CN117806371A - Construction attitude detection and adjustment method and related device for building materials - Google Patents
Construction attitude detection and adjustment method and related device for building materials Download PDFInfo
- Publication number
- CN117806371A CN117806371A CN202311706483.2A CN202311706483A CN117806371A CN 117806371 A CN117806371 A CN 117806371A CN 202311706483 A CN202311706483 A CN 202311706483A CN 117806371 A CN117806371 A CN 117806371A
- Authority
- CN
- China
- Prior art keywords
- target object
- equation
- transverse
- curved surface
- longitudinal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 239000004566 building material Substances 0.000 title claims abstract description 40
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 238000010276 construction Methods 0.000 title claims abstract description 26
- 230000036544 posture Effects 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 19
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 description 14
- 238000013461 design Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000005253 cladding Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/26—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D3/00—Control of position or direction
- G05D3/10—Control of position or direction without using feedback
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a construction attitude detection and adjustment method and a related device for building materials, wherein the method comprises the following steps: acquiring a preset three-dimensional curved surface equation; acquiring a central position and a geometric reference line of a target object based on image recognition; projecting the central position of the target object to the three-dimensional curved surface, and taking the projection point as an intermediate reference position; performing horizontal adjustment on the target object; acquiring a longitudinal curve equation and a transverse curve equation of each center reference position based on the three-dimensional curved surface equation to obtain focuses of the longitudinal curve equation and the transverse curve equation; the theoretical longitudinal tilt angle of the target object is obtained based on the focal point, the normal line, and the center position of the target object of the longitudinal curve equation, and the theoretical lateral tilt angle of the target object is obtained based on the focal point, the normal line, and the center position of the target object of the lateral curve equation, thereby obtaining the longitudinal adjustment angle and the lateral adjustment angle. The method and the device can efficiently detect the postures of all target objects and give adjustment suggestions.
Description
Technical Field
The application relates to the field of angle measurement, in particular to a construction attitude detection and adjustment method and a related device for building materials.
Background
In contemporary construction practice, the precise placement of building materials has become a critical means of achieving building functionality and aesthetics. In particular, the construction of curved structures, such as curtain walls, exterior wall cladding, roof cladding and solar panels, requires that the materials be precisely positioned in a predetermined shape to form a continuous or segmented curved surface. These cambered surfaces not only give the building a streamlined appearance, enhancing the visual appeal of the building, but also meet specific functional requirements by their unique shape.
For example, curved curtain wall designs not only provide a dynamic appearance to modern buildings, but also improve the aerodynamic characteristics of the building by its non-linear shape, helping to reduce wind loads. In the same way, if the exterior wall cladding adopts a curved surface design, rainwater can be effectively guided to flow to a designated area, and the erosion of water to a building structure is reduced. The arcuate design of the roof cladding panel not only increases the aesthetics of the roof, but also optimizes light reception or rain drainage depending on its shape.
The arrangement of the solar panels is particularly important, since its efficiency is directly dependent on the amount of solar radiation that can be received. By arranging the solar panels in a concave structure, efficient focusing of sunlight can be achieved, thereby greatly improving energy conversion efficiency. Such concave structures generally require precise geometric configurations and mounting angles to ensure that the solar radiation energy is maximally captured and utilized.
In addition, the placement mode of the building materials also needs to consider the factors such as the overall structural stability of the building, the thermal expansion characteristic of the materials, the long-term environmental influence and the like. Thus, architects and engineers must carefully calculate and design the position and angle of each piece of material to ensure the integrity and long-term performance of the entire structure. However, in real practice, even if architects and engineers give the best design, it is difficult for operators to accurately place building materials to a given location and at a designed angle during construction due to lack of references.
Taking the design of a concentrating solar water heater as an example, the core component is formed by arranging a plurality of reflecting mirrors according to the shape of concave mirrors, and concentrating the heat energy of sunlight to heat water. To ensure efficient concentration of solar energy, the normal to each mirror must pass through a predetermined focal point, which is accomplished by precise geometric arrangements and angular adjustments.
Traditionally, this adjustment is by using a cardan shaft to fix each mirror and manually adjusting the mirrors by an operator to align the mirrors to a common focus. This process is typically performed under sun conditions, and the mirrors are calibrated by observing the collection of reflected spots at the target locations. However, when a plurality of high-brightness spots are collected at the same position, the high brightness of the spots makes it difficult for the operator to determine whether the adjustment of each mirror is accurate or not, and whether the spots overlap perfectly or not. As the number of collected spots increases, errors are more likely to occur in the adjustment.
To avoid this, one approach is to cover the adjusted mirrors with a mask and then fine-tune the unadjusted mirrors one by one. Although this approach can reduce the brightness to some extent, it is still a cumbersome and inefficient process requiring a significant amount of manual effort and time. In addition, since there is a certain difference in the shape of the spot, there is an error in the adjustment. The adjusting method has high labor intensity and low efficiency, has higher requirements on the skills of operators, and increases the cost of system debugging and maintenance. Therefore, developing a more automated, accurate and easy to operate reflector adjustment mechanism has significant practical value for improving the performance of concentrating solar water heaters and reducing maintenance costs.
