CN114310875B - Crankshaft positioning identification method, device, storage medium and equipment - Google Patents
Crankshaft positioning identification method, device, storage medium and equipment Download PDFInfo
- Publication number
- CN114310875B CN114310875B CN202111563443.8A CN202111563443A CN114310875B CN 114310875 B CN114310875 B CN 114310875B CN 202111563443 A CN202111563443 A CN 202111563443A CN 114310875 B CN114310875 B CN 114310875B
- Authority
- CN
- China
- Prior art keywords
- crankshaft
- bounding box
- length
- minimum bounding
- initial minimum
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 230000004323 axial length Effects 0.000 claims abstract description 37
- 239000013598 vector Substances 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 7
- 239000000463 material Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The application provides a crankshaft positioning identification method, a device, a storage medium and equipment, wherein the method comprises the following steps: acquiring an initial minimum bounding box of a crankshaft based on point cloud data of the crankshaft to be identified, and extracting a first length of the initial minimum bounding box, wherein the first length is the axial length of the initial minimum bounding box; judging whether the first length is smaller than a preset reference length, wherein the reference length is the axial length of the crankshaft; and if the first length is smaller than the preset reference length, extending along the initial minimum bounding box to search for missing point clouds, so as to obtain a final minimum bounding box of the crankshaft. The application effectively solves the problem of inaccurate crankshaft identification caused by disconnection of the point cloud of the eccentric position of the crankshaft in the sorting process, and improves the reliability of crankshaft sorting.
Description
Technical Field
The present application relates to the field of robotics, and in particular, to a crankshaft positioning and identifying method, apparatus, storage medium and device.
Background
In the manufacturing industry, material sorting work is one of the very critical links. The sorting of materials mainly comprises the step of arranging various production materials at specified positions according to a certain sorting principle. In the work, the robot is guided to sort materials through the 3D visual positioning and identifying method, so that the labor cost is reduced. The design of a proper identification algorithm for different materials is a key factor for improving the overall detection rate.
Fig. 1 is a real object diagram of a crankshaft, because of the specificity of the crankshaft structure, the area with a block at the head of the crankshaft is cylindrical and other areas are not on the same axis, namely the eccentric position of the crankshaft, when the 3D camera is used for scanning the crankshaft to acquire point cloud data under the condition of stacking the crankshafts, the point cloud image of the crankshaft as shown in fig. 2 (a) can be obtained, as can be seen from fig. 2 (a), the condition that the point cloud data is broken occurs at the eccentric position of the crankshaft, the initial minimum bounding box of the crankshaft obtained under the condition is shown in fig. 2 (b), the condition that the minimum bounding box cannot completely enclose the whole crankshaft is existed, a certain error is caused for complete identification of the crankshaft, further, the subsequent failure of identifying the head position of the crankshaft is caused, and the difficulty is brought to the sorting work of the crankshaft.
Disclosure of Invention
The present application has been made in view of the above-mentioned problems, and it is an object of the present application to provide a crankshaft positioning recognition method, apparatus, storage medium and device which overcome or at least partially solve the above-mentioned problems.
In one aspect of the present application, a crankshaft positioning identification method is provided, comprising the steps of:
acquiring an initial minimum bounding box of a crankshaft based on point cloud data of the crankshaft to be identified, and extracting a first length of the initial minimum bounding box, wherein the first length is the axial length of the initial minimum bounding box;
judging whether the first length is smaller than a preset reference length, wherein the reference length is the axial length of the crankshaft;
and if the first length is smaller than the preset reference length, extending along the initial minimum bounding box to search for missing point clouds, so as to obtain a final minimum bounding box of the crankshaft.
Further, the extending along the initial minimum bounding box to search for the missing point cloud, and obtaining the final minimum bounding box of the crankshaft includes:
extracting an axial vector of the initial minimum bounding box;
the axial end face corresponding to the axial vector of the initial minimum bounding box is extended for a second length in the forward direction, and a first bounding box is obtained;
reversely extending the axial end face corresponding to the axial vector of the initial minimum bounding box by a second length to obtain a second bounding box;
and selecting a bounding box with a large number of point clouds contained inside from the first bounding box and the second bounding box as a final minimum bounding box of the crankshaft.
