A visual positioning method and system for improving the assembly precision of a body-in-white roof assembly

Abstract

The present application relates to the technical field of vehicle production, and especially relates to a visual positioning method and system for improving assembly precision of a body-in-white roof assembly. The method comprises the following steps: building a body-in-white roof assembly model and a workbench model, obtaining a reference calibration model based on the body-in-white roof assembly model placed on the workbench model; establishing a three-dimensional coordinate system based on the reference calibration model, and parameterizing the positioning point markers and the contour markers in the reference calibration model; collecting image information of the body-in-white roof assembly and the workbench in the actual assembly process, fitting and comparing the image information with the reference calibration model, and judging whether the body-in-white roof assembly in the actual assembly process has deviation; comparing the coordinate data of the feature markers and the positioning point markers, obtaining the feature deviation of the body-in-white roof assembly, and correcting the feature deviation, so as to avoid deformation of the body-in-white roof assembly in the assembly process, and improve the assembly yield and the assembly efficiency of the body-in-white roof assembly.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle production, and in particular to a visual positioning method and system for improving assembly precision of a body-in-white roof assembly. BACKGROUND

[0002] With the continuous progress of manufacturing processes and the increasing demand for product quality, automobile manufacturing processes have become an indispensable technical requirement for various automobile manufacturers to improve competitiveness. The degree of refinement of the automobile parts assembly process affects the performance of the whole vehicle and the reputation of the manufacturer. During the automobile assembly process, in order to reduce the deviation of the automobile parts assembly process, a robot is often used for automatic assembly.

[0003] In related technologies, during the assembly process of the body-in-white roof assembly, the mechanical tooling is not adjustable, and the mechanical tooling can only perform body assembly work according to a predetermined trajectory. The assembly flexibility is poor, which easily causes deformation of the body-in-white roof assembly, resulting in the need for rework or scrap treatment of the body. At the same time, the mechanical tooling uses hole positioning and face and edge positioning. If there is a deviation in positioning, the tooling and the mechanical workpiece will rub during assembly, which easily leads to wear and failure of the mechanical tooling, so that the mechanical tooling needs to be regularly maintained and replaced with parts. In addition, the mechanical tooling design is relatively complex, which increases the difficulty of debugging and maintenance. SUMMARY

[0004] The present application aims to solve the problem in the prior art that when there is a deviation in positioning during the assembly process of the body-in-white roof assembly, the mechanical tooling has poor assembly flexibility, which easily causes deformation of the body-in-white roof assembly and easily leads to wear and failure of the mechanical tooling. Therefore, the present application provides a visual positioning method and system for improving assembly precision of a body-in-white roof assembly.

[0005] In a first aspect, an embodiment of the present application provides a visual positioning method for improving assembly precision of a body-in-white roof assembly, comprising:

[0006] A body-in-white roof assembly model and a workbench model for supporting and positioning the body-in-white roof are built, and positioning point markers and contour markers are set on the body-in-white roof assembly model and the workbench model, respectively;

[0007] The body-in-white roof assembly model is placed on the workbench model according to actual assembly requirements to obtain a reference check model;

[0008] A three-dimensional coordinate system is established based on the reference check model, and the positioning point markers and the contour markers in the reference check model are set with parameters;

[0009] Image information of the body-in-white roof assembly and the workbench during the actual assembly process is continuously collected, and feature marker points of the image information are extracted based on image processing;

[0010] According to the fitting comparison between the image information and the reference check model, it is judged whether there is deviation in the body-in-white roof assembly in the actual assembly process.

[0011] If there is deviation in the body-in-white roof assembly, according to the comparison between the coordinate data of the feature mark points and the positioning point marks, the feature deviation of the body-in-white roof assembly is obtained and corrected.

[0012] According to some embodiments of the present application, the body-in-white roof assembly model is placed on the workbench model according to the actual assembly requirements to obtain a reference check model, which comprises: according to the positioning point marks and the contour marks set by the body-in-white roof assembly model and the workbench model, the model is combined according to the actual assembly requirements to obtain the reference check model.