Disclosure of Invention
In order to efficiently detect the postures of all target objects and give adjustment suggestions, the application provides a construction posture detection and adjustment method and a related device for building materials.
In a first aspect, the application provides a construction attitude detection and adjustment method for building materials, which adopts the following technical scheme:
a construction attitude detection and adjustment method of building materials comprises the following steps:
s1, acquiring a preset three-dimensional curved surface equation, wherein the three-dimensional curved surface equation corresponds to a building material combined model to be constructed;
s2, acquiring the central position and a geometric reference line of a target object based on image recognition, and taking the central position of one target object as a reference to correspond to a three-dimensional curved surface equation;
s3, projecting the central position of the target object to the three-dimensional curved surface based on the normal direction of the three-dimensional curved surface equation, and taking the projection point as an intermediate reference position;
s4, horizontally adjusting the target object based on a geometric reference line of the target object;
s5, acquiring an actual longitudinal inclination angle and an actual horizontal inclination angle of the target object;
s6, acquiring a longitudinal curve equation and a transverse curve equation of each center reference position based on the three-dimensional curved surface equation so as to obtain focuses of the longitudinal curve equation and the transverse curve equation;
s7, obtaining a theoretical longitudinal inclination angle of the target object based on the focus, the normal line and the central position of the target object of the longitudinal curve equation, and obtaining a theoretical transverse inclination angle of the target object based on the focus, the normal line and the central position of the target object of the transverse curve equation;
s8, obtaining a longitudinal adjustment angle based on the theoretical longitudinal inclination angle and the actual longitudinal inclination angle of the target object, and obtaining a transverse adjustment angle based on the theoretical transverse inclination angle and the actual transverse inclination angle of the target object.
By adopting the technical scheme, firstly, a three-dimensional curved surface equation of the geometric shape of the building material to be installed is defined and used as a reference of building material combined modeling. Building materials can be often placed into various regular curved surfaces or integrally fitted into curved surfaces. The device can be a plane or a curved surface, and levelness judgment can be performed based on the pre-recorded target object characteristics through computer vision, so that subsequent adjustment is facilitated. By projecting the center position of the target object onto the three-dimensional curved surface, the theoretical placement angle of the target object at the projection point can be obtained. Then, the theoretical placing posture of the target object at the current position needs to be obtained at the moment, and the theoretical placing posture of the target object at the projection point can be obtained by translating a distance and rotating a certain angle. The algorithm here by projection is a convenient solution. The longitudinal curve equation and the transverse curve equation of each center reference position are obtained based on the three-dimensional curve equation, and the three-dimensional curve is intercepted in the longitudinal direction and the transverse direction, which is equivalent to orthogonally decomposing the theoretical placement angle of the target object at the projection point into a transverse angle and a longitudinal angle, so that the later calculation is facilitated, and the calculation complexity is reduced. And finally, directly calculating through the focus coordinate, the normal direction and the central position coordinate of the target object, and omitting a large number of intermediate calculation steps, such as a triangular calculation process utilizing sine theorem and cosine theorem, so as to directly obtain the theoretical transverse inclination angle of the target object. However, these intermediate calculation processes are the theoretical proof basis for the establishment of the above steps, except that the computer may be omitted in the actual calculation process. Finally, the longitudinal adjustment angle is obtained through the theoretical longitudinal inclination angle and the actual longitudinal inclination angle of the target object, and the transverse adjustment angle is obtained through the theoretical transverse inclination angle and the actual transverse inclination angle of the target object, so that the required adjustment angle can be finally synthesized, and the gestures of all the target objects can be efficiently detected and adjustment suggestions can be given. In addition, the method has stronger robustness and can correspond to a plurality of different curved surface equations.
Optionally, the step S2 includes the following steps:
s21, obtaining images of at least two target objects to obtain a front view of each target object;
s22, acquiring position information and contour information of a target object in an image based on example segmentation;
s23, establishing a three-dimensional coordinate system, and converting the position information and the contour information of the target object into world coordinates based on a binocular vision algorithm; the x-y plane of the three-dimensional coordinate system is a horizontal plane, the y-z plane is parallel to the normal direction of the three-dimensional curved surface equation, and the z-axis direction is vertical;
s24, acquiring the shape and the boundary of each target object based on a feature detection algorithm so as to calculate the geometric center of the target object and give out corresponding center coordinates in a three-dimensional coordinate system;
s25, acquiring a transverse edge and a longitudinal edge of the target object based on a boundary detection algorithm, and giving out a corresponding transverse edge equation and a corresponding longitudinal edge equation in a three-dimensional coordinate system;
s26, selecting a target object as a reference object, and corresponding the center coordinates of the reference object to the reference point of the three-dimensional curved surface equation.