Further, the method further comprises: and calculating a difference value between the reference length and the first length, and taking the difference value as a second length.
Further, after obtaining the final minimum bounding box, the method further comprises:
and taking one end of the final minimum bounding box, which is larger than the initial minimum bounding box by a second length, as the head of the crankshaft.
Further, the method further comprises:
and if the first length is equal to the reference length, taking the initial minimum bounding box as a final minimum bounding box of the crankshaft.
Further, after the final minimum bounding box is obtained, the method further includes:
two adjacent bounding boxes with the same size are respectively established at the two end faces of the final minimum bounding box along the axial vector to the direction of the central point at each end face;
and respectively calculating the difference of the number of the point clouds of the two adjacent bounding boxes with the same size of each end face, and taking the end with the larger difference of the number of the point clouds as the head of the crankshaft.
Further, the acquiring the initial minimum bounding box of the crankshaft based on the point cloud data of the crankshaft to be identified comprises:
acquiring point cloud data of stacked crankshafts;
segmenting the point cloud data by using European clustering, and acquiring each segmented point cloud set;
and extracting the minimum bounding box of each point cloud set, wherein the minimum bounding box is the initial minimum bounding box of each crankshaft.
Further, before the obtaining of the initial minimum bounding box of the crankshaft based on the point cloud data of the crankshaft to be identified, the method further includes:
and analyzing the image data of the single crankshaft to obtain the axial length of the single crankshaft and the length of the head end face of the single crankshaft from the eccentric position, wherein the axial length of the two adjacent bounding boxes with the same size is larger than or equal to the length of the head end face of the single crankshaft from the eccentric position, and the axial length of the two adjacent bounding boxes with the same size is smaller than half of the axial length of the single crankshaft.
In another aspect of the present application, there is provided a crankshaft positioning recognition apparatus including:
the parameter extraction module is used for acquiring an initial minimum bounding box of the crankshaft based on point cloud data of the crankshaft to be identified, and extracting a first length of the initial minimum bounding box, wherein the first length is the axial length of the initial minimum bounding box;
the judging module is used for judging whether the first length is smaller than a preset reference length or not, and the reference length is the axial length of the crankshaft;
and the data searching module is used for extending along the initial minimum bounding box to search for missing point clouds if the first length is smaller than the preset reference length, so as to obtain a final minimum bounding box of the crankshaft.
In another aspect of the application, a computer readable storage medium is provided, in which a computer program is stored, wherein the computer program is arranged to perform the steps of the above method when run.
In another aspect of the present application, a crankshaft sorting apparatus is provided, including a robotic arm, a main control chip including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.
According to the crankshaft positioning identification method, the device, the storage medium and the equipment, point cloud data missing from the crankshaft are searched on the basis of the obtained initial minimum bounding box of the crankshaft, so that the final minimum bounding box capable of completely bounding the crankshaft image data is obtained, the problem of inaccurate crankshaft identification caused by disconnection of point cloud at the eccentric position of the crankshaft in the sorting process is effectively solved, and the reliability of crankshaft sorting is improved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. In the drawings:
FIG. 1 is a pictorial view of a crankshaft;
FIG. 2 (a) is a point cloud image of a stacked crankshaft;
FIG. 2 (b) is an initial minimum bounding box image of stacked crankshafts;
FIG. 3 is a flowchart of a crankshaft positioning identification method according to an embodiment of the present application;
FIG. 4 is a diagram of a method for searching a final minimum bounding box of a crankshaft according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a method for obtaining a crankshaft head position according to an embodiment of the present application;
FIG. 6 is a schematic diagram of a crankshaft positioning and identifying device according to an embodiment of the present application;
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. In addition, the technical features of the different embodiments of the present application described below may be combined with each other as long as they do not collide with each other.
Fig. 3 schematically illustrates a flowchart of a crankshaft positioning recognition method according to an embodiment of the present application, and as shown in fig. 3, the crankshaft positioning recognition method according to the present application includes the following steps:
s1, acquiring an initial minimum bounding box of a crankshaft based on point cloud data of the crankshaft to be identified, and extracting a first length of the initial minimum bounding box, wherein the first length is the axial length of the initial minimum bounding box;
in one embodiment of the present application, the obtaining the initial minimum bounding box of the crankshaft includes: acquiring point cloud data of the crankshaft; segmenting the point cloud data by using European clustering, and acquiring a segmented point cloud set; and extracting a minimum bounding box of each point cloud set, wherein the minimum bounding box is the initial minimum bounding box of the crankshaft.
Further, each initial minimum bounding box at least comprises image data such as side length, center point coordinates, unit vectors corresponding to the side length, vertex coordinates and the like of the initial minimum bounding box. Wherein the center point coordinates are (x o ,y o ,z o ) The axial vector (vector corresponding to the longest side) of the initial minimum bounding box is denoted as major vector, the vertex is marked as Pn (xn, yn, zn), and the value of n is 1-8.
It should be noted that, in the embodiment of the present application, the longest side of the initial minimum bounding box is taken as the axis of the initial minimum bounding box, and the first length of the initial minimum bounding box is the axial length of the initial minimum bounding box.
As can be seen from fig. 2 (b), the initial minimum bounding box of the crankshaft obtained through the image processing includes two cases, one is the initial minimum bounding box that completely identifies the crankshaft and one is the initial minimum bounding box that is broken off by the point cloud data at the eccentric position of the crankshaft, so after the initial minimum bounding box of the crankshaft is obtained, it is necessary to determine whether the initial minimum bounding box completely encloses the point cloud data of the crankshaft.
S2, judging whether the first length is smaller than a reference length, wherein the reference length is the axial length of the crankshaft;
and S3, if the first length is smaller than a preset reference length, extending along the initial minimum bounding box to search for missing point clouds, and obtaining a final minimum bounding box of the crankshaft.
In the embodiment of the application, when the first length of the initial minimum bounding box is smaller than the axial length of the crankshaft, the missing point cloud of the crankshaft is required to be searched, and then the point cloud data of the complete bounding crankshaft is obtained.
Further, fig. 4 schematically illustrates a schematic diagram of searching a final minimum bounding box of the crankshaft according to an embodiment of the present application, and as shown in fig. 4, the method for obtaining the final minimum bounding box of the crankshaft by extending along the initial minimum bounding box to search for missing point clouds is to reestablish two bounding box first bounding box and second bounding box along two end surfaces of the initial minimum bounding box in the axial direction respectively in a direction away from the central point of the initial minimum bounding box by extending a second length. The second length is a difference between the reference length and the first length.
Further, since only one of the first bounding box and the second bounding box contains the point cloud data of the missing portion of the crankshaft within the bounding box, it is possible to determine which bounding box is the final smallest bounding box containing the entire crankshaft point cloud data by comparing the number of point clouds within the two bounding boxes.
Further, the method of searching for the final minimum bounding box of the crankshaft further includes the steps not shown in fig. 1 of:
s31, extracting an axial vector of the initial minimum bounding box;
s32, extending a second length in the forward direction of the axial end face corresponding to the axial vector of the initial minimum bounding box to obtain a first bounding box;
further, the method for obtaining the first bounding box includes obtaining four vertex coordinates P1, P2, P3 and P4 of an axial end face corresponding to the initial minimum bounding box axial vector in a forward direction, extending the four vertices in the forward direction along the axial vector for a second length, and obtaining four new vertices np1, np2, np3 and np4.
Further, the first bounding box is established with np1, np2, np3, np4 and P5, P6, P7, P8 as vertices.
S33, reversely extending a second length at the axial end face corresponding to the axial vector reverse direction of the initial minimum bounding box to obtain a second bounding box;
further, the method for obtaining the second bounding box includes obtaining four vertex coordinates P5, P6, P7 and P8 of an axial end face corresponding to the initial minimum bounding box in an opposite direction to the axial vector, and extending the four vertices in the opposite direction to the axial vector for a second length to obtain four new vertices np5, np6, np7 and np8.
Further, a second bounding box is established with p1, p2, p3, p4, and nP5, nP6, nP7, nP8 as vertices.
S34, selecting a bounding box with a large number of point clouds contained in the first bounding box and the second bounding box as a final minimum bounding box of the crankshaft.
Further, when sorting the materials on the crankshaft, the head position of the crankshaft needs to be judged so as to place the crankshaft at the corresponding sorting position in order. Therefore, after step S34, step S35 is also included
And S35, taking one end of the final minimum bounding box, which is larger than the initial minimum bounding box by a second length, as the head of the crankshaft.
Further, in step S2, when it is determined that the first length is equal to the reference length, the initial minimum bounding box is a final minimum bounding box including the entire crankshaft point cloud data. Likewise, after the final minimum bounding box of the crankshaft is obtained, the head position of the crankshaft needs to be determined.
Further, fig. 5 schematically shows a schematic view of the acquisition of the crankshaft head position. The method for judging the position of the head of the crankshaft comprises the following steps:
s41, respectively establishing two adjacent bounding boxes with the same size on two end faces of the final minimum bounding box along the axial vector to the direction of the central point on each end face;
it should be noted that, in the embodiment of the present application, two adjacent bounding boxes with equal size should be guaranteed to include the eccentric position of the crankshaft at one end of the crankshaft head. It is therefore necessary to define the axial length of two adjacent bounding boxes of equal size.
Specifically, the axial length of two adjacent surrounding boxes with the same size is greater than or equal to the length of the head end face of the single crankshaft from the eccentric position, and the axial length of the two adjacent surrounding boxes with the same size is less than half of the axial length of the single crankshaft. In a specific implementation, the axial length of two adjacent bounding boxes of equal size is set at a value within this range.
S42, respectively calculating the difference of the number of the point clouds of the two adjacent bounding boxes with the same size of each end face, and taking one end with the larger difference of the number of the point clouds as the head of the crankshaft.
Further, before positioning and identifying the crankshaft, the method further comprises the step of obtaining basic parameters of the crankshaft, wherein the method for obtaining basic parameters of the crankshaft comprises the steps of clearing the crankshaft on the sorting platform, placing a single crankshaft on the platform, obtaining point cloud images of different directions of the single crankshaft, and obtaining the axial length of the single crankshaft and the length of the head end face of the single crankshaft from the eccentric position by analyzing image data of the point cloud images of different directions of the single crankshaft.
The axial length of the two adjacent surrounding boxes with the same size is larger than or equal to the length of the head end face of the single crankshaft from the eccentric position, and the axial length of the two adjacent surrounding boxes with the same size is smaller than half of the axial length of the single crankshaft.
Further, after the final minimum bounding box of the crankshaft and the head information of the crankshaft are determined, the mechanical arm can be controlled to sort the crankshaft and place the crankshaft in a corresponding position.
Fig. 6 schematically illustrates a crankshaft positioning and identifying device according to an embodiment of the present application, referring to fig. 6, the crankshaft positioning and identifying device according to an embodiment of the present application specifically includes a parameter extraction module 601, a judgment module 602, and a data search module 603, where:
the parameter extraction module 601 is configured to obtain an initial minimum bounding box of a crankshaft based on point cloud data of the crankshaft to be identified, and extract a first length of the initial minimum bounding box, where the first length is an axial length of the initial minimum bounding box;
a judging module 602, configured to judge whether the first length is smaller than a preset reference length, where the reference length is an axial length of the crankshaft;
and the data searching module 603 is configured to extend along the initial minimum bounding box to search for a missing point cloud if the first length is smaller than a preset reference length, so as to obtain a final minimum bounding box of the crankshaft.
Further, the apparatus also includes a first selection module,
the parameter extraction module 601 is further configured to extract an axial vector of the initial minimum bounding box;
the data searching module 603 extends a second length in the forward direction of the axial end face corresponding to the axial vector of the initial minimum bounding box, so as to obtain a first bounding box;
the data searching module 603 extends a second length reversely on the axial end face corresponding to the axial vector of the initial minimum bounding box reversely to obtain a second bounding box;
the first selection module selects, as a final minimum bounding box of the crankshaft, a bounding box having a large number of point clouds contained inside from the first bounding box and the second bounding box.
Further, the device also comprises a first calculation module, which is used for calculating the difference value between the reference length and the first length, and taking the difference value as a second length.
Further, the device also comprises a second selection module,
the second selection module takes one end of the final minimum bounding box, which is larger than the initial minimum bounding box by a second length, as the head of the crankshaft.
Further, the first selecting module is further configured to take the initial minimum bounding box as a final minimum bounding box of the crankshaft if the first length is equal to the reference length.
Further, the apparatus also includes a second computing module,
the data searching module 603 establishes two adjacent bounding boxes with the same size along the axial vector to the direction of the central point on two end surfaces of the final minimum bounding box respectively;
and the second calculation module is used for calculating the difference of the number of the point clouds of the two adjacent bounding boxes with the same size of each end face respectively, and taking one end with the larger difference of the number of the point clouds as the head of the crankshaft.
Further, the device also comprises an image processing module for acquiring the point cloud data of the crankshaft; segmenting the point cloud data by using European clustering, and acquiring a segmented point cloud set; and extracting a minimum bounding box of each point cloud set, wherein the minimum bounding box is the initial minimum bounding box of the crankshaft.
Further, the parameter extraction module 601 is further configured to perform image data analysis on a single crankshaft to obtain an axial length of the single crankshaft and a length of a head end face of the single crankshaft from an eccentric position, where an axial length of two adjacent bounding boxes with the same size is greater than or equal to a length of the head end face of the single crankshaft from the eccentric position, and an axial length of the two adjacent bounding boxes with the same size is less than half of the axial length of the single crankshaft.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present application without undue burden.
According to the crankshaft positioning identification method and device, the missing point cloud data of the crankshaft are searched on the basis of the obtained initial minimum bounding box of the crankshaft, so that the final minimum bounding box which can completely enclose the crankshaft image data is obtained, the problem of inaccurate crankshaft identification caused by disconnection of the point cloud at the eccentric position of the crankshaft in the sorting process is effectively solved, and the reliability of crankshaft sorting is improved.
Further, an embodiment of the present application provides a computer-readable storage medium having stored thereon a computer program, wherein the computer program is configured to perform the steps of the crankshaft positioning identification method in the above embodiment when run.
In this embodiment, the modules/units integrated with the crankshaft positioning recognition device may be stored in a computer readable storage medium if implemented as software functional units and sold or used as a stand alone product. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
According to another aspect of the embodiment of the present application, there is further provided a crankshaft sorting apparatus, including a mechanical arm and a main control chip, where the main control chip includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor, and when the processor executes the computer program, the steps in the above-mentioned embodiments of the respective robot gripping control methods are implemented, for example, S1-S3 shown in fig. 3. Alternatively, the processor may implement the functions of the modules/units in the crankshaft positioning recognition apparatus embodiment described above when executing the computer program, such as the parameter extraction module 601, the judgment module 602, and the data search module 603 shown in fig. 6.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like that is central to the crankshaft sorting apparatus and that utilizes various interfaces and lines to connect the various parts of the overall crankshaft sorting apparatus.
Those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the application and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. A crankshaft positioning and identifying method is characterized by comprising the following steps:
acquiring an initial minimum bounding box of a crankshaft based on point cloud data of the crankshaft to be identified, and extracting a first length of the initial minimum bounding box, wherein the first length is the axial length of the initial minimum bounding box;
judging whether the first length is smaller than a preset reference length, wherein the reference length is the axial length of the crankshaft;
if the first length is smaller than the preset reference length, extending along the initial minimum bounding box to search for missing point clouds, and obtaining a final minimum bounding box of the crankshaft;
the method further comprises the steps of:
and if the first length is equal to the reference length, taking the initial minimum bounding box as a final minimum bounding box of the crankshaft.
2. The method of claim 1, wherein the extending along the initial minimum bounding box to search for missing point clouds, resulting in a final minimum bounding box for the crankshaft comprises:
extracting an axial vector of the initial minimum bounding box;
the axial end face corresponding to the axial vector of the initial minimum bounding box is extended for a second length in the forward direction, and a first bounding box is obtained;
reversely extending the axial end face corresponding to the axial vector of the initial minimum bounding box by a second length to obtain a second bounding box;
and selecting a bounding box with a large number of point clouds contained inside from the first bounding box and the second bounding box as a final minimum bounding box of the crankshaft.
3. The method according to claim 2, wherein the method further comprises:
and calculating a difference value between the reference length and the first length, and taking the difference value as a second length.
4. A method according to claim 3, wherein after obtaining the final minimal bounding box, the method further comprises:
and taking one end of the final minimum bounding box, which is larger than the initial minimum bounding box by a second length, as the head of the crankshaft.
5. The method of claim 1, wherein after obtaining the final minimum bounding box, the method further comprises:
two adjacent bounding boxes with the same size are respectively established at the two end faces of the final minimum bounding box along the axial vector to the direction of the central point at each end face;
and respectively calculating the difference of the number of the point clouds of the two adjacent bounding boxes with the same size of each end face, and taking the end with the larger difference of the number of the point clouds as the head of the crankshaft.
6. The method of claim 1, wherein the obtaining an initial minimum bounding box of the crankshaft based on point cloud data of the crankshaft to be identified comprises:
acquiring point cloud data of stacked crankshafts;
segmenting the point cloud data by using European clustering, and acquiring each segmented point cloud set;
and extracting the minimum bounding box of each point cloud set, wherein the minimum bounding box is the initial minimum bounding box of each crankshaft.
7. The method of claim 5, wherein prior to the acquiring the initial minimum bounding box of the crankshaft based on the point cloud data of the crankshaft to be identified, the method further comprises:
and analyzing the image data of the single crankshaft to obtain the axial length of the single crankshaft and the length of the head end face of the single crankshaft from the eccentric position, wherein the axial length of the two adjacent bounding boxes with the same size is larger than or equal to the length of the head end face of the single crankshaft from the eccentric position, and the axial length of the two adjacent bounding boxes with the same size is smaller than half of the axial length of the single crankshaft.
8. A crankshaft positioning and identification device, the device comprising:
the parameter extraction module is used for acquiring an initial minimum bounding box of the crankshaft based on point cloud data of the crankshaft to be identified, and extracting a first length of the initial minimum bounding box, wherein the first length is the axial length of the initial minimum bounding box;
the judging module is used for judging whether the first length is smaller than a preset reference length or not, and the reference length is the axial length of the crankshaft;
the data searching module is used for extending along the initial minimum bounding box to search for missing point clouds if the first length is smaller than a preset reference length, so as to obtain a final minimum bounding box of the crankshaft;
the crankshaft further comprises a first selection module, wherein the first selection module is further used for taking the initial minimum bounding box as a final minimum bounding box of the crankshaft if the first length is equal to the reference length.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program, wherein the computer program is arranged to perform the steps of the method of any of claims 1-7 when run.
10. A crankshaft sorting apparatus comprising a robotic arm, a main control chip comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor performs the steps of the method according to any one of claims 1-7 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111563443.8A CN114310875B (en) | 2021-12-20 | 2021-12-20 | Crankshaft positioning identification method, device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111563443.8A CN114310875B (en) | 2021-12-20 | 2021-12-20 | Crankshaft positioning identification method, device, storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114310875A CN114310875A (en) | 2022-04-12 |
| CN114310875B true CN114310875B (en) | 2023-12-05 |
Family
ID=81053232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111563443.8A Active CN114310875B (en) | 2021-12-20 | 2021-12-20 | Crankshaft positioning identification method, device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114310875B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063898A (en) * | 2014-06-30 | 2014-09-24 | 厦门大学 | Three-dimensional point cloud auto-completion method |
| CN104392476A (en) * | 2014-12-04 | 2015-03-04 | 上海岩土工程勘察设计研究院有限公司 | Method of extracting three-dimensional axis of tunnel based on minimum bounding box algorithm |
| CN107481274A (en) * | 2017-08-11 | 2017-12-15 | 武汉理工大学 | A kind of three-dimensional makees the robustness reconstructing method of object point cloud |
| CN109671174A (en) * | 2018-12-20 | 2019-04-23 | 北京中飞艾维航空科技有限公司 | A kind of pylon method for inspecting and device |
| CN110120075A (en) * | 2019-05-17 | 2019-08-13 | 百度在线网络技术（北京）有限公司 | Method and apparatus for handling information |
| CN112509145A (en) * | 2020-12-22 | 2021-03-16 | 珠海格力智能装备有限公司 | Material sorting method and device based on three-dimensional vision |
| WO2021092771A1 (en) * | 2019-11-12 | 2021-05-20 | Oppo广东移动通信有限公司 | Target detection method and apparatus, and device and storage medium |
| CN113705669A (en) * | 2021-08-27 | 2021-11-26 | 上海商汤临港智能科技有限公司 | Data matching method and device, electronic equipment and storage medium |
-
2021
- 2021-12-20 CN CN202111563443.8A patent/CN114310875B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063898A (en) * | 2014-06-30 | 2014-09-24 | 厦门大学 | Three-dimensional point cloud auto-completion method |
| CN104392476A (en) * | 2014-12-04 | 2015-03-04 | 上海岩土工程勘察设计研究院有限公司 | Method of extracting three-dimensional axis of tunnel based on minimum bounding box algorithm |
| CN107481274A (en) * | 2017-08-11 | 2017-12-15 | 武汉理工大学 | A kind of three-dimensional makees the robustness reconstructing method of object point cloud |
| CN109671174A (en) * | 2018-12-20 | 2019-04-23 | 北京中飞艾维航空科技有限公司 | A kind of pylon method for inspecting and device |
| CN110120075A (en) * | 2019-05-17 | 2019-08-13 | 百度在线网络技术（北京）有限公司 | Method and apparatus for handling information |
| WO2021092771A1 (en) * | 2019-11-12 | 2021-05-20 | Oppo广东移动通信有限公司 | Target detection method and apparatus, and device and storage medium |
| CN112509145A (en) * | 2020-12-22 | 2021-03-16 | 珠海格力智能装备有限公司 | Material sorting method and device based on three-dimensional vision |
| CN113705669A (en) * | 2021-08-27 | 2021-11-26 | 上海商汤临港智能科技有限公司 | Data matching method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114310875A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008809B (en) | Method and device for acquiring form data and server | |
| US9483707B2 (en) | Method and device for recognizing a known object in a field of view of a three-dimensional machine vision system | |
| CN108364311B (en) | Automatic positioning method for metal part and terminal equipment | |
| CN111652085B (en) | Object identification method based on combination of 2D and 3D features | |
| US9418313B2 (en) | Method for searching for a similar image in an image database based on a reference image | |
| US8687895B2 (en) | Image processing apparatus, image processing method, and computer-readable medium | |
| CN111242240A (en) | Material detection method and device and terminal equipment | |
| Sansoni et al. | Optoranger: A 3D pattern matching method for bin picking applications | |
| CN111598076B (en) | Method and device for detecting and processing date in label image | |
| CN114783068A (en) | Gesture recognition method, gesture recognition device, electronic device and storage medium | |
| Huang et al. | Implementation of workpiece recognition and location based on opencv | |
| CN114972489A (en) | Tray identification method and device, storage medium and intelligent forklift equipment | |
| CN108960247B (en) | Image significance detection method and device and electronic equipment | |
| Mishchenko et al. | Model-based chart image classification | |
| EP2458556A1 (en) | Marker generation device, marker generation detection system, marker generation detection device, marker, marker generation method, and program therefor | |
| CN113516619B (en) | Product surface flaw identification method based on image processing technology | |
| CN114331961A (en) | Method for defect detection of an object | |
| CN109815763A (en) | Detection method, device and the storage medium of two dimensional code | |
| CN114310875B (en) | Crankshaft positioning identification method, device, storage medium and equipment | |
| CN110378337B (en) | Visual input method and system for drawing identification information of metal cutting tool | |
| CN117218633A (en) | Article detection method, device, equipment and storage medium | |
| CN115984759A (en) | Substation switch state identification method and device, computer equipment and storage medium | |
| CN116542926A (en) | Method, device, equipment and storage medium for identifying defects of two-dimension codes of battery | |
| CN115984219A (en) | Product surface defect detection method and device, electronic equipment and storage medium | |
| CN113139932B (en) | Deep learning defect image identification method and system based on ensemble learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |