Method and device for measuring three-dimensional shape of handicraft based on robot scanning viewpoint planning

Abstract

The application discloses a kind of based on robot scanning viewpoint planning process product three-dimensional measurement method and device, the method comprises: the size information of measured object is acquired, the minimum bounding box is determined according to size information, scanning viewpoint is planned according to the minimum bounding box, and coarse grid model is generated based on scanning viewpoint;Coarse grid model is discretized into point cloud model, and the hole recognition of point cloud model is carried out using maximum angle criterion, and the hole boundary feature point is obtained, the clustering of hole boundary feature point is carried out, and the local hole in point cloud model is determined, and the secondary fine scanning of each local hole is carried out, and secondary fine scanning model is generated;Point cloud registration and fusion are carried out to coarse grid model and secondary fine scanning model, and the digitization model of measured object is obtained, the integrity, precision and efficiency of scanning can be guaranteed, and the automatic measurement of process product is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of three-dimensional measurement of process products, and in particular to a three-dimensional measurement method and device for process products based on robot scanning viewpoint planning. BACKGROUND

[0002] It is of great significance to obtain a three-dimensional digital model of a process product by a three-dimensional measurement device, not only for the protection, repair and replication of process products, but also for the analysis and secondary development design of process structures, and the digital model can also be used to establish a digital art gallery for the dissemination and exchange of civilization.

[0003] Currently, the robot three-dimensional measurement method is widely used in industrial detection, cultural and creative design, and cultural relic protection. The robot + scanner three-dimensional measurement method has the advantages of high automation, strong flexibility, large working space, and repeatable measurement, and can meet the automatic measurement of process products. The existing robot three-dimensional scanning mostly adopts manual teaching for scanning viewpoint planning, which not only has high labor intensity and experience requirement, but also is difficult to guarantee the quality, efficiency and integrity of scanning. Since there is a lack of prior information such as the geometric appearance and structure size of the measured object, how to plan appropriate robot scanning viewpoints and construct a digital model of the measured object is a challenging task for automatic three-dimensional measurement of process products. SUMMARY

[0004] In view of the above technical problems, the embodiments of the present application propose a three-dimensional measurement method and device for process products based on robot scanning viewpoint planning to solve the technical problems mentioned in the background section. The two-step scanning method of step-by-step rotation scanning and secondary fine scanning is used for viewpoint planning, so as to guarantee the integrity, precision and efficiency of scanning and realize the automatic measurement of process products.

[0005] In a first aspect, the present application provides a three-dimensional measurement method for process products based on robot scanning viewpoint planning, comprising the following steps:

[0006] Obtaining the size information of the measured object, determining the minimum bounding box according to the size information, planning the scanning viewpoints according to the minimum bounding box, and generating a coarse grid model based on the scanning viewpoints;

[0007] Discretizing the coarse grid model into a point cloud model, identifying the hole boundary feature points of the point cloud model by using the maximum angle criterion, clustering the hole boundary feature points, determining each local hole in the point cloud model, and performing secondary fine scanning on each local hole to generate a secondary fine scanning model;

[0008] The point cloud registration and fusion of the coarse grid model and the secondary fine scanning model is performed to obtain the digital model of the measured object.

[0009] As preferred, the scanning viewpoints are planned according to the minimum bounding box, specifically including:

[0010] The scanning head of the scanner starts scanning from the initial scanning viewpoint VP0 on the top of the minimum bounding box, and the turntable rotates one circle;

[0011] The scanning head moves to the next scanning viewpoint, and the turntable continues to rotate one circle;

[0012] The above step-by-step rotation scanning operation is repeated until all scanning viewpoints are traversed.

[0013] As preferred, it further includes:

[0014] The scanning viewpoint set is calculated according to the following formula Wherein, vp i represents the position of the scanning viewpoint VP i , represents the scanning direction of the scanning viewpoint VP i :

[0015]

[0016]

[0017]

[0018]

[0019] Wherein, θ is the angle between the scanning direction of the initial scanning viewpoint VP0 and the end scanning viewpoint VP n , XOY plane is the bottom coordinate plane on which the measured object is placed, l is the single face scanning length of the scanner, d is the scanning distance, H is the length of the measured object, and L is the height of the measured object.

[0020] As preferred, the coarse grid model is generated based on the scanning viewpoints, specifically including: importing the scanning viewpoints into the CAM software for simulation optimization, generating a robot executable program, and performing actual scanning to obtain the coarse grid model.

[0021] As preferred, the maximum angle criterion is used for hole recognition of the point cloud model to obtain the hole boundary feature points, specifically including:

[0022] According to the data point P(x0, y0, z0) and its normal line n(a, b, c) in the point cloud model, a normal vector plane S is defined, and the plane equation is:

[0023] a(x-x0)+b(y-y0)+c(z-z0)=0;

[0024] The neighborhood point set of data point P Projecting onto the normal vector plane yields the projection point P. i If i = 1, 2, ..., k, then the projection point P i '(x i ',y i ',z i The formula for calculating the coordinates of ') is:

[0025]

[0026]

[0027]

[0028] After obtaining the coordinates of the projection point, a projection point P is randomly selected. i And construct vector PP i Then sort them in a clockwise direction, and calculate the two adjacent vectors PP according to the clockwise direction. i '(x i '-x0,y i '-y0,z i '-z0) and PP' i+1 (x' i+1 -x0,y' i+1 -y0,z' i+1 The angle α between -z0) i :

[0029]

[0030]

[0031]

[0032] PP i '·PP' i+1 =(x' i -x0)(x' i+1 -x0)+(y' i -y0)(y' i+1 -y0)+(z' i -z0)(z' i+1 -z0);

[0033] Angle α i The maximum included angle α max Compared with the threshold, if the maximum included angle α max If the value is less than the threshold, then data point P is an interior point; if the maximum included angle α is less than the threshold...max If the distance is greater than the threshold value, the data point P is a hole boundary feature point.

[0034] Preferably, the method of hole boundary feature point clustering comprises a DBSCAN algorithm.

[0035] Preferably, a secondary fine scanning is performed on each local hole to generate a secondary fine scanning model, and the secondary fine scanning specifically comprises:

[0036] An OBB bounding box is calculated for each local hole, and then a scanning viewpoint is planned according to the size of the middle plane of the OBB bounding box;

[0037] Scanning viewpoint Position coordinates in the O-XYZ coordinate system:

[0038]

[0039]

[0040] The O'-X'Y'Z' coordinate system is a coordinate system constructed based on the maximum middle plane of the OBB bounding box, is a unit vector of the Z' axis of the O'-X'Y'Z' coordinate system, is a rotation matrix of the O'-X'Y'Z' coordinate system relative to the O-XYZ coordinate system, and O' O-XYZ is the coordinate of the center point O' of the OBB bounding box in the O-XYZ, which can be obtained when the OBB bounding box is calculated, and vp O'-X'Y'Z' (0, 0, d) is the position coordinates of the scanning viewpoint VP in the O'-X'Y'Z' coordinate system, and d is the scanning distance.

[0041] A genetic algorithm is used to determine the optimal scanning path.

[0042] The scanning viewpoint of each local hole is imported into CAM software, and simulation optimization is performed according to the optimal scanning path to generate a robot executable program, and an actual scanning is performed to obtain a secondary fine scanning model.

[0043] In a second aspect, the present application provides a process product three-dimensional measurement device based on robot scanning viewpoint planning, comprising:

[0044] The coarse grid model generation module is configured to acquire size information of the measured object, determine a minimum bounding box according to the size information, plan a scanning viewpoint according to the minimum bounding box, and generate a coarse grid model based on the scanning viewpoint;

[0045] The secondary fine scanning model generation module is configured to discretize the coarse grid model into a point cloud model, perform hole recognition on the point cloud model using a maximum angle criterion to obtain hole boundary feature points, cluster the hole boundary feature points, determine each local hole in the point cloud model, perform secondary fine scanning on each local hole, and generate a secondary fine scanning model.

