CN111814918B - Cooperative target and target identification method - Google Patents
Cooperative target and target identification method Download PDFInfo
- Publication number
- CN111814918B CN111814918B CN202010891587.5A CN202010891587A CN111814918B CN 111814918 B CN111814918 B CN 111814918B CN 202010891587 A CN202010891587 A CN 202010891587A CN 111814918 B CN111814918 B CN 111814918B
- Authority
- CN
- China
- Prior art keywords
- point
- identification
- target
- polarizer
- points
- 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
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
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a cooperative target and a target identification method, and relates to a target and an identification method thereof. It has solved the problem of target identification among the prior art. The cooperative target and the target identification method comprise five circular ring marks with the same size, wherein the inner-outer radius ratio of the circular ring marks is 1:2, the center of the circular ring mark is taken as an identification point, a first identification point E is arranged inside the circular ring mark, a second identification point A is arranged close to the first identification point E, and third, fourth and fifth identification points B, C, D are arranged in a counterclockwise manner. The second, third, fourth, and fifth marking points A, B, C, D are the four vertices of a square, with the center of the square set to point F. The invention utilizes the specially arranged circular target to match with the identification method matched with the circular target, so that the circular position has multiple constraints which are easy to distinguish from the environment, and the constraints are easy to identify, the identification precision is high, the calculation amount required by a computer is small, the calculation amount is small, and the identification efficiency is high.
Description
Technical Field
The invention belongs to the technical field of photoelectric measurement, and relates to a target and an identification method thereof.
Background
In the industrial field, indoor small-range high-precision pose measurement is an important condition for realizing precision detection and high-precision control of industrial equipment, and the requirements of low-cost high-precision real-time pose measurement in the tail end positioning of a cooperative mechanical arm are greatly improved. The recognition precision of the camera on the combined target has certain influence on the visual positioning precision of the tail end. Scenes in the indoor industrial field are complex, pose situations between the tail end of the cooperative mechanical arm and the camera are variable, the recognition accuracy of the square target is lower than that of a round target, but the common round target is easy to be mismatched in a complex environment and low in efficiency. Therefore, it is important to design a positioning cooperative target with high accuracy and high recognition efficiency.
Disclosure of Invention
The invention aims to provide a cooperative target and a target identification method aiming at the problems in the prior art, and the cooperative target and the target identification method have high identification precision and high identification efficiency.
The purpose of the invention can be realized by the following technical scheme: a cooperation target comprises five circular ring marks with the same size, wherein the ratio of the inner radius to the outer radius of each circular ring mark is 1:2, the centers of the circular ring marks are identification points, one of the identification points is set as a first identification point E, a second identification point A which is close to the first identification point E is set as a third identification point, a fourth identification point and a fifth identification point B, C, D which are arranged anticlockwise, the second identification point, the third identification point, the fourth identification point and the fifth identification point A, B, C, D are four vertexes of a square, the center of the square is set as a point F, the first identification point E, the second identification point and the fourth identification point A, C are located on the same line segment, and the first identification point E is located at the trisection of the line segment and close to the second identification point A; the diameter of the outer circle of the circular ring mark is one third of the side length of the square. The circular ring mark positions of the cooperative targets are arranged so that the cooperative targets can have a plurality of easily-identified constraints, and therefore the cooperative targets can be identified quickly from a complex scene.
In some embodiments, the circle marks an outer radius that is one sixth of the side length of the square.
A method of target identification comprising the steps of:
step 1: target image self-adaptive thresholding processing;
step 2: according to the self-adaptive threshold value graph obtained in the step 1, traversing each pixel line by line from left to right, segmenting the connected part of the bright pixel and the dark pixel in an eight-connected searching mode, obtaining all edges and giving a characteristic value D if the pixel values are equal, wherein the pixel values are the same edge;
and step 3: performing ellipse fitting according to all the edges obtained in the step 2 to obtain the central coordinates and the sizes of the long axis and the short axis of all the fitted ellipses;
and 4, step 4: screening a fitting ellipse with the long and short axes smaller than the height 1/3 of the circular ring target image height;
and 5: for the ellipse retained according to step 4, sequentially traversing two ellipses with central coordinates of (A) and (B) respectivelyx m ,y m ）、（x n ,y n ) The major and minor axes are respectivelya m 、b m 、a n 、b n Characteristic values are respectivelyD m 、D n According to the concentric circle constraint condition in the circular ring mark, screening ellipses with certain concentricity, then according to the color feature constraint of circular ring target, screening the ellipses with the colors changing from outside to inside through white-black-white from the concentric ellipses, and recording the central average pixel coordinate of the ellipses under the condition (1)x m + x n ）/2, （y m + y n ) A/2, obtaining a similar circular ring mark and a central average pixel coordinate thereof;
step 6: traversing 5 central average pixel coordinate points A ', B ', C ', D ' and E ' recorded in step 5 in sequence, finding out a coordinate point E ' positioned in the quadrangle according to the constraint condition that the area of the quadrangle is equal to the area of four triangular areas formed by one point in the quadrangle and four sides of the quadrangle, finding out two coordinate points A ' and C ' collinear with the internal coordinate point according to a vector collinear method, then obtaining a point F ' according to the characteristic that the connecting line of the two points B ' and D ' and the connecting line of the two points A ' and C ' are vertically intersected at the point F ', and further determining the points A ', B ', C ', D ' and E ' meeting the condition according to the intersection invariance of the intersection ratio of the points A ', E ', F ' and C ' and the intersection ratio of the point A, E, F, C.
In some embodiments, in the adaptive thresholding process of step 1, to prevent artifacts from occurring between the pixel arrays with large extremum differences, the gray extremum of each tile is calculated, so thatP max —P min =，P max Is the gray maximum of the tile, P min is the gray minimum of said block ifNot less than 10, judging the pixel array contrast is obvious, and utilizing the pixel threshold value P’=(P max —P min ) And/2 to assign the pixel array black and white effect.
At a certain pointIn some embodiments, if<And 10, judging that the contrast of the pixel array is insufficient, deleting the pixel array to save the calculation time, and acquiring an adaptive threshold map.
In some embodiments, the ring mark and the inner and outer portions of the ring mark are made of a first polarizer and a second polarizer, respectively, the polarization directions of the first polarizer and the second polarizer are perpendicular to each other, a third polarizer is behind the ring mark, the third polarizer is driven to rotate by a rotating device, a background light is arranged behind the third polarizer, the third polarizer is rotated to enable the polarization direction of the third polarizer to be the same as that of the first polarizer and to be opposite to that of the second polarizer, so that the ring is white for light transmission, and the other portions are black for light opacity, the steps 1 to 6 are repeated to obtain new data of point coordinates of a ', B', C ', D', and E ', the new data are compared with the new data of point coordinates of a', B ', C', D ', and E', and the new data are obtained before the third polarizer rotates, and the new data are mutually verified, if the two groups of data have obvious difference, the identification is not accurate, and manual processing is needed to find out the problem.
In some embodiments, the ring is made transparent white when the ambient light is dark and other portions are opaque black, and the ring is made transparent black when the ambient light is bright and other portions are opaque white.
Compared with the prior art, the cooperative target and the target identification method have the following advantages:
the invention utilizes the specially arranged circular target to match with the identification method matched with the circular target, so that the circular position has multiple constraints which are easy to distinguish from the environment, and the constraints are easy to identify, the identification precision is high, the calculation amount required by a computer is small, the calculation amount is small, and the identification efficiency is high.
Drawings
In the drawings, which are not necessarily drawn to scale, like reference numerals may describe similar components in different views. Like reference numerals having different letter suffixes may represent different examples of similar components. The drawings illustrate generally, by way of example, but not by way of limitation, various embodiments discussed herein.
FIG. 1 is a schematic representation of a circular target of the present invention;
FIG. 2 is a schematic view of the center point of the projection of the circular target under the camera after ellipse fitting;
FIG. 3 is a schematic diagram showing the cross-ratio invariance of points A ', E', F ', C' and A, E, F, C;
FIG. 4 is a schematic flow chart of a circular target identification method according to the present invention;
fig. 5 is a schematic diagram of the second embodiment.
In the figure: the device comprises a first polaroid 1, a second polaroid 2, a third polaroid 3, a barrel 4, a gear ring 5, a gear 6 and a motor 7.
Detailed Description
The following are specific examples of the present invention, and the technical solutions of the present invention are further described with reference to the drawings, but the present invention is not limited to these examples, and the following embodiments do not limit the invention according to the claims. Moreover, all combinations of features described in the embodiments are not necessarily essential to the solution of the invention.
It will be understood by those of ordinary skill in the art that all directional references (e.g., above, below, upward, downward, top, bottom, left, right, vertical, horizontal, etc.) are illustratively used in the figures to aid the reader's understanding and do not imply (e.g., position, orientation, or use, etc.) a limitation on the scope of the invention, which is defined by the claims appended hereto. Additionally, the term "substantially" may refer to slight imprecision or deviation in conditions, amounts, values, or dimensions, etc., some of which may be within manufacturing or tolerance limits.
Example one
Referring to fig. 1, 2, 3, and 4, the present invention provides a cooperative target, which includes five circular markers with the same size, wherein the outer radius of the circular marker is 2cm, the inner radius ratio and the outer radius ratio of the circular marker are 1:2, and the center of the circular marker is an identification point. The first mark point E arranged inside is the second mark point a which is closer to the first mark point E, and the third, fourth and fifth mark points B, C, D are arranged counterclockwise. The second, third, fourth and fifth marking points A, B, C, D form the vertex of the square, the side length of the square is 12cm, and the center of the square is set as a point F. The first identification point E is located on the same line segment as the second and fourth identification points A, C, and the first identification point E is located at the trisection of the line segment and close to the second identification point a. The circular ring indicia may be printed on the paperboard.
The setting of the circular ring mark can ensure the accuracy of identification under complex environment. The first, second, third, fourth and fifth identification points A, B, C, D, E are used for resolving poses, and the setting of the position relationship is used for providing a restriction relationship, so that the accuracy of target identification is improved, and the identification efficiency is also improved.
The invention provides a method for identifying a cooperative target, wherein a software part is realized based on opencv (opencv is a cross-platform computer vision and machine learning software library issued based on BSD license), and the method specifically comprises the following steps:
step 1: adaptive thresholding:
a circular ring target image in an arbitrary complex scene is acquired, and the image is divided into a 4x4 pixel array and a 12x12 block with the pixel array as the center. In order to prevent artifacts between the pixel arrays with large extreme value difference, the gray extreme value of each image block is calculated, so thatP max —P min =，P max Is the gray maximum of the tile,P min the gray minimum value of the image block. When in useJudging that the pixel array contrast is obvious at more than or equal to 10 by utilizing a pixel threshold value P’=(P max —P min ) And/2 to assign the pixel array black and white effect. When in use<And 10, judging that the contrast of the pixel array is insufficient, and deleting the pixel array to save the calculation time. An adaptive threshold map is obtained.
Step 2: acquiring all edges and assigning a characteristic value D:
according to the self-adaptive threshold value graph obtained in the step 1, traversing each pixel line by line from left to right, and dividing the connected part of the bright pixel and the dark pixel according to an eight-connected searching modeAnd cutting the same edge if the pixel values are equal, and obtaining all the edges. Let the fixed point in the adaptive threshold map of step 1: (m,n) Corresponding to a pixel value off (m,n). Traverse all edge to points: (x,y) Finding a point (x+dx,y+dy) When is coming into contact withf x dx y dy(+,+)+f x y(,)Recorded as a dot (X, Y), let
In the formula (I), the compound is shown in the specification,gx,gyrespectively recordx,yThe black and white pixels on the axis point. The function saturrate _ cast<uint16_t>Is an anti-boundary-crossing function of opencv, and has the functions of preventing data overflow and ensuringgx,gyBelongs to [ 0-255]Within the range, the maximum and minimum horizontal and vertical coordinates of the same edge are takenX max、X min、Y max、Y minEdge points of (1)x i ,y i ) Containing informationgx i ,gy i Let us order
In the formula, Δ =0.0511, and Δ =0.0285 are used to adjust the central pixel point (c) ((r))Cx,Cy) And (4) deviation. And judging whether the ring-like mark is a ring-like mark or not through the characteristic value D.
And step 3: performing ellipse fitting according to all the edges obtained in the step 2:
the least squares fit of the ellipse was performed using the fitEllipse function in opencv (opencv is a BSD license (open source) based published cross-platform computer vision and machine learning software library). When the edge points are more than or equal to 6, the fitting algorithm is effective, and the edges less than 6 points are removed. The result is the center coordinates and the sizes of the major and minor axes of all the fitted ellipses.
And 4, step 4: and traversing all fitting ellipses to further screen the ellipses:
and (3) according to the position relation of the circular ring marks in the circular ring target, the central coordinate of the fitting ellipse is positioned in the circular ring target image in the step 1. The long and short axes of the fitted ellipse should be smaller than 1/3, which is the height of the circular target image row in step 1. The ellipse meeting the above condition is retained.
And 5: obtaining the similar circular ring mark and the center average pixel coordinate thereof:
according to the ellipse retained in the step 4, two ellipses are traversed in sequence, and the central coordinates of the ellipses are respectively (x m ,y m ）、（x n ,y n ) The major and minor axes are respectivelya m 、b m 、a n 、b n Characteristic values are respectivelyD m 、D n . The rings being marked as concentric circles, the centres of the ellipses being constrained, e.g.
Where c is a constant, set herein to 0.1, suitably tunable.
According to the characteristics of the circular target, the circular target is composed of white-black-white and white-black edgesD>0, black-white borderD<0, select coincidenceD m *D n <Two ellipses of 0 and satisfy simultaneously
The method can remove most irregular ellipses, reserve two ellipses meeting the conditions, and record the center average pixel coordinate (a)x m + x n ）/2, （y m + y n ) And/2, obtaining the similar circular ring mark and the center average pixel coordinate thereof.
Step 6: sequentially traversing the central average pixel coordinate points A ', B ', C ', D ', E ' recorded in the 5 steps 5:
setting the central average pixel coordinate points as A ', B ', C ', D ' and E ', finding out the internal coordinate point E ' based on the area of the quadrangle equal to the area of four triangles comprising one point inside and four sides of the quadrangle, finding out the coordinate points A ' and C ' collinear with the internal coordinate point E ' based on the vector collinear method, and taking one point Q in space to meet the requirement
In the formula (I), the compound is shown in the specification,m、nis constant andm>0、n>0、m+n=1, the points E ', A ', C ' are collinearl 1. The image recognition will have a certain error, so the constraint conditionm+nLimited by-1 | < 0.01, and connecting the other two points B 'and D' as a linel 2To find a linel 1、l 2The intersection point coordinate F ', the intersection ratio of the points A ', E ', F ', C ' is
The cross ratio of the point A, E, F, C is
In the formula, the cross ratio invariance of projective theorem is knownR（A，E，F，C）=R(A ', E', F ', C'). Certain errors can exist in image recognition, so that conditions are limited |R（A，E，F，C）-R(A ', E', F ', C') | is less than or equal to 0.01. The points A ', B ', C ', D ', E ' meeting the above conditions are preserved.
Example two
As shown in fig. 5, different from the above embodiment, the inner side and the outer side of the ring mark and the ring mark are made of a first polarizer 1 and a second polarizer 2, the polarization directions of the first polarizer and the second polarizer are perpendicular to each other, the first polarizer as the ring mark is embedded on the second polarizer, so that the first polarizer and the second polarizer are located on the same plane, the back of the inner side and the outer side of the ring mark and the ring mark is a third polarizer 3, the third polarizer can rotate, the background light is arranged behind the third polarizer, the background light source is arranged in a barrel 4, the first polarizer and the second polarizer are circular and are shielded at the outlet of the barrel, the third polarizer is also circular and is located between the second polarizer and the background light source, the outlet of the barrel is upward close to the second polarizer, the edge of the third polarizer is fixed in a ring gear 5, the gear ring is rotationally matched on the drum and is driven to rotate by a gear 6 driven by a motor 7.
