阅读说明：本技术 一种基于三维点云的墙面靠尺检测方法及系统 (Wall surface guiding rule detection method and system based on three-dimensional point cloud ) 是由 张富涛 曾翔 杨炼 于 2019-11-19 设计创作，主要内容包括：本发明的一种基于三维点云的墙面靠尺检测方法,包括：采集包含完整待测墙面的三维点云数据并进行预处理；从预处理后的数据中提取待测墙面数据,并建立新坐标系；根据测量位置和角度需求,计算出靠尺的端点位置,获取所有靠尺的位姿并对靠尺位姿自动调整；在新坐标系下,在待测墙面上与靠尺相应区域截取点云,拟合点云后获取靠尺初始位姿并检测靠尺区域的凸包区域,获取靠尺的最优位姿。本发明还公开了一种基于三维点云的墙面靠尺检测系统。本发明能检测靠尺的准确位置,利用该靠尺可实现墙面的平整度测量,测量结果精度高,误差小,且不受任何主观因素的影响,避免人工测量的局限性,置信度较高。(The invention discloses a wall surface guiding rule detection method based on three-dimensional point cloud, which comprises the following steps: collecting three-dimensional point cloud data containing a complete wall surface to be detected and preprocessing the three-dimensional point cloud data; extracting the data of the wall surface to be detected from the preprocessed data, and establishing a new coordinate system; calculating the end point position of the guiding rule according to the measurement position and angle requirements, acquiring the poses of all the guiding rules and automatically adjusting the poses of the guiding rules; and intercepting point clouds in an area corresponding to the guiding rule on the wall surface to be detected under the new coordinate system, fitting the point clouds, obtaining the initial pose of the guiding rule, detecting a convex hull area of the guiding rule area, and obtaining the optimal pose of the guiding rule. The invention also discloses a wall surface guiding rule detection system based on the three-dimensional point cloud. The invention can detect the accurate position of the guiding rule, can realize the flatness measurement of the wall surface by utilizing the guiding rule, has high measurement result precision and small error, is not influenced by any subjective factor, avoids the limitation of manual measurement and has higher confidence coefficient.)

1. A wall guiding rule detection method based on three-dimensional point cloud is characterized by comprising the following steps:

step 1, collecting three-dimensional point cloud data including a complete wall surface to be detected, and preprocessing the three-dimensional point cloud data;

step 2, extracting data of the wall surface to be detected from the preprocessed three-dimensional point cloud data, and establishing a new coordinate system by taking any one corner of the wall surface to be detected as an original point and taking the vertical and horizontal directions of the wall surface to be detected as coordinate axis directions;

step 3, calculating the end point position of each guiding rule according to the measurement position and angle requirements, acquiring the poses of all the guiding rules, and automatically adjusting the poses of the guiding rules;

and 4, in a new coordinate system, respectively intercepting point clouds in corresponding areas on the wall surface to be detected for each guiding rule obtained in the step 3, fitting the point clouds to obtain the initial pose of the guiding rule, detecting the convex hull area of the guiding rule area, and obtaining the optimal pose of the guiding rule.

2. The wall surface running rule detection method based on the three-dimensional point cloud as claimed in claim 1, wherein the preprocessing method in the step 1 specifically comprises the following steps: and carrying out downsampling processing on the three-dimensional point cloud data, then carrying out filtering denoising on the downsampled data, eliminating outliers in the data, removing environmental noise, and cutting the ROI.

3. The method for detecting the wall surface running rule based on the three-dimensional point cloud as claimed in any one of claim 1, wherein the method in the step 2 comprises the following steps: extracting all planes in the preprocessed three-dimensional point cloud data, classifying the point cloud of the planes according to the direction of each plane, extracting building data and interference data from the classified point cloud, performing direction correction on the building data through ground data, extracting data of a wall surface to be detected, and acquiring an original point of the wall surface to be detected.