By adopting the technical scheme, the views of different visual angles of the target object can be obtained by capturing a plurality of images of the target object. The front views provide a basis for subsequent image processing, and ensure the capability of observing the target object from different angles so as to facilitate the subsequent spatial positioning of the characteristic points of the target object by using a binocular vision algorithm. Example segmentation techniques are capable of distinguishing and marking different target objects in a single image. It provides accurate position and contour information for each target object.
The position of the object in the actual three-dimensional space can be calculated by combining the target object information in the two or more images through a binocular vision algorithm. This step involves converting the two-dimensional data extracted from the image into world coordinates in three-dimensional space.
The feature detection algorithm identifies the shape and boundaries of the target object and then calculates its geometric center. In a three-dimensional coordinate system, this central coordinate provides a key reference point for subsequent steps.
By means of a boundary detection algorithm, the lateral and longitudinal boundaries of the target object can be determined and converted into mathematical equations. In a three-dimensional coordinate system, these equations facilitate subsequent analysis of the pose of the object.
A target object is selected as a reference object, and its center coordinates are corresponded to the reference points of the three-dimensional curved surface equation. This step is a key step of combining the position information of the actual object with the theoretical surface equation, so as to convert the three-dimensional surface equation into a three-dimensional coordinate system.
Optionally, the step S23 includes the following steps:
s231 based onImage setting camera coordinate system C of one target object 1 And converting the position information and the contour information of the target object into corresponding coordinate points P, wherein the points P are arranged in a coordinate system C 1 Is [ X ] 1 ,Y 1 ,Z 1 ]；
S232, setting a camera coordinate system C based on the image of the second target object 2 And converting the position information and the contour information of the target object into corresponding coordinate points P, wherein the points P are arranged in a coordinate system C 2 Is [ X ] 2 ,Y 2 ,Z 2 ]；
S233, based on point P in coordinate system C 1 And in coordinate system C 2 The world coordinate W is obtained by calculating the coordinates of (1), wherein the world coordinate W is [ X ] W ,Y W ,Z W ]，
Optionally, the step S4 includes the following steps:
s41, calculating an included angle formed by a transverse side line of the target object and a horizontal reference plane, and judging that the target object is in a horizontal state if the included angle is smaller than a preset angle;
s42, if the included angle is larger than the preset angle, judging that the target object is in an inclined state, and returning an included angle formed by the transverse side line of the target object and the horizontal reference surface to serve as a levelness adjustment guide angle.
Optionally, the step S6 includes the following steps:
s61, acquiring coordinates of a central reference position, substituting the z-axis coordinates into a three-dimensional curved surface equation to obtain a transverse curve equation, wherein the transverse curve is a parabola obtained by intercepting a three-dimensional curved surface in an x-y plane;
s62, acquiring coordinates of a central reference position, substituting the x-axis coordinates into a three-dimensional curved surface equation to obtain a longitudinal curve equation, wherein a transverse curve is a parabola obtained by intercepting a three-dimensional curved surface in a y-z plane;
s63, obtaining a focus of the transverse curve equation and a focus of the longitudinal curve equation based on the transverse curve equation and the longitudinal curve equation.
Optionally, the step S7 includes the following steps:
s71, obtaining a first connecting line and a corresponding first connecting line equation based on a focus of the longitudinal curve equation and the central position of the target object;
s72, generating a first reference line which passes through the central position of the target object and is parallel to the normal line and a corresponding first reference line equation;
s73, obtaining a first angle bisector equation of the first connecting line and the first reference line based on the first connecting line equation and the first reference line equation;
s74, generating a first perpendicular line equation of the first angle bisector equation at the center position of the target object, and obtaining the theoretical longitudinal inclination angle of the target object based on the slope of the first perpendicular line equation.
Optionally, the step S7 includes the following steps:
s75, obtaining a second connecting line and a corresponding second connecting line equation based on the focus of the transverse curve equation and the central position of the target object;
s76, generating a second reference line which passes through the central position of the target object and is parallel to the normal line and a corresponding second reference line equation;
s77, obtaining a second angular bisector equation of the second connecting line and the second reference line based on the second connecting line equation and the second reference line equation;
s78, generating a second perpendicular line equation of the second angular bisector equation at the center of the target object, and obtaining the theoretical transverse inclination angle of the target object based on the slope of the second perpendicular line equation.
Optionally, the three-dimensional curved surface equation is a paraboloid corresponding to the combined modeling of the building materials to be constructed.
In a second aspect, the present application provides a computer device, which adopts the following technical scheme:
a computer apparatus, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: the construction posture detection and adjustment method of the building material is executed.
In a third aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:
a computer readable storage medium storing a computer program capable of being loaded by a processor and executing the method as described above.
The storage medium stores at least one instruction, at least one program, a set of codes, or a set of instructions that are loaded and executed by the processor to implement: the construction posture detection and adjustment method of the building material.
Drawings
Fig. 1 is a flowchart illustrating a method for detecting and calibrating a construction posture of a building material according to an embodiment of the invention.
FIG. 2 is a flowchart illustrating the sub-step S2 in an embodiment of the invention.
FIG. 3 is a flowchart illustrating the sub-step S6 in an embodiment of the invention.
