Augmented reality auxiliary marking system and method for satellite truss parts

Abstract

The invention provides a satellite truss part augmented reality auxiliary marking system and method, and the system comprises an optical recognition device which is used for carrying out the optical imaging of a label of a truss part, and obtaining a label image; the stereoscopic vision device is used for carrying out laser scanning and multi-view imaging on the truss parts to obtain part images and point clouds; the projection guiding device is used for sequentially projecting guiding information in the truss part marking process to a designated area of the workbench; and the augmented reality auxiliary marking control system is used for controlling and coordinating the optical recognition device, the stereoscopic vision device and the projection guiding device, integrating data information of all the devices and guiding an operator to complete marking of the assembly corresponding relation marks on the truss parts. According to the invention, the truss part can be automatically and accurately identified, an operator is guided to correctly complete assembly corresponding relation marking on the part, the quality and the development efficiency are improved, and the dependence on the technical level of the operator is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of satellite truss assembly, and in particular to an augmented reality-assisted marking system and method for satellite truss parts. Background Art

[0002] Truss structure is one of the main structural configurations of satellites and other spacecraft. It has the characteristics of light weight, strong load-bearing capacity, diverse forms and flexible design. It has been widely used in the structures of satellites and other spacecraft. For example, the US Lacrosse satellite, Hubble Space Telescope, James Webb Space Telescope, my country's Fengyun meteorological satellite, land exploration satellite, etc. all use carbon fiber truss structure.

[0003] Augmented reality is a technology that integrates virtual information with the real environment. The assembly field is an important application field of augmented reality. In this regard, a lot of research has been carried out at home and abroad, and it has been applied in the aerospace field. For example, Boeing has developed an auxiliary wiring system and successfully applied it in aircraft manufacturing; Lockheed Martin uses smart glasses for drilling and auxiliary assembly in the manufacture of Orion spacecraft, which improves the product qualification rate and manufacturing efficiency; Shanghai Jiaotong University has developed a prototype system for augmented reality assembly operation guidance training for aerospace products, which improves the guidance of assembly process, controllability of assembly process, and traceability of assembly quality; Beijing Satellite Environment Engineering Research Institute uses Unity3D to create visual process guidance information and verifies its application in satellite cable assembly.

[0004] The satellite truss structure is mainly assembled from carbon fiber rods, including square rods, round rods, etc., as well as parts such as multi-way joints. The satellite truss structure has a large number of parts, and dozens or even hundreds of parts need to determine the assembly relationship. Some parts are highly similar and difficult to accurately distinguish with the naked eye. At present, it mainly relies on manual comparison of three-dimensional models to distinguish and identify parts and complete the assembly correspondence marking. The workload is large and there is a risk of misjudgment, which may lead to incorrect assembly of the truss structure. Therefore, there is a need for an augmented reality-assisted marking system and method for satellite truss parts that can automatically and accurately identify truss parts, and guide operators to correctly complete the assembly correspondence marking on parts, improve quality and research and development efficiency, reduce dependence on the operator's technical level, and lay the foundation for the one-time correct assembly of complex trusses. Summary of the invention

[0005] In view of the defects in the prior art, an object of the present invention is to provide a satellite truss parts augmented reality assisted marking system and method.

[0006] According to the present invention, a satellite truss part augmented reality auxiliary marking system is provided, comprising:

[0007] An optical recognition device, used for optically imaging the labels of the truss parts to obtain label images;

[0008] Stereoscopic vision device, used to perform laser scanning and multi-view imaging on truss parts to obtain part images and point clouds;

[0009] A projection guide device projects the guide information in the truss part marking process sequentially to the designated area of ​​the workbench;

[0010] The augmented reality assisted marking control system is used to control and coordinate the optical recognition device, the stereoscopic vision device and the projection guidance device, integrate the data information of all devices, and guide the operator to complete the assembly correspondence marking on the marking truss parts.