[0046] The registration and fusion module is configured to perform point cloud registration and fusion on the coarse grid model and the secondary fine scanning model to obtain a digital model of the measured object.

[0047] In a third aspect, the present application provides an electronic device, comprising one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any of the implementation manners of the first aspect.

[0048] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, when the computer program is executed by a processor, the method described in any of the implementation manners of the first aspect is implemented.

[0049] Compared with the prior art, the present application has the following beneficial effects:

[0050] (1) The process product three-dimensional measurement method based on robot scanning viewpoint planning provided by the present application obtains the size information of the measured object by human measurement, performs preliminary scanning on the measured object by a step-by-step rotation scanning method to obtain a coarse grid model, performs hole boundary recognition and clustering on the coarse grid model by using a maximum angle criterion and a DBSCAN clustering algorithm, and performs secondary fine scanning viewpoint planning on the local hole region by using an OBB bounding box algorithm to obtain a secondary fine scanning model.

[0051] (2) The process product three-dimensional measurement method based on robot scanning viewpoint planning provided by the present application performs scanning path planning on the hole region in the secondary fine scanning model by using a genetic algorithm.

[0052] (3) The process product three-dimensional measurement method based on robot scanning viewpoint planning provided by the present application realizes a scanning viewpoint planning method for process products, avoids the low efficiency, high labor intensity, and high experience requirement of manual demonstration viewpoints, and effectively improves the scanning quality, efficiency, and integrity. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without any creative effort.

[0054] Figure 1 is an exemplary device architecture diagram to which an embodiment of the present application can be applied;

[0055] Figure 2 is a flowchart of a process of a three-dimensional measurement method for process products based on robot scanning viewpoint planning according to an embodiment of the present application;

[0056] Figure 3 is a flowchart of a process of a three-dimensional measurement method for process products based on robot scanning viewpoint planning according to an embodiment of the present application;

[0057] Figure 4 is a schematic diagram of step-by-step rotating scanning viewpoint planning of a three-dimensional measurement method for process products based on robot scanning viewpoint planning according to an embodiment of the present application;

[0058] Figure 5 is a coarse grid model of a certain wood carving process product obtained by step-by-step rotating scanning according to a three-dimensional measurement method for process products based on robot scanning viewpoint planning according to an embodiment of the present application;

[0059] Figure 6 is a schematic diagram of space point cloud projection and sorting according to an embodiment of the present application;

[0060] Figure 7 is a schematic diagram of a hole recognition result of a certain wood carving process product according to a three-dimensional measurement method for process products based on robot scanning viewpoint planning according to an embodiment of the present application;

[0061] Figure 8 is a schematic diagram of a hole clustering result of a certain wood carving process product according to a three-dimensional measurement method for process products based on robot scanning viewpoint planning according to an embodiment of the present application;

[0062] Figure 9 is a schematic diagram of viewpoint planning based on 0BB bounding box according to a three-dimensional measurement method for process products based on robot scanning viewpoint planning according to an embodiment of the present application;

[0063] Figure 10 is a schematic diagram of a hole viewpoint planning result of a certain wood carving process product according to a three-dimensional measurement method for process products based on robot scanning viewpoint planning according to an embodiment of the present application;

[0064] Figure 11A schematic diagram of an optimal scanning path calculated by a genetic algorithm for a process product three-dimensional measurement method based on robot scanning viewpoint planning according to an embodiment of the present application;

[0065] Figure 12 A schematic diagram of a secondary fine scanning model of a wood carving process product for a process product three-dimensional measurement method based on robot scanning viewpoint planning according to an embodiment of the present application;

[0066] Figure 13 A schematic diagram of a digitized model of a wood carving process product for a process product three-dimensional measurement method based on robot scanning viewpoint planning according to an embodiment of the present application;

[0067] Figure 14 A schematic diagram of a process product three-dimensional measurement device based on robot scanning viewpoint planning according to an embodiment of the present application;

[0068] Figure 15 A structural schematic diagram of a computer device suitable for implementing an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0069] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of the present application.

[0070] Figure 1 An exemplary device architecture 100 of a process product three-dimensional measurement method based on robot scanning viewpoint planning or a process product three-dimensional measurement device based on robot scanning viewpoint planning to which embodiments of the present application can be applied is shown.

[0071] As shown in Figure 1 , the device architecture 100 can include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0072] A user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various applications, such as data processing applications, file processing applications, etc. can be installed on the terminal devices 101, 102, 103.

[0073] Terminal devices 101, 102, and 103 can be either hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices, including but not limited to smartphones, tablets, laptops, and desktop computers. When terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software programs or software modules (e.g., software programs or software modules used to provide distributed services) or as a single software program or software module. No specific limitations are imposed here.

[0074] Server 105 can be a server that provides various services, such as a background data processing server that processes files or data uploaded by terminal devices 101, 102, and 103. The background data processing server can process the acquired files or data and generate processing results.

[0075] It should be noted that the three-dimensional measurement method of process products based on robot scanning viewpoint planning provided in this application embodiment can be executed by server 105 or by terminal devices 101, 102, and 103. Correspondingly, the three-dimensional measurement device of process products based on robot scanning viewpoint planning can be set in server 105 or in terminal devices 101, 102, and 103.

[0076] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Any number of terminal devices, networks, and servers can be included depending on implementation needs. If the data being processed does not need to be retrieved remotely, the above architecture may not include a network, requiring only servers or terminal devices.

[0077] Figure 2 The present application illustrates an embodiment of a method for three-dimensional measurement of manufactured goods based on robot scanning viewpoint planning, comprising the following steps:

[0078] S1. Obtain the size information of the object being measured, determine the minimum bounding box based on the size information, plan the scanning viewpoint based on the minimum bounding box, and generate a coarse mesh model based on the scanning viewpoint.

[0079] In a specific embodiment, planning the scanning viewpoint based on the minimum bounding box specifically includes:

[0080] The scanner head begins scanning from the initial scanning viewpoint VP0 at the top of the smallest bounding box, and the turntable rotates one revolution.

[0081] The scanning head moves to the next scanning viewpoint, and the turntable continues to rotate one revolution;

[0082] Repeat the step-by-step rotational scan operation as described above until all scan viewpoints have been traversed.

[0083] In specific embodiments, further comprising:

[0084] The scanning viewpoint set is calculated according to the following formula Wherein, vp i represents the position of the scanning viewpoint VP i , represents the scanning direction of the scanning viewpoint VP i :

[0085]

[0086]

[0087]

[0088]

[0089] Wherein, θ is the angle between the scanning direction of the initial scanning viewpoint VP0 and the end scanning viewpoint VP n , XOY plane is the bottom coordinate plane of the measured object, l is the single face scanning length of the scanner, d is the scanning distance, H is the length of the measured object, and L is the height of the measured object.

[0090] In specific embodiments, generating a coarse grid model based on the scanning viewpoints specifically includes: importing the scanning viewpoints into CAM software for simulation optimization, generating a robot executable program, and performing actual scanning to obtain a coarse grid model.

[0091] Specifically, referring to Figure 3 , a coarse grid model of the measured object is obtained by step-by-step rotary scanning based on the size information of the measured object. The size information includes length L, width W, and height H. Specifically, first, the size information of the measured object obtained by manual measurement is used to obtain the minimum bounding box. Then, the scanning viewpoints are planned according to the minimum bounding box: the scanner starts from the initial scanning viewpoint VP0 at the top of the minimum bounding box, the turntable rotates one circle, then the scanning head moves to the next scanning viewpoint, the turntable continues to rotate one circle, and the above operation is repeated until all the viewpoints are traversed, as shown in Figure 4 Due to the limitations of the scanning system itself and for subsequent convenience in data processing of the scanned digitized model, the scanning direction of the initial viewpoint VP0 and the end viewpoint VP n is set to 30° with the XOY plane, so that:

[0092]

[0093]

[0094] The scanned data is processed directly using the software that comes with the scanner to obtain a coarse grid model of the object being measured.

[0095] The embodiments of this application are as follows: Figure 4 Using a wood carving as an example, a step-by-step rotary scanning method was used to plan the viewpoint for the wood carving. The planned scanning viewpoint was then imported into CAM software for simulation optimization. Finally, an executable robot program was generated, and an actual scanning was performed to obtain its coarse mesh model, as shown below. Figure 5 As shown.

[0096] S2, the coarse mesh model is discretized into a point cloud model, and the maximum angle criterion is used to identify holes in the point cloud model to obtain the feature points of the hole boundary. The feature points of the hole boundary are clustered to determine each local hole in the point cloud model. A second fine scan is performed on each local hole to generate a second fine scan model.

[0097] In a specific embodiment, the maximum angle criterion is used to identify holes in the point cloud model to obtain hole boundary feature points, specifically including:

[0098] Based on the data point P(x0,y0,z0) and its normal n(a,b,c) in the point cloud model, a normal vector plane S is defined, and its equation is:

[0099] a(x-x0)+b(y-y0)+c(z-z0)=0;

[0100] The neighborhood point set of data point P Projecting onto the normal vector plane yields the projection point P. i If i = 1, 2, ..., k, then the projection point P i '(x i ',y i ',z i The formula for calculating the coordinates of ') is:

[0101]

[0102]

[0103]

[0104] After obtaining the coordinates of the projection point, a projection point P is randomly selected. i And construct vector PP i Then sort them in a clockwise direction, and calculate the two adjacent vectors PP according to the clockwise direction. i '(x i '-x0,y i '-y0,z i '-z0) and PP' i+1 (x'i+1 x0, y0 i+1 -y0, z0 i+1 -z0) between the angle a i :

[0105]

[0106]

[0107]

[0108] PP i '·PP' i+1 = (x' i -x0) (x' i+1 -x0) + (y' i -y0) (y' i+1 -y0) + (z' i -z0) (z' i+1 -z0) ;

[0109] The maximum angle a i in the angle a max is compared with a threshold value, if the maximum angle a max is less than the threshold value, the data point P is an internal point, if the maximum angle a max is greater than the threshold value, the data point P is a hole boundary feature point.

[0110] Specifically, the software matched with the scanner is used to discretize the rough grid model of the measured object into a point cloud model; the maximum angle criterion is used to identify the hole in the point cloud model, and the size of the threshold value is usually determined according to the spatial complexity and distribution density of the point cloud data, and the embodiment of the application finds through testing that when the threshold value is set to the hole boundary feature points can be better identified. The hole identification result of the point cloud model of a certain wood carving handicraft product is shown in Figure 7 .

[0111] In specific embodiments, the hole boundary feature point clustering method includes a DBSCAN algorithm.

[0112] Specifically, since the identified hole boundary feature point set contains all hole boundary feature points of the point cloud model, the identified hole boundary feature points need to be clustered to determine the number of holes and the single hole boundary feature point set of the point cloud model. Considering that the hole boundary feature point set has the characteristics of small data volume and obvious density variation, and the DBSCAN algorithm is a relatively representative density-based clustering algorithm, which reflects the density of data point set in space through neighborhood, does not need a preset cluster number before clustering, and can identify abnormal points as noise during clustering, in addition, it can also find clusters of any size and any shape. Therefore, the DBSCAN clustering algorithm is used to cluster the hole boundary feature points of a certain wood carving handicraft product, and the result is as shown in Figure 8 .

[0113] In specific embodiments, each local hole is subjected to secondary fine scanning to generate a secondary fine scanning model, specifically including:

[0114] The OBB bounding box of each local hole is calculated, and then the scanning view point is planned according to the size of the middle plane of the OBB bounding box;

[0115] The scanning view point The position coordinates in the O-XYZ coordinate system are:

[0116]

[0117] wherein the O'-X'Y'Z' coordinate system is a coordinate system constructed based on the maximum middle plane of the OBB bounding box, is a unit vector of the Z' axis of the O'-X'Y'Z' coordinate system, is a rotation matrix of the O'-X'Y'Z' relative to the O-XYZ coordinate system, O' O-XYZ is the coordinate of the center point O' of the OBB bounding box in the O-XYZ, which can be obtained when calculating the OBB bounding box, vp O'-X'Y'Z' (0, 0, d) is the position coordinates of the scanning view point VP in the O'-X'Y'Z' coordinate system, and d is the scanning distance;

[0118] A genetic algorithm is used to determine the optimal scanning path;

[0119] The scanning view point of each local hole is imported into the CAM software, and simulation optimization is performed according to the optimal scanning path to generate a robot executable program, and actual scanning is performed to obtain a secondary fine scanning model.

[0120] Specifically, the OBB bounding box of each local hole is calculated, and then the scanning view point is planned according to the size of the middle plane of the OBB bounding box, as shown in Figure 9As shown. In order to improve the efficiency of the secondary fine scanning, a genetic algorithm is used to determine the optimal scanning path, and the scanning viewpoint planning result of a certain wood carving point cloud model is as shown in Figure 10 As shown. The optimal scanning path is as shown in Figure 11 As shown. The point cloud model of the wood carving is imported into the CAM software, and the simulation and optimization are performed according to the optimal scanning path to avoid collision in the scanning process, and then the robot executable program is generated for actual scanning, and the scanning result is as shown in Figure 12 As shown.

[0121] S3, the point cloud registration and fusion of the coarse grid model and the secondary fine scanning model are performed to obtain the digital model of the measured object.

[0122] Specifically, the point cloud registration and fusion of the coarse grid model and the secondary fine scanning model are performed through the scanner supporting software to obtain the final digital model of the measured object. The registration result of the coarse model and the secondary fine scanning model of a certain wood carving handicraft is as shown in Figure 13 As shown.

[0123] The above steps S1-S3 do not represent the order between the steps, but only the step symbol.

[0124] Further referring to Figure 14 As an implementation of the method shown in the above figures, the application provides an embodiment of a handicraft three-dimensional measurement device based on robot scanning viewpoint planning. The device embodiment corresponds to the method embodiment shown in Figure 2 As shown. The device can be applied to various electronic devices.

[0125] The application embodiment provides a handicraft three-dimensional measurement device based on robot scanning viewpoint planning, which comprises:

[0126] The coarse grid model generation module 1 is configured to obtain the size information of the measured object, determine the minimum bounding box according to the size information, plan the scanning viewpoint according to the minimum bounding box, and generate the coarse grid model based on the scanning viewpoint;

[0127] The secondary fine scanning model generation module 2 is configured to discretize the coarse grid model into a point cloud model, identify the hole boundary feature points of the point cloud model by using the maximum angle criterion, cluster the hole boundary feature points, determine each local hole in the point cloud model, perform secondary fine scanning on each local hole, and generate a secondary fine scanning model;

[0128] The registration and fusion module 3 is configured to perform point cloud registration and fusion of the coarse grid model and the secondary fine scanning model to obtain the digital model of the measured object.

[0129] Reference will be made to Figure 15It illustrates an electronic device suitable for implementing embodiments of this application (e.g., Figure 1 A schematic diagram of the structure of a computer device 1500 (shown as a server or terminal device). Figure 15 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0130] like Figure 15 As shown, the computer device 1500 includes a central processing unit (CPU) 1501 and a graphics processing unit (GPU) 1502, which can perform various appropriate actions and processes according to programs stored in read-only memory (ROM) 1503 or programs loaded from storage portion 1509 into random access memory (RAM) 1504. The RAM 1504 also stores various programs and data required for the operation of the device 1500. The CPU 1501, GPU 1502, ROM 1503, and RAM 1504 are interconnected via a bus 1505. An input / output (I / O) interface 1506 is also connected to the bus 1505.

[0131] The following components are connected to I / O interface 1506: an input section 1507 including a keyboard, mouse, etc.; an output section 1508 including an LCD, speaker, etc.; a storage section 1509 including a hard disk, etc.; and a communication section 1510 including a network interface card, such as a LAN card, modem, etc. The communication section 1510 performs communication processing via a network such as the Internet. A drive 1511 may also be connected to I / O interface 1506 as needed. A removable medium 1512, such as a hard disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 1511 as needed so that computer programs read from it can be installed into storage section 1509 as needed.

[0132] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1510, and / or installed from removable medium 1512. When the computer program is executed by central processing unit (CPU) 1501 and graphics processing unit (GPU) 1502, the functions defined in the methods of this application are performed.

[0133] Note that the computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a computer-readable medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present context, a computer-readable medium can be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present context, a computer-readable signal medium can include a computer-readable program code in a baseband or propagated as carrier waves in a propagated data signal associating with a carrier wave. Such a propagated signal can take a wide variety of forms including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium that can be used to carry or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The program contained in the computer-readable medium can be transmitted in any suitable format including, but not limited to, wireless, wireline, optical fiber cable, RF, or any suitable combination thereof.

[0134] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0135] The flow and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of apparatuses, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow and block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or combinations of hardware and software.

[0136] The modules involved in the embodiments of the present application can be implemented in the form of software or in the form of hardware. The described modules can also be arranged in a processor.

[0137] As another aspect, the present application also provides a computer readable medium, which can be included in the electronic device described in the above embodiments, or can exist independently without being assembled into the electronic device. The computer readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire size information of a measured object, determine a minimum bounding box according to the size information, plan a scanning viewpoint according to the minimum bounding box, and generate a coarse mesh model based on the scanning viewpoint; discretize the coarse mesh model into a point cloud model, perform hole identification on the point cloud model using a maximum angle criterion to obtain hole boundary feature points, cluster the hole boundary feature points, determine each local hole in the point cloud model, perform secondary fine scanning on each local hole, and generate a secondary fine scanning model; and perform point cloud registration and fusion on the coarse mesh model and the secondary fine scanning model to obtain a digital model of the measured object.

[0138] The above description is merely the preferred embodiments and the explanation of the technical principles of the present application. It should be understood by those skilled in the art that the scope of the application involved in the present application is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combinations of the above technical features or equivalent features without departing from the above inventive concept. For example, the above features can be replaced with the technical features disclosed in the present application (but not limited to) having similar functions to form technical solutions.

Claims

1. A method for three-dimensional measurement of an arti¬ cle of manufacture based on robot scan viewpoint planning, characterized by, The method comprises the following steps: acquiring size information of the measured object, determining a minimum bounding box according to the size information, planning a scanning viewpoint according to the minimum bounding box, and specifically comprising: the scanning head of the scanner starts scanning from an initial scanning viewpoint VP0 at the top of the minimum bounding box, and the turntable rotates one circle; the scanning head moves to the next scanning viewpoint, and the turntable continues to rotate one circle; The above step-by-step rotational scanning operation is repeated until all scanning viewpoints are traversed; the set of scanning viewpoints is calculated according to the following formula wherein vp i represents the position of the scanning viewpoint VP i , represents the scanning direction of the scanning viewpoint VP i . wherein θ is an angle between a scanning direction of the initial scanning viewpoint VP0 and an end scanning viewpoint VP n and an XOY plane, the XOY plane is a bottom coordinate plane on which the measured object is placed, l is a single plane scanning length of the scanner, d is a scanning distance, H is a length of the measured object, and L is a height of the measured object; and generating a coarse mesh model based on the scanning viewpoints. discretizing the coarse grid model into a point cloud model, identifying holes in the point cloud model using the maximum angle criterion to obtain hole boundary feature points, clustering the hole boundary feature points to determine each local hole in the point cloud model, and performing secondary fine scanning on each local hole to generate a secondary fine scanning model; point cloud registration and fusion of the coarse grid model and the secondary fine scanning model to obtain a digital model of the measured object.

2. The robotic scan viewpoint planning based process artifact three-dimensional measurement method of claim 1, wherein, The generation of the coarse grid model based on the scanning viewpoint specifically comprises: importing the scanning viewpoint into CAM software for simulation optimization, generating a robot executable program, and performing actual scanning to obtain the coarse grid model.

3. The robotic scan viewpoint planning based process artifact three-dimensional measurement method of claim 1, wherein, The hole identification using the maximum angle criterion for the point cloud model to obtain the hole boundary feature points specifically comprises: defining a normal plane S according to a data point P(x0, y0, z0) and its normal n(a, b, c) in the point cloud model, and the plane equation is: a(x-x0)+b(y-y0)+c(z-z0)=0; The neighborhood point set of the data point P is projected onto the normal plane to obtain a projection point P i , i = 1, 2, …, k, then the coordinate calculation formula of the projection point P i '(x i , y i , z i ) is: After the coordinates of the projection points are obtained, a projection point P is randomly selected i and a vector PP is constructed i , then sorted in clockwise direction, according to the clockwise direction, the included angle α between two adjacent vectors PP i (x i '-x0,y i '-y0,z i '-z0) and PP i+1 (x i+1 '-x0,y i+1 '-y0,z i+1 '-z0) is calculated i : PP i '·PP' i+1 =(x' i -x0)(x' i+1 -x0)+(y' i -y0)(y' i+1 -y0)+(z' i -z0)(z' i+1 -z0); The maximum included angle a i between the included angle a max and a threshold value is compared, if the maximum included angle a max is less than the threshold value, the data point P is an internal point, if the maximum included angle a max is greater than the threshold value, the data point P is a hole boundary feature point.

4. The robotic scan viewpoint planning based process artifact three-dimensional measurement method of claim 1, wherein, The hole boundary feature point clustering method comprises a DBSCAN algorithm.

5. The robotic scan viewpoint planning based process artifact three-dimensional measurement method of claim 1, wherein, The secondary fine scanning on each local hole to generate a secondary fine scanning model specifically comprises: OBB bounding box calculation is performed on each local hole, and then scanning viewpoint planning is performed according to the size of the middle plane of the OBB bounding box; Scan viewpoint Position coordinates in O-XYZ coordinate system: Wherein, the O'-X'Y'Z' coordinate system is a coordinate system constructed based on the maximum middle plane of the OBB bounding box, is a unit vector of the Z' axis of the O'-X'Y'Z' coordinate system, is a rotation matrix of the O'-X'Y'Z' coordinate system relative to the O-XYZ coordinate system, O' O-XYZ is the coordinate of the center point O' of the OBB bounding box under the O-XYZ, which can be obtained when the OBB bounding box is calculated, vp O'-X'Y'Z' (0, 0, d) is the position coordinate of the scanning viewpoint VP under the O'-X'Y'Z' coordinate system; determining an optimal scanning path using a genetic algorithm; importing the scanning viewpoints of each local hole into CAM software, and performing simulation optimization according to the optimal scanning path to generate a robot executable program, and performing actual scanning to obtain the secondary fine scanning model.

6. A process product three-dimensional measurement device based on robot scanning viewpoint planning, adopting the process product three-dimensional measurement method based on robot scanning viewpoint planning according to any one of claims 1-5, characterized in that, comprises: a coarse grid model generation module configured to acquire size information of the measured object, determine a minimum bounding box according to the size information, plan a scanning viewpoint according to the minimum bounding box, and generate a coarse grid model based on the scanning viewpoint; a secondary fine scanning model generation module configured to discretize the coarse grid model into a point cloud model, identify holes in the point cloud model using the maximum angle criterion to obtain hole boundary feature points, cluster the hole boundary feature points to determine each local hole in the point cloud model, and perform secondary fine scanning on each local hole to generate a secondary fine scanning model; a registration and fusion module configured to perform point cloud registration and fusion of the coarse grid model and the secondary fine scanning model to obtain a digital model of the measured object.

7. An electronic device comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program, when executed by the processor, implements the method of any one of claims 1-5.

Images