FIG. 4 is a flowchart showing the sub-step S7 in an embodiment of the invention.
Detailed Description
The present application is described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the inventive concepts. As part of this specification, some of the drawings of the present disclosure represent structures and devices in block diagram form in order to avoid obscuring the principles of the disclosure. In the interest of clarity, not all features of an actual implementation are necessarily described. Furthermore, the language used in the present disclosure has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter, resort to the requisite claims to determine such inventive subject matter. Reference in the present disclosure to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment, and multiple references to "one embodiment" or "an embodiment" should not be understood as necessarily all referring to the same embodiment.
The terms "a," "an," and "the" are not intended to refer to a singular entity, but rather include the general class of which a particular example may be used for illustration, unless clearly defined. Thus, the use of the terms "a" or "an" may mean any number of at least one, including "one", "one or more", "at least one", and "one or more than one". The term "or" means any of the alternatives and any combination of alternatives, including all alternatives, unless alternatives are explicitly indicated as mutually exclusive. The phrase "at least one of" when combined with a list of items refers to a single item in the list or any combination of items in the list. The phrase does not require all of the listed items unless specifically so defined.
Referring to fig. 1, the application discloses a construction attitude detection and adjustment method of a building material, which comprises the following steps S1-S8.
S1, acquiring a preset three-dimensional curved surface equation, wherein the three-dimensional curved surface equation corresponds to a building material combined model to be constructed.
Firstly, defining a three-dimensional curved surface equation of the geometric shape of the building material to be installed, and taking the equation as a reference of the combined modeling of the building material. Building materials can be often placed into various regular curved surfaces or integrally fitted into curved surfaces. The device can be a plane or a curved surface, and levelness judgment can be performed based on the pre-recorded target object characteristics through computer vision, so that subsequent adjustment is facilitated.
S2, acquiring the central position and the geometric reference line of the target object based on image recognition, and taking the central position of one target object as a reference to correspond to a three-dimensional curved surface equation.
The adjustment method of the present embodiment is applicable to a building material having a regular shape, such as a spherical circular arc plate, a flat plate, etc., which takes a square plane mirror as an example in this example, and the three-dimensional curved surface equation is a paraboloid corresponding to the combined shape of the building material to be constructed. When the building materials are arranged in an array, and the arrangement positions and the arrangement angles are proper, light entering along the normal line can be collected on a parallel line passing through the focus.
Specifically, referring to FIG. 2, S2 includes the following steps S21-S26.
S21, obtaining images of at least two target objects to obtain front views of the target objects.
By capturing multiple images of the target object, views of different perspectives thereof may be obtained. The front views provide a basis for subsequent image processing, and ensure the capability of observing the target object from different angles so as to facilitate the subsequent spatial positioning of the characteristic points of the target object by using a binocular vision algorithm.
S22, acquiring position information and contour information of a target object in the image based on example segmentation.
Example segmentation techniques are capable of distinguishing and marking different target objects in a single image. It provides accurate position and contour information for each target object.
Specifically, S22 may include the following substeps:
s221, inputting the sample picture into a target detection model, determining a target circumscribed frame based on target frame detection, and determining a target individual set based on semantic segmentation to serve as a contour region. The target external frame is used for reflecting the imaging position of the target object in the input detection picture, and the target individual set is used for reflecting the pixel points positioned in the imaging area of the target object.
The target detection model is a pre-trained instance segmentation model, and can be used for target frame detection and semantic segmentation. The target frame detection can frame and select a region associated with a target object in the sample picture, and the target object is distinguished from other objects in the sample picture through a target circumscribed frame. The semantic segmentation can classify the pixels belonging to the imaging of the target object area and the pixels belonging to the imaging of the non-target object area in the sample picture to obtain a target individual set.
S222, generating a contour line based on the contour area.
And carrying out target frame detection and semantic segmentation on the sample picture to obtain a contour region, and generating a corresponding contour line.
S223, dividing the sample picture into images each containing a target object based on the target external frame.
One or more target objects may appear in the sample picture and be located at different positions in the sample picture. Because each target external frame corresponds to one target object respectively, the step can divide the sample picture into a plurality of pieces by utilizing the target external frames, so that each target object is positioned at the center of an image respectively, interference in different target object division processes is avoided, meanwhile, the reduced sample picture contains less irrelevant features, the parameters generated by subsequent model processing are reduced, and the processing efficiency is improved.
S224, pixel interpolation is carried out between adjacent pixels based on pixel information of adjacent pixel points of the sample picture so as to amplify the sample picture.
The pixel density of the original pixels is reduced, so that the contour area of the sample picture is subjected to percentage sampling in the later period.
S225, combining the target external frame and the target individual set to output characteristic information of the target; wherein the characteristic information is pixel information of the pixel points.
By combining the target external frame and the target individual set, the interference of non-target objects and background environments in the sample picture on the extraction of the characteristic information can be reduced, the occupied calculated amount in the extraction process of the characteristic information is reduced, and the operation speed and the accuracy are improved.