[0011] Preferably, it also includes:

[0012] A workbench, used to place truss parts, project guidance information, place calibration targets, and provide operating space for operators;

[0013] A support frame is used to install an optical recognition device, a stereoscopic vision device and a projection guidance device.

[0014] Preferably, the optical recognition device includes an industrial camera, a camera lens, an illumination light source and a camera bracket; the industrial camera is used to generate digital images, the camera lens is used to transform light, the illumination light source is used to illuminate the target, and the camera bracket is used to adjust the position and posture of the industrial camera.

[0015] Preferably, the stereoscopic vision device includes an image sensor, a lens, a laser and a laser galvanometer; the image sensor is used to generate a digital image, the lens is used to transform light, the laser is used to generate a line laser, and the laser galvanometer is used to scan the line laser on the surface of the object to be measured.

[0016] Preferably, the projection guiding device comprises a projection light source, a projection lens and a display module; the light source is used to generate projection light, the projection lens is used to transform the projection light, and the display module is used to generate a projection image.

[0017] Preferably, the augmented reality assisted marking control system includes an industrial computer, a keyboard, a mouse, an optical recognition device control circuit, a stereoscopic vision device control circuit and a projection guidance device control circuit.

[0018] Preferably, the augmented reality assisted marking control system can control the entire satellite truss parts augmented reality assisted marking process, realizing human-computer interaction, parts recognition, point cloud alignment, projection guidance, quality inspection and data management.

[0019] Preferably, the industrial computer is electrically connected to a keyboard, a mouse, an optical recognition device, a stereoscopic vision device and a projection guidance device respectively.

[0020] According to the present invention, a satellite truss part augmented reality assisted marking method is provided, comprising:

[0021] Step S1: According to the truss three-dimensional model and assembly process information, the assembly relationship of the truss parts is marked, and the geometric model of all the marked truss parts is generated, and then the point cloud model of all the truss parts is generated, and the truss part model database is established;

[0022] Step S2: calibrating the stereo vision device using a target placed on the workbench;

[0023] Step S3: traverse all m parts of the truss;

[0024] Step S4: the operator holds a truss part with a number i, and points the label of the truss part i toward the camera lens of the optical recognition device, and the optical recognition device performs optical imaging on the label of the truss part i to obtain an image containing the label of the truss part i;

[0025] Step S5: processing the image containing the label of the truss part i in the industrial computer of the augmented reality-assisted marking control system, and realizing automatic recognition of the content of the label of the truss part i by using an optical character recognition algorithm;

[0026] Step S6: according to the recognition result of the tag content of the truss part i, the corresponding geometric model and point cloud model are retrieved in the truss part model database;

[0027] Step S7: reading the geometric model, point cloud model and marking information of the truss part i;

[0028] Step S8: traverse the front view, rear view, left view, right view, top view and bottom view of the truss part i;

[0029] Step S9: performing augmented reality auxiliary marking on view j of truss part i;

[0030] Step S10: Determine whether all views of the truss part i have been traversed. If so, proceed to step S11. If not, proceed to the next view and proceed to step S9.

[0031] Step S11: outputting a marking result record table of truss part i;

[0032] Step S12: Determine whether all parts of the truss have been traversed. If so, end the process; if not, proceed to the next part and enter step S4.

[0033] Preferably, step S9 includes the following sub-steps:

[0034] Step S9.1: Determine whether view j of truss part i is marked. If so, proceed to step S9.2. If not, prompt that view j is unmarked and end the process.

[0035] Step S9.2: Setting the projection parameters of the truss part i so that the truss part i is orthographically projected on the work surface according to a 1:1 ratio and a set view;

[0036] Step S9.3: Projecting the view j of the truss part i onto the work surface by means of a projection guide device;

[0037] Step S9.4: enabling the operator to place the truss part i according to the projection information;

[0038] Step S9.5: measuring the placed truss part i through a stereo vision device to generate a point cloud;

[0039] Step S9.6: registering the measured point cloud of the object with the ideal model point cloud through a point cloud registration algorithm, and comparing the consistency between the object and the model based on the registration error;

[0040] Step S9.7: Determine whether the real object is consistent with the model. If so, proceed to step S9.8. If not, prompt to re-place the truss part i and proceed to step S9.4.

[0041] Step S9.8: enabling the operator to paste a mark at a corresponding position of the truss part i according to the projection information of the view j;

[0042] Step S9.9: Measuring the marked truss part i by a stereoscopic vision device to generate an image;

[0043] Step S9.10: Identify and locate the pasted marker using a target detection algorithm;

[0044] Step S9.11: Recognize the pasted marked content through the OCR algorithm;

[0045] Step S9.12: Determine whether the position and content of the pasted mark are correct. If so, proceed to step S9.13. If not, prompt to re-paste the mark and proceed to step S9.8.

[0046] Step S9.13: Record the marking results of view j of truss part i.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The present invention realizes accurate identification of truss parts by using an optical recognition device, realizes detection of truss parts and their markings by using a stereoscopic vision device, realizes projection of marking guidance information by using a projection guidance device, and intuitively and correctly guides operators to complete assembly correspondence markings on truss parts through an augmented reality-assisted marking control system, thereby realizing augmented reality-assisted marking, improving satellite truss quality and development efficiency, and reducing dependence on the operator's technical level.

[0049] 2. The present invention can automatically and accurately identify truss parts to guide operators to correctly complete the assembly correspondence markings on the parts, thereby improving quality and development efficiency, laying the foundation for achieving one-time correct assembly of complex trusses, and having high practicality.

[0050] Other beneficial effects of the present invention will be explained in the specific implementation manner through the introduction of specific technical features and technical solutions. Through the introduction of these technical features and technical solutions, those skilled in the art should be able to understand the beneficial technical effects brought about by the technical features and technical solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0052] Figure 1 It is a system block diagram of the present invention.

[0053] Figure 2 The figure is a flow chart of the method of the present invention.

[0054] Figure 3 This is a flow chart of augmented reality-assisted marking of view j of truss part i in the present invention. DETAILED DESCRIPTION

[0055] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0056] Reference Figure 1 As shown, a satellite truss part augmented reality assisted marking system includes:

[0057] Optical recognition device, stereoscopic vision device, projection guidance device, augmented reality auxiliary marking control system, workbench, support frame;

[0058] The optical recognition device is used to perform optical imaging on the labels of the truss parts to obtain the label images; it includes an industrial camera, a camera lens, an illumination light source, and a camera bracket. The industrial camera is used to generate digital images, the camera lens is used to transform light, the illumination light source is used to illuminate the target, and the camera bracket is used to adjust the position and posture of the industrial camera.

[0059] The stereoscopic vision device is used to perform laser scanning and multi-view imaging on truss parts to obtain part images and point clouds; it includes an image sensor, a lens, a laser, and a laser galvanometer. The image sensor is used to generate digital images, the lens is used to transform light, the laser is used to generate line lasers, and the laser galvanometer is used to scan the line lasers on the surface of the object to be measured.

[0060] The projection guidance device is used to sequentially project the guidance information of each step in the truss part marking process to the specified area of ​​the workbench to provide guidance to the operator; it includes a projection light source, a projection lens, and a display module, wherein the light source is used to generate projection light, the projection lens is used to transform the projection light, and the display module is used to generate a projection image.

[0061] The augmented reality assisted marking control system is used to control the augmented reality assisted marking process of the entire satellite truss parts, which includes an industrial computer, a keyboard, a mouse, an optical recognition device control circuit, a stereoscopic vision device control circuit, and a projection guidance device control circuit. The industrial computer is electrically connected to the keyboard, the mouse, the optical recognition device, the stereoscopic vision device, and the projection guidance device, respectively, to ultimately achieve the purposes of human-computer interaction, part recognition, point cloud registration, projection guidance, quality inspection, data management, etc.

[0062] The workbench is used to place truss parts, project guidance information, place calibration targets, and provide operating space for operators;

[0063] The support frame is used to install optical recognition devices, stereoscopic vision devices, and projection guidance devices.

[0064] Reference Figure 2 As shown, a satellite truss part augmented reality assisted marking method includes the following steps:

[0065] Step S1, start;

[0066] Step S2, marking the assembly relationship of the truss parts according to the truss three-dimensional model and assembly process information, generating a geometric model of all the marked truss parts, and generating a point cloud model of all the truss parts on this basis, and establishing a truss part model database;

[0067] Step S3, calibrating the stereoscopic vision device using a target placed on the workbench;

[0068] Step S4, traverse all m parts of the truss;

[0069] Step S5, the operator holds the truss part i (i=1, 2, ..., m, where m is the number of parts) and points the label of the truss part i toward the camera lens of the optical recognition device, and the optical recognition device performs optical imaging on the label of the truss part i to obtain an image containing the label of the truss part i;

[0070] Step S6, processing the image containing the label of the truss part i in the industrial computer of the augmented reality-assisted marking control system, and realizing automatic recognition of the label content of the truss part i by using an OCR algorithm;

[0071] Step S7, according to the recognition result of the tag content of the truss part i, the corresponding geometric model and point cloud model are retrieved in the truss part model database;

[0072] Step S8, reading the geometric model, point cloud model and marking information of the truss part i;

[0073] Step S9, traversing the six views of the truss part i, namely, front, back, left, right, top and bottom views;

[0074] Step S10, performing augmented reality auxiliary marking on view j of truss part i;

[0075] Step S11, determine whether all views of the truss part i have been traversed, if so, proceed to step S12, if not, proceed to the next view and proceed to step S10;

[0076] Step S12, outputting a marking result record table of truss part i;

[0077] Step S13, determine whether all parts of the truss have been traversed, if so, go to step S14, if not, continue to the next part and go to step S5;

[0078] Step S14, end.

[0079] Reference Figure 3 As shown, the specific process of "performing augmented reality-assisted marking on view j of truss part i" is as follows:

[0080] Step Q1, start;

[0081] Step Q2, determine whether view j of truss part i is marked, if so, go to step Q3, if not, prompt that view j is not marked, and go to step Q15;

[0082] Step Q3, setting the projection parameters of the truss part i to ensure that the truss part i can be projected onto the work surface according to a 1:1 ratio and a set view;

[0083] Step Q4, projecting the view j of the truss part i onto the work surface by means of a projection guiding device;

[0084] Step Q5, the operator places the truss part i according to the projection information;

[0085] Step Q6, quickly measuring the placed truss parts i through a stereo vision device to generate a point cloud;

[0086] Step Q7, registering the measured physical point cloud with the ideal model point cloud through a point cloud registration algorithm, and comparing the consistency between the physical object and the model based on the registration error;

[0087] Step Q8, judging whether the real object is consistent with the model, if so, proceeding to step Q9, if not, prompting to rearrange the truss part i, and proceeding to step Q5;

[0088] Step Q9, the operator pastes a mark at the corresponding position of the truss part i according to the projection information of the view j;

[0089] Step Q10, quickly measuring the marked truss part i by a stereoscopic vision device to generate an image;

[0090] Step Q11, identifying and locating the pasted marker by using a target detection algorithm;

[0091] Step Q12, recognizing the pasted marked content through an OCR algorithm;

[0092] Step Q13, judging whether the position and content of the pasted mark are correct, if so, proceeding to step Q14, if not, prompting to re-paste the mark, and proceeding to step Q9;

[0093] Step Q14, recording the marking result of view j of truss part i.

[0094] Step Q15, end.

[0095] The satellite truss parts augmented reality auxiliary marking system and method provided by the present invention can automatically and accurately identify truss parts, and guide operators to correctly complete the assembly correspondence marking on the parts, thereby improving quality and development efficiency and reducing dependence on the operator's technical level.

[0096] The above is a basic embodiment of the present invention. The technical solution of the present invention is further described below through a preferred embodiment.

[0097] Example 1

[0098] like Figure 1As shown, a satellite truss part augmented reality assisted marking system includes an optical recognition device, a stereoscopic vision device, a projection guidance device, an augmented reality assisted marking control system, a workbench, and a support frame; wherein:

[0099] The optical recognition device is used to perform optical imaging on the labels of truss parts to obtain label images; it includes: an industrial camera, a camera lens, an illumination light source, and a camera bracket. The industrial camera is used to generate digital images with a resolution of not less than 5 million pixels, the camera lens is used to transform light, and the field of view angle is not less than 40°, the illumination light source is a white LED light source, which is used to illuminate the target, and the camera bracket is a 6-degree-of-freedom adjustment bracket, which is used to adjust the position and posture of the industrial camera.

[0100] The stereoscopic vision device is used to perform laser scanning and multi-view imaging on truss parts to achieve the acquisition of part images and point clouds; it includes: an image sensor, a lens, a laser, and a laser galvanometer. The image sensor is used to generate digital images with a resolution of not less than 10 million pixels and a quantity of not less than 2. The lens is used to transform light with a field of view of not less than 50° and the quantity is consistent with that of the image sensor. The laser is used to generate line lasers with a quantity of not less than 7 line lasers. The laser galvanometer is used to scan the line laser on the surface of the object to be measured with a scanning frequency of not less than 1 Hz.

[0101] The projection guidance device is used to sequentially project the guidance information of each step in the truss part marking process to the designated area of ​​the workbench to provide guidance to the operator; it includes: a projection light source, a projection lens, and a display module. The light source is used to generate projection light, and the projection brightness is not less than 4000 lumens. The projection lens is used to transform the projection light, and the minimum projection ratio is not greater than 1.4:1. The display module is used to generate a projection image, and the resolution is not less than 2 million pixels.

[0102] The augmented reality assisted marking control system is used to control the augmented reality assisted marking process of the entire satellite truss parts, realize human-computer interaction, part recognition, point cloud registration, projection guidance, quality inspection, data management, etc.; it includes: an industrial computer, a keyboard, a mouse, an optical recognition device control circuit, a stereoscopic vision device control circuit, and a projection guidance device control circuit. The industrial computer is electrically connected to the keyboard, the mouse, the optical recognition device, the stereoscopic vision device, and the projection guidance device respectively.

[0103] The workbench is used to place truss parts, project guidance information, place calibration targets, and provide operating space for operators;

[0104] The support frame is used to install optical recognition devices, stereoscopic vision devices, and projection guidance devices.

[0105] Reference Figure 2As shown, this embodiment also provides a satellite truss part augmented reality assisted marking method, comprising the following steps:

[0106] Step 1, start;

[0107] Step 2: According to the truss three-dimensional model and assembly process information, the assembly relationship of all m truss parts is marked, and the geometric model of all m truss parts with marking is generated. On this basis, the point cloud model of all m truss parts is generated to establish a truss part model database;

[0108] Step 3, calibrating the stereo vision device using a target placed on the workbench;

[0109] Step 4, traverse all m parts of the truss;

[0110] Step 5: The operator holds the truss part i (i=1, 2, ..., m, where m is the number of parts) and points the label of the truss part i toward the camera lens of the optical recognition device. The optical recognition device performs optical imaging on the label of the truss part i to obtain an image containing the label of the truss part i.

[0111] Step 6, processing the image containing the truss part i label in the industrial computer of the augmented reality assisted marking control system, and realizing automatic recognition of the truss part i label content by using the OCR algorithm;

[0112] Step 7, according to the recognition result of the tag content of the truss part i, the corresponding geometric model and point cloud model are retrieved in the truss part model database;

[0113] Step 8, reading the geometric model, point cloud model and marking information of the truss part i;

[0114] Step 9, traverse the six views of the truss part i, namely, front, back, left, right, top and bottom views;

[0115] Step 10, performing augmented reality auxiliary marking on view j of truss part i;

[0116] Step 11, determine whether all views of truss part i have been traversed, if so, go to step 12, if not, continue to the next view and go to step 10;

[0117] Step 12, outputting a marking result record table of truss part i;

[0118] Step 13, determine whether all m parts of the truss have been traversed. If so, go to step 14. If not, continue to the next part and go to step 5.

[0119] Step 14, end.

[0120] Among them, Figure 3 As shown, the specific process of performing augmented reality-assisted marking on view j of truss part i in step 10 is as follows:

[0121] Step 10.1, start;

[0122] Step 10.2, determine whether view j of truss part i is marked, if so, go to step 10.3, if not, it prompts that view j is unmarked, and go to step 10.15;

[0123] Step 10.3, set the projection parameters of the truss part i to ensure that the truss part i can be projected on the work surface according to the 1:1 ratio and the set view;

[0124] Step 10.4, projecting the view j of the truss part i onto the work surface by means of a projection guide device;

[0125] Step 10.5, the operator places the truss part i according to the projection information;

[0126] Step 10.6, quickly measure the placed truss part i through a stereo vision device to generate a point cloud;

[0127] Step 10.7, registering the measured object point cloud with the ideal model point cloud through the iterative closest point (ICP) point cloud registration algorithm, and comparing the consistency between the object and the model based on the registration error;

[0128] Step 10.8, determine whether the real object is consistent with the model, if so, go to step 10.9, if not, it will prompt to re-place the truss part i and go to step 10.5;

[0129] Step 10.9, the operator pastes a mark at the corresponding position of the truss part i according to the projection information of the view j;

[0130] Step 10.10, quickly measuring the marked truss part i by a stereoscopic vision device to generate an image;

[0131] Step 10.11, identify and locate the pasted markers using the YOLO (You Only Look Once) target detection algorithm;

[0132] Step 10.12, recognizing the pasted marked content through the OCR algorithm;

[0133] Step 10.13, determine whether the pasted mark position and content are correct, if so, proceed to step 10.14, if not, prompt to re-paste the mark and proceed to step 10.9;

[0134] Step 10.14, record the marking results of view j of truss part i.

[0135] Step 10.15, end.

[0136] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0137] In the description of the present application, it should be understood that the terms "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0138] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A satellite truss parts augmented reality assisted marking system, characterized in that: include: An optical recognition device, used for optically imaging the labels of the truss parts to obtain label images; Stereoscopic vision device, used to perform laser scanning and multi-view imaging on truss parts to obtain part images and point clouds; A projection guide device projects the guide information in the truss part marking process sequentially to the designated area of ​​the workbench; The augmented reality assisted marking control system is used to control and coordinate the optical recognition device, the stereoscopic vision device and the projection guidance device, integrate the data information of all devices, and guide the operator to complete the assembly correspondence marking on the marking truss parts.

2. The satellite truss parts augmented reality assisted marking system according to claim 1, characterized in that: Also includes: A workbench, used to place truss parts, project guidance information, place calibration targets, and provide operating space for operators; A support frame is used to install an optical recognition device, a stereoscopic vision device and a projection guidance device.

3. The satellite truss parts augmented reality assisted marking system according to claim 1, characterized in that: The optical recognition device includes an industrial camera, a camera lens, an illumination light source and a camera bracket; the industrial camera is used to generate digital images, the camera lens is used to transform light, the illumination light source is used to illuminate the target, and the camera bracket is used to adjust the position and posture of the industrial camera.

4. The satellite truss parts augmented reality assisted marking system according to claim 1, characterized in that: The stereoscopic vision device includes an image sensor, a lens, a laser and a laser galvanometer; the image sensor is used to generate a digital image, the lens is used to transform light, the laser is used to generate a line laser, and the laser galvanometer is used to scan the line laser on the surface of the object to be measured.

5. The satellite truss parts augmented reality assisted marking system according to claim 1, characterized in that: The projection guiding device comprises a projection light source, a projection lens and a display module; the light source is used to generate projection light, the projection lens is used to transform the projection light, and the display module is used to generate a projection image.

6. The satellite truss parts augmented reality assisted marking system according to claim 1, characterized in that: The augmented reality auxiliary marking control system includes an industrial computer, a keyboard, a mouse, an optical recognition device control circuit, a stereoscopic vision device control circuit and a projection guidance device control circuit.

7. The satellite truss parts augmented reality assisted marking system according to claim 6, characterized in that: The augmented reality assisted marking control system can control the entire satellite truss part augmented reality assisted marking process, and realize human-computer interaction, part recognition, point cloud registration, projection guidance, quality inspection and data management.

8. The satellite truss parts augmented reality assisted marking system according to claim 7, characterized in that: The industrial computer is electrically connected to a keyboard, a mouse, an optical recognition device, a stereoscopic vision device and a projection guiding device respectively.

9. A satellite truss parts augmented reality assisted marking method, based on the satellite truss parts augmented reality assisted marking system according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step S1: According to the truss three-dimensional model and assembly process information, the assembly relationship of the truss parts is marked, and the geometric model of all the marked truss parts is generated, and then the point cloud model of all the truss parts is generated, and the truss part model database is established; Step S2: calibrating the stereo vision device using a target placed on the workbench; Step S3: traverse all m parts of the truss; Step S4: the operator holds a truss part with a number i, and points the label of the truss part i toward the camera lens of the optical recognition device, and the optical recognition device performs optical imaging on the label of the truss part i to obtain an image containing the label of the truss part i; Step S5: processing the image containing the label of the truss part i in the industrial computer of the augmented reality-assisted marking control system, and realizing automatic recognition of the content of the label of the truss part i by using an optical character recognition algorithm; Step S6: according to the recognition result of the tag content of the truss part i, the corresponding geometric model and point cloud model are retrieved in the truss part model database; Step S7: reading the geometric model, point cloud model and marking information of the truss part i; Step S8: traverse the front view, rear view, left view, right view, top view and bottom view of the truss part i; Step S9: performing augmented reality-assisted marking on view j of truss part i; Step S10: Determine whether all views of the truss part i have been traversed. If so, proceed to step S11. If not, proceed to the next view and proceed to step S9. Step S11: outputting a marking result record table of truss part i; Step S12: Determine whether all parts of the truss have been traversed. If so, end the process; if not, proceed to the next part and enter step S4.

10. The satellite truss parts augmented reality assisted marking method according to claim 9, characterized in that: The step S9 includes the following sub-steps: Step S9.1: Determine whether view j of truss part i is marked. If so, proceed to step S9.

2. If not, prompt that view j is unmarked and end the process. Step S9.2: Setting the projection parameters of the truss part i so that the truss part i is orthographically projected on the work surface according to a 1:1 ratio and a set view; Step S9.3: Projecting the view j of the truss part i onto the work surface by means of a projection guide device; Step S9.4: enabling the operator to place the truss part i according to the projection information; Step S9.5: measuring the placed truss part i through a stereo vision device to generate a point cloud; Step S9.6: registering the measured point cloud of the object with the ideal model point cloud through a point cloud registration algorithm, and comparing the consistency between the object and the model based on the registration error; Step S9.7: Determine whether the real object is consistent with the model. If so, proceed to step S9.

8. If not, prompt to re-place the truss part i and proceed to step S9.

4. Step S9.8: enabling the operator to paste a mark at a corresponding position of the truss part i according to the projection information of the view j; Step S9.9: Measuring the marked truss part i by a stereoscopic vision device to generate an image; Step S9.10: Identify and locate the pasted marker using a target detection algorithm; Step S9.11: Recognize the pasted marked content through the OCR algorithm; Step S9.12: Determine whether the position and content of the pasted mark are correct. If so, proceed to step S9.

13. If not, prompt to re-paste the mark and proceed to step S9.

8. Step S9.13: Record the marking results of view j of truss part i.

Images