the positions or positional relationships commonly understood by those skilled in the art, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0038] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0039] In this embodiment, if Figure 1 As shown, an automatic synthesis method of airport cement road panel blocks based on intersection rectangle verification includes the following steps:

[0040] S1: Identify the board seams in the airport cement pavement image based on a semantic segmentation algorithm; preferably, the semantic segmentation algorithm is Unet or Deeplabv3.

[0041] S2: convert the plate seam segments into the GPS coordinate system according to the GPS information of the image, and merge and remove outlier segments;

[0042] S3: Calculate the intersection points between mutually perpendicular plate seam segments;

[0043] S4: Combine the intersection points into quadrilaterals, and perform rectangle verification on the quadrilaterals to merge them into plates;

[0044] S5: Cluster the plates according to their diagonal lengths and remove irregular plates. By identifying the plate seams in the cement pavement image, extracting the plate seam line segments and calculating the intersections, combining them into quadrilaterals based on the intersections, and performing rectangle verification on the quadrilaterals to merge them into plates, the efficiency of plate drawing can be greatly improved compared to manual drawing of airport cement plates.

[0045] Furthermore, step S2 further includes the following steps:

[0046] S21: skeletonize the plate seam mask to extract the plate seam centerline, and perform straight line fitting on the plate seam centerline;

[0047] S22: Convert the plate seam line segments to the GPS coordinate system according to the GPS information of the image to obtain the line segment set of all plate seams , calculate the azimuth of all line segments in the GPS coordinate system;

[0048] S23: Calculate the line segment set The Euclidean distance between the line segment vertices in the step S23 is used to merge the collinear line segments within the set distance; preferably, in step S23, the collinear line segments within 0.2 meters are merged.

[0049] S24: Clustering is performed based on the angle of the plate seam segments. The clustering method is DBSCAN or MeanShift. Histogram statistics are performed on the number of categories, and outlier segments below the histogram mean are removed.

[0050] Furthermore, step S3 further includes the following steps:

[0051] S31: Extend the line segment to both ends by several meters, here, extend the line segment to both ends by 10 meters. Calculate the angle between each two intersecting line segments. If the difference between the angle and 90° is less than 2°, calculate the intersection of the two line segments, and obtain the intersection of all mutually perpendicular line segments.

[0052] S32: Calculate the Euclidean distance between the intersection points and merge the neighboring points within a certain distance; preferably, merge the neighboring points within 0.2 meters, for example, search for neighboring points with one point as the center.

[0053] S33: Calculate the average value of the coordinates of the neighboring points as the coordinates of the merged point to obtain the set of all merged plate seam intersection points .

[0054] In this embodiment, step S4 further includes the following steps:

[0055] S41: Set of intersection points of plate seams For each intersection point, find the ten nearest intersection points according to the distance, and combine them into multiple non-repeating point sets in groups of four. Each point set is used as a vertex to construct a quadrilateral, and a quadrilateral set is obtained. ;

[0056] S42: Calculate whether the vector dot product of two adjacent edges is 0 to verify the quadrilateral set For each quadrilateral in the , when the vector dot product of two adjacent edges is 0, the corresponding quadrilateral is constructed as a plate and added to the plate set Specifically, in the plate collection There are often some special-shaped plates that are synthesized due to false detection of plate seams. These plates are obviously different in size from normal plates and need to be eliminated, that is, processed through step S5, which also includes the following steps:

[0057] S51: Computational Block Collection The diagonal length of each plate rectangle in is calculated, and clustering is performed based on the diagonal length; the clustering method is DBSCAN or MeanShift.

[0058] S52: Perform histogram statistics on the clustering results, and select the diagonal length of the largest number of categories as the reference length;

[0059] S53: Calculate the difference between the diagonal length of all plates and the reference length. If the difference is greater than 0.5, the corresponding plate is judged as an irregular plate and is removed.

[0060] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An automatic synthesis method of airport cement pavement panels based on intersection rectangle verification, characterized by: The following steps are involved: S1: Identify board seams in airport cement pavement images based on semantic segmentation algorithm; S2: convert the plate seam segments into the GPS coordinate system according to the GPS information of the image, and merge and remove outlier segments; S3: Calculate the intersection points between mutually perpendicular plate seam segments; S4: Combine the intersection points into quadrilaterals, and perform rectangle verification on the quadrilaterals to merge them into plates; S5: Cluster the plates according to their diagonal lengths and remove irregular-shaped plates.

2. The automatic synthesis method of airport cement pavement slab blocks based on intersection rectangle verification according to claim 1 is characterized by: In step S1, the semantic segmentation algorithm is Unet or Deeplabv3.

3. The automatic synthesis method of airport cement pavement slab blocks based on intersection rectangle verification according to claim 2 is characterized by: The step S2 further includes the following steps: S21: skeletonize the plate seam mask to extract the plate seam centerline, and perform straight line fitting on the plate seam centerline; S22: Convert the plate seam line segments to the GPS coordinate system according to the GPS information of the image to obtain the line segment set of all plate seams , calculate the azimuth of all line segments in the GPS coordinate system; S23: Calculate the line segment set The Euclidean distance between the line segment vertices in , merge the collinear line segments within the set distance; S24: Clustering is performed according to the angles of the plate seam segments, a histogram is performed on the number of categories, and outlier segments with values ​​lower than the histogram mean are removed.

4. The automatic synthesis method of airport cement pavement panels based on intersection rectangle verification according to claim 3 is characterized by: In step S23, collinear line segments within 0.2 meters are merged.

5. The automatic synthesis method of airport cement pavement slab blocks based on intersection rectangle verification according to claim 4 is characterized by: In step S24, the clustering method is DBSCAN or MeanShift.

6. The automatic synthesis method of airport cement pavement slab blocks based on intersection rectangle verification according to claim 5 is characterized by: The step S3 further includes the following steps: S31: Extend the line segment to both ends by several meters, calculate the angle between every two intersecting line segments, and if the difference between the angle and 90° is less than 2°, calculate the intersection point of the two line segments to obtain the intersection points of all mutually perpendicular line segments; S32: Calculate the Euclidean distance between the intersection points and merge the points of the nearest neighbors within a certain distance; S33: Calculate the average value of the coordinates of the neighboring points as the coordinates of the merged point to obtain the set of all merged plate seam intersection points .

7. The automatic synthesis method of airport cement pavement slab blocks based on intersection rectangle verification according to claim 6 is characterized by: In step S32, the points of the nearest neighbors within 0.2 meters are merged.

8. The automatic synthesis method of airport cement pavement panels based on intersection rectangle verification according to claim 7 is characterized by: The step S4 further includes the following steps: S41: Set of intersection points of plate seams For each intersection point, find the ten nearest intersection points according to the distance, and combine them into multiple non-repeating point sets in groups of four. Each point set is used as a vertex to construct a quadrilateral, and a quadrilateral set is obtained. ; S42: Calculate whether the vector dot product of two adjacent edges is 0 to verify the quadrilateral set For each quadrilateral in the , when the vector dot product of two adjacent edges is 0, the corresponding quadrilateral is constructed as a plate and added to the plate set .

9. The automatic synthesis method of airport cement pavement slab blocks based on intersection rectangle verification according to claim 8 is characterized by: The step S5 further includes the following steps: S51: Computational Block Collection The diagonal length of each plate rectangle in , and clustering is performed based on the diagonal length; S52: Perform histogram statistics on the clustering results, and select the diagonal length of the largest number of categories as the reference length; S53: Calculate the difference between the diagonal length of all plates and the reference length. If the difference is greater than 0.5, the corresponding plate is judged as an irregular plate and is removed.

10. The automatic synthesis method of airport cement pavement panels based on intersection rectangle verification according to claim 9 is characterized in that: In step S51, the clustering method is DBSCAN or MeanShift.

Images