S23, establishing a three-dimensional coordinate system, and converting the position information and the contour information of the target object into world coordinates based on a binocular vision algorithm. The x-y plane of the three-dimensional coordinate system is a horizontal plane, the y-z plane is parallel to the normal direction of the three-dimensional curved surface equation, and the z-axis direction is vertical.
The position of the object in the actual three-dimensional space can be calculated by combining the target object information in the two or more images through a binocular vision algorithm. This step involves converting the two-dimensional data extracted from the image into world coordinates in three-dimensional space.
Specifically, in the present embodiment, S23 includes the following steps S231 to S233:
s231 setting a camera coordinate system C based on the image of the first target object 1 And converting the position information and the contour information of the target object into corresponding coordinate points P, wherein the points P are arranged in a coordinate system C 1 Is [ X ] 1 ,Y 1 ,Z 1 ]；
S232, setting a camera coordinate system C based on the image of the second target object 2 And converting the position information and the contour information of the target object into corresponding coordinate points P, wherein the points P are arranged in a coordinate system C 2 Is [ X ] 2 ,Y 2 ,Z 2 ]；
S233, based on point P in coordinate system C 1 And in coordinate system C 2 The world coordinate W is obtained by calculating the coordinates of (1), wherein the world coordinate W is [ X ] W ,Y W ,Z W ]，
For example, for two camera coordinate systems C 1 And C 2 If they each observe the same point P in the world coordinate system W, the coordinates of P in the world coordinate system W can be determined mathematically. Let us assume that in the camera coordinate system C 1 In which the point P has the coordinates of [ X ] 1 ,Y 1 ,Z 1 ]In camera coordinate system C 2 In which the point P has the coordinates of [ X ] 2 ,Y 2 ,Z 2 ]. The distance between the origins of the two coordinate systems is d and the focal length of the camera is f.
For camera coordinate system C 1 The method comprises the following steps:
for camera coordinate system C 2 The method comprises the following steps:
here, [ X ] W ,Y W ,Z W ]Is the coordinates of point P in world coordinate system W.
Solving the world coordinate W, and solving X according to the above equation W ,Y W And Z W :
Combining all the above equations, one can get:
s24, acquiring the shape and the boundary of each target object based on a feature detection algorithm so as to calculate the geometric center of the target object and give out corresponding center coordinates in a three-dimensional coordinate system.
The feature detection algorithm identifies the shape and boundaries of the target object and then calculates its geometric center. In a three-dimensional coordinate system, this central coordinate provides a key reference point for subsequent steps.
S25, acquiring a transverse edge and a longitudinal edge of the target object based on a boundary detection algorithm, and giving out a corresponding transverse edge equation and a corresponding longitudinal edge equation in a three-dimensional coordinate system.
By means of a boundary detection algorithm, the lateral and longitudinal boundaries of the target object can be determined and converted into mathematical equations. In a three-dimensional coordinate system, these equations facilitate subsequent analysis of the pose of the object.
S26, selecting a target object as a reference object, and corresponding the center coordinates of the reference object to the reference point of the three-dimensional curved surface equation.
A target object is selected as a reference object, and its center coordinates are corresponded to the reference points of the three-dimensional curved surface equation. This step is a key step of combining the position information of the actual object with the theoretical surface equation, so as to convert the three-dimensional surface equation into a three-dimensional coordinate system.
S3, projecting the central position of the target object to the three-dimensional curved surface based on the normal direction of the three-dimensional curved surface equation, and taking the projection point as an intermediate reference position.
By projecting the center position of the target object onto the three-dimensional curved surface, the theoretical placement angle of the target object at the projection point can be obtained. Then, the theoretical placing posture of the target object at the current position needs to be obtained at the moment, and the theoretical placing posture of the target object at the projection point can be obtained by translating a distance and rotating a certain angle. The algorithm here by projection is a convenient solution.
S4, horizontally adjusting the target object based on the geometric reference line of the target object.
The level adjustment is performed to facilitate subsequent orthogonal decomposition. Meanwhile, the characteristics of the square plate can fall on the transverse direction and the longitudinal direction after decomposition by horizontal adjustment, so that the calculation is convenient.
As an example, S4 may include the following steps S41 to S42.
S41, calculating an included angle formed by the transverse side line of the target object and the horizontal reference plane, and judging that the target object is in a horizontal state if the included angle is smaller than a preset angle.
S42, if the included angle is larger than the preset angle, judging that the target object is in an inclined state, and returning an included angle formed by the transverse side line of the target object and the horizontal reference surface to serve as a levelness adjustment guide angle.
S5, acquiring the actual longitudinal inclination angle and the actual horizontal inclination angle of the target object.
The actual longitudinal tilt angle and the actual horizontal tilt angle of the target object may be calculated by means of a geometrical reference line of the target object.
S6, acquiring a longitudinal curve equation and a transverse curve equation of each center reference position based on the three-dimensional curved surface equation so as to obtain focuses of the longitudinal curve equation and the transverse curve equation.
