CN116697940A - Skid flatness detection method and device, computer equipment and storage medium - Google Patents
Skid flatness detection method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN116697940A CN116697940A CN202310647935.8A CN202310647935A CN116697940A CN 116697940 A CN116697940 A CN 116697940A CN 202310647935 A CN202310647935 A CN 202310647935A CN 116697940 A CN116697940 A CN 116697940A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cloud data
- plane
- coordinate system
- camera
- 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.)
- Pending
Links
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 238000001514 detection method Methods 0.000 title claims description 24
- 238000000034 method Methods 0.000 claims abstract description 61
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 230000033001 locomotion Effects 0.000 claims description 32
- 238000006243 chemical reaction Methods 0.000 claims description 28
- 239000011159 matrix material Substances 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000005259 measurement Methods 0.000 abstract description 11
- 238000012360 testing method Methods 0.000 abstract description 7
- 238000012545 processing Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000001914 filtration Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000002146 bilateral effect Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- 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
- G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a method, a device, computer equipment and a storage medium for detecting the flatness of a skid, wherein the method comprises the following steps: collecting target point cloud data corresponding to each plane to be detected in each cross beam through a camera, wherein each cross beam comprises a plurality of planes to be detected; respectively determining a first plane equation of each target point cloud data according to a preset plane algorithm and each target point cloud data; converting each first plane equation from a camera coordinate system to a preset coordinate system to obtain a second plane equation of each target point cloud data under the preset coordinate system; determining a Z-axis vector of a reference coordinate system according to the normal vector of each second plane equation; and determining the flatness coefficient of the skid according to the angle difference value between each normal vector and the Z-axis quantity. The non-contact measurement of the flatness of the skid is realized, the testing precision and the testing efficiency of the flatness of the skid are improved, and the safety and the reliability of the transportation of the skid are improved.
Description
Technical Field
The present invention relates to the field of production line management, and in particular, to a method and apparatus for detecting flatness of a sled, a computer device, and a storage medium.
Background
Skid is a conveyor system device for a motor vehicle production line, which is used for carrying and transporting motor vehicle bodies. The top of skid is provided with many crossbeams, and the upper surface of crossbeam and the bottom surface direct contact of automobile body, i.e. the crossbeam directly plays the effect of bearing the automobile body. Therefore, the flatness of the upper surface of the cross beam in the skid influences the overall flatness of the skid, and the detection of the flatness of the cross beam is an important means for ensuring the transportation safety and reliability. However, the existing flatness detection methods are mainly contact measurement or artificial visual detection. For contact measurement, a measuring tool is required to be used for contact with the cross beam to detect, damage is easily caused to the cross beam, the operation complexity is high, the measurement efficiency is low, and meanwhile, the contact measurement is difficult to measure for finer flatness difference. For visual inspection, the operation time is long and the accuracy is low, and no minute flatness change can be found. This results in the problem that the skid itself is easily damaged, and the measurement accuracy is low and the measurement efficiency is low in the overall flatness test of the skid.
Disclosure of Invention
The embodiment of the invention provides a method, a device, computer equipment and a storage medium for detecting the flatness of a skid, and aims to solve the problems that the skid is easy to damage and the detection precision and the detection efficiency are both at lower level when the whole flatness of the skid is detected in the method in the prior art.
In a first aspect, an embodiment of the present invention provides a method for detecting flatness of a skid, where the skid includes a plurality of beams, the method includes:
collecting target point cloud data corresponding to each plane to be detected in each cross beam through a camera, wherein each cross beam comprises a plurality of planes to be detected;
respectively determining a first plane equation of each target point cloud data according to a preset plane algorithm and each target point cloud data;
converting each first plane equation from a camera coordinate system to a preset coordinate system to obtain a second plane equation of each target point cloud data under the preset coordinate system;
determining a Z-axis vector of the preset coordinate system according to the normal vector of each second plane equation;
and determining the flatness coefficient of the skid according to the angle difference value between each normal vector and the Z-axis quantity.
In a second aspect, an embodiment of the present invention provides a device for detecting flatness of a sled, including:
the acquisition unit is used for acquiring target point cloud data corresponding to each plane to be detected in each cross beam through a camera, and each cross beam comprises a plurality of planes to be detected;
the first determining unit is used for determining a first plane equation of each target point cloud data according to a preset plane algorithm and each target point cloud data;
the conversion unit is used for converting each first plane equation from a camera coordinate system to a preset coordinate system to obtain a second plane equation of each target point cloud data under the preset coordinate system;
the second determining unit is used for determining a Z-axis vector of the preset coordinate system according to the normal vector of each second plane equation;
and the third determining unit is used for determining the flatness coefficient of the skid according to the angle difference value between each normal vector and the Z-axis quantity.
In a third aspect, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the method for detecting the smoothness of a sled according to the first aspect when executing the computer program.
In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium storing a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method for detecting the flatness of a sled as described in the first aspect.
The embodiment of the invention provides a method and a device for detecting the flatness of a skid, computer equipment and a storage medium, wherein the method comprises the following steps: collecting target point cloud data corresponding to each plane to be detected in each cross beam through a camera, wherein each cross beam comprises a plurality of planes to be detected; respectively determining a first plane equation of each target point cloud data according to a preset plane algorithm and each target point cloud data; converting each first plane equation from a camera coordinate system to a preset coordinate system to obtain a second plane equation of each target point cloud data under the preset coordinate system; determining a Z-axis vector of the preset coordinate system according to the normal vector of each second plane equation; and determining the flatness coefficient of the skid according to the angle difference value between each normal vector and the Z-axis quantity. According to the embodiment of the invention, the camera is used for carrying out contactless photographing on the cross beam in the skid and generating the three-dimensional point cloud, the plane equation is fitted on the plane to be detected through the three-dimensional point cloud, and finally the calculation of the planeness coefficient of the skid is carried out according to the fitted plane equation in the point cloud and the deviation of the normal vector of the plane equation, so that the contactless measurement of the planeness of the skid is realized, the testing precision of the planeness of the skid is improved, the testing efficiency of the planeness of the skid is improved, and the safety and reliability of skid transportation in an automobile production line are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of an application scenario of a method for detecting the flatness of a sled according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for detecting the flatness of a sled according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a first sub-process in the method for detecting the flatness of a sled according to the embodiment of the present invention;
FIG. 4 is a schematic flow chart of a second sub-process in the method for detecting the flatness of a sled according to the embodiment of the present invention;
FIG. 5 is a schematic flow chart of a third sub-process in the method for detecting the flatness of a sled according to the embodiment of the present invention;
FIG. 6 is a schematic flow chart of a fourth sub-process in the method for detecting the flatness of a sled according to the embodiment of the present invention;
FIG. 7 is a schematic block diagram of a skid flatness detection apparatus according to an embodiment of the present invention;
Fig. 8 is a schematic block diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Referring to fig. 1 and fig. 2, fig. 1 is a schematic diagram of an application scenario of a method for detecting the flatness of a sled according to an embodiment of the present invention, and fig. 2 is a schematic flowchart of the method for detecting the flatness of a sled according to an embodiment of the present invention. The detection method of the smoothness of the skid is applied to a terminal or a server. The terminal can be a PCL (Point Cloud Library, point cloud database) system connected with a camera or a mechanical arm, a series of point cloud algorithms and operation strategies are stored in the terminal, and the terminal can acquire point cloud data of a plane to be detected of a cross beam in the skid and further process and operate the point cloud data. The camera here is a camera provided with a three-dimensional imaging sensor, which may be in particular a three-dimensional scanner or an RGB-D (RGB-Depth) camera. The camera can perform laser throwing on a target detection object and convert the reflected laser beam into three-dimensional coordinate points to form a data set. Each point data in the dataset represents a set of X, Y, Z geometric coordinates and an intensity value that records the intensity of the return signal based on the object surface reflectivity. When these points are combined together, a point cloud is formed, i.e., a collection of data points representing a 3D shape or object in space. The point cloud data can reflect the current form of the target detection object. The camera is arranged at the tail end of the mechanical arm, namely, the camera is installed in a mode that eyes are on hands, and the shooting position of the camera can be changed through the movement of the mechanical arm.
It should be noted that, in fig. 1, only one camera connected to the terminal is illustrated, and in the actual operation process, a plurality of cameras may be provided, so as to collect point cloud data on different skids or different planes to be detected of the cross beam in the skids respectively.
Referring to fig. 2, fig. 2 is a schematic flowchart of a method for detecting the flatness of a sled according to an embodiment of the present invention. As shown in fig. 2, the method is used for detecting the flatness of the skid, and the skid comprises a plurality of cross beams, wherein the cross beams are arranged at the top end of the skid in a mutually parallel posture. As shown in fig. 2, the method includes the following steps S110 to S150.
S110, collecting target point cloud data corresponding to each plane to be detected in each cross beam through a camera, wherein each cross beam comprises a plurality of planes to be detected.
In this embodiment, each cross beam is divided into a plurality of areas to be detected uniformly in advance, and the upper surface of the area to be detected (the surface in direct contact with the vehicle body) corresponds to the plane to be detected. The camera can acquire point cloud data corresponding to each plane to be detected, preprocesses the point cloud data and extracts features, and finally acquires target point cloud data of the plane to be detected for subsequent series of processing of the target point cloud data of the plane to be detected. The cameras can sequentially collect the target point cloud data of each plane to be detected, and a plurality of cameras can collect the target point cloud data of each plane to be detected.
In one embodiment, referring to FIG. 3, step S110 may include steps S111-S113:
s111, collecting first point cloud data of each plane to be detected through the camera.
The camera collects point cloud data of the plane to be detected, and actually obtains point clouds of all objects in the complete shooting area. Therefore, in the collected first point cloud data, besides the point cloud data corresponding to the plane to be detected, background point cloud and redundant noise points exist, and the background point cloud and the noise points are redundant points. The first point cloud data is required to be preprocessed, redundant points are removed, and accurate point cloud data of the plane to be detected can be obtained.
In one embodiment, the camera is mounted on a robotic arm that is movable in response to control instructions from the terminal. At this time, referring to fig. 4, step S111 includes:
s1111, sending a first motion instruction to the mechanical arm, wherein the first motion instruction instructs the mechanical arm to move the camera to a target position.
The camera is arranged on the mechanical arm in a manner that the eyes are on the hands, namely, the camera is fixed relative to the mechanical arm, and the movement of the mechanical arm drives the camera to change the position. The first movement instruction comprises a movement end point and a planning path of the mechanical arm, and after the mechanical arm receives the first movement instruction, the mechanical arm moves according to the movement end point and the planning path in the first movement instruction until the position of the camera is changed to be above the target position.
S1112, when the mechanical arm moves the camera to a target position, acquiring first point cloud data corresponding to a target to-be-detected plane by the camera, wherein the target to-be-detected plane is the to-be-detected plane corresponding to the first point cloud data acquired by the camera at the target position.
The target position is the position of the point cloud data which can be acquired and corresponds to a certain plane to be detected, and the camera can acquire first point cloud data on the target plane to be detected and corresponding to the target position at the target position. The target positions with the same relative positions can be set for each plane to be detected, namely, the shooting angles and shooting distances of the cameras at each target position relative to the corresponding target plane to be detected are the same, so that the data relevance among the collected first point cloud data is improved, and the efficiency of subsequent data processing is improved.
S1113, determining whether the first point cloud data of each plane to be detected are acquired; if yes, step S1115, if no, step S1114 is performed.
And controlling the camera to stop collecting the first point cloud data only when the target point cloud data of each plane to be detected are collected. Specifically, a number may be set for each plane to be detected, and when the first point cloud data of one target plane to be detected is acquired, the first point cloud data is stored as data with a corresponding number, and then the number may be checked to determine whether each first point cloud data has been acquired.
S1114, generating a second motion instruction, and returning to execute step S1111 by using the second motion instruction as the first motion instruction.
If the first point cloud data of the plane to be detected is not acquired, a second motion instruction can be generated according to the information of the plane to be detected, for which the first point cloud data is not acquired at present. Specifically, another plane to be detected closest to the previous target plane to be detected of the acquired target point cloud data can be used as a new target plane to be detected, the motion end point of the mechanical arm is set to be a target position corresponding to the new target plane to be detected, new path planning is performed at the same time, and a second motion instruction is generated according to the new motion end point and the path planning. After the second motion instruction is generated, the original first motion instruction is covered, so that the mechanical arm drives the camera to acquire first point cloud data of another plane to be detected.
S1115, determining that acquisition of the first point cloud data is completed.
When the first point cloud data of each plane to be detected is acquired, the current acquisition of the first point cloud data of each plane to be detected can be determined.
In this embodiment, when it is determined that the first point cloud data of each plane to be detected is collected, it is determined that the collection of the first point cloud data is completed.
In this embodiment, the mechanical arm drives the camera to move between each target position, collects the cloud data of the target points of each plane to be detected, and determines whether the collection is completed, so that the comprehensiveness and the order of the collection of the cloud data can be ensured.
And S112, removing redundant points in the first point cloud data based on a preset redundancy removal strategy to obtain second point cloud data corresponding to the first point cloud data respectively.
The preset redundancy removing strategy is a prestored algorithm strategy capable of removing redundancy points. Specifically, the preset redundancy removal policy may be gaussian bilateral filtering, straight-through filtering or a region-of-interest method.
Gaussian bilateral filtering is a nonlinear filtering method used for smoothing point cloud data while preserving edge information. The method calculates the weight of each point in the first point cloud data by combining the space distance and the color difference, thereby realizing the smoothing processing of the image or the point cloud data. The basic operation is to calculate, for each pixel or point, a weighted average of all points in its neighborhood as a new value for that pixel or point. The weights of the points consist of two parts: one part is a gaussian function based on spatial distance and the other part is a gaussian function based on color differences. Points with smaller color differences with closer spatial distances are weighted more heavily. The Gaussian bilateral filtering can effectively remove noise points in the point cloud data, and meanwhile edge information of the point cloud is reserved.
The through filtering is to set a threshold range and then remove points not in the range to realize the preprocessing of the first point cloud data. Which is typically used to limit the range of point cloud data in a certain axial direction. For example, a pass-through filter may be used to remove points in the first point cloud data for which the Z-axis coordinate is not within a specified range. In this way, points far away from the region of interest can be effectively removed, thereby improving the quality of the first point cloud data.
The region of interest (Region of Interest, ROI) is then a method for extracting a specific region in the first point cloud data. The preprocessing of the image or point cloud data is realized by setting a region of interest and then only preserving the data in the region. The ROI refers to a specific region in the image or point cloud data, which contains information of interest, i.e., specific information required. In preprocessing the first point cloud data, the ROI may be used to extract specific portions of the first point cloud data for further analysis and processing. The ROI may be defined by a variety of methods. For example, the ROI may be determined by manual selection, threshold segmentation, edge detection, and the like. After the ROI is determined, only the data within the ROI may be retained for further analysis and processing. The use of the ROI can effectively reduce the data volume and improve the efficiency of data processing. The method can make the interested target or feature get more attention, thereby improving the accuracy of the point cloud data analysis.
In summary, redundant points in the first point cloud data can be removed by presetting a redundancy removal policy, so as to obtain preprocessed second point cloud data, wherein the second point cloud data mainly comprises point cloud data corresponding to a plane to be detected.
S113, respectively extracting target point cloud clusters in the second point cloud data based on a preset region growth segmentation strategy, and determining the target point cloud clusters as the target point cloud data.
In this embodiment, the second point cloud data includes target point cloud data corresponding to the plane to be detected, but also includes some unnecessary miscellaneous point data, such as miscellaneous point data that is not in the range of the plane to be detected. In order to remove the remaining miscellaneous point data and obtain the final target point cloud data, a preset region growth segmentation strategy needs to be invoked. The preset region growing and dividing strategy is a point cloud data processing strategy based on region growing and dividing, and the region growing and dividing algorithm can combine point clouds with similarity to form a region. First, a seed point is found out for each region to be segmented and used as a starting point of growth, and then points with the same or similar properties as the seeds in the surrounding vicinity of the seed point are merged into the region where the seed point is located. And the new points continue to grow as seeds around until no more points meeting the condition can be included, and one point cloud area is grown.
The most main point cloud area grown in the second point cloud data is the point cloud area corresponding to the plane to be detected, and among unnecessary miscellaneous points, a part of the point cloud area cannot be grown into an effective point cloud area, and a part of the point cloud area is grown into a point cloud area smaller than the most main point cloud area. The largest point cloud area formed by growth in the second point cloud data is the target point cloud cluster, and the corresponding target point cloud data of the plane to be detected on the upper surface of the beam is the target point cloud cluster. Only the point cloud data corresponding to the surface of the beam is included in the target point cloud data, and background point cloud data and other existing miscellaneous point data are removed. Assuming that each cross beam is uniformly divided into three planes to be detected, the size of the area surrounded by the edges of the cloud data of the target point obtained by the three planes to be detected is the same, but the geometry coordinates and the intensity values of X, Y, Z corresponding to each point data are different, and the geometry coordinates and the intensity values of X, Y, Z of the point data also determine the plane equation corresponding to the cloud data of the target point.
S120, respectively determining a first plane equation of each target point cloud data according to a preset plane algorithm and each target point cloud data.
In this embodiment, the predetermined plane algorithm may be a RANSAC (Random Sample Consensus, random consensus sampling) algorithm. The RANSAC algorithm is generally used to estimate parameters of a mathematical model from observed data containing outliers. It is possible to fit the model by randomly selecting a subset of data and by iteration determine the best fit model. When applied in target point cloud data, the RANSAC algorithm basically operates as follows: for a given target point cloud data, a set of point data is randomly selected as the interior points, for example, three point data (three point data may determine a plane) may be selected from the target point cloud data as the interior points, and an initial plane equation may be fit using the interior points. Specifically, the coordinate data of three points can be used for fitting an initial plane equation, then the initial plane equation is tested by using the point data points remained in the target point cloud data, and the point data conforming to the initial plane equation are classified into a common identification set. Specifically, a consensus threshold may be set, and if the error between the point data and the preset plane equation is less than the consensus threshold, the point data may be classified into the consensus. If the number of points in the consensus set exceeds a preset threshold, the initial plane equation is considered to be more fit. The plane equation may then be re-fitted using all points in the consensus set to refine the plane equation. This process is repeated a number of times, each time a new plane equation is generated, and finally the plane equation with the best fitting degree is selected as the first plane equation. And determining the form of the plane to be detected corresponding to the cloud data of the current target point according to the finally fitted first plane equation so as to enable the subsequent flatness detection of the plane to be detected. Each piece of target point cloud data corresponds to a respective first plane equation, and the first plane equation can reflect the plane morphology of the plane to be detected to the greatest extent.
In an embodiment, referring to fig. 5, after determining the first plane equation of each target point cloud data, it is further required to determine whether the acquired target point cloud data meets a preset standard based on the first plane equation, and when the acquired target point cloud data meets the preset standard, the flatness detection may be performed using the target point cloud data (step S115 is executed), and when the acquired target point cloud data does not meet the preset standard, the target point cloud data needs to be re-acquired by the camera (step S110 is executed); the judging process specifically includes the following steps S310-S360:
s310, determining a first centroid of the target point cloud data according to the first plane equation.
From the first plane equation, a first centroid of a plane corresponding to the first plane equation may be determined. In this process, all point data in the target point cloud data are projected to a plane corresponding to the first plane equation. The specific projection operation is as follows: and determining X-axis and Y-axis information corresponding to each point, substituting the X-axis and Y-axis information corresponding to each point into a first plane equation, solving Z-axis data of a projection point corresponding to each point in the first plane equation, and replacing Z-axis data in original point data with Z-axis data of the projection point to obtain projection point coordinate data of each point data in the target point cloud data.
Then, according to each projection point data of the target point cloud data in the first plane equation, calculating an average value of coordinates of each projection point data to obtain coordinates of the first centroid. Specifically, assuming that there are N pieces of projection point data, the coordinates of each projection point data are (X i ，Y i ，Z i ) Where i=1, 2, …, N. The coordinates of the first centroid of the target point cloud data are (X c ，Y c ，Z c ) Wherein X is c ＝X 1 +X 2 +…+X N /N，Y c ＝Y 1 +Y 2 +…+Y N /N，Z c ＝Z 1 +Z 2 +…+Z N N. I.e. X of the first centroid c Coordinates are each projection point X i Average of coordinates, Y of first centroid c Coordinates are each projection point Y i Mean value of coordinates, Z of first centroid c The coordinate is each projection point Z i Average of coordinates.
S320, converting each first centroid from a camera coordinate system to a preset coordinate system to obtain a second centroid of each target point cloud data under the preset coordinate system.
When the camera collects the target point cloud data, the camera collects the target point cloud data of different planes to be detected at different positions, so that the obtained point cloud data at different positions are different. In order to synchronize the first centroid of each plane to be detected, the first centroid needs to be converted from the respective camera coordinate system into a preset coordinate system, and in particular, the first centroid can be converted by using a hand-eye matrix. The predetermined coordinate system is a predetermined unified coordinate system, and the origin thereof may be set on a fixed reference object, such as a beam. The first barycenters of the cloud data of the target points corresponding to the planes to be detected are all converted into a preset coordinate system, so that the first barycenters can be converted and operated in the same coordinate system. The first centroid with the camera coordinates is converted into a preset coordinate system, namely, the second centroid with the beam coordinates.
S330, respectively determining the connecting lines of the second centroids in the cross beams.
Since the area size included in each target point cloud data is the same, and each target point cloud data on the single beam actually corresponds to a uniformly axially divided area of the single beam, the areas corresponding to each target point cloud data are collinear, and therefore each second centroid corresponding to each target point cloud data in the single beam is collinear. Furthermore, the connecting line of the second mass center in each cross beam can be obtained, and the connecting line corresponding to each cross beam is obtained. Wherein, the connecting line corresponding to each beam represents the extending direction corresponding to each beam.
S340, judging whether the maximum included angle between the connecting lines is larger than a preset included angle threshold value; if yes, step S350 is executed, and if no, step S360 is executed.
The preset included angle threshold is a preset threshold, which represents the included angle of the beams fixedly arranged, and optionally, the preset included angle threshold can be set to be a smaller threshold of 0 degrees and the like. Since the number of the cross beams can be multiple, multiple included angles can exist between the multiple connecting lines. And selecting the maximum included angle for comparison, and obtaining the maximum difference value between the maximum included angle and a preset included angle threshold value, so that the most accurate comparison result can be ensured.
S350, re-acquiring target point cloud data through a camera.
In this embodiment, when it is determined that the maximum included angle between the connecting lines is greater than the preset included angle threshold, the cloud data of the target point is re-acquired through the camera, that is, the step S110 is executed again.
Specifically, if the maximum included angle between the connecting lines is greater than the preset included angle threshold, it is indicated that an error point exists in the second centroid obtained at this time, and the relationship of the included angles between the beams cannot be truly reflected. At this time, the cloud data of the target point of each plane to be detected in each beam needs to be acquired again to remove errors.
S360, flatness detection is conducted by using the cloud data of the target points.
That is, when the maximum included angle is smaller than or equal to the preset included angle threshold, determining the flatness coefficient of the sled according to the angle difference value between each normal vector and the Z-axis quantity.
Specifically, if the maximum included angle of the connecting line is smaller than or equal to the preset included angle threshold, it can be determined that the second centroid at this time can truly reflect the included angle relationship between the measurements, which is the second centroid corresponding to the accurately obtained target point cloud data, and further, the obtained target point cloud data can be used for subsequent flatness calculation operation.