[0013] According to some embodiments of the present application, the three-dimensional coordinate system is established based on the reference check model, and the parameterization setting of the positioning point marks and the contour marks in the reference check model comprises:

[0014] According to the reference check model, a base point is selected to establish a three-dimensional coordinate system, and parameterization processing is performed based on the three-dimensional coordinate system;

[0015] According to the three-dimensional coordinate system after parameterization processing, the coordinate parameters of each positioning point mark and the coordinate parameters of the contour mark are determined.

[0016] According to some embodiments of the present application, the image information of the body-in-white roof assembly and the workbench in the actual assembly process is continuously collected, and the feature mark points of the image information are extracted based on image processing, which comprises:

[0017] The image information of the body-in-white roof assembly and the workbench in the actual assembly process is collected from multiple directions, and the collected image information is processed, wherein the image processing includes gray processing, threshold segmentation and morphological processing;

[0018] According to the processed image information, the feature mark points are extracted, wherein the feature mark points include positioning holes, assembly holes and contour mark points on the body-in-white roof assembly.

[0019] According to some embodiments of the present application, the fitting comparison between the image information and the reference check model, it is judged whether there is deviation in the body-in-white roof assembly in the actual assembly process comprises:

[0020] According to the fitting comparison between the image information and the reference check model, wherein the fitting process is based on the workbench model;

[0021] According to the coordinate parameter information corresponding to each feature mark point and the coordinate parameter information corresponding to the positioning point mark in the reference verification model, it is determined whether there is deviation in the white body roof assembly in the actual assembly process.

[0022] According to the coordinate parameter information corresponding to each feature mark point and the coordinate parameter information corresponding to the positioning point mark in the reference verification model, it is determined whether there is deviation in the white body roof assembly in the actual assembly process.

[0023] According to some embodiments of the present application, the comparison of the coordinate parameter information corresponding to each feature mark point and the coordinate parameter information corresponding to the positioning point mark in the reference verification model includes:

[0024] According to the comparison of the coordinate parameter information corresponding to each feature mark point and the coordinate parameter information corresponding to the positioning point mark in the reference verification model, if the coordinate parameter information of the feature mark point and the corresponding positioning point mark is different, there is deviation in the white body roof assembly in the actual assembly process.

[0025] According to some embodiments of the present application, if the white body roof assembly has deviation, the comparison of the coordinate data of the feature mark point and the positioning point mark is performed to obtain the feature deviation amount of the white body roof assembly and to correct it.

[0026] According to the comparison of the coordinate data of the feature mark point and the positioning point mark, the coordinate parameter difference value of each feature mark point and the corresponding positioning point mark is obtained.

[0027] According to the coordinate parameter difference value, the feature deviation amount of the white body roof assembly is obtained.

[0028] According to the feature deviation amount, a correction control instruction is generated to control the robot to realize position correction of the white body roof assembly.

[0029] According to some embodiments of the present application, the correction control instruction is generated according to the feature deviation amount to control the robot to realize position correction of the white body roof assembly.

[0030] The image information of the white body roof assembly and the workbench after position correction is collected, and the coordinate parameter information corresponding to each feature mark point and the coordinate parameter information corresponding to the positioning point mark in the reference verification model are compared according to the image information, to determine whether the feature deviation amount of the white body roof assembly after position correction is less than a preset deviation amount value.

[0031] In a second aspect, the embodiments of the present application provide a visual positioning system for improving the assembly precision of a white body roof assembly, characterized in that the system comprises:

[0032] The model creating module is configured to build a body-in-white roof assembly model according to actual dimensions, build a workbench model for supporting and positioning the body-in-white roof, and place the body-in-white roof assembly model on the workbench model to obtain a reference calibration model;

[0033] The image collecting module is configured to continuously collect image information of the body-in-white roof assembly and the workbench in the actual assembly process in multiple dimensions, and extract feature marker points of the image information based on image processing.

[0034] The image processing module is configured to extract feature marker points of the image information based on image processing of the image information collected by the image collecting module, wherein the image processing includes grayscale processing, threshold segmentation, and morphological processing.

[0035] The data collecting module is configured to obtain coordinate parameter information corresponding to each feature marker point based on a three-dimensional coordinate system, according to the reference calibration model obtained by the model creating module and the feature marker points obtained by the image processing module.