4. The method for detecting the wall surface running rule based on the three-dimensional point cloud as claimed in claim 3, wherein the step 2 specifically comprises:

step 201, performing plane segmentation on the preprocessed three-dimensional point cloud data, extracting all plane point clouds, performing plane fitting to obtain direction information, and calculating the main direction and the minimum bounding box size of the point clouds;

step 202, classifying all plane point clouds according to plane directions to obtain a plurality of groups of point cloud data in different directions;

step 203, screening point cloud data in different directions, extracting three groups of planes which are perpendicular to each other in pairs to serve as building self data, and filtering interference data in other directions;

204, screening out a plane data Set1 which is parallel to the ground and contains the ground according to the direction and the shooting angle of the data acquired by the visual sensor, extracting ground point cloud data F1 according to the coordinate direction of the visual sensor, calculating the inclination angle of the ground point cloud data F1, and rotationally calibrating the point cloud data of all wall surfaces and cylindrical surfaces to the direction vertical to a world coordinate system;

step 205, selecting wall surface point cloud data W1 of the wall surface to be detected from all the plane point cloud data perpendicular to the ground point cloud data F1, extracting plane point cloud data W2 which is perpendicular to the wall surface point cloud data W1 and is bordered on the left side of the wall surface point cloud data W1, calculating the intersection point of the wall surface point cloud data W1, the plane point cloud data W2 and the ground point cloud data F1, namely the lower left corner of the wall surface, serving as the original point position of the wall surface to be detected, and establishing a new coordinate system by taking the vertical direction and the horizontal direction of the wall surface to be detected as coordinate axis directions.

5. The method as claimed in claim 4, wherein in step 204, the visual sensor collects data with the Z direction facing upward, and the point cloud data with the smallest Z value in the Set1 is the ground point cloud data F1.

6. The method for detecting the wall surface running rule based on the three-dimensional point cloud as claimed in claim 1, wherein the method in the step 3 comprises the following steps: and positioning missing positions of point cloud data of the wall surface to be measured, detecting holes on the wall surface to be measured to remove noise and interference data, calculating the positions of two end points of each guiding rule on the wall surface to be measured according to the measured positions, angle requirements and the actual size of the guiding rules, acquiring the poses of all the guiding rules and automatically adjusting the poses of all the guiding rules.

7. The method for detecting the wall surface running rule based on the three-dimensional point cloud as claimed in claim 6, wherein the step 3 specifically comprises the following steps:

step 301, calculating the height and length of the wall surface to be detected, extracting the overall outline of the wall surface point cloud data of the wall surface to be detected, judging whether the wall surface data is missing or not, and if so, positioning the missing position;

step 302, detecting an opening on a wall surface to be measured, respectively positioning the positions of a door opening and a window opening, and carrying out local denoising processing on point cloud data near the opening to remove noise caused by mutation of a measurement object and interference data near the opening;

and 303, calculating the positions of the two end points of each guiding rule on the wall surface to be measured and the angle between each guiding rule and the horizontal plane according to the measurement position and angle requirement of the wall surface to be measured and the actual size of each guiding rule, acquiring the positions of all the guiding rules on the wall surface to be measured, and automatically adjusting the pose of each guiding rule.

8. The method as claimed in claim 7, wherein in step 303, when the door opening is measured across the opening, it is ensured that the top end of the 45 ° running rule does not exceed the range of the wall to be measured, and there is no suspended part when the running rule crosses the door opening.

9. The method for detecting the wall surface running rule based on the three-dimensional point cloud as claimed in claim 1, wherein the method in the step 4 comprises the following steps: and (3) respectively intercepting point clouds on the wall surface to be measured and the corresponding areas of the guiding rulers obtained in the step (3) in a new coordinate system, respectively fitting the point clouds, obtaining the initial pose of each guiding ruler, detecting all convex hull areas of each guiding ruler area, obtaining all possible poses of each guiding ruler, and selecting the optimal pose from all possible poses of each guiding ruler.

10. The method for detecting the wall surface guiding ruler based on the three-dimensional point cloud as claimed in claim 9, wherein in the step 4, each guiding ruler adopts the following method:

step 401, performing local smoothing on wall point cloud data of a wall surface to be detected, and eliminating data fluctuation of a visual sensor;

step 402, according to the position and the angle to be measured, intercepting point cloud data C in the corresponding area on the wall surface to be measured according to the shape and the size of the guiding rule obtained in the step 3, and performing skeleton extraction on the intercepted point cloud data C;

step 403, performing straight line fitting on the point cloud data C to obtain an initial pose P0 of the guiding rule;

step 404, on the basis of the initial pose P0, detecting all convex hull areas of the guiding rule area, acquiring an extreme point of each convex hull area, and combining the two end points of the guiding rule to form a Set2 through which the actual guiding rule may pass;

step 405, in the point Set2, combining every two points into a straight line, judging whether all convex hull points are positioned at one side of the straight line, if so, calculating the farthest gap from the point cloud data C to the guiding rule as the measurement value of the current guiding rule;

and 406, selecting the condition with the minimum measurement result from all the running rule postures as the optimal running rule pose.

11. The method for detecting the wall surface running rule based on the three-dimensional point cloud as claimed in claim 10, further comprising: and measuring the flatness of the designated position of the wall surface to be measured or the whole wall through the guiding rule with the optimal pose, and outputting a flatness measurement result of the designated position or the explosion point position of the whole wall.

12. A wall surface guiding ruler detection system based on three-dimensional point cloud obtained by the wall surface guiding ruler detection method based on three-dimensional point cloud according to any one of claims 1-12, comprising:

the data preprocessing module is used for acquiring three-dimensional point cloud data comprising a complete wall surface to be detected and preprocessing the three-dimensional point cloud data;

the wall surface data extraction module is used for extracting the data of the wall surface to be detected from the preprocessed three-dimensional point cloud data, taking any one corner of the wall surface to be detected as an original point and taking the vertical direction and the horizontal direction of the wall surface to be detected as coordinate axis directions, and establishing a new coordinate system;

the measuring position calculating module is used for calculating the end point position of each guiding rule according to the measuring position and angle requirements, acquiring the poses of all the guiding rules and automatically adjusting the poses of the guiding rules;

and the measurement calculation output module is used for intercepting point clouds of all the guiding rulers acquired by the measurement position calculation module in corresponding areas on the wall surface to be detected respectively under a new coordinate system, acquiring the initial pose of the guiding ruler after the point clouds are fitted, detecting the convex hull area of the guiding ruler area and acquiring the optimal pose of the guiding ruler.

Technical Field

The invention relates to a wall surface guiding rule detection method and system, in particular to a wall surface guiding rule detection method and system based on three-dimensional point cloud.

Background

In the construction stage, the actual measurement actual quantity passes through the entity test of the construction site, and the quality state of the product is fed back in time, so that a project manager can improve the construction process in time. At present, the actual measurement actual quantity still continues to use a relatively old data acquisition mode, and the flatness measurement of the wall surface is measured by actual measurement actual quantity personnel by using a 2-meter guiding rule.

Due to the limitation of the operation efficiency, the data acquisition can be carried out only on the point positions of the measurement part by manpower, the sampling rate is low, and most of operators measure the flatness of the wall surface only by feeling, but do not strictly adopt the wedge-shaped clearance gauge for combined measurement. Therefore, aiming at various defects of manual measurement and the problems that the workload of measuring the wall surface evenness is the largest and the measurement is the most complicated in the whole actual measurement actual quantity stage, the automatic measurement of the wall surface evenness is needed to be completed according to the visual sensor.

Disclosure of Invention

In view of the above, the present invention provides a wall surface running rule detection method based on three-dimensional point cloud, including:

step 1, collecting three-dimensional point cloud data including a complete wall surface to be detected, and preprocessing the three-dimensional point cloud data;

step 2, extracting data of the wall surface to be detected from the preprocessed three-dimensional point cloud data, and establishing a new coordinate system by taking any angle of the wall surface to be detected as an original point and taking the vertical and horizontal directions of the wall surface to be detected as coordinate axis directions;

step 3, under a new coordinate system, calculating the end point position of each guiding rule according to the measurement position and angle requirements, acquiring the poses of all the guiding rules, and automatically adjusting the poses of the guiding rules;

and 4, in a new coordinate system, respectively intercepting point clouds in corresponding areas on the wall surface to be detected for each guiding rule obtained in the step 3, fitting the point clouds, obtaining the initial pose of the guiding rule, detecting the convex hull area of the guiding rule area, and obtaining the optimal pose of the guiding rule.

As a further improvement of the present invention, the pretreatment method in step 1 specifically comprises: and carrying out downsampling processing on the three-dimensional point cloud data, then carrying out filtering denoising on the downsampled data, eliminating outliers in the data, removing environmental noise, and cutting the ROI.

As a further improvement of the invention, the method of the step 2 comprises the following steps: extracting all planes in the preprocessed three-dimensional point cloud data, classifying the point cloud of the planes according to the direction of each plane, extracting building data and interference data from the classified point cloud, performing direction correction on the building data through ground data, extracting data of a wall surface to be detected, and acquiring an original point of the wall surface to be detected.

As a further improvement of the present invention, the step 2 specifically includes:

step 201, performing plane segmentation on the preprocessed three-dimensional point cloud data, extracting all plane point clouds, performing plane fitting to obtain direction information, and calculating the main direction and the minimum bounding box size of the point clouds;

step 202, classifying all plane point clouds according to plane directions to obtain a plurality of groups of point cloud data in different directions;

step 203, screening point cloud data in different directions, extracting three groups of planes which are perpendicular to each other in pairs to serve as building self data, and filtering interference data in other directions;

204, screening out a plane data Set1 which is parallel to the ground and contains the ground according to the direction and the shooting angle of the data acquired by the visual sensor, extracting ground point cloud data F1 according to the coordinate direction of the visual sensor, calculating the inclination angle of the ground point cloud data F1, and rotationally calibrating the point cloud data of all wall surfaces and cylindrical surfaces to the direction vertical to a world coordinate system;

step 205, selecting wall surface point cloud data W1 of the wall surface to be detected from all the plane point cloud data perpendicular to the ground point cloud data F1, extracting plane point cloud data W2 which is perpendicular to the wall surface point cloud data W1 and is bordered on the left side of the wall surface point cloud data W1, and calculating the intersection point of the wall surface point cloud data W1, the plane point cloud data W2 and the ground point cloud data F1, namely the lower left corner of the wall surface, as the original point position of the wall surface to be detected.

As a further improvement of the present invention, in step 204, the Z direction of the data collected by the vision sensor faces upward, and the point cloud data with the minimum Z value in the plane data Set1 is the ground point cloud data F1.

As a further improvement of the invention, the method of the step 3 comprises the following steps: and positioning missing positions of point cloud data of the wall surface to be measured, detecting holes on the wall surface to be measured to remove noise and interference data, calculating the positions of two end points of each guiding rule on the wall surface to be measured and the angle between each guiding rule and a horizontal plane according to the measuring position and angle requirements and the actual size of each guiding rule, acquiring the poses of all the guiding rules and automatically adjusting the poses of the guiding rules.

As a further improvement of the present invention, the step 3 specifically includes:

step 301, calculating the height and length of the wall surface to be detected, extracting the overall outline of the wall surface point cloud data of the wall surface to be detected, judging whether the wall surface data is missing or not, and if so, positioning the missing position;

step 302, detecting an opening on a wall surface to be measured, respectively positioning the positions of a door opening and a window opening, and carrying out local denoising processing on point cloud data near the opening to remove noise caused by mutation of a measurement object and interference data near the opening;

and 303, calculating the positions of two end points of each guiding rule on the wall surface to be measured and the angle between each guiding rule and the horizontal plane according to the measurement position and angle requirements of the wall surface to be measured and the actual size of each guiding rule, acquiring the poses of all the guiding rules, and automatically adjusting the poses of all the guiding rules.

As a further improvement of the present invention, in step 303, when the door opening is measured across the opening, it is to be ensured that the top end of the 45-degree guiding rule does not exceed the range of the wall surface to be measured, and no suspended part exists when the guiding rule crosses the door opening.

As a further improvement of the invention, the method of the step 4 comprises the following steps: and (3) respectively intercepting point clouds on the wall surface to be measured and the corresponding areas of the guiding rulers obtained in the step (3) in a new coordinate system, respectively fitting the point clouds, obtaining the initial pose of each guiding ruler, detecting all convex hull areas of each guiding ruler area, obtaining all possible poses of each guiding ruler, and selecting the optimal pose from all possible poses of each guiding ruler.

As a further improvement of the present invention, in step 4, the following method is adopted for each guiding rule:

step 401, performing local smoothing on wall point cloud data of a wall surface to be detected, and eliminating data fluctuation of a visual sensor;

step 402, according to the position and the angle to be measured, intercepting point cloud data C in the corresponding area on the wall surface to be measured according to the shape and the size of the guiding rule obtained in the step 3, and performing skeleton extraction on the intercepted point cloud data C;

step 403, performing straight line fitting on the point cloud data C to obtain an initial pose P0 of the guiding rule;

step 404, on the basis of the initial pose P0, detecting all convex hull areas of the guiding rule area, acquiring an extreme point of each convex hull area, and combining the two end points of the guiding rule to form a Set2 through which the actual guiding rule may pass;

step 405, in the point Set2, combining every two points into a straight line, judging whether all convex hull points are positioned at one side of the straight line, if so, calculating the farthest gap from the point cloud data C to the guiding rule as the measurement value of the current guiding rule;

and 406, selecting the condition with the minimum measurement result from all the running rule postures as the optimal running rule pose.

As a further improvement of the invention, the method also comprises the following steps: and measuring the flatness of the designated position of the wall surface to be measured or the whole wall through the guiding rule with the optimal pose, and outputting a flatness measurement result of the designated position or the explosion point position of the whole wall.

The invention also provides a wall surface guiding ruler detection system based on the three-dimensional point cloud, which comprises the following steps:

the data preprocessing module is used for acquiring three-dimensional point cloud data comprising a complete wall surface to be detected and preprocessing the three-dimensional point cloud data;

the wall surface data extraction module is used for extracting the data of the wall surface to be detected from the preprocessed three-dimensional point cloud data, taking any one corner of the wall surface to be detected as an original point and taking the vertical direction and the horizontal direction of the wall surface to be detected as coordinate axis directions, and establishing a new coordinate system;

the measuring position calculating module is used for calculating the end point position of each guiding rule according to the measuring position and angle requirements, acquiring the poses of all the guiding rules and automatically adjusting the poses of the guiding rules;

and the measurement calculation output module is used for intercepting point clouds of all the guiding rulers acquired by the measurement position calculation module in corresponding areas on the wall surface to be detected respectively under a new coordinate system, acquiring the initial pose of the guiding ruler after the point clouds are fitted, detecting the convex hull area of the guiding ruler area and acquiring the optimal pose of the guiding ruler.

The invention has the beneficial effects that:

(1) in the process that a computer acquires the inclined three-dimensional point cloud data acquired at any angle, the detection method can correctly eliminate the interference of non-building information and extract and distinguish the point cloud information of the wall surface to be measured.

(2) After a specific wall surface to be measured is obtained, a new coordinate system is established by taking the lower left corner of the wall surface as the original point and the wall surface direction as the coordinate axis direction, on the basis of the new coordinate system and according to specific measurement requirements, the detection method and the detection system can detect the accurate position of the guiding rule, and the flatness of the wall surface can be measured by using the accurate guiding rule in subsequent measurement. When only the designated position is measured, the pose of the analog guiding ruler can be automatically adjusted according to the actual situation of the wall surface, the correctness of the position of the guiding ruler is ensured, and the guiding ruler can be used for measuring the flatness of the designated position of the wall surface. The guiding rule with the optimal pose can be used for measuring the flatness of the appointed measuring position of the wall surface or the whole wall, and outputting the wall surface flatness measuring result of the appointed measuring position or the explosion point position of the whole wall. The measuring method is completely consistent with the measuring means of actual measuring workers, the measuring result is high in precision, the algorithm error is small, the method is not influenced by any subjective factor, the limitation of manual measurement is avoided, and the confidence coefficient is high.

(3) The guiding rule detected by the detection method and the detection system can be used for wall surface measurement, ceiling/ground positioning and the like, is suitable for various wall surfaces, and has strong universality.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings. The drawings described below are merely some embodiments of the present disclosure, and other drawings may be derived from those drawings by those of ordinary skill in the art without inventive effort.

Fig. 1 is a schematic flow chart of a wall surface running rule detection method based on three-dimensional point cloud according to a first embodiment of the present invention;

FIG. 2 is a schematic view of a process for extracting data of a wall to be measured;

FIG. 3 is a graph of the effect of a measurement across a door opening;

FIG. 4 is a schematic view of an optimal guiding rule pose;

fig. 5 is a system block diagram of a wall surface running rule detection system based on three-dimensional point cloud according to the second embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings.

While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art so that they can be readily implemented by those skilled in the art. As can be readily understood by those skilled in the art to which the present invention pertains, the embodiments to be described later may be modified into various forms without departing from the concept and scope of the present invention. Wherever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms "a", "an" and "the" include plural forms as well, unless the contrary is expressly stated. The term "comprising" as used in the specification embodies particular features, regions, constants, steps, actions, elements and/or components and does not exclude the presence or addition of other particular features, regions, constants, steps, actions, elements, components and/or groups.

All terms including technical and scientific terms used hereinafter have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms defined in dictionaries are to be interpreted as meanings complied with in the relevant technical documents and the present disclosure, and cannot be interpreted as having a very formal meaning without definition.