In this embodiment, by comparing the included angle of the connecting line of the second centroid to perform error judgment on the acquisition of the cloud data of the target point, the acquired cloud data of the target point can be ensured to be correct point cloud data, and errors occurring during the conversion of the coordinate system can be avoided.
S130, converting each first plane equation from a camera coordinate system to a preset coordinate system to obtain a second plane equation of each target point cloud data under the preset coordinate system.
In this embodiment, when the camera collects the target point cloud data, it collects the target point cloud data of different planes to be detected at different positions, so the obtained point cloud data at different positions are different. In order to synchronize the first plane equation of each plane to be detected, the first plane equation needs to be converted from the respective camera coordinate system into a preset coordinate system, and the conversion can be specifically performed by using a hand-eye matrix. The preset coordinate system is a preset unified coordinate system, and the origin of the preset unified coordinate system can be arranged on a fixed reference object, such as a cross beam or a mechanical arm. The first plane equation of the target point cloud data corresponding to each plane to be detected is converted into a preset coordinate system, so that the first plane equation can be converted and operated in the same coordinate system. The first plane equation with the camera coordinates is converted into a preset coordinate system, and then converted into the second plane equation with the beam coordinates.
In one embodiment, referring to FIG. 6, step S130 may include steps S131-S134:
s131, acquiring a hand-eye matrix between a camera coordinate system and a preset coordinate system.
The hand-eye matrix describes the relationship between the camera coordinate system and the preset coordinate system. The preset coordinate system may be a robot coordinate system, which represents a fixed coordinate system corresponding to the movement of the robot, rather than a camera coordinate system that is constantly changing. Because the camera and the mechanical arm are connected in an eye-on-hand mode, the hand-eye matrix can be determined through a calibration method. The calibration process typically includes the following steps: first, a calibration plate, which is a plate with a special pattern, is prepared, which can be used to determine the spatial relationship between the camera and the robot arm. Secondly, shooting calibration pictures by using a camera, placing a calibration plate at the tail end of the mechanical arm before shooting, and then shooting a plurality of calibration pictures with different angles by using the camera. Then, the characteristic points in the calibration picture are extracted, and specifically, the characteristic points can be extracted from the calibration picture by using a computer vision algorithm, and the characteristic points are usually corner points or circle centers on the calibration plate. Finally, the hand-eye matrix may be calculated according to the feature points, and in particular, may be calculated according to the extracted feature points and motion information (including translation and rotation) of the mechanical arm, using an optimization algorithm such as Tsai-Lenz algorithm and Horaud algorithm. The process can determine the relation between the camera coordinate system and the mechanical arm coordinate system, so that coordinate system conversion of the target point cloud data is realized. In addition, there are a variety of hand-eye matrix determination methods that have proven effective, and the present invention is not limited.
And S132, regarding each first plane equation, taking at least three point data which are not collinear with each other in the first plane equation as a conversion point data set of the first plane equation respectively.
For each first plane equation, at least three point data which are not collinear with each other in the first plane equation can be selected, and then the point data are used as conversion point data sets, and each first plane equation corresponds to a respective conversion point data set. The point data in the conversion point data sets can directly determine a unique first plane equation, so that if the coordinate transformation is performed on the point data in the conversion point data sets, the transformed conversion point data sets can still determine a unique first plane equation.
And S133, performing matrix multiplication operation on camera coordinates of the conversion point data sets in the camera coordinate system according to the hand-eye matrix to obtain beam coordinates of the conversion point data sets in the preset coordinate system.
According to the hand-eye matrix, matrix multiplication operation is carried out on the camera coordinates of the point data in each conversion point data set, so that the beam coordinates of the point data in each conversion point data set can be obtained respectively. Specifically, the hand-eye matrix is a homogeneous transformation matrix of 4*4, and for each point data, it is assumed that the camera coordinates of the point data are (X 1 ，Y 1 ，Z 1 ) In the transformation, it is necessary to convert it into homogeneous form of coordinates, i.e. (X) 1 ，Y 1 ，Z 1 ,1). Then, matrix multiplication is performed on the homogeneous coordinates of the point data to obtain converted homogeneous coordinates (X w ，Y w ，Z w W), and then dividing the converted homogeneous coordinates by W to obtain converted beam coordinates (X w /W，Y w /W，Z w /W). The coordinate conversion of the first plane equation can be achieved by performing coordinate conversion on the point data in the conversion point data set.
S134, determining second plane equations corresponding to the first plane equations respectively according to the beam coordinates.
According to the beam coordinates of the point data in the converted conversion point data set, a second plane equation can be determined in a preset coordinate system, and each second plane equation has the same plane morphology corresponding to the first plane equation, and the difference is only that the coordinate system in which the second plane equation is positioned is different.
In this embodiment, the second plane equations corresponding to the cloud data of the multiple target points are set in the same coordinate system, so that mutual comparison of the multiple second plane equations can be realized, and a basis is provided for subsequent flatness measurement.
S140, determining the Z-axis vector of the cross beam according to the normal vector of each second plane equation.
In this embodiment, the Z-axis vector corresponding to the beam may be determined by the normal vector of the second plane equation, where the Z-axis vector of the reference coordinate system is the Z-axis vector of the coordinate system of the plane in which the upper surface of the beam is located, and the plane determined by the X-axis and the Y-axis in the reference coordinate system is the plane in which each plane to be detected is approximately located, which cannot accurately encapsulate each plane to be detected therein, but is only one plane for reference. The Z-axis vector is the normal vector of the plane determined by the X-axis and the Y-axis in the reference coordinate system.
In one embodiment, step S140 specifically includes: according to each second plane equation, calculating to obtain the normal vector of each second plane equation; and carrying out normal vector average calculation on the normal vector of each second plane equation to obtain the Z-axis vector.
In this embodiment, the normal vector of each second plane equation may be calculated first, and then the average value of each normal vector may be solved, and the average value may be used as the Z-axis vector of the reference coordinate system. Since the upper surface of the beam is not a definite plane, the plane equation cannot be obtained, and therefore, the Z-axis vector of the reference coordinate system can be determined through the normal vector average calculation of each second plane equation. The Z-axis vector is only one reference value, is used for reflecting the normal vector of the plane where each plane to be detected is approximately located, and is used as reference data for flatness detection. That is, the Z-axis vector is determined, and the reference coordinate system is determined.
S150, determining the flatness coefficient of the skid according to the angle difference value between each normal vector and the Z-axis quantity.
In this embodiment, the reference plane defined by the X-axis and the Y-axis in the reference coordinate system represented by the Z-axis vector may be coplanar or non-coplanar with the plane represented by each second plane equation, and thus there may be different angle differences between the Z-axis vector and the normal vector of the second plane equation. These angle differences can be used to characterize the degree of deviation of the plane represented by the second plane equation from the reference plane, the greater the respective angle difference, the greater the deviation of the plane represented by the second plane equation from the reference plane, and the worse the flatness. Conversely, the smaller the difference of each angle is, the smaller the deviation between the plane represented by the second plane equation and the reference plane is, and the better the flatness is.
In one embodiment, the step S150 specifically includes: acquiring each angle difference value between each normal vector and each Z-axis vector; and determining an average angle difference value between each normal vector and the Z-axis quantity according to each angle difference value, and taking the average angle difference value as the flatness coefficient.
In this embodiment, the average angle difference value is calculated by averaging, so that an average angle difference value can be obtained, and the average angle difference value can be used as a flatness coefficient, and the flatness coefficient can represent the comprehensive flatness of the cross beam, and further represents the flatness of the skid. Wherein, the magnitude of the flatness coefficient is in direct proportion to the flatness of the skid.
Therefore, the embodiment of the invention performs non-contact photographing on the cross beam in the skid by using the camera and generates the three-dimensional point cloud, then performs fitting of a plane equation on a plane to be detected by the three-dimensional point cloud, and finally calculates the flatness coefficient of the skid according to the plane equation fitted in the point cloud and the deviation of the normal vector thereof, thereby realizing non-contact measurement on the flatness of the skid, improving the testing precision of the flatness of the skid, improving the testing efficiency of the flatness of the skid, and improving the safety and reliability of skid transportation in an automobile production line.
Referring to fig. 7, fig. 7 is a schematic block diagram of a skid flatness detecting device 70 according to an embodiment of the invention. As shown in fig. 7, the present invention further provides a skid flatness detecting device 70 corresponding to the above method for detecting the flatness of a skid. The device comprises a unit for executing the skid flatness detection method, and the device can be configured in a terminal or a server, wherein the terminal can be a desktop computer, a tablet computer, a portable computer, an operation terminal of a PLC system and the like. Specifically, referring to fig. 7, the skid flatness detecting device 70 includes an acquisition unit 71, a first determining unit 72, a conversion unit 73, a second determining unit 74, and a third determining unit 75.
The acquisition unit 71 is used for acquiring target point cloud data corresponding to each plane to be detected in each beam through a camera;
a first determining unit 72, configured to determine a first plane equation of each target point cloud data according to a preset plane algorithm and each target point cloud data;
a conversion unit 73, configured to convert each of the first plane equations from a camera coordinate system to a preset coordinate system, to obtain a second plane equation of each of the target point cloud data in the preset coordinate system;
a second determining unit 74 for determining a Z-axis vector of the reference coordinate system according to the normal vector of each of the second plane equations;
a third determining unit 75, configured to determine a flatness coefficient of the sled according to an angle difference between each normal vector and the Z-axis amount.
In an embodiment, the acquisition unit 71 is further configured to:
collecting first point cloud data of each plane to be detected through the camera;
removing redundant points in the first point cloud data based on a preset redundancy removal strategy to obtain second point cloud data corresponding to the first point cloud data respectively;
and respectively extracting target point cloud clusters in the second point cloud data based on a preset region growth segmentation strategy, and determining the target point cloud clusters as the target point cloud data.
In an embodiment, the conversion unit 73 is further configured to:
calibrating a hand-eye matrix between a camera coordinate system and a preset coordinate system;
for each first plane equation, respectively taking at least three point data which are not collinear with each other in the first plane equation as a conversion point data set of the first plane equation;
according to the hand-eye matrix, performing matrix multiplication operation on camera coordinates of each conversion point data set in the camera coordinate system to obtain beam coordinates of each conversion point data set in the preset coordinate system;
and determining a second plane equation corresponding to each first plane equation according to each beam coordinate.
In an embodiment, the second determining unit 74 is further configured to:
according to each second plane equation, calculating to obtain the normal vector of each second plane equation;
and carrying out normal vector average calculation on the normal vector of each second plane equation to obtain the Z-axis vector.
In an embodiment, the third determining unit 75 is further configured to:
acquiring each angle difference value between each normal vector and each Z-axis vector;
and determining an average angle difference value between each normal vector and the Z-axis quantity according to each angle difference value, and taking the average angle difference value as the flatness coefficient.
In one embodiment, the skid flatness detection apparatus 70 further includes a monitoring unit for:
determining a first centroid according to the first plane equation;
converting each first centroid from a camera coordinate system to a preset coordinate system to obtain a second centroid of each target point cloud data under the preset coordinate system;
determining the connecting line of the second mass centers in the cross beams respectively;
if the maximum included angle between the connecting lines is greater than the preset included angle threshold value, returning to the start acquisition unit 71;
if the maximum included angle is smaller than or equal to the preset included angle threshold, the third determining unit 75 is started.
In one embodiment, the skid flatness detection device 70 further comprises a control unit for:
sending a first motion instruction to the mechanical arm, wherein the first motion instruction instructs the mechanical arm to move the camera to a target position;
when the mechanical arm moves the camera to a target position, collecting target point cloud data corresponding to a target to-be-detected plane through the camera, wherein the target to-be-detected plane is a to-be-detected plane corresponding to the target point cloud data collected by the camera at the target position;
Determining whether the cloud data of the target point of each plane to be detected are acquired;
if the target point cloud data of the planes to be detected are not acquired, generating a second motion instruction, taking the second motion instruction as the first motion instruction, and returning to execute the step of sending the first motion instruction to the mechanical arm until the target point cloud data of each plane to be detected are acquired.
It should be noted that, as will be clearly understood by those skilled in the art, the specific implementation process of the above-mentioned skid flatness detection device 70 and each unit may refer to the corresponding descriptions in the foregoing method embodiments, and for convenience and brevity of description, the description is omitted here.
The skid flatness detection means described above may be implemented in the form of a computer program which can be run on a computer device as shown in fig. 8.
Referring to fig. 8, fig. 8 is a schematic block diagram of a computer device 800 according to an embodiment of the present invention. The computer device can be a terminal or a server, wherein the terminal can be an electronic device with an image display function, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, a wearable device and the like. The server may be an independent server or a server cluster formed by a plurality of servers.
With reference to FIG. 8, the computer device 800 includes a processor 802 and a memory and network interface 805 connected by a system bus, wherein the memory may include a storage medium 803 and an internal memory 804.
The storage medium 803 may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform a method for detecting the flatness of a sled.
The processor 802 is used to provide computing and control capabilities to support the operation of the overall computer device 800.
The internal memory 804 provides an environment for the execution of a computer program 8032 in the storage medium 803, which when executed by the processor 802, causes the processor 802 to perform a method for detecting the flatness of a sled.
The network interface 805 is used for network communication with other devices. It will be appreciated by those skilled in the art that the architecture shown in fig. 8 is merely a block diagram of some of the architecture associated with the present inventive arrangements and is not limiting of the computer device 800 to which the present inventive arrangements may be applied, and that a particular computer device 800 may include more or less components than those shown, or may combine some of the components, or have a different arrangement of components.
Wherein the processor 802 is configured to execute a computer program 8032 stored in the memory, so as to implement the following steps:
collecting target point cloud data corresponding to each plane to be detected in each cross beam through a camera, wherein each cross beam comprises a plurality of planes to be detected;
respectively determining a first plane equation of each target point cloud data according to a preset plane algorithm and each target point cloud data;
converting each first plane equation from a camera coordinate system to a preset coordinate system to obtain a second plane equation of each target point cloud data under the preset coordinate system;
determining a Z-axis vector of a reference coordinate system according to the normal vector of each second plane equation;
and determining the flatness coefficient of the skid according to the angle difference value between each normal vector and the Z-axis quantity.
It should be appreciated that in embodiments of the invention, the processor may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Those skilled in the art will appreciate that all or part of the flow in a method embodying the above described embodiments may be accomplished by computer programs instructing the relevant hardware. The computer program comprises program instructions, and the computer program can be stored in a storage medium, which is a computer readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present invention also provides a storage medium. The storage medium may be a computer readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. The program instructions, when executed by the processor, cause the processor to perform the steps of:
collecting target point cloud data corresponding to each plane to be detected in each cross beam through a camera, wherein each cross beam comprises a plurality of planes to be detected;
respectively determining a first plane equation of each target point cloud data according to a preset plane algorithm and each target point cloud data;
converting each first plane equation from a camera coordinate system to a preset coordinate system to obtain a second plane equation of each target point cloud data under the preset coordinate system;
Determining a Z-axis vector of a reference coordinate system according to the normal vector of each second plane equation;
and determining the flatness coefficient of the skid according to the angle difference value between each normal vector and the Z-axis quantity.
The storage medium may be a U-disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, or other various computer-readable storage media that can store program codes.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the device embodiments described above are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be combined, divided and deleted according to actual needs. In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The integrated unit may be stored in a storage medium if implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a terminal, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. A method for detecting flatness of a skid, the skid comprising a plurality of beams, the method comprising:
collecting target point cloud data corresponding to each plane to be detected in each cross beam through a camera, wherein each cross beam comprises a plurality of planes to be detected;
respectively determining a first plane equation of each target point cloud data according to a preset plane algorithm and each target point cloud data;
converting each first plane equation from a camera coordinate system to a preset coordinate system to obtain a second plane equation of each target point cloud data under the preset coordinate system;
determining a Z-axis vector of a reference coordinate system according to the normal vector of each second plane equation;
and determining the flatness coefficient of the skid according to the angle difference value between each normal vector and the Z-axis quantity.
2. The method for detecting the flatness of a sled according to claim 1, wherein the capturing, by a camera, cloud data of target points corresponding to each plane to be detected in each beam includes:
collecting first point cloud data of each plane to be detected through the camera;
Removing redundant points in the first point cloud data based on a preset redundancy removal strategy to obtain second point cloud data corresponding to the first point cloud data respectively;
and respectively extracting target point cloud clusters in the second point cloud data based on a preset region growth segmentation strategy, and determining the target point cloud clusters as the target point cloud data.
3. The method of claim 2, wherein the camera is mounted on a robotic arm; the collecting, by the camera, first point cloud data of each plane to be detected includes:
sending a first motion instruction to the mechanical arm, wherein the first motion instruction instructs the mechanical arm to move the camera to a target position;
when the mechanical arm moves the camera to a target position, acquiring first point cloud data corresponding to a target to-be-detected plane by the camera, wherein the target to-be-detected plane is the to-be-detected plane corresponding to the first point cloud data acquired by the camera at the target position;
determining whether the first point cloud data of each plane to be detected are acquired;
if the first point cloud data of the planes to be detected are not all acquired, generating a second motion instruction, taking the second motion instruction as the first motion instruction, and returning to execute the step of sending the first motion instruction to the mechanical arm until the first point cloud data of each plane to be detected are all acquired.
4. The method for detecting the flatness of a sled according to claim 1, wherein the converting each of the first plane equations from a camera coordinate system to a preset coordinate system to obtain a second plane equation of each of the target point cloud data in the preset coordinate system includes:
calibrating a hand-eye matrix between a camera coordinate system and a preset coordinate system;
for each first plane equation, respectively taking at least three point data which are not collinear with each other in the first plane equation as a conversion point data set of the first plane equation;
according to the hand-eye matrix, performing matrix multiplication operation on camera coordinates of each conversion point data set in the camera coordinate system to obtain beam coordinates of each conversion point data set in the preset coordinate system;
and determining a second plane equation corresponding to each first plane equation according to each beam coordinate.
5. The method for detecting the flatness of a sled according to claim 1, wherein the determining the Z-axis vector of the preset coordinate system according to the normal vector of each of the second plane equations comprises:
according to each second plane equation, calculating to obtain the normal vector of each second plane equation;
And carrying out normal vector average calculation on the normal vector of each second plane equation to obtain the Z-axis vector.
6. The method of claim 1, wherein determining the flatness coefficient of the sled based on the angle difference between each normal vector and the Z-axis amount comprises:
acquiring each angle difference value between each normal vector and each Z-axis vector;
and determining an average angle difference value between each normal vector and the Z-axis quantity according to each angle difference value, and taking the average angle difference value as the flatness coefficient.
7. The method for detecting the flatness of a sled according to any one of claims 1-6, wherein after calculating the first plane equation of each target point cloud data according to each target point cloud data, further comprises:
determining a first centroid of the target point cloud data according to the first plane equation;
converting each first centroid from a camera coordinate system to a preset coordinate system to obtain a second centroid of each target point cloud data under the preset coordinate system;
determining the connecting line of the second mass centers in the cross beams respectively;
If the maximum included angle between the connecting lines is larger than a preset included angle threshold value, returning to execute the step of collecting target point cloud data corresponding to each plane to be detected in each cross beam through a camera;
the determining the flatness coefficient of the sled according to the angle difference between each normal vector and the Z-axis quantity comprises the following steps:
and if the maximum included angle is smaller than or equal to the preset included angle threshold, determining the flatness coefficient of the skid according to the angle difference value between each normal vector and the Z-axis quantity.
8. The utility model provides a skid roughness detection device, its characterized in that, skid roughness detection device is used for detecting the roughness of skid, the skid includes many crossbeams, skid roughness detection device includes:
the acquisition unit is used for acquiring target point cloud data corresponding to each plane to be detected in each cross beam through a camera, and each cross beam comprises a plurality of planes to be detected;
the first determining unit is used for determining a first plane equation of each target point cloud data according to a preset plane algorithm and each target point cloud data;
the conversion unit is used for converting each first plane equation from a camera coordinate system to a preset coordinate system to obtain a second plane equation of each target point cloud data under the preset coordinate system;
The second determining unit is used for determining a Z-axis vector of the preset coordinate system according to the normal vector of each second plane equation;
and the third determining unit is used for determining the flatness coefficient of the skid according to the angle difference value between each normal vector and the Z-axis quantity.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of detecting the flatness of a sled according to any of claims 1-7 when executing the computer program.
10. A computer readable storage medium, characterized in that the storage medium stores a computer program comprising program instructions that, when executed by a processor, cause the processor to perform the method of skid flatness detection as claimed in any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310647935.8A CN116697940A (en) | 2023-06-01 | 2023-06-01 | Skid flatness detection method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310647935.8A CN116697940A (en) | 2023-06-01 | 2023-06-01 | Skid flatness detection method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116697940A true CN116697940A (en) | 2023-09-05 |
Family
ID=87840436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310647935.8A Pending CN116697940A (en) | 2023-06-01 | 2023-06-01 | Skid flatness detection method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116697940A (en) |
-
2023
- 2023-06-01 CN CN202310647935.8A patent/CN116697940A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7327857B2 (en) | Non-contact measurement method and apparatus | |
| JP5671281B2 (en) | Position / orientation measuring apparatus, control method and program for position / orientation measuring apparatus | |
| EP2416113B1 (en) | Position and orientation measurement apparatus and position and orientation measurement method | |
| US8103376B2 (en) | System and method for the on-machine 2-D contour measurement | |
| US20160203387A1 (en) | Vision system and analytical method for planar surface segmentation | |
| EP2551633B1 (en) | Three dimensional distance measuring device and method | |
| WO2020168685A1 (en) | Three-dimensional scanning viewpoint planning method, device, and computer readable storage medium | |
| Wu et al. | A novel high precise laser 3D profile scanning method with flexible calibration | |
| US20230267593A1 (en) | Workpiece measurement method, workpiece measurement system, and program | |
| CN108133477A (en) | A kind of object detecting method and intelligent machine arm | |
| JP7353757B2 (en) | Methods for measuring artifacts | |
| JP5976089B2 (en) | Position / orientation measuring apparatus, position / orientation measuring method, and program | |
| Lee et al. | Development of laser-vision system for three-dimensional circle detection and radius measurement | |
| US20220148153A1 (en) | System and method for extracting and measuring shapes of objects having curved surfaces with a vision system | |
| CN116579955B (en) | New energy battery cell weld reflection point denoising and point cloud complement method and system | |
| CN117372489A (en) | Point cloud registration method and system for double-line structured light three-dimensional measurement | |
| CN112016354B (en) | Method for detecting loading state of grain tank of grain transporting vehicle based on visual identification | |
| CN116697940A (en) | Skid flatness detection method and device, computer equipment and storage medium | |
| CN114862969A (en) | Onboard holder camera angle self-adaptive adjusting method and device of intelligent inspection robot | |
| CN105783782B (en) | Surface curvature is mutated optical profilometry methodology | |
| Lourenço et al. | Extrinsic calibration of 2D laser range finders using planar features | |
| Owczarek et al. | Examination of optical coordinate measurement systems in the conditions of their operation | |
| Spence et al. | Automotive sheet metal and grid digitizing solutions | |
| CN117173376B (en) | Mobile track planning method and system for medical equipment | |
| Uyanik et al. | A method for determining 3D surface points of objects by a single camera and rotary stage |
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 |