[0036] The judging module is configured to compare the coordinate parameter information corresponding to each feature marker point obtained by the data collecting module with the coordinate parameters corresponding to the positioning point markers, to determine whether the body-in-white roof assembly in the actual assembly process has a deviation, and to obtain a feature deviation amount.

[0037] According to some embodiments of the present application, the system further comprises:

[0038] The executing module is configured to correct the position of the body-in-white roof assembly according to the judgment result of the judging module and the obtained feature deviation amount.

[0039] The calibration comparison module is configured to calibrate and compare when the executing module corrects the position of the body-in-white roof assembly, to ensure the accuracy of the position correction of the body-in-white roof assembly.

[0040] Compared with the prior art, the technical scheme provided by the embodiments of the present application has at least the following beneficial effects:

[0041] By establishing a standard three-dimensional reference calibration model, setting a positioning point mark and a contour mark on the model, establishing a three-dimensional model based on the reference calibration model and giving coordinate parameters, and setting a positioning point mark and a contour mark on the model for parameter quantization, when the body-in-white roof assembly on the work station is assembled, the image information of the body-in-white roof assembly is collected in real time through a visual sensor, the feature mark points are extracted from the image information through preprocessing, and the image information is fitted and compared with the reference calibration model to determine whether the body-in-white roof assembly in the actual assembly process deviates from the predetermined position. If there is a deviation, the feature deviation amount of the body-in-white roof assembly is obtained by comparing the coordinate data of the feature mark points and the positioning point mark, and the correction control instruction is generated to control the robot to correct the position of the body-in-white roof assembly. The method of the application is flexible in the assembly process, and can automatically adjust and correct when there is a deviation in the assembly process of the body-in-white roof assembly. After correction, the next assembly is performed. In this way, the body-in-white roof assembly is prevented from deforming during the assembly process, and the assembly yield and efficiency of the body-in-white roof assembly are improved.

[0042] Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will become apparent to those having ordinary skill in the art upon examination of the following or can be learned from practice of the application. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can also be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0044] Figure 1 is a flowchart of a visual positioning method for improving the assembly precision of a body-in-white roof assembly according to an embodiment of the application;

[0045] Figure 2 is a sub-flowchart of a visual positioning method for improving the assembly precision of a body-in-white roof assembly according to an embodiment of the application;

[0046] Figure 3 is another sub-flowchart of a visual positioning method for improving the assembly precision of a body-in-white roof assembly according to an embodiment of the application;

[0047] Figure 4 is a block diagram of a visual positioning system for improving the assembly precision of a body-in-white roof assembly according to an embodiment of the application. DETAILED DESCRIPTION

[0048] Embodiments of the present application are described below in detail with reference to the accompanying drawings. The embodiments described with reference to the accompanying drawings are exemplary, and it should be understood that the specific embodiments described herein are merely to explain the present application and not intended to limit the present application.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description herein is for describing the specific embodiments only and is not intended to be limiting of the application. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0050] Only parts of the apparatuses related to the present application are shown in the drawings, and not all of the parts. Before discussing the example embodiments in more detail, it should be mentioned that some of the example embodiments are described as processes or methods depicted as flow charts. Although the processes are described in a certain order, many of the operations can be performed concurrently, in parallel, or simultaneously. In addition, the order of the operations can be re-arranged. The processes can be terminated when their operations are completed, but the processes can also have additional steps not included in the figure. The processes can correspond to methods, functions, procedures, subroutines, subprograms, etc.

[0051] The terms "component," "module," "system," "unit," and the like are used in this specification to represent a computer-related entity, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a unit can be, but is not limited to, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and / or a distributed application between two or more computers. In addition, the units can be executed from various computer-readable media having various data structures stored thereon. The units can communicate, for example, by signals having one or more data packets (e.g., from a second unit data from a local system, a distributed system, and / or a network with another unit interacting with the local system, the distributed system, and / or the network). For example, the Internet interacts with other systems through signals.

[0052] A visual positioning method and system for improving the assembly precision of a body-in-white roof assembly are described below with reference to the accompanying drawings.

