CN113743492B - Method and device for ordering positions of rows and columns of pressing plates - Google Patents
Method and device for ordering positions of rows and columns of pressing plates Download PDFInfo
- Publication number
- CN113743492B CN113743492B CN202111004495.1A CN202111004495A CN113743492B CN 113743492 B CN113743492 B CN 113743492B CN 202111004495 A CN202111004495 A CN 202111004495A CN 113743492 B CN113743492 B CN 113743492B
- Authority
- CN
- China
- Prior art keywords
- points
- point
- coordinate
- coordinate points
- corner
- 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
- 238000003825 pressing Methods 0.000 title claims abstract description 94
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012545 processing Methods 0.000 claims abstract description 12
- 230000009466 transformation Effects 0.000 claims description 47
- 239000011159 matrix material Substances 0.000 claims description 29
- 238000007621 cluster analysis Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 230000001131 transforming effect Effects 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 abstract description 17
- 230000008569 process Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Economics (AREA)
- Mathematical Optimization (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method and a device for ordering the positions of rows and columns of pressing plates. According to the invention, after the coordinate point of each pressing plate is obtained through target detection, the coordinate point is used for realizing the ordering of the pressing plate row and column positions, which is equivalent to the problem of converting the ordering into two-dimensional ordering, and the processing process is simplified. The coordinate points are processed and then are sequenced by adopting a clustering method, so that the fact that the number of the pressing plates is a few lines can be automatically judged, the information such as parameter threshold values of the clusters is not required to be set manually, the operation is simple, the accuracy is high, the generalization capability of the pressing plate pictures with different resolutions and different row numbers is high, and the experience threshold value is not required to be adjusted for specific application scenes.
Description
Technical Field
The invention relates to the technical field of intelligent monitoring and control of power grids, in particular to a method and a device for ordering positions of rows and columns of pressing plates.
Background
Along with the comprehensive construction and deep application of the intelligent substation, the level of intellectualization and automation of secondary equipment is higher and higher. The pressing plate is an important tie for connecting the protection device with the primary equipment, and the accuracy and rationality of the switching state directly influence the stable, safe and efficient operation of the transformer substation. Currently, the state monitoring of the pressing plate is mainly determined by manual visual observation. However, the number of the protection pressing plates in the intelligent substation is large, and false detection is caused by false misjudgment.
Aiming at the problem of automatic recognition of the state of the pressing plate, students at home and abroad develop a great deal of researches, including an image processing method for performing feature matching based on computer vision and directly recognizing and positioning the pressing plate based on a target detection network. In the aspect of ordering the row positions of the pressing plates, the coordinate positions are generally adopted for direct judgment, however, in practical application, the problems of offset of shooting viewing angles and the like exist, and the row ordering cannot be effectively completed.
Disclosure of Invention
Based on the above situation in the prior art, the invention aims to provide a method and a device for ordering the positions of pressing plates, which improve the accuracy of ordering the positions of the pressing plates and avoid potential safety hazards possibly caused by manual equipment operation.
To achieve the above object, according to one aspect of the present invention, there is provided a platen array position sorting method, including the steps of:
s1, acquiring coordinate points of each pressing plate to be sequenced;
s2, acquiring a coordinate point which is an outer point in the point set from the obtained coordinate points;
s3, acquiring coordinate points of four corner points in the obtained coordinate points which are external points;
S4, performing perspective transformation on coordinate points of the four corner points to obtain a transformation matrix M from the coordinate points of each corner point to four vertexes of a rectangle;
s5, performing perspective transformation on the matrix M, and transforming coordinate points of all pressing plates into the rectangular area;
and S6, performing cluster analysis on the transformed coordinate points to obtain row and column positions of each pressing plate.
Further, the acquiring the coordinate point which is the outer point in the point set includes:
S21, randomly selecting three points from the obtained coordinate points to serve as an outer point set;
S22, traversing the rest coordinate points, judging whether each coordinate point is in an area surrounded by an outer point set, and if yes, not processing the coordinate point; if not, updating the outer point set, and adding the coordinate point into the outer point set.
Further, the acquiring the coordinate points of the outer points in the point set further includes:
S23, when the outlier set is changed, judging whether all outliers in the outlier set are in a triangle surrounded by any three other outliers, and if so, deleting the outliers from the outlier set; if not, the outlier is not processed.
Further, the obtaining the coordinate points of the four corner points includes:
Recording the current judging outer point as A, selecting another outer point B as a datum point, traversing the rest outer points C, and calculating the angles of AB and AC;
if the angle is smaller than the threshold value, the point A is the corner point; otherwise, the point A is a non-corner point; to obtain four corner points.
Further, using perspective transformation for coordinate points of four corner points to obtain a transformation matrix M from the coordinate point of each corner point to four vertices of a rectangle includes:
the transformation matrix M is obtained according to the following formulas (1) and (2):
wherein, (x 1,y1),(x2,y2),(x3,y3),(x4,y4) is coordinates ;(x′1,y′1),(x′2,y′2),(x′3,y′3),(x′4,y′4) of four corner points, which are coordinates of four corner points after the transformation; n=1, 2,3,4;
further, the transforming the matrix M to transform coordinate points of all the pressing plates into the rectangular area includes:
All coordinate points are brought into the above formula (2) to obtain transformed coordinates.
Further, performing cluster analysis on the transformed coordinate points to obtain row and column positions of each pressing plate includes:
Performing cluster analysis on the ordinate values in each transformed coordinate point to obtain the optimal category number as the number of the rows of the pressing plate;
the coordinate points of each row of pressing plates are arranged from small to large according to the abscissa value.
Further, after step S1, the method further includes the steps of:
performing straight line fitting on the acquired coordinate point set;
calculating the distance between each coordinate point and the fitted straight line, and executing the step S2 if the distance is greater than or equal to a set threshold value;
Otherwise, the coordinate points are arranged from small to large according to the abscissa value.
According to another aspect of the invention, there is provided a press plate rank position ordering apparatus, including a coordinate point acquisition module, an outer point acquisition module, a corner point acquisition module, a transformation matrix acquisition module, a coordinate point transformation module, and a rank position ordering module; wherein,
The coordinate point acquisition module is used for acquiring coordinate points of each pressing plate to be ordered;
the external point acquisition module is used for acquiring coordinate points which are external points in the point set in the obtained coordinate points;
The corner acquisition module is used for acquiring coordinate points of four corner points in the obtained coordinate points which are external points;
the transformation matrix acquisition module is used for obtaining a transformation matrix M from coordinate points of each corner point to four vertexes of a rectangle by using perspective transformation for the coordinate points of the four corner points;
The coordinate point transformation module is used for performing perspective transformation on the matrix M and transforming coordinate points of all pressing plates into the rectangular area;
the rank position ordering module is used for carrying out cluster analysis on the transformed coordinate points to obtain rank positions of each pressing plate.
According to a third aspect of the present invention, there is provided a storage medium storing a computer program which, when executed by a processor, implements the method of any one of claims 1-8.
In summary, the invention provides a method and a device for ordering the positions of rows and columns of pressing plates, which are characterized in that after coordinate points of each pressing plate are obtained, angular points are searched in the coordinate points, and clustering analysis is performed after the coordinate points are transformed according to the angular points and by utilizing perspective transformation, so that the positions of rows and columns of each pressing plate are obtained. The invention has the following beneficial technical effects:
(1) After the coordinate point of each pressing plate is obtained through target detection, the coordinate point is used for realizing the ordering of the pressing plate row and column positions, which is equivalent to the problem of converting the pressing plate row and column positions into two-dimensional ordering, and the processing process is simplified.
(2) The method has the advantages that after the coordinate points are processed, the method of clustering is adopted for sorting, the fact that the pressing plates share a plurality of rows can be automatically judged, information such as parameter threshold values of clustering is not needed to be set manually, the clustering number corresponding to the optimal value is found according to the outline coefficients of the evaluation indexes, namely, the fact that the pressing plates share a plurality of rows is automatically judged, the operation is simple and convenient, the accuracy is high, the picture generalization capability of the pressing plates aiming at different resolutions and different row numbers is high, and the experience threshold value is not needed to be adjusted aiming at specific application scenes.
(3) Aiming at the condition that only a single row of pressing plates is needed, the pressing plates are missed to be detected or other screen cabinet pressing plates are included in the recognition result, special steps are set for processing, the conditions are screened out in advance, and recognition errors possibly caused by the special conditions are avoided.
Drawings
FIG. 1 is a flow chart of a platen array position ordering method of the present invention;
FIG. 2 is a platen picture for object detection;
FIG. 3 is a schematic diagram of coordinate point positions after coordinate points are acquired;
FIG. 4 is a schematic view of the obtained outlier position;
FIG. 5 is a schematic view of the acquired corner locations;
FIG. 6 is a schematic diagram of transformed coordinate point locations;
FIG. 7 is a profile factor of the clustering result from 2 to 8 passes of the cluster number k;
FIG. 8 is a schematic diagram of a rank ordering result for a platen;
FIG. 9 is a schematic diagram of the coordinate positions of only one row of platens;
FIG. 10 is a schematic diagram of the coordinate locations of a platen in which a missed detection exists in the platen area;
FIG. 11 is a block diagram of a platen array position ordering apparatus according to the present invention.
Detailed Description
The objects, technical solutions and advantages of the present invention will become more apparent by the following detailed description of the present invention with reference to the accompanying drawings. It should be understood that the description is only illustrative and is not intended to limit the scope of the invention. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the present invention.
The following describes the technical scheme of the present invention in detail with reference to the accompanying drawings. According to one embodiment of the present invention, there is provided a method for ordering positions of rows and columns of pressing plates, the method having a flow chart as shown in fig. 1, comprising the steps of:
S1, acquiring coordinate points of each pressing plate to be ordered. The method comprises the steps of firstly obtaining pictures containing the pressing plates to be ordered, obtaining a detection result by adopting a target detection method for the pictures, wherein the detection result is a plurality of rectangular frames containing target pressing plates, and taking the center point coordinates of each rectangular frame as coordinate points of the pressing plates for the convenience of calculation. The neural network may be used for target detection, where the target detection network includes, but is not limited to, YOLO V3, SSD, and other target detection networks. After the detection result is obtained, each detected platen target needs to be judged to be in a row and column, which is equivalent to converting the row and column into a two-dimensional ordering problem, n platen switches detected by the target are selected, a single point, such as a center point, in each platen region is selected to represent the position of each platen switch, namely the coordinate point of the platen, and the problem is simplified as follows: for n points with coordinates (x 1,y1)、(x2,y2)、…、(xn,yn) on the two-dimensional plane, the points can be divided into a plurality of rows and columns according to the positions, and the number of rows and the number of columns of each point are determined. For example, a picture with 27 detected platens is shown in FIG. 2, after target detection and acquisition of coordinate points for each platen, changing to a positional ordering of 27 points as shown in FIG. 3.
S2, acquiring the coordinate points which are external points in the point set in the obtained coordinate points, wherein the corner points are the external points, so that the external points are acquired firstly to eliminate the interference of the internal points, and the complexity of directly solving the corner points is reduced. FIG. 4 shows a schematic representation of the obtained outlier position, comprising the steps of:
S21, randomly selecting three points as an outer point set
S22, traversing the rest of the outer points, judging whether the outer points are in the area surrounded by the outer point set by a ray method, and if so, not processing the current point; if outside the area, updating the outlier set, and adding the current point into the outlier.
S23, judging all the outer points after the outer point set is changed, and eliminating newly formed inner points after the outer point set is updated, wherein the specific steps are that judging each outer point in the set by a ray method, and if the current point is not in a triangle formed by any three points, judging the outer point; otherwise, the point is a false outlier, and the point is deleted from the outlier set.
The ray method is used for judging the relation between the points and the areas, rays in any direction are made through the points, and if the angles between the points and the polygonal areas are even numbers (including 0), the points are outside the polygonal areas, namely the points are outer points; if odd, the point is inside the polygonal area, i.e. the inner point.
S3, acquiring coordinate points of four corner points in the obtained coordinate points which are external points. Specifically, the current judging outer point is recorded as A, another outer point B is selected as a reference point, the rest outer points C are traversed, and the angles of AB and AC are calculated; if the angle is smaller than the threshold value, the point A is the corner point; otherwise, the point A is a non-corner point; to obtain four corner points (x 1,y1),(x2,y2),(x3,y3),(x4,y4). A schematic diagram of the acquired corner locations is shown in fig. 5.
S4, performing perspective transformation on coordinate points of the four corner points to obtain a transformation matrix M from the coordinate points of each corner point to the four vertexes of a rectangle. The homography transformation matrix M for transforming the four corner points into rectangular distribution can be obtained by taking the four corner points as reference points. The transformation matrix M may be obtained, for example, according to the following formulas (1) and (2):
After the four corner points are preset to be transformed into rectangles, if the transformed corner point coordinates are (x′1,y′1),(x′2,y′2),(x′3,y′3),(x′4,y′4),, the coordinates need to meet the condition that the corner points are connected into rectangles, namely:
the homography matrix realizes distortion correction, and for the original point and the transformed point, the transformation relation can be expressed as follows:
Wherein, (x 1,y1),(x2,y2),(x3,y3),(x4,y4) is coordinates ;(x′1,y′1),(x′2,y′2),(x′3,y′3),(x′4,y′4) of four corner points, which are coordinates of four corner points after transformation; n=1, 2,3,4; After bringing the parameters into equations (1) and (2), 8 elements of the matrix M can be found.
S5, performing perspective transformation on the matrix M, and transforming coordinate points of all pressing plates into the rectangular area. All coordinate points are brought into the above formula (2) to obtain transformed coordinates. Fig. 6 shows a schematic diagram of the transformed coordinate point positions.
And S6, performing cluster analysis on the transformed coordinate points to obtain row and column positions of each pressing plate. Performing cluster analysis on the ordinate values in each transformed coordinate point to obtain the optimal category number as the number of the rows of the pressing plate; the coordinate points of each row of pressing plates are arranged from small to large according to the abscissa value. Taking the 27 coordinate points as an example, cluster analysis is used on the ordinate of the 27 transformed points, for example, a Kmeans clustering method can be used, the clustering number k is traversed from 2 to 8 (generally, the pressing plate does not exceed 8 rows, and the upper limit can be increased according to requirements), a contour coefficient is used as an index for evaluating the clustering effect, the value range of the contour coefficient is [ -1,1], the larger the contour coefficient represents the better the clustering effect, as shown in fig. 7, the maximum value of the contour coefficient is obtained at k=3, namely, the best classification is that the 27 points are clustered into 3 types, namely, 3 rows. The three rows are ordered, and the abscissa is ordered for each coordinate point of the same row, so that the final row and column position of each pressing plate in the row is obtained by determining the column of the pressing plate, as shown in fig. 8. The sorting method provided by the embodiment can automatically judge that the pressing plates share a plurality of rows, does not need to manually set information such as parameter threshold values of clustering, is convenient and high in accuracy, and is simple and convenient to operate compared with a method needing to set threshold value adjustment judging conditions, and has strong generalization capability on pressing plate pictures with different resolutions and different row numbers, and experience threshold values do not need to be adjusted for specific application scenes.
In the practical application process, some special cases exist, and the processing method is further provided in this embodiment.
Special case 1: only one row of pressing plates is provided, and four corner points are not present, so that inclination cannot be corrected through perspective transformation, and Kmeans clustering does not support the condition of gathering into class 1. A schematic of the coordinate positions of only one row of platens is shown in fig. 9. Thus, the step S1 may be further followed by the step of: performing straight line fitting on the acquired coordinate point set; calculating the distance between each coordinate point and the fitted straight line, and executing the step S2 if the distance is greater than or equal to a set threshold value; otherwise, the coordinate points are arranged from small to large according to the abscissa value. After the coordinate points of each pressing plate are obtained, judging whether the coordinate points of all the pressing plates are on the same straight line, for example, calculating the residual square sum after fitting the straight line, and determining that the residual square sum is on the same straight line when the residual square sum is smaller than the threshold value. If the above condition is met, only one row is directly judged (because in the actual situation, there is no case that there is only one pressing plate in each row of the plurality of rows of pressing plates, so that judgment is one row instead of one column), and then the row and column position result is obtained by determining the row and column of the pressing plate in the row according to the abscissa ordering of the coordinate points of each pressing plate.
Special case 2: the platen areas have individual missed platens, resulting in a different number of platens per row. And under the condition that the judgment of the rows is not affected, judging whether the number of the pressing plates in each row is equal to the maximum number of the pressing plates in the row, and returning the pressing plate detection missing alarm information if the number of the pressing plates in each row is smaller than the maximum number of the pressing plates in each row. The method comprises the following specific steps:
(1) Recording the number of pressing plates in each row as n 1、n2、…、ni;
(2) Obtaining the maximum value of the number of single-row pressing plates of the pressing plates to be n max;
(3) Comparing the number of the pressing plates in each row with a maximum value n max, detecting that the pressing plates in the row have the defects when the number of the pressing plates in each row is smaller than the maximum value, otherwise, detecting that the pressing plates in each row are normal.
This step may be performed after the last step of the main program, the rank order of the platens is obtained. For example, fig. 10 shows a schematic diagram of coordinate positions of the press plates where missing detection exists in the press plate area, and in addition to the press plate row and column position judgment result, alarm information of 1,2 and 6 press plates missing in the 3 rd, 4 th, 5 th and 6 th rows is returned.
According to a second embodiment of the present invention, there is provided a platen rank position ordering apparatus, the apparatus having a block diagram as shown in fig. 11, including a coordinate point acquisition module, an outlier acquisition module, a corner point acquisition module, a transformation matrix acquisition module, a coordinate point transformation module, and a rank position ordering module.
The coordinate point acquisition module is used for acquiring coordinate points of each pressing plate to be ordered;
the external point acquisition module is used for acquiring coordinate points which are external points in the point set in the obtained coordinate points;
The corner acquisition module is used for acquiring coordinate points of four corner points in the obtained coordinate points which are external points;
the transformation matrix acquisition module is used for obtaining a transformation matrix M from coordinate points of each corner point to four vertexes of a rectangle by using perspective transformation for the coordinate points of the four corner points;
The coordinate point transformation module is used for performing perspective transformation on the matrix M and transforming coordinate points of all pressing plates into the rectangular area;
the rank position ordering module is used for carrying out cluster analysis on the transformed coordinate points to obtain rank positions of each pressing plate.
The specific process of each module in the device for realizing the functions is the same as each step of the fault locating method in the first embodiment provided by the present invention, and will not be described herein.
According to a third embodiment of the present invention, there is provided a storage medium storing a computer program which, when executed by a processor, implements a method as described in the first embodiment of the present invention.
In summary, the invention relates to a method and a device for ordering the positions of rows and columns of pressing plates, which are characterized in that after coordinate points of each pressing plate are obtained, angular points are searched in the coordinate points, and clustering analysis is performed after the coordinate points are transformed according to the angular points and by utilizing perspective transformation, so that the positions of rows and columns of each pressing plate are obtained. According to the invention, after the coordinate point of each pressing plate is obtained through target detection, the coordinate point is used for realizing the ordering of the pressing plate row and column positions, which is equivalent to the problem of converting the ordering into two-dimensional ordering, and the processing process is simplified. The coordinate points are processed and then are sequenced by adopting a clustering method, so that the fact that the number of the pressing plates is a few lines can be automatically judged, the information such as parameter threshold values of the clusters is not required to be set manually, the operation is simple, the accuracy is high, the generalization capability of the pressing plate pictures with different resolutions and different row numbers is high, and the experience threshold value is not required to be adjusted for specific application scenes. Aiming at the condition that only a single row of pressing plates is needed, the pressing plates are missed to be detected or other screen cabinet pressing plates are included in the recognition result, special steps are set for processing, the conditions are screened out in advance, and recognition errors possibly caused by the special conditions are avoided.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It is to be understood that the above-described embodiments of the present invention are merely illustrative of or explanation of the principles of the present invention and are in no way limiting of the invention. Accordingly, any modification, equivalent replacement, improvement, etc. made without departing from the spirit and scope of the present invention should be included in the scope of the present invention. Furthermore, the appended claims are intended to cover all such changes and modifications that fall within the scope and boundary of the appended claims, or equivalents of such scope and boundary.
Claims (7)
1. A method of ordering platen array positions, comprising the steps of:
s1, acquiring coordinate points of each pressing plate to be sequenced;
s2, acquiring a coordinate point which is an outer point in the point set from the obtained coordinate points;
s3, acquiring coordinate points of four corner points in the obtained coordinate points which are external points;
S4, performing perspective transformation on coordinate points of four corner points to obtain a transformation matrix M from the coordinate points of each corner point to four vertexes of a rectangle, wherein the transformation matrix M comprises:
the transformation matrix M is obtained according to the following formulas (1) and (2):
Wherein, (x 1,y1),(x2,y2),(x3,y3),(x4,y4) is coordinates ;(x′1,y′1),(x′2,y′2),(x′3,y′3),(x′4,y′4) of four corner points, which are coordinates of four corner points after the transformation; n=1, 2,3,4;
S5, performing perspective transformation on the matrix M, and transforming coordinate points of all pressing plates into the rectangular area, wherein the method comprises the following steps: bringing all coordinate points into the above formula (2) to obtain transformed coordinates;
S6, carrying out cluster analysis on the transformed coordinate points to obtain row and column positions of each pressing plate, wherein the cluster analysis comprises the following steps: performing cluster analysis on the ordinate values in each transformed coordinate point to obtain the optimal category number as the number of the rows of the pressing plate;
the coordinate points of each row of pressing plates are arranged from small to large according to the abscissa value.
2. The method of claim 1, wherein the acquiring the coordinate points that are outliers in the set of points comprises:
S21, randomly selecting three points from the obtained coordinate points to serve as an outer point set;
S22, traversing the rest coordinate points, judging whether each coordinate point is in an area surrounded by an outer point set, and if yes, not processing the coordinate point; if not, updating the outer point set, and adding the coordinate point into the outer point set.
3. The method of claim 2, wherein the acquiring the coordinate points that are outer points in the set of points further comprises:
S23, when the outlier set is changed, judging whether all outliers in the outlier set are in a triangle surrounded by any three other outliers, and if so, deleting the outliers from the outlier set; if not, the outlier is not processed.
4. A method according to claim 3, wherein said obtaining coordinate points of four corner points comprises:
Recording the current judging outer point as A, selecting another outer point B as a datum point, traversing the rest outer points C, and calculating the angles of AB and AC;
if the angle is smaller than the threshold value, the point A is the corner point; otherwise, the point A is a non-corner point; to obtain four corner points.
5. The method according to claim 1, further comprising the step after step S1 of:
performing straight line fitting on the acquired coordinate point set;
calculating the distance between each coordinate point and the fitted straight line, and executing the step S2 if the distance is greater than or equal to a set threshold value;
Otherwise, the coordinate points are arranged from small to large according to the abscissa value.
6. The device is characterized by comprising a coordinate point acquisition module, an outer point acquisition module, a corner point acquisition module, a transformation matrix acquisition module, a coordinate point transformation module and a rank position ordering module; wherein,
The coordinate point acquisition module is used for acquiring coordinate points of each pressing plate to be ordered;
the external point acquisition module is used for acquiring coordinate points which are external points in the point set in the obtained coordinate points;
The corner acquisition module is used for acquiring coordinate points of four corner points in the obtained coordinate points which are external points;
The transformation matrix obtaining module is configured to obtain a transformation matrix M from coordinate points of each corner to four vertices of a rectangle by using perspective transformation for coordinate points of the four corners, where the transformation matrix M includes:
the transformation matrix M is obtained according to the following formulas (1) and (2):
wherein, (x 1,y1),(x2,y2),(x3,y3),(x4,y4) is coordinates ;(x′1,y′1),(x′2,y′2),(x′3,y′3),(x′4,y′4) of four corner points, which are coordinates of four corner points after the transformation; n=1, 2,3,4;
The coordinate point transformation module is used for performing perspective transformation on the matrix M, transforming coordinate points of all pressing plates into the rectangular area, and comprises the following steps: bringing all coordinate points into the above formula (2) to obtain transformed coordinates;
the rank position ordering module is used for carrying out cluster analysis on the transformed coordinate points to obtain rank positions of each pressing plate, and comprises the following steps: performing cluster analysis on the ordinate values in each transformed coordinate point to obtain the optimal category number as the number of the rows of the pressing plate;
the coordinate points of each row of pressing plates are arranged from small to large according to the abscissa value.
7. A storage medium storing a computer program which, when executed by a processor, implements the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111004495.1A CN113743492B (en) | 2021-08-30 | 2021-08-30 | Method and device for ordering positions of rows and columns of pressing plates |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111004495.1A CN113743492B (en) | 2021-08-30 | 2021-08-30 | Method and device for ordering positions of rows and columns of pressing plates |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113743492A CN113743492A (en) | 2021-12-03 |
| CN113743492B true CN113743492B (en) | 2024-04-19 |
Family
ID=78733802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111004495.1A Active CN113743492B (en) | 2021-08-30 | 2021-08-30 | Method and device for ordering positions of rows and columns of pressing plates |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113743492B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114972828A (en) * | 2022-05-14 | 2022-08-30 | 上海贝特威自动化科技有限公司 | Clustering-based two-dimensional coordinate row and column sorting method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108320290A (en) * | 2017-12-29 | 2018-07-24 | ***股份有限公司 | Target Photo extracts antidote and device, computer equipment and recording medium |
| WO2019080229A1 (en) * | 2017-10-25 | 2019-05-02 | 南京阿凡达机器人科技有限公司 | Chess piece positioning method and system based on machine vision, storage medium, and robot |
-
2021
- 2021-08-30 CN CN202111004495.1A patent/CN113743492B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019080229A1 (en) * | 2017-10-25 | 2019-05-02 | 南京阿凡达机器人科技有限公司 | Chess piece positioning method and system based on machine vision, storage medium, and robot |
| CN108320290A (en) * | 2017-12-29 | 2018-07-24 | ***股份有限公司 | Target Photo extracts antidote and device, computer equipment and recording medium |
Non-Patent Citations (2)
| Title |
|---|
| 基于图像处理的变电站视频智能分析研究;朱红岷;戴道清;李静正;;计算机工程与应用(07);全文 * |
| 葡萄采摘机器人采摘点的视觉定位;雷旺雄;卢军;;江苏农业学报(04);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113743492A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110458898B (en) | Camera calibration board, calibration data acquisition method, distortion correction method and device | |
| US20220270293A1 (en) | Calibration for sensor | |
| CN109257582B (en) | Correction method and device for projection equipment | |
| CN108009515B (en) | Power transmission line positioning and identifying method of unmanned aerial vehicle aerial image based on FCN | |
| CN113592950B (en) | Multi-camera calibration method and related equipment in large space environment based on optical dynamic capturing | |
| CN109978925B (en) | Robot pose recognition method and robot thereof | |
| CN108846401A (en) | Commodity detect terminal, method, system and computer equipment, readable medium | |
| CN106648511A (en) | Self-adaptive display method and device of display resolutions | |
| CN106791700B (en) | Enterprise critical area personnel path safety monitoring system and method | |
| JPS5916023A (en) | Positioning of microscopic object | |
| CN112883955B (en) | Shelf layout detection method, device and computer readable storage medium | |
| CN113743492B (en) | Method and device for ordering positions of rows and columns of pressing plates | |
| CN108154516B (en) | Point cloud topological segmentation method and device for closed space | |
| CN106648510A (en) | Display method and device for display resolution | |
| CN112465889A (en) | Plant point cloud segmentation method, system and storage medium based on two-dimensional-three-dimensional integration | |
| CN113177941B (en) | Steel coil edge crack identification method, system, medium and terminal | |
| CN113382200A (en) | Camera layout method and device | |
| KR20230118881A (en) | Image processing method and image processing system | |
| CN109353398B (en) | Commodity identification method, device and system, storage medium and shopping cart | |
| CN116453061A (en) | Remote pig selling supervision method, device and equipment based on image recognition | |
| EP4202858A1 (en) | Method and device for cargo counting, computer equipment, and storage medium | |
| CN113326793B (en) | Remote pedestrian position identification method, system and storage medium | |
| CN113932712B (en) | Melon and fruit vegetable size measurement method based on depth camera and key points | |
| CN111860035A (en) | Book cover detection method and device, storage medium and electronic equipment | |
| CN105141963A (en) | Image motion estimation method and device |
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 |