KR102437913B1 - Shape separating system with 3-dimensional shape measurement and cad design information - Google Patents

Abstract

A shape classification system through quantitative comparison of 3D shape measurement results and CAD design data is disclosed. A shape classification method according to an embodiment includes: acquiring shape data of a 3D object using a 3D modeling technique; obtaining measurement data measured using a three-dimensional measurement technology; and comparing and analyzing the obtained shape data of the 3D object and the obtained measurement data based on a least squares method to determine a degree of similarity to the shape of the 3D object.

Description

[SHAPE SEPARATING SYSTEM WITH 3-DIMENSIONAL SHAPE MEASUREMENT AND CAD DESIGN INFORMATION]

The following description relates to a technology for product recognition and classification required in an industrial automation process, and relates to a method and system for judging and classifying the shape of a product by comparing and analyzing the measured three-dimensional measurement result and the designed drawing information. .

With the development of the 4D industry, automation of the production process is rapidly developing. A three-dimensional measurement system, such as a three-dimensional laser scanning technique, is widely applied to determine the shape of a created product. In order to determine and classify products produced in an automated process, it is necessary to compare and analyze the measurement data of the object and the design data. It takes a lot of time and money to make an optimal decision with a large amount of data with a lot of external conditions such as 3D, rotation, and movement.

Accordingly, an algorithm for matching, determining, and optimizing measurement data and design data is required.

Based on the observation position of the measurement system, the predicted data map for various shapes of the object is formed using the observation equation, and the optimal shape is found and analyzed through the mapping function between the measurement data and the predicted data. It is possible to provide a shape classification system and method for improving the degree and time of comparative analysis and discrimination.

In order to clearly determine the object in the automated process, to produce a three-dimensional map of various states that can be measured from the design data of the object, and to improve the performance with the calculation speed of object identification and classification through measurement data and comparative analysis A shape classification system and method may be provided.

The shape classification method performed by the shape classification system includes: acquiring shape data of a 3D object using a 3D modeling technique; obtaining measurement data measured using a three-dimensional measurement technology; and comparing and analyzing the obtained shape data of the 3D object and the obtained measurement data based on a least squares method to determine a degree of similarity to the shape of the 3D object.

The obtaining of the shape data includes converting the shape data obtained by designing the shape of the object using a modeling tool into a VRML format, and observing the converted shape data in the VRML format to match the measurement surface of the measurement system. It may include generating 3D mapping data according to the location.

The obtaining of the shape data includes obtaining each plane information by converting it into the VRML-based point format, and collecting observable plane information using the observation equation of the measurement system to generate 3D mapping data. may include the step of

The acquiring of the measurement data includes acquiring the measurement data through a three-dimensional measurement technique including a stereo vision of a measurement system or a laser scanning technique, and obtaining a feature point for the shape of a three-dimensional object from the obtained measurement data. may include steps.

The obtained measurement data may refer to 3D surface information data for a shape of a 3D object from which an error is removed using an error removal algorithm including a medium filter and background information is removed.

The determining of the degree of similarity includes moving the center using the obtained shape data and the average value of the obtained measurement data to match the center, and based on the matched center, the obtained shape data and the It may include determining the agreement information of the obtained measurement data using the least squares method using the principle of affine transformation of shape analysis.

The shape classification system includes: a shape data acquisition unit configured to acquire shape data of a 3D object using a 3D modeling technique; a measurement data acquisition unit that acquires measurement data measured using a three-dimensional measurement technology; and a determination unit configured to compare and analyze the obtained shape data of the 3D object and the obtained measurement data based on the least squares method to determine the degree of similarity to the shape of the 3D object.

The shape data acquisition unit converts the shape data obtained by designing the shape of the object using a modeling tool into a VRML format, and converts the shape data in the converted VRML format according to an observation position that matches the measurement surface of the measurement system. 3D mapping data can be generated.

The shape data acquisition unit acquires each plane information as it is converted into the VRML-based point format, and collects observable plane information using the observation equation of the measurement system to generate 3D mapping data. .

The measurement data acquisition unit may acquire measurement data through a three-dimensional measurement technique including stereo vision of a measurement system or a laser scanning technique, and acquire feature points for the shape of a three-dimensional object from the obtained measurement data.

The obtained measurement data may refer to 3D surface information data for a shape of a 3D object from which an error is removed using an error removal algorithm including a medium filter and background information is removed.

The determination unit, using the obtained shape data and the average value of the obtained measurement data to execute a center movement to match the center, based on the matched center, the obtained shape data and the obtained measurement data The matching information can be determined using the least squares method using the principle of affine transformation of shape analysis.

High-speed automation performance in the production process by analyzing the data acquired from the measurement system and data generation algorithm that transforms 3D data by applying the observation equation of the measurement system from CAD data, and searching for the optimal mapping map to perform classification and judgment can contribute to improvement.

1 is a view for explaining an operation of a shape classification system according to an embodiment.
2 is a diagram illustrating plane information obtained after converting 3D modeled shape data into VRML in a shape classification system according to an embodiment.
3 is a block diagram for explaining the configuration of a shape classification system according to an embodiment.
4 is a flowchart illustrating a shape classification method in a shape classification system according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings.

In order to acquire and classify the shape of an object passing at a high speed in a high-speed automation system, it is necessary to analyze and judge the data that fits the model at a high speed. However, the three-dimensional shape is complicated, and a lot of errors and time are consumed in determining the object according to the shape and position on which the object is placed. Accordingly, in the embodiment, the shape of a three-dimensional object is obtained from design data designed by a three-dimensional modeling technique such as CAD, and the data measured by stereo vision or three-dimensional measurement technology is directly compared and analyzed to the degree of similarity of the three-dimensional shape. The technique for judging will be described.

1 is a view for explaining an operation of a shape classification system according to an embodiment.

Data obtained by determining the shape of a three-dimensional object produced by a three-dimensional modeling tool for various situations (eg, rotation and movement) that can exist in an actual industrial site, and converting it into an observable form from the observation equation of the measurement system You can create maps. The three-dimensional data measured at the industrial site is compared and analyzed with various data maps, and the optimal shape can be determined and the object can be judged or classified therefrom.

The shape classification system consists of a process of processing a three-dimensional object produced by a three-dimensional modeling tool, a process of processing actual measurement data, and a process of discriminating an object through comparative analysis of two data.

After the shape classification system converts the shape data produced by the modeling tool into VRML format data, it can rotate and move the data according to the measurement shape of the measurement system. In this case, the modeling tool may refer to a tool capable of a 3D modeling technique such as 3D CAD. The shape classification system may acquire shape data (3D CAD Data) 101 for a 3D object from design data designed through a 3D modeling technique such as 3D CAD.

The shape classification system may generate 3D mapping data from the shape data using the observation equation of the camera (102). The shape classification system can convert the rotated and moved data into 3D mapping data from the shape data using the observation equation determined by the metrology system. In this case, the measurement system is a system for measuring a three-dimensional object, and can actually measure a component, a size, a position, a shape, and the like of the three-dimensional object.

FIG. 2 is a diagram illustrating information about each plane obtained after converting 3D modeled shape data into VRML in the shape classification system according to an embodiment. 3D mapping data can be generated by collecting the information of the observable surface from the observation equation of the metrology system by using the edge search and the collection vector equation of the surface in each plane information. In other words, the 3D modeled shape data may be transformed into a VRML-based point format. 3D mapping data may be generated so that the transformed data corresponds to various observation positions (eg, top, bottom, left, and right) matching the measurement surface according to the 3D measurement system. For example, the 3D mapping data may define a possible rotation angle of the object, and may be generated as data corresponding to the rotation angle.

Various camera observation equations exist, and the observation equations used in the examples are as follows.

,

,

는 2차항까지 고려한 영상의 굴절량이다. Here, x and y are the image coordinate system, and X, Y, and Z are the object coordinate system. C _x , C _y represents the proportion of the image coordinate system and the object coordinate system, dis is the distance between the camera center and the object coordinate system point O, m _x , m _y are the offset amounts of the central axis, and the subscript m means rotation. That is, (X _m , Y _m , Z _m ) is a three-dimensional rotation of (X, Y, Z).

is the amount of refraction of the image considering up to the second term.

The shape classification system may acquire 3D measurement data using stereo vision or 3D measurement technology (111). The shape classification system may acquire feature points in consideration of the shape of the object ( 112 ). The measurement data may refer to 3D surface information data of an object in which an error is removed by using an error removal algorithm such as a medium filter and background information is removed.

The shape classification system can compare and analyze the feature points of the three-dimensional mapping data and the measurement data through a mapping function (103). The shape classification system forms a predicted data map for various shapes of an object using an observation equation based on the observation position of the measurement system, and searches for and analyzes the optimal shape through a mapping function between the measurement data and the predicted data. The degree of similarity of the dimensional object (measurement object) may be determined.

In detail, the shape classification system uses the average value of each of the measurement data and the three-dimensional mapping data to move the centers to match the centers, and to determine the coincidence information of the two data whose centers are matched using the least squares method. can At this time, the least-squares method is generally used to quantitatively grasp the causal relationship when a functional relationship exists between any two economic variables x and y. When a reference variable is predicted by a linear assumption as one or more predictive variables, it is a standard that minimizes the sum of the squares of the distance between the actual reference variable and the reference variable predicted by the linear assumption. In the embodiment, the least-squares method using the principle of affine transformation, which is a three-dimensional shape analysis using data comparison analysis, may be applied.

The shape classification system may determine and classify the shape based on the best matching modeling result through error analysis as the comparative analysis is performed ( 104 ). For example, the shape classification system may perform error analysis by finding an optimal solution based on a database storing information related to the object.

In order to obtain a high degree of result, the shape classification system may perform an introspection method with the optimal information derived by the least-squares method to obtain information on object identification, rotation and movement of the object, and output the obtained information.

3 is a block diagram for explaining the configuration of a shape classification system according to an embodiment, and FIG. 4 is a flowchart for explaining a shape classification method in the shape classification system according to an embodiment.

The processor of the shape classification system 100 may include a shape data acquisition unit 310 , a measurement data acquisition unit 320 , and a determination unit 330 . The components of the processor may be representations of different functions performed by the processor according to a control instruction provided by a program code stored in the shape classification system. The processor and components of the processor may control the shape classification system to perform steps 410 to 430 included in the shape classification method of FIG. 4 . In this case, the processor and the components of the processor may be implemented to execute instructions according to the code of the operating system included in the memory and the code of at least one program.

The processor may load the program code stored in the file of the program for the shape classification method into the memory. For example, when a program is executed in the shape classification system, the processor may control the shape classification system to load the program code from the program file into the memory according to the control of the operating system. At this time, each of the shape data acquisition unit 310 , the measurement data acquisition unit 320 , and the determination unit 330 executes a command of a corresponding part of the program code loaded in the memory to execute subsequent steps 410 to 430 . may be different functional representations of a processor for

In step 410 , the shape data acquisition unit 310 may acquire shape data of a 3D object using a 3D modeling technique. The shape data acquisition unit 310 converts the shape data obtained by designing the shape of the object using a modeling tool into a VRML format, and places the converted VRML format shape data at an observation position that matches the measurement surface of the measurement system. Accordingly, 3D mapping data can be generated. In other words, it is possible to generate 3D mapping data by collecting only observable data from the observation position using the VRML format shape data again using the surface format. In this case, the 3D mapping data may refer to data obtained by modeling a 3D surface of a 3D object (object). The shape data acquisition unit 310 acquires each plane information by converting it into a VRML-based point format, and collects observable plane information using the observation equation of the measurement system to generate 3D mapping data. have.

In operation 420 , the measurement data acquisition unit 320 may acquire measurement data measured using a three-dimensional measurement technique. The measurement data acquisition unit 320 acquires measurement data through three-dimensional measurement technology including stereo vision of a measurement system or a laser scanning technique, and acquires feature points for the shape of a three-dimensional object (object) from the obtained measurement data can do. In this case, the obtained measurement data may refer to 3D surface information data of an object in which an error is removed using an error removal algorithm including a medium filter and background information is removed.

In step 430 , the determination unit 330 may compare and analyze the obtained shape data of the 3D object and the obtained measurement data based on the least squares method to determine the degree of similarity to the shape of the 3D object. The determination unit 330 matches the center by moving the center using the average value for the obtained shape data and the obtained measurement data, and matches information between the obtained shape data and the obtained measurement data based on the matched center. It can be determined using the least-squares method using the principle of affine transformation of shape analysis. For example, the determination unit 330 may determine the degree of similarity by numerically quantifying the coincidence information between the shape data and the measurement data as a percentage. The determination unit 330 may present the shape of the 3D object related to each degree of similarity according to the degree of similarity as the matching information is digitized as a percentage. For example, the determination unit 330 may provide a list of shapes of 3D objects estimated to be 70% similar when the matching information between the shape data and the measurement data is 70%, and when the matching information is 80%, You can provide a list of shapes of 3D objects that are estimated to be 80% similar. In this case, the shape list of the 3D object may be provided using the shape information of the 3D object stored in the database. In addition, the determination unit 330 may not only identify the 3D object by determining the degree of similarity, but may also determine the category of the shape of the 3D object.

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA). , a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. may be embodied in The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible by those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (12)

In the shape classification method performed by the shape classification system,
obtaining shape data of a three-dimensional object using a three-dimensional modeling technique;
obtaining measurement data measured using a three-dimensional measurement technology; and
Comparing and analyzing the obtained shape data of the 3D object and the obtained measurement data based on the least squares method to determine the degree of similarity to the shape of the 3D object
including,
The step of obtaining the shape data includes:
The shape data obtained by designing the shape of the object using a modeling tool is converted into VRML format, and plane information is obtained by converting the obtained shape data into a VRML-based point format, and the measurement system collecting observable plane information using the observation equation of
including,
The step of determining the degree of similarity is
Using the obtained shape data and the average value for the obtained measurement data, the center is moved to match the center, and based on the matched center, matching information of the obtained shape data and the obtained measurement data is formed Performing comparative analysis using the least squares method using the principle of affine transformation of analysis
A shape classification method comprising a. delete delete According to claim 1,
The step of acquiring the measurement data includes:
Acquiring measurement data through three-dimensional measurement technology including stereo vision of a measurement system or a laser scanning technique, and acquiring feature points for the shape of a three-dimensional object from the obtained measurement data
A shape classification method comprising a. 5. The method of claim 4,
The obtained measurement data is
It removes errors using an error removal algorithm including a medium filter, and refers to 3D surface information data about the shape of a 3D object from which background information has been removed.
Shape classification method. delete In the shape classification system,
a shape data acquisition unit for acquiring shape data of a 3D object using a 3D modeling technique;
a measurement data acquisition unit that acquires measurement data measured using a three-dimensional measurement technology; and
A determination unit that compares and analyzes the obtained shape data of the three-dimensional object and the obtained measurement data based on the least-squares method to determine the degree of similarity to the shape of the three-dimensional object
including,
The shape data acquisition unit,
The shape data obtained by designing the shape of the object using a modeling tool is converted into VRML format, and plane information is obtained by converting the obtained shape data into a VRML-based point format, and the measurement system Collecting observable plane information using the observation equation of , and generating three-dimensional mapping data so that the collected observable plane information corresponds to a plurality of observation positions matching the measurement surface of the measurement system,
The judging unit,
Using the obtained shape data and the average value for the obtained measurement data, the center is moved to match the center, and based on the matched center, matching information of the obtained shape data and the obtained measurement data is formed Comparison analysis is performed using the least squares method using the principle of affine transformation of analysis.
Shape classification system. delete delete 8. The method of claim 7,
The measurement data acquisition unit,
Acquiring measurement data through three-dimensional measurement technology including stereo vision of a measurement system or a laser scanning technique, and obtaining feature points for the shape of a three-dimensional object from the obtained measurement data
Shape classification system, characterized in that. 11. The method of claim 10,
The obtained measurement data is
It removes errors using an error removal algorithm including a medium filter, and refers to 3D surface information data about the shape of a 3D object from which background information has been removed.
Shape classification system. delete

Images