[0053] Figure 1 is a flowchart of a visual positioning method for improving the assembly precision of a body-in-white roof assembly according to an example embodiment, as shown in Figure 1 The method includes the following steps:

[0054] Step S100: build a white body roof assembly model and a workbench model for supporting and positioning the white body roof, and set a positioning point mark and a contour mark on the white body roof assembly model and the workbench model respectively;

[0055] In this step, it should be noted that the white body roof assembly model and the workbench model for supporting and positioning the white body roof can be created by using existing modeling software. Of course, the creation process needs to be created according to the actual size of the white body roof assembly and the workbench. In this way, a standard white body roof assembly assembly environment model is constructed, and the positioning hole, mounting hole and edge part of the actual white body roof assembly can be set with a feature positioning point mark and a contour mark, which is used to better determine the position deviation of the white body roof assembly.

[0056] It should also be noted that the white body roof assembly model and the workbench model created also need to be optimized, and the white body roof assembly assembly environment model and the workbench model after optimization are subjected to attribute editing, which can include parameter attributes, coordinate attributes and material attributes, etc. Finally, a data interface can be called for subsequent image processing process fitting, for example, a data interface API can be called by using visual studio. Through the calling of different interfaces, the data information of the white body roof assembly model and the workbench model is obtained.

[0057] Step S200: placing the white body roof assembly model on the workbench model according to the actual assembly requirements to obtain a reference check model;

[0058] In this step, the white body roof assembly model and the workbench model after optimization and attribute editing need to be combined according to the positioning point mark and the contour mark set on the white body roof assembly model and the workbench model to obtain a reference check model according to the actual assembly requirements.

[0059] Exemplarily, due to the positioning point mark and the contour mark set on the white body roof assembly model and the workbench model, for example, a plurality of positioning point marks are set at different positions of the contact surface of the white body roof assembly model and the workbench model, and a plurality of positioning point marks are set at different positions of the contact surface of the workbench model and the white body roof assembly model. It should be noted that the plurality of positioning point marks of the workbench model correspond one-to-one to the plurality of positioning point marks of the white body roof assembly model. The white body roof assembly model is placed on the workbench model according to the actual assembly requirements to obtain a reference check model.

[0060] Step S300: establishing a three-dimensional coordinate system based on the reference calibration model, and parameterizing the positioning point markers and the contour markers in the reference calibration model;

[0061] In this step, in order to quantitatively calibrate each positioning point marker and contour marker point in the model, a point in the reference calibration model can be selected as a reference point to establish a three-dimensional coordinate system, for example, a corner of the bottom surface of the model can be selected as a reference point to establish a three-dimensional coordinate system, and the three-dimensional coordinate system is assigned with coordinate parameters, and then the positioning point markers and the contour markers in the reference calibration model are parameterized based on the three-dimensional coordinate system. The parameterization of the positioning point markers and the contour markers in the reference calibration model can be understood as determining the spatial coordinate values of each positioning point marker and contour marker point in the three-dimensional coordinate system.

[0062] Step S400: continuously collecting image information of the body-in-white roof assembly and the workbench in the actual assembly process, and extracting feature marker points of the image information based on image processing;

[0063] In this step, the workbench can be understood as an automatic work area of the body-in-white roof assembly. In an actual production scene, the body-in-white roof assembly is transferred to the automatic work area by hoisting equipment, and the image information of the body-in-white roof assembly and the work area is obtained by photographing the body-in-white roof assembly from multiple directions through a pre-set visual collection device. It can be understood that the image information includes all feature information of the body-in-white roof assembly, such as the positions and sizes of each part or frame in the body-in-white roof assembly. Further, feature marker points are extracted from the image information, wherein the feature marker points can include glass mounting rubber nail hole positions, body feature holes, and positioning hole information of the body-in-white roof assembly.

[0064] In one embodiment, the body-in-white roof assembly and the automatic work area are collected by a visual device from a pre-set teaching photographing point to photograph the body image. The visual device integrates a three-dimensional laser scanner and a two-dimensional camera. The three-dimensional laser scanning and the two-dimensional camera photograph each other, transmit and compare data, and can measure the positioning data of the body in space. The body is photographed by controlling the visual device to move to the teaching photographing point. The two-dimensional camera photographs the feature marker points of the collection plane, and the three-dimensional laser scanner photographs the feature marker points of multiple positions of the body frame. The feature marker points can be pre-set body positioning markers, such as front and rear windshield rubber nail mounting hole positions. The feature marker points are identified from the obtained body image.

[0065] It should be noted that the collected image information is subjected to image processing, and the image processing includes grayscale processing, threshold segmentation and morphological processing. The image processing of the collected image information can be understood as noise reduction processing of the image to remove irrelevant noise in the image, so as to more efficiently extract the feature marker point from the image information.

[0066] In one embodiment, the data of the visual shooting device is transmitted to the software of the visual industrial computer for processing, and then transmitted to the control system and the robot through I / O. The visual industrial computer is provided with an internal trigger clock control visual special industrial computer, which can realize high-speed and stable image acquisition (when the visual industrial computer controls the shooting time sequence according to an external trigger signal, the signal transmission speed cannot realize stable high-speed shooting function), and the speed can realize 90 images / s. The shooting data and photos can be freely set to local and external hard disk storage mode. While the real-time image processing is performed, the image data and result data are stored in real time, which is convenient for production data backup and traceable management. The front and rear blocking visual shooting can each independently adopt a set of visual electrical cabinet for data processing.

[0067] Step S500: According to the fitting comparison between the image information and the reference verification model, it is judged whether the white body roof assembly in the actual assembly process exists deviation or not;

[0068] In this step, the image information subjected to image processing is fitted and compared with the reference verification model. Exemplarily, the fitting comparison can be understood as parameterizing the collected actual scene image information, taking the workbench model as a reference datum point. If the white body roof assembly and the feature marker point obtained from the image information do not coincide with the preset white body roof assembly model and the feature marker point positioning point mark after fitting, it can be determined that the white body roof assembly in the actual assembly process exists deviation. If the white body roof assembly and the feature marker point obtained from the image information coincide with the preset white body roof assembly model and the feature marker point positioning point mark, it can be determined that the white body roof assembly in the actual assembly process does not exist deviation.

[0069] Step S600: If the white body roof assembly exists deviation, the feature deviation amount of the white body roof assembly is obtained and corrected according to the comparison between the coordinate data of the feature marker point and the positioning point mark.

[0070] In this step, if it is judged that the actual production process body-in-white roof assembly exists deviation, the coordinate data of the feature mark point and the positioning point mark are obtained through the three-dimensional coordinate system in the preset model, and the coordinate data of the feature mark point and the positioning point mark can be expressed by three-dimensional coordinate points (X, Y, Z) for example, such as the feature mark point represented as (X1, Y1, Z1) and the positioning point mark represented as (X2, Y2, Z3). Then, the coordinate parameters of the feature mark point and the coordinate parameters of the positioning point mark are operated, and of course, the operation process can be through coordinate difference or converted into vector for processing, so as to obtain the feature deviation of the body-in-white roof assembly. The corresponding control instruction is generated by the feature deviation to control the robot to correct the deviation of the body-in-white roof assembly. After the robot corrects the deviation of the body-in-white roof assembly, in order to ensure that the deviation after correction meets the preset standard, the body-in-white roof assembly after deviation correction can also be monitored through correction inspection.

[0071] Please continue to refer to Figure 2 In one embodiment, in judging whether the body-in-white roof assembly in the actual assembly process exists deviation according to the image information and the reference verification model fitting comparison, the following steps can also be included:

[0072] Step S510: fitting comparison is performed according to the image information and the reference verification model, wherein the fitting process is based on the workbench model;

[0073] Step S520: based on the three-dimensional coordinate system, the coordinate parameter information corresponding to each feature mark point of the fitted image information is obtained;

[0074] Step S530: according to the comparison of the coordinate parameter information corresponding to each feature mark point and the coordinate parameter information corresponding to the positioning point mark in the reference verification model, it is judged whether the body-in-white roof assembly in the actual assembly process exists deviation.

[0075] Please continue to refer to Figure 3 In one embodiment, in the step of if the body-in-white roof assembly exists deviation, comparing the coordinate data of the feature mark point and the positioning point mark, obtaining the feature deviation of the body-in-white roof assembly and correcting it, the following steps can also be included:

[0076] Step S610: comparing the coordinate data of the feature mark point and the positioning point mark, obtaining the coordinate parameter difference value of each feature mark point and the corresponding positioning point mark;

[0077] Step S620: according to the coordinate parameter difference value, the feature deviation of the body-in-white roof assembly is obtained;

[0078] Step S630: generating a correction control instruction according to the feature deviation amount to control the robot to correct the position of the body-in-white roof assembly.

[0079] Through the above method steps, by establishing a standard three-dimensional reference check model, setting the positioning point mark and the contour mark on the model, establishing a three-dimensional model based on the reference check model and giving coordinate parameters, and quantifying the parameters of the positioning point mark and the contour mark on the model, when the body-in-white roof assembly on the work station is being assembled, the visual sensor collects image information of the body-in-white roof assembly in real time, and the feature mark points are extracted by preprocessing the image information, and the image information is fitted and compared with the reference check model to determine whether there is a deviation between the actual assembly process of the body-in-white roof assembly and the predetermined position. If there is a deviation, the feature deviation amount of the body-in-white roof assembly is obtained by comparing the coordinate data of the feature mark points and the positioning point mark, and a correction control instruction is generated based on the feature deviation amount to control the robot to correct the position of the body-in-white roof assembly. The method of the present application is flexible in the assembly process, and when there is a deviation in the assembly process of the body-in-white roof assembly, automatic adjustment and correction can be realized, and the next assembly is performed after correction. In this way, the deformation of the body-in-white roof assembly during the assembly process is avoided, and the assembly yield and efficiency of the body-in-white roof assembly are improved.

[0080] Please refer to Figure 4 In some embodiments, a visual positioning system 200 for improving the assembly accuracy of a body-in-white roof assembly is also provided, which comprises:

[0081] The model creation module 210 is configured to build a body-in-white roof assembly model according to the actual size, and a workbench model for supporting and positioning the body-in-white roof, and place the body-in-white roof assembly model on the workbench model to obtain a reference check model according to the actual assembly requirements;

[0082] The image acquisition module 220 is configured to continuously acquire image information of the body-in-white roof assembly and the workbench in the actual assembly process in multiple dimensions, and extract feature mark points of the image information based on image processing;

[0083] The image processing module 230 is configured to extract feature mark points of the image information based on image processing of the image information acquired by the image acquisition module 220, wherein the image processing includes grayscale processing, threshold segmentation, and morphological processing;

[0084] The data acquisition module 240 is configured to obtain coordinate parameter information corresponding to each feature mark point based on a three-dimensional coordinate system according to the reference check model obtained by the model creation module 210 and the feature mark points obtained by the image processing module 230.

[0085] The judging module 250 is configured to judge whether there is deviation in the white body roof assembly during the actual assembly process according to the comparison between the coordinate parameter information corresponding to each feature mark point obtained by the data acquisition module 240 and the coordinate parameter corresponding to the positioning mark, and obtain a feature deviation amount.

[0086] The executing module 260 is configured to perform position correction on the white body roof assembly according to the judgment result of the judging module 250 and the obtained feature deviation amount.

[0087] The verification comparison module 270 is configured to perform verification comparison when the executing module performs position correction on the white body roof assembly, so as to ensure the accuracy of the position correction of the white body roof assembly.

[0088] Meanwhile, in another embodiment, an electronic device is also provided, which has data processing capability and can convert processed data into control instructions to realize automatic control of a mechanical tool. Exemplarily, the electronic device comprises:

[0089] a processor;

[0090] a memory for storing processor-executable instructions;

[0091] wherein the processor is configured to:

[0092] implement the steps of the visual positioning method for improving the assembly precision of the white body roof assembly as described in the above embodiment.

[0093] In another embodiment, a readable storage medium is also provided, which has a computer program stored thereon, and the computer program is executed by a processor to implement the steps of the visual positioning method for improving the assembly precision of the white body roof assembly as described in the above embodiment.

[0094] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0095] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0096] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0097] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0098] In one typical configuration, the computing device includes one or more processors (CPU's), input / output interfaces, network interfaces, and memory.

[0099] The memory can include non-persistent memory and / or persistent memory, such as flash memory, read-only memory (ROM), and / or volatile or non-volatile random access memory (RAM), among others. The memory is an example of computer-readable media.

[0100] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can implement information storage by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers. It should also be noted that the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus including the element.

[0101] The terms "first", "second", "third", etc. in the specification and claims of the present application and the drawings are used to distinguish different objects, not to describe a particular order. In addition, the terms "comprise" and "have" and any variants thereof are intended to cover non-exclusive inclusion. For example, a series of steps or units are included, or optionally, other steps or units not listed are included, or optionally, other steps or units inherent to such a process, method, product or device are included.

[0102] Only parts related to the present application are shown in the drawings, not all. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowchart describes each operation (or step) as a sequential process, many of the operations can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operations are completed, but can also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, etc.

[0103] The terms "component," "module," "system," "unit," and the like are used in the description of this specification to represent a computer-related entity, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a unit can be, but is not limited to, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and / or a distributed among two or more computers. In addition, these units can be executed from various computer-readable media having various data structures stored thereon. The units can communicate, for example, according to a signal having one or more data packets (e.g., from a second unit data from interacting with a local system, a distributed system, and / or another unit of a network. For example, the Internet, by a signal with other systems through local and / or remote processes.

[0104] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "exemplary embodiment", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the specification, the exemplary description of the above terms does not necessarily mean the same embodiment or example.

[0105] It is obvious that the described embodiments are only a part of the embodiments of the present application, not all the embodiments. In this document, the reference to "embodiments" means that the specific features, structures, or characteristics described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears at various places in the specification does not necessarily mean the same embodiment, nor is it independent or alternative to other embodiments. It is obvious to those skilled in the art that the embodiments described herein can be combined with other embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0106] Although the embodiments of the present application have been shown and described, those skilled in the art can understand that various changes, modifications, replacements, and variations of the embodiments can be made without departing from the principles and spirit of the present application, and the scope of the present application is defined by the claims and their equivalents.

Claims

1. A visual positioning method for improving the assembly accuracy of a body-in-white roof assembly, characterized in that, The method comprises the following steps: Setting up a body-in-white roof assembly model and a workbench model for supporting and positioning the body-in-white roof, and setting up positioning point marks and contour marks on the body-in-white roof assembly model and the workbench model respectively; Placing the body-in-white roof assembly model on the workbench model according to actual assembly requirements to obtain a reference check model; Establishing a three-dimensional coordinate system based on the reference check model, and setting up parameters for the positioning point marks and the contour marks in the reference check model; Continuously collecting image information of the body-in-white roof assembly and the workbench during the actual assembly process, and extracting feature mark points of the image information based on image processing; Fitting and comparing the image information with the reference check model to determine whether the body-in-white roof assembly during the actual assembly process has deviation; If the body-in-white roof assembly has deviation, comparing the coordinate data of the feature mark points with the coordinate data of the positioning point marks to obtain the feature deviation of the body-in-white roof assembly and to correct it.

2. The visual positioning method for improving the assembly precision of the body-in-white roof assembly of claim 1, wherein, The step of placing the body-in-white roof assembly model on the workbench model according to actual assembly requirements to obtain a reference check model comprises the following steps:

3. The visual positioning method for improving the assembly precision of the body-in-white roof assembly of claim 1, wherein, According to the positioning point marks and the contour marks set up on the body-in-white roof assembly model and the workbench model, combining the models according to actual assembly requirements to obtain the reference check model. The step of establishing a three-dimensional coordinate system based on the reference check model, and setting up parameters for the positioning point marks and the contour marks in the reference check model comprises the following steps: Selecting a base point according to the reference check model to establish a three-dimensional coordinate system, and performing parameterization processing based on the three-dimensional coordinate system; 4. The visual positioning method for improving the assembly precision of the body-in-white roof assembly of claim 1, wherein, According to the three-dimensional coordinate system after parameterization processing, determining the coordinate parameters of each positioning point mark and the coordinate parameters of the contour mark. The step of continuously collecting image information of the body-in-white roof assembly and the workbench during the actual assembly process, and extracting feature mark points of the image information based on image processing comprises the following steps: Collecting image information of the body-in-white roof assembly and the workbench during the actual assembly process from multiple directions, and performing image processing on the collected image information, wherein the image processing comprises grayscale processing, threshold segmentation and morphological processing; 5. The visual positioning method for improving the assembly precision of the body-in-white roof assembly of claim 1, wherein, Extracting feature mark points from the processed image information, wherein the feature mark points comprise positioning holes, assembly holes and contour mark points on the body-in-white roof assembly. The step of fitting and comparing the image information with the reference check model to determine whether the body-in-white roof assembly during the actual assembly process has deviation comprises the following steps: Fitting and comparing the image information with the reference check model, wherein the fitting process takes the workbench model as the reference; Obtaining coordinate parameter information corresponding to each feature mark point based on the three-dimensional coordinate system after fitting the image information; 6. The visual positioning method for improving the assembly precision of the body-in-white roof assembly of claim 5, wherein, Comparing the coordinate parameter information corresponding to each feature mark point with the coordinate parameter information corresponding to the positioning point marks in the reference check model to determine whether the body-in-white roof assembly during the actual assembly process has deviation. The step of comparing the coordinate parameter information corresponding to each feature mark point with the coordinate parameter information corresponding to the positioning point marks in the reference check model to determine whether the body-in-white roof assembly during the actual assembly process has deviation comprises the following steps: According to the coordinate parameter information of each feature mark point and the coordinate parameter information of the positioning mark in the reference verification model, if the coordinate parameter information of the feature mark point and the corresponding positioning mark is not the same, the white body roof assembly in the actual assembly process has deviation.

7. The visual positioning method for improving the assembly precision of the body-in-white roof assembly of claim 1, wherein, If the white body roof assembly has deviation, the feature deviation amount of the white body roof assembly is obtained by comparing the coordinate data of the feature mark point and the positioning mark, and the white body roof assembly is corrected. According to the coordinate data of the feature mark point and the positioning mark, the coordinate parameter difference value of each feature mark point and the corresponding positioning mark is obtained. According to the coordinate parameter difference value, the feature deviation amount of the white body roof assembly is obtained. According to the feature deviation amount, a correction control instruction is generated to control the robot to correct the position of the white body roof assembly.

8. The visual positioning method for improving the assembly precision of the body-in-white roof assembly of claim 1, wherein, According to the feature deviation amount, a correction control instruction is generated to control the robot to correct the position of the white body roof assembly. The system comprises:

9. A vision positioning system for improving the assembly accuracy of the body-in-white roof assembly, characterized in that, A model creation module is configured to build a white body roof assembly model according to the actual size, and a workbench model for supporting the positioning of the white body roof, and place the white body roof assembly model on the workbench model to obtain a reference verification model according to the actual assembly requirements. An image acquisition module is configured to continuously acquire image information of the white body roof assembly and the workbench in the actual assembly process in multiple dimensions, and extract feature mark points of the image information based on image processing. An image processing module is configured to extract feature mark points of the image information based on image processing of the image information acquired by the image acquisition module, wherein the image processing includes grayscale processing, threshold segmentation and morphological processing. A data acquisition module is configured to obtain coordinate parameter information of each feature mark point based on a three-dimensional coordinate system according to the reference verification model obtained by the model creation module and the feature mark points obtained by the image processing module. A judgment module is configured to compare the coordinate parameter information of each feature mark point and the corresponding positioning mark, and determine whether the white body roof assembly in the actual assembly process has deviation, and obtain the feature deviation amount. The system further comprises:

10. The visual positioning system for improving assembly accuracy of a body-in-white roof assembly of claim 9, wherein, An execution module is configured to correct the position of the white body roof assembly according to the judgment result of the judgment module and the obtained feature deviation amount. A verification comparison module is configured to verify and compare when the white body roof assembly is corrected by the execution module to ensure the accuracy of the position correction of the white body roof assembly. ​

Images