The longitudinal curve equation and the transverse curve equation of each center reference position are obtained based on the three-dimensional curve equation, and the three-dimensional curve is intercepted in the longitudinal direction and the transverse direction, which is equivalent to orthogonally decomposing the theoretical placement angle of the target object at the projection point into a transverse angle and a longitudinal angle, so that the later calculation is facilitated, and the calculation complexity is reduced.
As an example, referring to fig. 3, S6 may include the following steps S61-S63.
S61, acquiring coordinates of a central reference position, substituting the z-axis coordinates into a three-dimensional curved surface equation to obtain a transverse curve equation, wherein the transverse curve is a parabola obtained by intercepting a three-dimensional curved surface in an x-y plane;
s62, acquiring coordinates of a central reference position, substituting the x-axis coordinates into a three-dimensional curved surface equation to obtain a longitudinal curve equation, wherein a transverse curve is a parabola obtained by intercepting a three-dimensional curved surface in a y-z plane;
s63, obtaining a focus of the transverse curve equation and a focus of the longitudinal curve equation based on the transverse curve equation and the longitudinal curve equation.
S7, obtaining a theoretical longitudinal inclination angle of the target object based on the focus, the normal line and the central position of the target object of the longitudinal curve equation, and obtaining a theoretical transverse inclination angle of the target object based on the focus, the normal line and the central position of the target object of the transverse curve equation.
By directly performing the calculation with the focal point coordinates, the normal direction, and the center position coordinates of the target object, a large number of intermediate calculation steps, such as a trigonometric calculation process using the sine theorem and the cosine theorem, can be omitted, and the theoretical transverse tilt angle of the target object can be directly obtained. However, these intermediate calculation processes are the theoretical proof basis for the establishment of the above steps, except that the computer may be omitted in the actual calculation process.
As an example, referring to fig. 4, S7 may include the following steps S71-S78.
S71, obtaining a first connecting line and a corresponding first connecting line equation based on the focal point of the longitudinal curve equation and the central position of the target object.
S72, generating a first reference line which passes through the center position of the target object and is parallel to the normal line and a corresponding first reference line equation.
S73, obtaining a first angle bisector equation of the first connecting line and the first reference line based on the first connecting line equation and the first reference line equation.
S74, generating a first perpendicular line equation of the first angle bisector equation at the center position of the target object, and obtaining the theoretical longitudinal inclination angle of the target object based on the slope of the first perpendicular line equation.
And S75, obtaining a second connecting line and a corresponding second connecting line equation based on the focus of the transverse curve equation and the center position of the target object.
S76, generating a second reference line which passes through the center position of the target object and is parallel to the normal line and a corresponding second reference line equation.
And S77, obtaining a second angular bisector equation of the second connecting line and the second reference line based on the second connecting line equation and the second reference line equation.
S78, generating a second perpendicular line equation of the second angular bisector equation at the center of the target object, and obtaining the theoretical transverse inclination angle of the target object based on the slope of the second perpendicular line equation.
S8, obtaining a longitudinal adjustment angle based on the theoretical longitudinal inclination angle and the actual longitudinal inclination angle of the target object, and obtaining a transverse adjustment angle based on the theoretical transverse inclination angle and the actual transverse inclination angle of the target object.
Finally, the longitudinal adjustment angle is obtained through the theoretical longitudinal inclination angle and the actual longitudinal inclination angle of the target object, and the transverse adjustment angle is obtained through the theoretical transverse inclination angle and the actual transverse inclination angle of the target object, so that the required adjustment angle can be finally synthesized.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the construction gesture detection and adjustment method of the building material of the above embodiment.
In an embodiment, a computer readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the construction attitude detection and adjustment method of the building material of the above embodiment.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments of the present application may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (10)
1. The construction posture detection and adjustment method for the building material is characterized by comprising the following steps of:
s1, acquiring a preset three-dimensional curved surface equation, wherein the three-dimensional curved surface equation corresponds to a building material combined model to be constructed;
s2, acquiring the central position and a geometric reference line of a target object based on image recognition, and taking the central position of one target object as a reference to correspond to a three-dimensional curved surface equation;
s3, projecting the central position of the target object to the three-dimensional curved surface based on the normal direction of the three-dimensional curved surface equation, and taking the projection point as an intermediate reference position;
s4, horizontally adjusting the target object based on a geometric reference line of the target object;
s5, acquiring an actual longitudinal inclination angle and an actual horizontal inclination angle of the target object;
s6, acquiring a longitudinal curve equation and a transverse curve equation of each center reference position based on the three-dimensional curved surface equation so as to obtain focuses of the longitudinal curve equation and the transverse curve equation;
s7, obtaining a theoretical longitudinal inclination angle of the target object based on the focus, the normal line and the central position of the target object of the longitudinal curve equation, and obtaining a theoretical transverse inclination angle of the target object based on the focus, the normal line and the central position of the target object of the transverse curve equation;
s8, obtaining a longitudinal adjustment angle based on the theoretical longitudinal inclination angle and the actual longitudinal inclination angle of the target object, and obtaining a transverse adjustment angle based on the theoretical transverse inclination angle and the actual transverse inclination angle of the target object.
2. The construction posture detection and adjustment method of a building material according to claim 1, characterized in that S2 includes the steps of:
s21, obtaining images of at least two target objects to obtain a front view of each target object;
s22, acquiring position information and contour information of a target object in an image based on example segmentation;
s23, establishing a three-dimensional coordinate system, and converting the position information and the contour information of the target object into world coordinates based on a binocular vision algorithm; the x-y plane of the three-dimensional coordinate system is a horizontal plane, the y-z plane is parallel to the normal direction of the three-dimensional curved surface equation, and the z-axis direction is vertical;
s24, acquiring the shape and the boundary of each target object based on a feature detection algorithm so as to calculate the geometric center of the target object and give out corresponding center coordinates in a three-dimensional coordinate system;
s25, acquiring a transverse edge and a longitudinal edge of the target object based on a boundary detection algorithm, and giving out a corresponding transverse edge equation and a corresponding longitudinal edge equation in a three-dimensional coordinate system;
s26, selecting a target object as a reference object, and corresponding the center coordinates of the reference object to the reference point of the three-dimensional curved surface equation.
3. The construction posture detecting and adjusting method of the building material according to claim 2, characterized in that the
S23 includes the steps of:
s231 setting a camera coordinate system C based on the image of the first target object 1 And converting the position information and the contour information of the target object into corresponding coordinate points P, wherein the points P are arranged in a coordinate system C 1 Is [ X ] 1 ,Y 1 ,Z 1 ]；
S232, setting a camera coordinate system C based on the image of the second target object 2 And converting the position information and the contour information of the target object into corresponding coordinate points P, wherein the points P are arranged in a coordinate system C 2 Is [ X ] 2 ,Y 2 ,Z 2 ]；
S233, based on point P in coordinate system C 1 And in coordinate system C 2 The world coordinate W is obtained by calculating the coordinates of (1), wherein the world coordinate W is [ X ] W ,Y W ,Z W ]，
4. A construction attitude detection and adjustment method for a building material according to claim 1 or 3, characterized in that S4 includes the steps of:
s41, calculating an included angle formed by a transverse side line of the target object and a horizontal reference plane, and judging that the target object is in a horizontal state if the included angle is smaller than a preset angle;
s42, if the included angle is larger than the preset angle, judging that the target object is in an inclined state, and returning an included angle formed by the transverse side line of the target object and the horizontal reference surface to serve as a levelness adjustment guide angle.
5. The construction attitude detection and adjustment method for building materials according to claim 4, wherein S6 includes the steps of:
s61, acquiring coordinates of a central reference position, substituting the z-axis coordinates into a three-dimensional curved surface equation to obtain a transverse curve equation, wherein the transverse curve is a parabola obtained by intercepting a three-dimensional curved surface in an x-y plane;
s62, acquiring coordinates of a central reference position, substituting the x-axis coordinates into a three-dimensional curved surface equation to obtain a longitudinal curve equation, wherein a transverse curve is a parabola obtained by intercepting a three-dimensional curved surface in a y-z plane;
s63, obtaining a focus of the transverse curve equation and a focus of the longitudinal curve equation based on the transverse curve equation and the longitudinal curve equation.
6. The construction attitude detection and adjustment method for building materials according to claim 5, wherein S7 includes the steps of:
s71, obtaining a first connecting line and a corresponding first connecting line equation based on a focus of the longitudinal curve equation and the central position of the target object;
s72, generating a first reference line which passes through the central position of the target object and is parallel to the normal line and a corresponding first reference line equation;
s73, obtaining a first angle bisector equation of the first connecting line and the first reference line based on the first connecting line equation and the first reference line equation;
s74, generating a first perpendicular line equation of the first angle bisector equation at the center position of the target object, and obtaining the theoretical longitudinal inclination angle of the target object based on the slope of the first perpendicular line equation.
7. The construction attitude detection and adjustment method for building materials according to claim 6, wherein S7 includes the steps of:
s75, obtaining a second connecting line and a corresponding second connecting line equation based on the focus of the transverse curve equation and the central position of the target object;
s76, generating a second reference line which passes through the central position of the target object and is parallel to the normal line and a corresponding second reference line equation;
s77, obtaining a second angular bisector equation of the second connecting line and the second reference line based on the second connecting line equation and the second reference line equation;
s78, generating a second perpendicular line equation of the second angular bisector equation at the center of the target object, and obtaining the theoretical transverse inclination angle of the target object based on the slope of the second perpendicular line equation.
8. The method for detecting and adjusting construction postures of building materials according to claim 1, wherein the three-dimensional curved surface equation is a paraboloid corresponding to a combined modeling of the building materials to be constructed.
9. A computer device, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: a construction posture detection and adjustment method of the building material according to any one of claims 1 to 8 is performed.
10. A computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, the at least one instruction, the at least one program, the code set, or instruction set being loaded and executed by the processor to implement: the construction posture detection and adjustment method of a building material according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311706483.2A CN117806371B (en) | 2023-12-12 | 2023-12-12 | Construction attitude detection and adjustment method and related device for building materials |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311706483.2A CN117806371B (en) | 2023-12-12 | 2023-12-12 | Construction attitude detection and adjustment method and related device for building materials |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117806371A true CN117806371A (en) | 2024-04-02 |
| CN117806371B CN117806371B (en) | 2024-07-09 |
Family
ID=90419615
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311706483.2A Active CN117806371B (en) | 2023-12-12 | 2023-12-12 | Construction attitude detection and adjustment method and related device for building materials |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117806371B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110189375A (en) * | 2019-06-26 | 2019-08-30 | 中国科学院光电技术研究所 | A kind of images steganalysis method based on monocular vision measurement |
| CN113031635A (en) * | 2021-02-26 | 2021-06-25 | 上海高仙自动化科技发展有限公司 | Attitude adjusting method and device, cleaning robot and storage medium |
| CN113805215A (en) * | 2020-06-16 | 2021-12-17 | 中联重科股份有限公司 | Engineering machine pose determining method and device, engineering machine and storage medium |
| WO2022037389A1 (en) * | 2020-08-18 | 2022-02-24 | 维数谷智能科技（嘉兴）有限公司 | Reference plane-based high-precision method and system for estimating multi-degree-of-freedom attitude of object |
| CN117152257A (en) * | 2023-10-31 | 2023-12-01 | 罗普特科技集团股份有限公司 | Method and device for multidimensional angle calculation of ground monitoring camera |
-
2023
- 2023-12-12 CN CN202311706483.2A patent/CN117806371B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110189375A (en) * | 2019-06-26 | 2019-08-30 | 中国科学院光电技术研究所 | A kind of images steganalysis method based on monocular vision measurement |
| CN113805215A (en) * | 2020-06-16 | 2021-12-17 | 中联重科股份有限公司 | Engineering machine pose determining method and device, engineering machine and storage medium |
| WO2022037389A1 (en) * | 2020-08-18 | 2022-02-24 | 维数谷智能科技（嘉兴）有限公司 | Reference plane-based high-precision method and system for estimating multi-degree-of-freedom attitude of object |
| CN113031635A (en) * | 2021-02-26 | 2021-06-25 | 上海高仙自动化科技发展有限公司 | Attitude adjusting method and device, cleaning robot and storage medium |
| CN117152257A (en) * | 2023-10-31 | 2023-12-01 | 罗普特科技集团股份有限公司 | Method and device for multidimensional angle calculation of ground monitoring camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117806371B (en) | 2024-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Herráez et al. | 3D modeling by means of videogrammetry and laser scanners for reverse engineering | |
| CN103955916B (en) | Automobile panorama camera calibration method and apparatus | |
| CN104820973B (en) | The method for correcting image of distortion curve radian detection template | |
| Cheng et al. | Automatic registration of terrestrial and airborne point clouds using building outline features | |
| Bian et al. | 3D reconstruction of single rising bubble in water using digital image processing and characteristic matrix | |
| CN111860404A (en) | Photovoltaic panel hot spot positioning method and system | |
| CN105118040A (en) | Document image distortion rectifying method based on structured laser beams | |
| CN104331900A (en) | Corner sub-pixel positioning method in CCD (charge coupled device) camera calibration | |
| Bonanos et al. | Heliostat surface shape characterization for accurate flux prediction | |
| CN108917633A (en) | Fuel assembly deformation detection system based on underwater binocular vision | |
| Xu et al. | UAV-based bridge geometric shape measurement using automatic bridge component detection and distributed multi-view reconstruction | |
| CN117806371B (en) | Construction attitude detection and adjustment method and related device for building materials | |
| CN113432572B (en) | Complex structure optimal measuring point planning method based on three-dimensional scanning | |
| WO2024037123A1 (en) | Full-field refined dni prediction method | |
| CN113808033A (en) | Image document correction method, system, terminal and medium | |
| CN111445513B (en) | Plant canopy volume acquisition method and device based on depth image, computer equipment and storage medium | |
| CN116524041A (en) | Camera calibration method, device, equipment and medium | |
| Sproul et al. | The development of the heliostat focusing and canting enhancement technique: an optical heliostat alignment tool for the national solar thermal test facility | |
| CN110390715A (en) | Method that is a kind of while detecting building roof, building masonry wall and ground area shading | |
| US10373321B2 (en) | Sun position tracking method based on black sun effect of image sensor, computer program stored in medium, and solar sensor using the same | |
| CN115588127A (en) | Method for fusing airborne laser point cloud and multispectral image | |
| CN111539964B (en) | Plant canopy surface area acquisition method and device based on depth image, computer equipment and storage medium | |
| Monterreal et al. | An improved methodology for heliostat testing and evaluation at the Plataforma Solar de Almería | |
| Goroshin et al. | Estimating Residential Solar Potential Using Aerial Data | |
| CN117742389B (en) | Heliostat cleaning posture calibration method based on image recognition technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |