CN115100416A - Irregular steel plate pose identification method and related equipment - Google Patents
Irregular steel plate pose identification method and related equipment Download PDFInfo
- Publication number
- CN115100416A CN115100416A CN202210736233.2A CN202210736233A CN115100416A CN 115100416 A CN115100416 A CN 115100416A CN 202210736233 A CN202210736233 A CN 202210736233A CN 115100416 A CN115100416 A CN 115100416A
- Authority
- CN
- China
- Prior art keywords
- point
- steel plate
- point cloud
- plane
- information
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Manipulator (AREA)
Abstract
The invention belongs to the field of automatic optical detection, and particularly relates to an irregular steel plate pose identification method and related equipment, wherein the method comprises the following steps: shooting a pose image of the steel plate, removing a background outside a steel plate detection area through preprocessing, and extracting point cloud information in the steel plate detection area; smoothing the point cloud information by a least square method to obtain point cloud origin data; dividing point cloud original point data by using a preset clustering algorithm to obtain single point cloud information of a single steel plate; carrying out pose identification on the individual point cloud information to obtain point cloud set data with normal vector characteristics; determining a best fit plane according to the point cloud set data; calculating the central point of the best fitting plane by using a Mean-shift algorithm; and acquiring coordinate information of the steel plate according to the best fit plane and the central point, and grabbing the steel plate by using a manipulator according to the coordinate information. The invention can improve the efficiency of the grabbing robot system, thereby improving the production efficiency.
Description
Technical Field
The invention belongs to the field of automatic optical detection, and particularly relates to an irregular steel plate pose identification method and related equipment.
Background
With the development of science and technology, the robot industry is continuously advanced, so that the robot technology improves the quality of life of people and is applied to various aspects of life, medical treatment, manufacturing and the like. The industrial production is one of the main applications of the robot, and the monotonous repeated labor in a factory, such as tasks of aligning, sorting, stacking, loading and unloading production objects in a production line, is changed from the original manual responsibility to the robot responsibility, so that the workload of factory staff is greatly reduced, and people can better concentrate on non-mechanical tasks. On the production line, the traditional feeding mechanism occupies a large area and has low reliability, and manual feeding can generate fatigue and danger. The traditional robot system is usually only suitable for a structured simple scene, single repeated operation is carried out in an off-line programming mode, irregular steel plates stacked in a scattered mode are grabbed in a common scene, the traditional machine vision algorithm can only segment and identify single position characteristics of the steel plates, and the pose calculation effect of workpieces stacked in the scattered mode is poor, so that the system based on the algorithm cannot efficiently guide the robot to grab operation, namely, the existing majority of robot systems cannot meet the intelligent requirement of daily promotion in industrial production.
Disclosure of Invention
The embodiment of the invention provides an irregular steel plate pose identification method and related equipment, and aims to solve the problem of low production efficiency caused by inaccurate identification of positions of irregular steel plates in the existing manufacturing industry.
In a first aspect, an embodiment of the present invention provides an irregular steel plate pose identification method, including the following steps:
s1, shooting a steel plate pose image, removing the background outside a steel plate detection area through pretreatment, and extracting point cloud information in the steel plate detection area;
s2, smoothing the point cloud information through a least square method to obtain point cloud origin data;
s3, segmenting the point cloud origin data by using a preset clustering algorithm to obtain single point cloud information of a single steel plate;
s4, carrying out pose identification on the single point cloud information to obtain point cloud set data with normal vector characteristics;
s5, determining a best fit plane according to the point cloud set data;
s6, calculating the center point of the best fitting plane by using a Mean-shift algorithm;
and S7, acquiring coordinate information of the steel plate according to the best fit plane and the central point, and grabbing the steel plate by using a manipulator according to the coordinate information.
Further, in step S1, the method of preprocessing includes:
removing outliers of point clouds in the steel plate pose image based on statistical filtering, wherein the outliers comprise noise around the point clouds;
and identifying the steel plate detection area by using an AABB bounding box and combining through filtering, and removing the influence of the area boundary.
Further, in step S3, the preset clustering algorithm specifically includes:
s31, sorting the point cloud origin data according to the Z-axis coordinate value, acquiring a seed point P with the largest Z-axis coordinate value, and putting the seed point P into a cluster set Q;
s32, constructing kd numbers related to the seed point P, searching n neighbors of the seed point P, calculating the distance between each neighbor and the seed point P, and putting the point corresponding to the neighbor with the distance smaller than a preset distance threshold value r into a neighbor array;
s33, traversing the neighbor array, calculating an included angle between a normal vector corresponding to each neighbor and a normal vector of the seed point P, putting a preset point of the neighbor with an included angle smaller than a preset included angle threshold value into the cluster set Q, wherein according to the definition, the cluster set Q satisfies the following relational expression:
s34, taking the next point of the seed point P in the cluster set Q as a new seed point, and repeating the steps S32-S34 until no new point can be added to the cluster set Q, wherein each point in the cluster set Q is the single point cloud information of the obtained single steel plate.
Furthermore, in step S4, the step of performing pose identification on the individual point cloud information to obtain point cloud set data with normal vector features includes the following sub-steps:
s41, calculating the point cloud centroid of a random point through a neighborhood point of the random point in the individual point cloud information;
s42, calculating a covariance matrix C through the random points and the point cloud centroids;
s43, calculating an eigenvector of the covariance matrix C by a singular value solution, wherein the minimum value of the eigenvector is the normal vector characteristic of the random point;
and S44, taking the corresponding points of which the values of the normal vector features are larger than a preset feature threshold value as the point cloud set data.
Further, in step S5, the step of determining a best fit plane according to the point cloud set data includes:
and randomly selecting three points in the point cloud set data to form a sampling plane by using a RANSAC method, calculating the distance between each point in the point cloud set data and the sampling plane, putting the points which are larger than a preset plane distance threshold value into a plane point set, repeating the steps until the number of the plane point concentrated points is maximum, and taking the sampling plane at the moment as the best fitting plane.
Further, in step S6, the step of calculating the center point of the best fit plane using the Mean-shift algorithm includes the following sub-steps:
s61, randomly acquiring the central point x in the best fitting plane i Searching said center point x using kd-Tree i Neighborhood S of k ;
S62, counting the central point x i And the neighborhood S k The vectors formed by the inner points are calculated by addition to obtain the sampling vectorsThe coordinate of the end point of the sampling vector is taken as x i+1 The sampling vectorThe following relation is satisfied:
s63, repeating the steps S61-S62 until the coordinates of the end point of the sampling vector do not change any more.
Further, in step S7, the coordinate information of the steel plate uses the best-fit plane as a plane where the steel plate is located, and uses the coordinates of the end point of the sampling vector as the coordinates of the plane where the steel plate is located.
In a second aspect, an embodiment of the present invention further provides an irregular steel plate pose recognition system, including:
the image acquisition module is used for shooting a steel plate pose image, removing the background outside a steel plate detection area through pretreatment, and extracting point cloud information in the steel plate detection area;
the data smoothing module is used for smoothing the point cloud information by a least square method to obtain point cloud origin data;
the segmentation module is used for segmenting the point cloud origin data by using a preset clustering algorithm to obtain single point cloud information of a single steel plate;
the pose identification module is used for carrying out pose identification on the single point cloud information to obtain point cloud set data with normal vector characteristics;
the fitting plane calculation module is used for determining a best fitting plane according to the point cloud set data;
the central point calculating module is used for calculating the central point of the optimal fitting plane by using a Mean-shift algorithm;
and the coordinate determination module is used for acquiring coordinate information of the steel plate according to the best fit plane and the central point and grabbing the steel plate by using a manipulator according to the coordinate information.
In a third aspect, an embodiment of the present invention further provides a computer device, including: the invention further provides a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the irregular steel plate pose identification method in any one of the above embodiments.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program implements the steps in the irregular steel plate pose identification method according to any one of the above embodiments.
The method has the advantages that the irregular steel plate position is identified by adopting the method of fitting the plane and then determining the coordinate information, so that the operation efficiency of a robot system for grabbing the steel plate in a factory environment can be improved, and the production efficiency is improved.
Drawings
FIG. 1 is a flowchart illustrating steps of an irregular steel plate pose identification method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an irregular steel plate pose recognition system 200 according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating steps of an irregular steel plate pose identification method according to an embodiment of the present invention, which specifically includes the following steps:
s1, shooting a steel plate pose image, removing the background outside the steel plate detection area through pretreatment, and extracting point cloud information in the steel plate detection area.
In the embodiment of the invention, the shooting object of the steel plate pose image is a steel plate on a transport plate or a transport frame, the placing positions of the steel plates are not completely consistent, and the height and the direction of the steel plates are different.
Further, in step S1, the method of preprocessing includes:
removing outliers of the point cloud in the steel plate pose image based on statistical filtering, wherein the outliers comprise noise around the point cloud;
and identifying the steel plate detection area by using an AABB bounding box and combining through filtering, and removing the influence of the area boundary.
And S2, smoothing the point cloud information by a least square method to obtain point cloud origin data.
And S3, segmenting the point cloud origin data by using a preset clustering algorithm to obtain the individual point cloud information of a single steel plate.
Further, in step S3, the preset clustering algorithm specifically includes:
s31, sorting the point cloud origin data according to the Z-axis coordinate value, acquiring a seed point P with the largest Z-axis coordinate value, and putting the seed point P into a cluster set Q;
s32, constructing kd numbers related to the seed point P, searching n neighbors of the seed point P, calculating the distance between each neighbor and the seed point P, and putting the point corresponding to the neighbor with the distance smaller than a preset distance threshold value r into a neighbor array;
s33, traversing the neighbor array, calculating an included angle between a normal vector corresponding to each neighbor and a normal vector of the seed point P, and putting a preset point of the neighbor with an included angle smaller than a preset included angle threshold value into the cluster set Q, wherein the cluster set Q satisfies the following relational expression according to the definition:
s34, taking the next point of the seed point P in the cluster set Q as a new seed point, and repeating the steps S32-S34 until no new point can be added to the cluster set Q, wherein each point in the cluster set Q is the single point cloud information of the obtained single steel plate.
And S4, carrying out pose identification on the single point cloud information to obtain point cloud set data with normal vector characteristics.
Furthermore, in step S4, the step of performing pose identification on the individual point cloud information to obtain point cloud set data with normal vector features includes the following sub-steps:
and S41, calculating the point cloud centroid of a random point through the neighborhood point of the random point in the individual point cloud information.
Illustratively, let the random point be p i Said neighborhood point comprising at least p i1 、p i2 、p i3 …, the point cloud centroid satisfies:
and S42, calculating a covariance matrix C through the random points and the point cloud centroid.
According to step S41, the covariance matrix C satisfies:
s43, calculating the eigenvector of the covariance matrix C by a singular value solution, wherein the minimum value of the eigenvector is the normal vector characteristic of the random point.
At λ j For the value of the j-th characteristic,for the jth eigenvector, the singular value solution can be represented as:
and S44, taking the corresponding point of which the value of the normal vector characteristic is greater than a preset characteristic threshold value as the point cloud set data.
And S5, determining the best fitting plane according to the point cloud set data.
Further, in step S5, the step of determining a best fit plane according to the point cloud set data includes:
and randomly selecting three points in the point cloud set data to form a sampling plane by using a RANSAC method, calculating the distance from each point in the point cloud set data to the sampling plane, putting the points which are greater than a preset plane distance threshold value into a plane point set, repeating the steps until the number of the plane point concentration points is maximum, and taking the sampling plane at the moment as the best fitting plane.
And S6, calculating the central point of the best fitting plane by using a Mean-shift algorithm.
Further, in step S6, the step of calculating the center point of the best fit plane using the Mean-shift algorithm includes the following sub-steps:
s61, randomly acquiring the central point x in the best fitting plane i Searching said center point x using kd-Tree i Neighborhood S of k ;
S62, counting the central point x i And the neighborhood S k The vectors formed by the inner points are calculated by addition to obtain the sampling vectorsThe coordinate of the end point of the sampling vector is taken as x i+1 The sample vectorThe following relation is satisfied:
s63, repeating the steps S61-S62 until the coordinates of the end point of the sampling vector do not change any more.
And S7, acquiring coordinate information of the steel plate according to the best fit plane and the central point, and grabbing the steel plate by using a manipulator according to the coordinate information.
Further, in step S7, the coordinate information of the steel plate is determined by taking the best fit plane as a plane where the steel plate is located and taking the coordinates of the end point of the sampling vector as the coordinates of the plane where the steel plate is located.
The method has the advantages that the irregular steel plate position is identified by adopting the method of fitting the plane and then determining the coordinate information, so that the operation efficiency of a robot system for grabbing the steel plate in a factory environment can be improved, and the production efficiency is improved.
Referring to fig. 2, fig. 2 is a schematic structural diagram of an irregular steel plate pose recognition system 200 according to an embodiment of the present invention, where the irregular steel plate pose recognition system 200 includes:
the image acquisition module 201 is used for shooting a steel plate pose image, removing the background outside a steel plate detection area through preprocessing, and extracting point cloud information in the steel plate detection area;
a data smoothing module 202, configured to smooth the point cloud information by using a least square method to obtain point cloud origin data;
the segmentation module 203 is configured to segment the point cloud origin data by using a preset clustering algorithm to obtain individual point cloud information of a single steel plate;
a pose identification module 204, configured to perform pose identification on the individual point cloud information to obtain point cloud set data with normal vector features;
a fitting plane calculation module 205 for determining a best fitting plane from the point cloud set data;
a center point calculating module 206, configured to calculate a center point of the best fit plane using a Mean-shift algorithm;
and the coordinate determination module 207 is used for acquiring coordinate information of the steel plate according to the best fit plane and the central point and grabbing the steel plate by using a manipulator according to the coordinate information.
The irregular steel plate pose identification system 200 can implement the steps in the irregular steel plate pose identification method in the above embodiment, and can implement the same technical effects, and the description in the above embodiment is referred to, and is not repeated here.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a computer device provided in an embodiment of the present invention, where the computer device 300 includes: a memory 302, a processor 301, and a computer program stored on the memory 302 and executable on the processor 301.
The processor 301 calls the computer program stored in the memory 302 to execute the steps in the irregular steel plate pose identification method provided by the embodiment of the present invention, and with reference to fig. 1, the method specifically includes:
and S1, shooting a steel plate pose image, removing the background outside the steel plate detection area through preprocessing, and extracting point cloud information in the steel plate detection area.
Further, in step S1, the method of preprocessing includes:
removing outliers of the point cloud in the steel plate pose image based on statistical filtering, wherein the outliers comprise noise around the point cloud;
and identifying the steel plate detection area by using an AABB bounding box and combining through filtering, and removing the influence of the area boundary.
And S2, smoothing the point cloud information by a least square method to obtain point cloud origin data.
And S3, segmenting the point cloud origin data by using a preset clustering algorithm to obtain the single point cloud information of a single steel plate.
Further, in step S3, the preset clustering algorithm specifically includes:
s31, sorting the point cloud origin data according to the Z-axis coordinate value, acquiring a seed point P with the largest Z-axis coordinate value, and putting the seed point P into a cluster set Q;
s32, constructing kd numbers related to the seed point P, searching n neighbors of the seed point P, calculating the distance between each neighbor and the seed point P, and putting the point corresponding to the neighbor with the distance smaller than a preset distance threshold value r into a neighbor array;
s33, traversing the neighbor array, calculating an included angle between a normal vector corresponding to each neighbor and a normal vector of the seed point P, putting a preset point of the neighbor with an included angle smaller than a preset included angle threshold value into the cluster set Q, wherein according to the definition, the cluster set Q satisfies the following relational expression:
s34, taking the next point of the seed point P in the cluster set Q as a new seed point, and repeating the steps S32-S34 until no new point can be added to the cluster set Q, wherein each point in the cluster set Q is the single point cloud information of the obtained single steel plate.
And S4, carrying out pose identification on the single point cloud information to obtain point cloud set data with normal vector characteristics.
Further, in step S4, the step of performing pose recognition on the individual point cloud information to obtain point cloud set data with normal vector features includes the following sub-steps:
s41, calculating the point cloud mass center of a random point through a neighborhood point of the random point in the single point cloud information;
s42, calculating a covariance matrix C through the random points and the point cloud centroid;
s43, calculating an eigenvector of the covariance matrix C by a singular value solution, wherein the minimum value of the eigenvector is the normal vector characteristic of the random point;
and S44, taking the corresponding points of which the values of the normal vector features are larger than a preset feature threshold value as the point cloud set data.
And S5, determining a best fit plane according to the point cloud set data.
Further, in step S5, the step of determining a best fit plane according to the point cloud set data includes:
and randomly selecting three points in the point cloud set data to form a sampling plane by using a RANSAC method, calculating the distance from each point in the point cloud set data to the sampling plane, putting the points which are greater than a preset plane distance threshold value into a plane point set, repeating the steps until the number of the plane point concentration points is maximum, and taking the sampling plane at the moment as the best fitting plane.
And S6, calculating the central point of the best fitting plane by using a Mean-shift algorithm.
Further, in step S6, the step of calculating the center point of the best fit plane using the Mean-shift algorithm includes the following sub-steps:
s61, randomly obtaining the central point x in the best fitting plane i Searching said middle using kd-TreeCenter point x i Of (2) neighborhood S k ;
S62, counting the central point x i And the neighborhood S k The vectors formed by the inner points are calculated by addition to obtain the sampling vectorsThe coordinate of the end point of the sampling vector is taken as x i+1 The sampling vectorThe following relation is satisfied:
s63, repeating the steps S61-S62 until the coordinates of the end point of the sampling vector do not change any more.
And S7, acquiring coordinate information of the steel plate according to the best fit plane and the central point, and grabbing the steel plate by using a manipulator according to the coordinate information.
Further, in step S7, the coordinate information of the steel plate is determined by taking the best fit plane as a plane where the steel plate is located and taking the coordinates of the end point of the sampling vector as the coordinates of the plane where the steel plate is located.
The computer device 300 provided in the embodiment of the present invention can implement the steps in the method for identifying an irregular steel plate pose in the foregoing embodiment, and can implement the same technical effects, and the description in the foregoing embodiment is omitted here for brevity.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process and step in the irregular steel plate pose identification method provided in the embodiment of the present invention, and can implement the same technical effect, and in order to avoid repetition, details are not repeated here.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the description of the foregoing embodiments, it is clear to those skilled in the art that the method of the foregoing embodiments may be implemented by software plus a necessary general hardware platform, and certainly may also be implemented by hardware, but in many cases, the former is a better implementation. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, which are illustrative, but not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. An irregular steel plate pose identification method is characterized by comprising the following steps:
s1, shooting a steel plate pose image, removing the background outside a steel plate detection area through preprocessing, and extracting point cloud information in the steel plate detection area;
s2, smoothing the point cloud information by a least square method to obtain point cloud origin data;
s3, segmenting the point cloud origin data by using a preset clustering algorithm to obtain single point cloud information of a single steel plate;
s4, performing pose identification on the single point cloud information to obtain point cloud set data with normal vector characteristics;
s5, determining a best fit plane according to the point cloud set data;
s6, calculating the center point of the best fitting plane by using a Mean-shift algorithm;
and S7, acquiring coordinate information of the steel plate according to the best fit plane and the central point, and grabbing the steel plate by using a manipulator according to the coordinate information.
2. The irregular steel plate pose identification method according to claim 1, wherein in step S1, the preprocessing method comprises:
removing outliers of the point cloud in the steel plate pose image based on statistical filtering, wherein the outliers comprise noise around the point cloud;
and identifying the steel plate detection area by using an AABB bounding box and combining through filtering, and removing the influence of the area boundary.
3. The irregular steel plate pose identification method according to claim 1, wherein in step S3, the preset clustering algorithm specifically comprises:
s31, sorting the point cloud origin data according to the Z-axis coordinate value, acquiring a seed point P with the largest Z-axis coordinate value, and putting the seed point P into a cluster set Q;
s32, constructing kd numbers related to the seed point P, searching n neighbors of the seed point P, calculating the distance between each neighbor and the seed point P, and putting the point corresponding to the neighbor with the distance smaller than a preset distance threshold value r into a neighbor array;
s33, traversing the neighbor array, calculating an included angle between a normal vector corresponding to each neighbor and a normal vector of the seed point P, and putting a preset point of the neighbor with an included angle smaller than a preset included angle threshold value into the cluster set Q, wherein the cluster set Q satisfies the following relational expression according to the definition:
s34, taking the next point of the seed point P in the cluster set Q as a new seed point, and repeating the steps S32-S34 until no new point can be added to the cluster set Q, wherein each point in the cluster set Q is the single point cloud information of the obtained single steel plate.
4. The irregular steel plate pose identification method according to claim 3, wherein in the step S4, the step of performing pose identification on the individual point cloud information to obtain point cloud set data with normal vector features comprises the following sub-steps:
s41, calculating the point cloud centroid of a random point through a neighborhood point of the random point in the individual point cloud information;
s42, calculating a covariance matrix C through the random points and the point cloud centroids;
s43, calculating an eigenvector of the covariance matrix C by a singular value solution, wherein the minimum value of the eigenvector is the normal vector characteristic of the random point;
and S44, taking the corresponding point of which the value of the normal vector characteristic is greater than a preset characteristic threshold value as the point cloud set data.
5. The irregular steel plate pose identification method according to claim 4, wherein in step S5, the step of determining the best fit plane according to the point cloud set data specifically comprises:
and randomly selecting three points in the point cloud set data to form a sampling plane by using a RANSAC method, calculating the distance from each point in the point cloud set data to the sampling plane, putting the points which are greater than a preset plane distance threshold value into a plane point set, repeating the steps until the number of the plane point concentration points is maximum, and taking the sampling plane at the moment as the best fitting plane.
6. The irregular steel plate pose identification method according to claim 5, wherein the step of calculating the center point of the best fit plane using a Mean-shift algorithm in step S6 comprises the substeps of:
s61, randomly acquiring the central point x in the best fitting plane i Searching the center point x using a kd-Tree i Of (2) neighborhood S k ;
S62, counting the central point x i And the neighborhood S k The vectors formed by the inner points are calculated by addition to obtain the sampling vectorsThe coordinate of the end point of the sampling vector is taken as x i+1 The sample vectorThe following relation is satisfied:
s63, repeating the steps S61-S62 until the coordinates of the end point of the sampling vector do not change any more.
7. The irregular steel plate pose identification method according to claim 6, wherein in step S7, the best fit plane is used as the steel plate plane, and the end point coordinate of the sampling vector is used as the coordinate of the steel plate plane.
8. An irregular steel plate pose recognition system, comprising:
the image acquisition module is used for shooting a steel plate pose image, removing the background outside a steel plate detection area through preprocessing, and extracting point cloud information in the steel plate detection area;
the data smoothing module is used for smoothing the point cloud information by a least square method to obtain point cloud origin data;
the segmentation module is used for segmenting the point cloud origin data by using a preset clustering algorithm to obtain single point cloud information of a single steel plate;
the pose identification module is used for carrying out pose identification on the single point cloud information to obtain point cloud set data with normal vector characteristics;
the fitting plane calculation module is used for determining a best fitting plane according to the point cloud set data;
the central point calculating module is used for calculating the central point of the best fitting plane by using a Mean-shift algorithm;
and the coordinate determination module is used for acquiring coordinate information of the steel plate according to the best fit plane and the central point and grabbing the steel plate by using a manipulator according to the coordinate information.
9. A computer device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the irregular steel plate pose identification method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which when executed by a processor, implements the steps in the irregular steel plate pose recognition method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210736233.2A CN115100416A (en) | 2022-06-27 | 2022-06-27 | Irregular steel plate pose identification method and related equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210736233.2A CN115100416A (en) | 2022-06-27 | 2022-06-27 | Irregular steel plate pose identification method and related equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115100416A true CN115100416A (en) | 2022-09-23 |
Family
ID=83295593
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210736233.2A Pending CN115100416A (en) | 2022-06-27 | 2022-06-27 | Irregular steel plate pose identification method and related equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115100416A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115908426A (en) * | 2023-02-22 | 2023-04-04 | 江苏金恒信息科技股份有限公司 | Plate sample processing method and system based on three-dimensional point cloud positioning algorithm |
-
2022
- 2022-06-27 CN CN202210736233.2A patent/CN115100416A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115908426A (en) * | 2023-02-22 | 2023-04-04 | 江苏金恒信息科技股份有限公司 | Plate sample processing method and system based on three-dimensional point cloud positioning algorithm |
CN115908426B (en) * | 2023-02-22 | 2023-06-23 | 江苏金恒信息科技股份有限公司 | Board sample processing method and system based on three-dimensional point cloud positioning algorithm |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109801337B (en) | 6D pose estimation method based on instance segmentation network and iterative optimization | |
US20200057917A1 (en) | Object Location Method, Device and Storage Medium Based on Image Segmentation | |
CN112070818A (en) | Robot disordered grabbing method and system based on machine vision and storage medium | |
Sui et al. | Sum: Sequential scene understanding and manipulation | |
CN108280488B (en) | Grippable object identification method based on shared neural network | |
CN111428731A (en) | Multi-class target identification and positioning method, device and equipment based on machine vision | |
US12017368B2 (en) | Mix-size depalletizing | |
CN111428815A (en) | Mechanical arm grabbing detection method based on Anchor angle mechanism | |
Czajewski et al. | 3D object detection and recognition for robotic grasping based on RGB-D images and global features | |
Schnieders et al. | Fully convolutional one-shot object segmentation for industrial robotics | |
CN115100416A (en) | Irregular steel plate pose identification method and related equipment | |
CN114029941B (en) | Robot grabbing method and device, electronic equipment and computer medium | |
CN113762159B (en) | Target grabbing detection method and system based on directional arrow model | |
CN113591839A (en) | Feature extraction model construction method, target detection method and device | |
CN113034526A (en) | Grabbing method, grabbing device and robot | |
CN114800533B (en) | Sorting control method and system for industrial robot | |
CN109815887B (en) | Multi-agent cooperation-based face image classification method under complex illumination | |
CN116188540A (en) | Target identification and pose estimation method based on point cloud information | |
Arbeiter et al. | Efficient segmentation and surface classification of range images | |
Chen et al. | A Framework for 3D Object Detection and Pose Estimation in Unstructured Environment Using Single Shot Detector and Refined LineMOD Template Matching | |
CN114049380A (en) | Target object positioning and tracking method and device, computer equipment and storage medium | |
Ali et al. | Segmentation and pose estimation of planar metallic objects | |
Rasouli et al. | Integrating three mechanisms of visual attention for active visual search | |
Zhang et al. | Robotic grasp detection using effective graspable feature selection and precise classification | |
Hofer et al. | Depth-based visual servoing using low-accurate arm |
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 |