WO2021203664A1

WO2021203664A1 - Wall cross-sectional size measurement method, apparatus, and system

Info

Publication number: WO2021203664A1
Application number: PCT/CN2020/121261
Authority: WO
Inventors: 张富涛; 曾翔; 王佳盛; 杨炼
Original assignee: 广东博智林机器人有限公司
Priority date: 2020-04-09
Filing date: 2020-10-15
Publication date: 2021-10-14
Also published as: CN111412842A; CN111412842B

Abstract

A wall cross-sectional size measurement method, apparatus, and system. The wall cross-sectional size measurement method comprises: acquiring original point cloud data containing a wall to be measured, wherein said wall comprises a cross section to be measured (S102); extracting from the original point cloud data point cloud data corresponding to said wall (S104); extracting, from the point cloud data corresponding to said wall, point cloud data corresponding to said cross section (S106); and determining, according to the point cloud data corresponding to said cross section, the cross-sectional size of said cross section at any preset height (S108). The measurement apparatus correspondingly comprises an acquisition module (20), a first extraction module (22), a second extraction module (24), and a determination module (26). The measurement system comprises a vision sensor (30) and a processor (32).

Description

Method, device and system for measuring cross-sectional size of wall

Technical field

This application relates to the field of building physical measurement, and specifically to a method, device, and system for measuring the cross-sectional size of a wall surface.

Background technique

In the construction phase of the building, the actual measured amount passes the physical test on the construction site, and feedback the quality status of the product in time, so that the project manager can improve the construction process in time. At present, the actual measurement is still using relatively old data collection methods. For example, the measurement of the wall section size (wall section thickness) is measured by the actual measurement personnel using a steel tape measure. For the walls of a construction site, even if it is the same wall, it is difficult to ensure that the thickness of the section at different heights is the same. Due to the limitation of work efficiency, manual data collection can only be performed on part of the measurement points, and the sampling rate is low. Moreover, limited by the accuracy of the tools used, it is difficult for operators to obtain a very accurate measurement value.

Aiming at the problems of low work efficiency and low measurement accuracy in the manual measurement of wall cross-sectional dimensions during the construction phase, no effective solutions have been proposed.

Summary of the invention

The embodiments of the present application provide a method, device, and system for measuring the cross-sectional size of a wall surface, so as to at least solve the technical problems of low work efficiency and low measurement accuracy in manually measuring the cross-sectional size of the wall during the construction phase of the building.

According to one aspect of the embodiments of the present application, there is provided a method for measuring the cross-sectional size of a wall surface, including: obtaining original point cloud data containing the wall surface to be tested, wherein the wall surface to be tested includes the cross-section to be tested; The point cloud data corresponding to the wall to be measured is extracted from the cloud data; the point cloud data corresponding to the section to be measured is extracted from the point cloud data corresponding to the wall to be measured; the section to be measured is determined according to the point cloud data corresponding to the measured section The size of the section at any preset height.

Optionally, before extracting the point cloud data corresponding to the wall to be measured from the original point cloud data, the above method further includes: performing down-sampling processing on the original point cloud data; and performing filtering and denoising processing on the original point cloud data.

Optionally, extracting the point cloud data corresponding to the wall to be tested from the original point cloud data includes: filtering out the point cloud data of the building surface from the original point cloud data; extracting the point cloud data of the building surface from the point cloud data to be tested. Measure the point cloud data of the wall.

Optionally, filtering out the point cloud data of the building surface from the original point cloud data includes: performing plane segmentation processing on the original point cloud data to extract point cloud data of different planes; filtering from the point cloud data of different planes The point cloud data corresponding to the three vertical planes two by two are used as the point cloud data of the building surface.

Optionally, from the point cloud data of different planes, filtering out the point cloud data corresponding to the three vertical planes two by two as the point cloud data of the building surface includes: performing plane fitting processing on the point cloud data of different planes, Obtain the direction of the plane normal vector corresponding to each plane, and classify the planes based on the direction of the plane normal vector to obtain the point cloud data corresponding to the planes in different directions; filter out the point cloud data corresponding to the planes in different directions The point cloud data corresponding to the three vertical planes is used as the point cloud data of the building surface.

Optionally, extracting the point cloud data of the wall to be measured from the point cloud data of the building surface includes: filtering out points parallel to the ground from the point cloud data of the building surface according to the data collection angle and coordinate direction of the sensor Cloud data, and extract the ground point cloud data from the filtered point cloud data parallel to the ground; the point cloud data of the building surface except the point cloud data parallel to the ground are two sets of mutually perpendicular point clouds Data, as the point cloud data constituting the wall to be tested.

Optionally, before taking two sets of mutually perpendicular point cloud data in the point cloud data of the building surface except the point cloud data parallel to the ground as the point cloud data constituting the wall to be measured, the above method further includes: judgment Two sets of mutually perpendicular point cloud data constitute the unevenness; if the two sets of mutually perpendicular point cloud data constitute a convexity, the two sets of mutually perpendicular point cloud data are used as the point cloud data of the wall to be measured; if The concavity and convexity formed by the two sets of mutually perpendicular point cloud data is concave, and the two sets of mutually perpendicular point cloud data are regarded as interference point cloud data.

Optionally, extracting the ground point cloud data from the filtered point cloud data parallel to the ground, including: the Z-direction of the sensor collected data is facing upward, and the filtered point cloud data of the building surface parallel to the ground The point cloud data with the smallest Z value is the ground point cloud data.

Optionally, after the point cloud data corresponding to the wall to be measured is extracted from the original point cloud data, the above method further includes: calculating the inclination angle of the point cloud data of the wall to be measured with respect to the gravity plane; The point cloud data of the surface is rotated and calibrated so that the plane normal vector corresponding to the point cloud data of the ground faces vertically upward.

Optionally, extracting the point cloud data corresponding to the section to be tested from the point cloud data corresponding to the wall to be tested includes: traversing the point cloud data corresponding to the wall to be tested, and comparing the point cloud data of the wall to be tested The point cloud width data and the preset section size range, the point cloud data of the wall to be measured corresponding to the point cloud width data falling within the preset section size range is used as the point cloud data of the candidate section to be measured, and the point cloud width data is Point cloud data on the short side of the wall to be tested.

Optionally, after the point cloud data of the wall to be measured corresponding to the point cloud width falling within the preset cross-sectional size range is used as the point cloud data of the candidate to-be-measured section, the above method further includes: From the cloud data, select the point cloud data with the largest section height as the point cloud data of the target section to be measured. From the collection of point cloud data of the wall to be measured, find the point cloud data of the target section to be measured perpendicular to and adjacent to each other The point cloud data of is used as the point cloud data of the reference surface, where the point cloud data of the reference surface is used for the size measurement of the section to be measured.

Optionally, determining the size of the section to be measured at any preset height according to the point cloud data corresponding to the section to be measured includes: determining that the section to be measured is at any predetermined height based on the point cloud data of the target section to be measured and the point cloud data of the reference plane The cross-section size of the preset height.

Optionally, determining the size of the section to be measured at any preset height according to the point cloud data of the target section to be measured and the point cloud data of the reference plane, including: filtering out the section to be measured from the point cloud data of the reference plane The point cloud data whose distance from the line of intersection with the reference plane is within a preset range is used as the first reference plane point cloud data; Measure the two edge contour data in the height direction of the section, and select the edge contour data far from the first datum point cloud data from the two edge contour data as the first edge contour data; according to the preset height range from the first edge The second edge contour data is intercepted from the contour data, and the second datum point cloud data is intercepted from the first datum point cloud data. The preset height range is based on the preset height, and the preset values are selected from up and down respectively The measurement range is determined by the height; the section size of the section to be measured at the preset height is determined according to the point cloud data of the second reference plane and the second edge profile data.

Optionally, determining the cross-sectional size of the section to be measured at a preset height according to the second reference surface point cloud data and the second edge profile data includes: fitting processing to the second reference surface point cloud data to obtain the second reference surface point The plane equation of the cloud data in the preset coordinate system, the preset coordinate system is the coordinate system determined by the ground wall corner position as the origin, and the wall direction of the datum plane as the coordinate axis direction; determine the point cloud data corresponding to the second edge profile data The distance from the plane equation is taken as the size of the section to be measured at the preset height.

According to another aspect of the embodiments of the present application, there is also provided an apparatus for measuring the cross-sectional size of a wall surface, including: an acquisition module for acquiring original point cloud data containing the wall surface to be tested, wherein the wall surface to be tested includes The section to be tested; the first extraction module is used to extract the point cloud data corresponding to the wall to be tested from the original point cloud data; the second extraction module is used to extract the point cloud data corresponding to the wall to be tested Point cloud data corresponding to the measured cross-section; the determination module is used to determine the cross-sectional size of the tested cross-section at any preset height according to the point cloud data corresponding to the tested cross-section.

According to another aspect of the embodiments of the present application, there is also provided a system for measuring the cross-sectional dimensions of a wall surface, including: a vision sensor and a processor, wherein the vision sensor is used to obtain raw point cloud data containing the wall surface to be measured , And send the original point cloud data to the processor, where the wall to be tested includes the cross section to be tested; the processor is communicatively connected with the vision sensor, and is used to extract the point cloud corresponding to the wall to be tested from the original point cloud data Data; extract the point cloud data corresponding to the section to be measured from the point cloud data corresponding to the wall to be measured; determine the section size of the section to be measured at any preset height according to the point cloud data corresponding to the section to be measured.

According to another aspect of the embodiments of the present application, a non-volatile storage medium is also provided. The non-volatile storage medium includes a stored program. When the program is running, the device where the non-volatile storage medium is located is controlled to execute the above wall The measurement method of the cross-sectional dimensions of the surface.

According to another aspect of the embodiments of the present application, there is also provided a processor, which is configured to run a program stored in a memory, wherein the method for measuring the cross-sectional dimension of the wall surface is executed when the program is running.

In the embodiment of the present application, the original point cloud data including the wall to be tested is acquired; the point cloud data corresponding to the wall to be tested is extracted from the original point cloud data, where the wall to be tested includes the cross section to be tested; The point cloud data corresponding to the section to be measured is extracted from the point cloud data corresponding to the wall to be measured; the section size of the wall to be measured is determined according to the point cloud data corresponding to the section to be measured, and the point cloud data of the building is collected. Using point cloud data to automatically measure the cross-sectional size of the cross-section at any preset height, thereby achieving the technical effect of improving the measurement efficiency and measurement accuracy of the cross-sectional size of the wall of the building, thereby solving the problem of manually measuring the wall during the construction phase. The cross-sectional dimensions of the surface have technical problems of low work efficiency and low measurement accuracy.

Description of the drawings

The drawings described here are used to provide a further understanding of the application and constitute a part of the application. The exemplary embodiments and descriptions of the application are used to explain the application, and do not constitute an improper limitation of the application. In the attached picture:

Fig. 1 is a flowchart of a method for measuring the cross-sectional size of a wall surface according to an embodiment of the present application;

2 is a structural diagram of a measuring device for the cross-sectional size of a wall surface according to an embodiment of the present application;

Fig. 3 is a structural diagram of a system for measuring the cross-sectional size of a wall surface according to an embodiment of the present application.

Detailed ways

In order to enable those skilled in the art to better understand the solutions of the application, the technical solutions in the embodiments of the application will be clearly and completely described below in conjunction with the drawings in the embodiments of the application. Obviously, the described embodiments are only These are a part of the embodiments of this application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work should fall within the protection scope of this application.

It should be noted that the terms "first" and "second" in the specification and claims of the application and the above-mentioned drawings are used to distinguish similar objects, and not necessarily used to describe a specific sequence or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations of them are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those clearly listed. Those steps or units may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or equipment.

According to an embodiment of the present application, an embodiment of a method for measuring the cross-sectional size of a wall is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions And, although the logical sequence is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than here.

Fig. 1 is a flowchart of a method for measuring the cross-sectional size of a wall surface according to an embodiment of the present application. As shown in Fig. 1, the method includes the following steps:

Step S102: Obtain original point cloud data including the wall to be measured, where the wall to be measured includes the cross-section to be measured.

Point cloud data means that the scanned data is recorded in the form of points. Each point contains three-dimensional coordinates, and some may contain color information or reflection intensity information. The color information is usually obtained by obtaining a color image through a camera, and then assigning the color information of the pixel at the corresponding position to the corresponding point in the point cloud. The acquisition of intensity information is the intensity of the echo collected by the laser scanner receiving device. This intensity information is related to the surface material, roughness, incident angle and direction of the target, as well as the emission energy of the instrument and the laser wavelength.

In an optional embodiment of the present application, the point cloud data can be acquired through a visual sensor.

The vision sensor is the direct source of information for the entire machine vision system, which is mainly composed of one or two graphic sensors, sometimes with a light projector and other auxiliary equipment. The main function of the vision sensor is to obtain enough original images to be processed by the machine vision system. The image sensor can use a laser scanner, a linear and area CCD camera, or a TV camera, or it can be the latest digital camera.

In step S104, the point cloud data corresponding to the wall to be measured is extracted from the original point cloud data.

Since the original point cloud data includes non-buildings in addition to buildings, it is necessary to distinguish the point cloud data of buildings from the collected point cloud data in the target area.

Step S106: Extract the point cloud data corresponding to the section to be measured from the point cloud data corresponding to the wall to be measured.

Step S108: Determine the cross-sectional size of the to-be-measured cross-section at any preset height according to the point cloud data corresponding to the to-be-measured cross-section.

Through the above steps, by collecting the point cloud data of the building, the point cloud data is used to automatically measure the cross-sectional size of the wall at any height, thereby achieving the technical effect of improving the measurement efficiency and measurement accuracy of the cross-sectional size of the wall of the building.

In an optional embodiment of the present application, before performing step S104, it is also necessary to perform down-sampling processing on the original point cloud data; and perform filtering and denoising processing on the original point cloud data.

After obtaining the three-dimensional point cloud data containing the complete wall to be tested, the obtained point cloud data is first down-sampled. The down-sampling process is a process of reducing the signal sampling rate, which is usually used to reduce the data transmission rate Or data size. By down-sampling the data, you can reduce the amount of computer calculations. Then filter and denoise the point cloud data to eliminate outliers in the data, and remove environmental noise and invalid points.

In an optional embodiment of the present application, step S104 can be implemented by the following methods: filtering out the point cloud data of the building surface from the original point cloud data; extracting the wall to be tested from the point cloud data of the building surface Point cloud data of the surface.

According to an optional embodiment of the present application, the point cloud data of the building surface is filtered from the original point cloud data in the following manner: plane segmentation is performed on the original point cloud data to extract point cloud data of different planes; Among the point cloud data of the plane, the point cloud data corresponding to the three vertical planes two by two are selected as the point cloud data of the building surface.

According to an optional embodiment of the present application, from the point cloud data of different planes, the point cloud data corresponding to the three vertical planes two by two are selected as the point cloud data of the building surface, including: point cloud data of different planes The data is subjected to plane fitting processing to obtain the direction of the plane normal vector corresponding to each plane, and the planes are classified based on the direction of the plane normal vector to obtain the point cloud data corresponding to the planes in different directions; the points corresponding to the planes in different directions From the cloud data, the point cloud data corresponding to the three vertical planes two by two are selected as the point cloud data of the building surface.

The extraction of building information mainly includes the following steps:

Perform plane segmentation on the acquired original 3D point cloud data, extract all plane point clouds, and perform plane fitting to obtain direction information. At the same time, calculate the main direction of the point cloud itself and the minimum bounding box size. The minimum bounding box is a simple Geometric space.

According to the plane direction, all plane point clouds are classified, and multiple sets of point cloud data in different directions are obtained.

Filter the point cloud data in different directions, extract three sets of two perpendicular planes as the building's own data, and roughly filter out the interference data in other directions (such as randomly placed workpieces with surfaces that are not parallel to the wall).

Through the above method, it is possible to distinguish between buildings and non-buildings in the point cloud data according to the design feature information of the buildings themselves.

According to an optional embodiment of the present application, the point cloud data of the wall to be measured is extracted from the point cloud data of the building surface by the following way: according to the data collection angle and coordinate direction of the sensor, from the point cloud data of the building surface Filter out the point cloud data parallel to the ground from the cloud data; extract the ground point cloud data from the filtered point cloud data parallel to the ground; divide the point cloud data parallel to the ground from the point cloud data of the building surface The other two sets of mutually perpendicular point cloud data are used as the point cloud data constituting the wall to be tested.

In an optional embodiment of the present application, two sets of mutually perpendicular point cloud data except for the point cloud data parallel to the ground in the point cloud data of the building surface are used as the point cloud data constituting the wall to be measured Before, it is necessary to judge the unevenness of the two sets of mutually perpendicular point cloud data; if the unevenness of the two sets of mutually perpendicular point cloud data is convex, the two sets of mutually perpendicular point cloud data are used as the wall to be measured. Point cloud data; if the concavity and convexity composed of two sets of mutually perpendicular point cloud data is concave, the two sets of mutually perpendicular point cloud data are regarded as interference point cloud data.

From the azimuth angle of the origin of the original point cloud data, judge whether the concavity and convexity of the point cloud composed of the two sets of mutually perpendicular point cloud data meet the actual situation (from the observation angle of the viewpoint, the cross-sectional size is convex), if it is satisfied, The two sets of mutually perpendicular point cloud data are regarded as the final point cloud data of the wall to be measured, otherwise the two sets of mutually perpendicular point cloud data are regarded as interference data.

According to an optional embodiment of the present application, extracting the ground point cloud data from the filtered point cloud data parallel to the ground includes: the Z direction of the sensor collected data is positively upward, and the filtered point cloud data is parallel to the ground Among the point cloud data of the building surface, the point cloud data with the smallest Z value is the ground point cloud data.

According to the data collection angle of the visual sensor itself that collects the point cloud data, the plane data set Set1 parallel to the ground (including the ground) is filtered out, and the ground data F1 is extracted according to the coordinate direction of the visual sensor (for example, the Z direction of the sensor data The positive direction is upward, then the point cloud data with the smallest Z value in Set1 is the ground data).

Through this method, the ground point cloud data and the wall point cloud data can be distinguished from the point cloud data of the building.

In some optional embodiments of the present application, after the point cloud data corresponding to the wall to be measured is extracted from the original point cloud data, it is also necessary to calculate the inclination angle of the point cloud data of the wall to be measured with respect to the gravity surface; The point cloud data of the building surface is rotated and calibrated according to the inclination angle, so that the plane normal vector corresponding to the point cloud data on the ground faces vertically upwards.

Taking into account the poor ground flatness, the direction of the building wall is used to calculate the inclination angle of the actual wall point cloud relative to the gravity plane, and all the building point cloud data are rotated and calibrated to the direction perpendicular to the world coordinate system. And according to the Z value of the ground plane near the wall, the point cloud data of all building information is translated, so that the average Z value of the ground near the wall corner is 0.

After calibrating the point cloud data of the building by the above method, you can use the corner position on the ground as the origin of the coordinates and the direction of the wall as the coordinate axis direction to establish a new coordinate system. The wall is subsequently calculated based on the point cloud data of the wall. The basis of the cross-sectional dimensions.

According to an optional embodiment of the present application, step S106 can be implemented by the following method: traverse the point cloud data corresponding to the wall to be tested, and compare the point cloud width data in the point cloud data of the wall to be tested with the preset cross-sectional size Scope, the point cloud data of the wall to be tested corresponding to the point cloud width data falling within the preset section size range is used as the point cloud data of the candidate to be tested section, and the point cloud width data is the point on the short side of the wall to be tested Cloud data.

Extracting the point cloud data corresponding to the section to be measured from the point cloud data corresponding to the wall to be measured mainly includes the following steps:

Traverse two sets of vertical wall point cloud data Set2 and Set3, filter them, and initially select the candidate measurement object Set4 whose point cloud width meets the design value of the section size (the wall thickness has a certain design range).

Traverse all candidate measurement objects Set4, get each plane point cloud element O in it, and find the point cloud B bordering O in the point cloud data set of another wall direction perpendicular to O, as the adjacent wall Surface/cylinder data.

In another optional embodiment of the present application, after taking the point cloud data of the wall to be tested corresponding to the point cloud width within the preset cross-sectional size range as the point cloud data of the candidate to-be-tested section, from the candidate to be tested From the point cloud data of the measured section, the point cloud data with the largest section height is selected as the point cloud data of the target section to be measured. The point cloud data that are mutually perpendicular and adjacent to each other are used as the point cloud data of the reference plane, wherein the point cloud data of the reference plane is used for the size measurement of the section to be measured.

If there are multiple sets of point cloud data that meet the screening results, select the one with the largest section height (the section data is relatively more complete and the measurable area is wider) as the final measurement object.

Through the above method, based on the identification of the building information data, the cross-section contained in the data can be identified based on the prior characteristics of the cross-sectional size, and combined with the pertinence of data collection, it can be identified in multiple cross-sections that may exist Output the cross-sectional data you want to measure.

According to an optional embodiment of the present application, step S108 can be implemented by the following method: determining the cross-sectional size of the cross-section to be tested at any preset height according to the point cloud data of the target cross-section to be measured and the point cloud data of the reference plane.

In an optional embodiment of the present application, determining the size of the section to be measured at any preset height according to the point cloud data of the target section to be measured and the point cloud data of the reference plane can be achieved by the following method: From the point cloud data of the target, the point cloud data whose distance from the intersection line of the target section to be measured and the reference plane is within a preset range is selected as the first reference plane point cloud data; the edge of the point cloud data of the target section to be measured is extracted Contour data, extract two edge contour data along the height direction of the target section to be measured from the edge contour data, and select the edge contour data far away from the first datum point cloud data from the two edge contour data as the first edge Contour data; intercept the second edge contour data from the first edge contour data according to the preset height range, and intercept the second datum point cloud data from the first datum surface point cloud data according to the preset cross-sectional measurement height, and the preset height range The measurement range is determined based on the preset height, and the height of the preset value is selected from the top and the bottom; the section size of the section to be measured at the preset height is determined according to the point cloud data of the second datum surface and the second edge profile data .

According to the above-mentioned data information of the wall section O to be measured, only the data whose distance from O in the reference plane B is within a certain range is retained. The preset range can be set according to requirements.

The edge contour of the section to be measured is extracted to obtain a closed point cloud contour data C; in C, two edge contours along the height of the wall are extracted, and the side edge contour data L far away from the corresponding reference plane is filtered out.

Within a certain range above and below the specified measurement height of the section, the corresponding edge profile data D in L is intercepted; at the same time, the corresponding wall surface data T is intercepted at the corresponding height in the corresponding reference plane B.

Using T as the reference data, fit the plane equation, and calculate the distance from the corresponding point cloud data in D to the plane equation, which is the measurement result of the section size at the specified measurement height.

Through the above method, taking the ground height as the origin, you can measure only the specified height of the wall according to the actual measurement requirements, or you can measure the different heights of the entire wall; and it can adapt to various possible wall conditions , Automatically avoid abnormal locations.

The method for measuring the cross-sectional size of the wall surface provided by the embodiment of the present application can automatically complete the measurement of the designated position (or the height of the entire wall) of the cross-sectional size. In the oblique three-dimensional point cloud data collected by the computer at any angle, the measurement method can correctly eliminate the interference of non-building information, and extract and distinguish the point cloud information of the section to be measured from the point cloud data of the building information ; After obtaining the specific section to be measured, the method uses the corner position on the ground as the coordinate origin and the wall direction as the coordinate axis direction to establish a new coordinate system. On the basis of the new coordinate system, according to the specific measurement requirements, the cross-sectional dimension measurement is performed on the specified height of the cross-section or even the entire height. When only measuring the specified height position, the measuring height can be slightly adjusted according to the actual situation of the wall. The measurement method is completely consistent with the measurement methods of the actual workers. The measurement results rely on the accuracy of the equipment, the algorithm error is small, and it is not affected by any subjective factors, avoiding the limitations of manual measurement, and has a high confidence.

It should be noted that the above-mentioned method for measuring the cross-sectional dimensions of the wall is also suitable for measuring the depth of the doorway.

Fig. 2 is a structural diagram of a device for measuring the cross-sectional size of a wall surface according to an embodiment of the present application. As shown in Fig. 2, the device includes:

The acquiring module 20 is configured to acquire original point cloud data including the wall to be measured, where the wall to be measured includes the cross-section to be measured.

The first extraction module 22 is used to extract point cloud data corresponding to the wall to be tested from the original point cloud data.

The second extraction module 24 is used to extract the point cloud data corresponding to the section to be measured from the point cloud data corresponding to the wall to be measured.

The determining module 26 is used to determine the cross-sectional size of the to-be-tested cross-section at any preset height according to the point cloud data corresponding to the to-be-tested cross-section.

It should be noted that, for the preferred implementation of the embodiment shown in FIG. 2, reference may be made to the related description of the embodiment shown in FIG. 1, which will not be repeated here.

Fig. 3 is a structural diagram of a system for measuring cross-sectional dimensions of a wall surface according to an embodiment of the present application. As shown in Fig. 3, the system includes a vision sensor 30 and a processor 32, wherein,

The vision sensor 30 is used to obtain original point cloud data including the wall to be measured, and send the original point cloud data to the processor 32, where the wall to be measured includes the cross-section to be measured.

The processor 32 is communicatively connected with the vision sensor 30, and is used to extract the point cloud data corresponding to the wall to be measured from the original point cloud data; to extract the point corresponding to the section to be measured from the point cloud data corresponding to the wall to be measured Cloud data: Determine the cross-section size of the cross-section to be tested at any preset height according to the point cloud data corresponding to the cross-section to be tested.

Point cloud data means that the scanned data is recorded in the form of points. Each point contains three-dimensional coordinates, and some may contain color information or reflection intensity information. The above target area is the area where the building is located.

Through the above system, the point cloud data of the building is collected, and the cross-sectional size of the wall is automatically measured using the point cloud data, thereby achieving the technical effect of improving the measurement efficiency and measurement accuracy of the cross-sectional size of the wall of the building.

It should be noted that, for the preferred implementation of the embodiment shown in FIG. 3, reference may be made to the related description of the embodiment shown in FIG. 1, which will not be repeated here.

The embodiment of the present application provides a non-volatile storage medium, the non-volatile storage medium includes a stored program, and when the program is running, the device where the non-volatile storage medium is located is controlled to execute the above method for measuring the cross-sectional size of the wall surface. .

The non-volatile storage medium is used to store programs that perform the following functions: obtain the original point cloud data containing the wall to be tested, where the wall to be tested includes the cross section to be tested; extract the wall to be tested from the original point cloud data Corresponding point cloud data; extract the point cloud data corresponding to the section to be measured from the point cloud data corresponding to the wall to be measured; determine the section size of the section to be measured at any preset height according to the point cloud data corresponding to the section to be measured.

The embodiment of the present application also provides a processor, which is configured to run a program stored in a memory, where the above method for measuring the cross-sectional dimension of the wall surface is executed when the program is running.

The processor is used to run programs that perform the following functions: obtain the original point cloud data containing the wall to be tested; extract the point cloud data corresponding to the wall to be tested from the original point cloud data, where the wall to be tested includes the section to be tested ; Extract the point cloud data corresponding to the section to be measured from the point cloud data corresponding to the wall to be measured; determine the section size of the section to be measured at any preset height according to the point cloud data corresponding to the section to be measured.

The serial numbers of the foregoing embodiments of the present application are for description only, and do not represent the superiority or inferiority of the embodiments.

In the above-mentioned embodiments of the present application, the description of each embodiment has its own focus. For a part that is not described in detail in an embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units may be a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, units or modules, and may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , Including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage media include: U disk, read-only memory (ROM, ReBZLJd-Only Memory), random access memory (RBZLJM, RBZLJndom BZLJccess Memory), mobile hard disk, magnetic disk or CD-ROM and other media that can store program codes .

The above are only the preferred embodiments of this application. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and modifications can be made, and these improvements and modifications are also Should be regarded as the scope of protection of this application.

Industrial applicability

The solutions provided in the embodiments of this application can be applied to the field of building physical measurement. In the embodiments of this application, the original point cloud data including the wall to be tested is acquired; the points corresponding to the wall to be tested are extracted from the original point cloud data. Cloud data, where the wall to be measured includes the section to be measured; the point cloud data corresponding to the section to be measured is extracted from the point cloud data corresponding to the wall to be measured; the wall to be measured is determined according to the point cloud data corresponding to the section to be measured By collecting point cloud data of the building, using point cloud data to automatically measure the cross-sectional size of the cross-section at any preset height, so as to improve the measurement efficiency and measurement accuracy of the cross-sectional size of the wall of the building Technical effect.

Claims

A method for measuring the cross-sectional size of a wall surface, including:

Acquiring original point cloud data containing the wall to be tested, where the wall to be tested includes the cross-section to be tested;

Extracting the point cloud data corresponding to the wall to be measured from the original point cloud data;

Extracting the point cloud data corresponding to the section to be measured from the point cloud data corresponding to the wall to be measured;

The size of the cross-section of the cross-section to be measured at any preset height is determined according to the point cloud data corresponding to the cross-section to be measured.
The method according to claim 1, wherein before extracting the point cloud data corresponding to the wall to be measured from the original point cloud data, the method further comprises:

Performing down-sampling processing on the original point cloud data; and

Perform filtering and denoising processing on the original point cloud data.
The method according to claim 1, wherein extracting the point cloud data corresponding to the wall surface to be measured from the original point cloud data comprises:

Filter out the point cloud data of the building surface from the original point cloud data;

The point cloud data of the wall to be measured is extracted from the point cloud data of the building surface.
The method according to claim 3, wherein filtering out the point cloud data of the building surface from the original point cloud data comprises:

Perform plane segmentation processing on the original point cloud data to extract point cloud data of different planes;

From the point cloud data of the different planes, the point cloud data corresponding to the three vertical planes two by two are screened out as the point cloud data of the building surface.
The method according to claim 4, wherein, from the point cloud data of the different planes, filtering out the point cloud data corresponding to the three vertical planes two by two as the point cloud data of the building surface comprises:

Perform plane fitting processing on the point cloud data of the different planes, obtain the direction of the plane normal vector corresponding to each plane, and classify the planes based on the direction of the plane normal vector to obtain the planes corresponding to different directions Point cloud data;

From the point cloud data corresponding to the planes in different directions, the point cloud data corresponding to the three vertical planes two by two are selected as the point cloud data of the building surface.
The method according to claim 5, wherein extracting the point cloud data of the wall to be measured from the point cloud data of the building surface comprises:

According to the data collection angle and coordinate direction of the sensor, the point cloud data parallel to the ground is filtered from the point cloud data of the building surface, and the ground point is extracted from the filtered point cloud data parallel to the ground Cloud data

Two sets of mutually perpendicular point cloud data except for the point cloud data parallel to the ground in the point cloud data of the building surface are used as the point cloud data constituting the wall to be measured.
The method according to claim 6, wherein, in the point cloud data of the building surface, two sets of mutually perpendicular point cloud data except for the point cloud data parallel to the ground are used as the point cloud data constituting the wall to be measured. Before point cloud data, the method further includes:

Judging the unevenness of the two sets of mutually perpendicular point cloud data;

If the concavity and convexity formed by the two sets of mutually perpendicular point cloud data is convex, use the two sets of mutually perpendicular point cloud data as the point cloud data of the wall to be measured;

If the concavity and convexity formed by the two sets of mutually perpendicular point cloud data is concave, the two sets of mutually perpendicular point cloud data are regarded as interference point cloud data.
The method according to claim 6, wherein extracting ground point cloud data from the filtered point cloud data parallel to the ground comprises:

The positive Z-direction of the data collected by the sensor faces upwards, and the point cloud data with the smallest Z value among the point cloud data of the building surface that is screened out parallel to the ground is the ground point cloud data.
The method according to claim 6, wherein after extracting the point cloud data corresponding to the wall to be measured from the original point cloud data, the method further comprises:

Calculating the inclination angle of the point cloud data of the wall to be measured relative to the gravity plane;

Rotation calibration is performed on the point cloud data of the building surface according to the inclination angle, so that the plane normal vector corresponding to the point cloud data on the ground faces vertically upwards.
The method according to claim 6, wherein extracting the point cloud data corresponding to the section to be measured from the point cloud data corresponding to the wall to be measured comprises:

Traverse the point cloud data corresponding to the wall to be tested, compare the point cloud width data in the point cloud data of the wall to be tested with the preset cross-sectional size range, and find points that fall within the preset cross-sectional size range The point cloud data of the wall to be measured corresponding to the cloud width data is used as the point cloud data of the candidate section to be measured, and the point cloud width data is the point cloud data of the short side of the wall to be measured.
The method according to claim 10, wherein, after the point cloud data of the wall to be measured corresponding to the point cloud width data falling within the preset cross-sectional size range is used as the point cloud data of the candidate to-be-measured section, the Methods also include:

From the point cloud data of the candidate section to be measured, the point cloud data with the largest section height is selected as the point cloud data of the target section to be measured. The point cloud data of the target cross-section to be measured is perpendicular to and adjacent to each other as the point cloud data of the reference surface, wherein the point cloud data of the reference surface is used for the size measurement of the cross-section to be measured.
The method according to claim 11, wherein determining the cross-sectional size of the cross-section to be measured at any preset height according to the point cloud data corresponding to the cross-section to be measured comprises:

The cross-sectional size of the cross-section to be tested at any preset height is determined according to the point cloud data of the target cross-section to be measured and the point cloud data of the reference plane.
The method according to claim 12, wherein determining the cross-sectional size of the cross-section to be tested at any preset height according to the point cloud data of the target cross-section to be measured and the cloud data of the reference plane point comprises:

Filtering out the point cloud data from the intersection line of the target cross-section to be measured and the reference surface within a preset range from the point cloud data of the reference surface, as the first reference surface point cloud data;

The edge contour data of the point cloud data of the target section to be measured is extracted, two edge contour data along the height direction of the target section to be measured are extracted from the edge contour data, and from the two edge contour data Selecting edge contour data far away from the first reference plane point cloud data as the first edge contour data;

The second edge contour data is intercepted from the first edge contour data according to the preset height range, and the second reference surface point cloud data is intercepted from the first reference surface point cloud data. The preset height range is based on The preset height is used as the reference, and the measurement range determined by the height of the preset value is selected up and down respectively;

The cross-sectional size of the to-be-measured cross-section at the preset height is determined according to the second reference plane point cloud data and the second edge profile data.
The method according to claim 13, wherein determining the cross-sectional size of the to-be-tested cross-section at the preset height according to the second datum point cloud data and the second edge profile data comprises:

Fitting processing to the second datum point cloud data to obtain the plane equation of the second datum point cloud data in a preset coordinate system, where the preset coordinate system takes the ground wall corner position as the origin, and The wall direction of the datum plane is the coordinate system determined by the coordinate axis direction;

The distance between the point cloud data corresponding to the second edge contour data and the plane equation is determined, and the distance is taken as the cross-sectional size of the to-be-measured cross-section at the preset height.
A measuring device for the cross-sectional size of a wall surface, including:

An acquiring module, configured to acquire original point cloud data including a wall to be tested, wherein the wall to be tested includes a cross-section to be tested;

The first extraction module is configured to extract point cloud data corresponding to the wall to be tested from the original point cloud data;

The second extraction module is configured to extract point cloud data corresponding to the section to be measured from the point cloud data corresponding to the wall to be measured;

The determining module is configured to determine the cross-sectional size of the to-be-tested cross-section at any preset height according to the point cloud data corresponding to the to-be-tested cross-section.
A measuring system for the cross-sectional dimension of a wall surface, including: a vision sensor and a processor, wherein,

The vision sensor is configured to acquire original point cloud data including a wall to be measured, and send the original point cloud data to the processor, wherein the wall to be measured includes a cross-section to be measured;

The processor is in communication connection with the vision sensor, and is configured to extract point cloud data corresponding to the wall to be measured from the original point cloud data; from the point cloud data corresponding to the wall to be measured The point cloud data corresponding to the section to be measured is extracted; the section size of the section to be measured at any preset height is determined according to the point cloud data corresponding to the section to be measured.
A non-volatile storage medium, the non-volatile storage medium includes a stored program, and when the program is running, the device where the non-volatile storage medium is located is controlled to execute any one of claims 1 to 14 The measurement method of the cross-sectional dimensions of the wall described above.
A processor configured to run a program stored in a memory, wherein the method for measuring the cross-sectional size of a wall surface according to any one of claims 1 to 14 is executed when the program is running.