And (3) rotating the third polaroid to enable the polarization direction of the third polaroid to be the same as that of the first polaroid and opposite to that of the second polaroid to enable the ring to be in a light-transmitting white color and other parts to be in a light-tight black color, repeating the steps 1 to 6 to obtain new data of point coordinates of A ', B', C ', D' and E ', comparing the new data with the new data of the point coordinates of A', B ', C', D 'and E' measured before the third polaroid rotates, mutually verifying, and if the two groups of data have obvious difference, explaining that the identification is inaccurate and needing manual processing to find out the problem. Since different environments have different effects on the recognition of rings of different brightness.
EXAMPLE III
Different from the above embodiment, when the ambient light is dark, the ring is made to be transparent white, and the other parts are opaque black, and when the ambient light is bright, the ring is made to be transparent black, and the other parts are opaque white. Such an arrangement may make the ring easier to distinguish from a complex background.
Although some terms are used more herein, the possibility of using other terms is not excluded. These terms are used merely to more conveniently describe and explain the nature of the present invention; they are to be construed as being without limitation to any additional limitations that may be imposed by the spirit of the present invention. The order of execution of the operations, steps, and the like in the apparatuses and methods shown in the specification and drawings may be implemented in any order as long as the output of the preceding process is not used in the subsequent process, unless otherwise specified. The descriptions using "first", "next", etc. for convenience of description do not imply that they must be performed in this order.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (7)
1. A cooperative target is characterized by comprising five circular ring marks with the same size, wherein the ratio of the inner radius to the outer radius of each circular ring mark is 1:2, the center of each circular ring mark is taken as an identification point, one identification point is taken as a first identification point E, a second identification point A which is close to the first identification point E is taken as a second identification point A, the three, four and five identification points B, C, D are arranged in a counterclockwise manner, the second, third, fourth and fifth identification points A, B, C, D are four vertexes of a square, the center of the square is taken as a point F, the first identification point E, the second and fourth identification points A, C are located on the same line segment, and the first identification point E is located at the trisection of the line segment and close to the second identification point A; the diameter of the outer circle of the circular ring mark is one third of the side length of the square.
2. The cooperative target as recited in claim 1, wherein the circular marker outer radius is one sixth of the square side length.
3. A target recognition method according to claim 1, comprising the steps of:
step 1: target image self-adaptive thresholding processing;
step 2: according to the self-adaptive threshold value graph obtained in the step 1, traversing each pixel line by line from left to right, segmenting the connected part of the bright pixel and the dark pixel in an eight-connected searching mode, obtaining all edges and giving a characteristic value D if the pixel values are equal, wherein the pixel values are the same edge;
and step 3: performing ellipse fitting according to all the edges obtained in the step 2 to obtain the central coordinates and the sizes of the long axis and the short axis of all the fitted ellipses;
and 4, step 4: screening a fitting ellipse with the long and short axes smaller than the height 1/3 of the circular ring target image height;
and 5: for the ellipse retained according to step 4, sequentially traversing two ellipses with central coordinates of (A) and (B) respectivelyx m ,y m ）、（x n ,y n ) The major and minor axes are respectivelya m 、b m Anda n 、b n the characteristic values are respectivelyD m 、D n According to the concentric constraint condition in the circular ring mark screening the ellipse with a certain concentricity, then according to the colour feature constraint of circular ring target screening the ellipse whose colour is changed from outside to inside through white-black-white, and recording the central average pixel coordinate (in accordance with conditional ellipse) ((x m + x n ）/2, （y m +y n ) A/2, obtaining a similar circular ring mark and a central average pixel coordinate thereof;
step 6: traversing 5 central average pixel coordinate points A ', B ', C ', D ' and E ' recorded in the step 5 in sequence, finding out a coordinate point E ' positioned in the quadrangle according to the constraint condition that the area of the quadrangle is equal to the area of four triangular areas formed by one point in the quadrangle and four sides of the quadrangle, finding out two coordinate points A ' and C ' collinear with the internal coordinate point according to a vector collinear method, then obtaining a point F ' according to the characteristic that the connecting line of the two points B ' and D ' and the connecting line of the two points A ' and C ' are vertically intersected at the point F ', and further determining the points A ', B ', C ', D ' and E ' meeting the condition according to the intersection invariance of the intersection ratio of the points A ', E ', F ' and C ' and the intersection ratio of the point A, E, F, C.
4. The target identification method of claim 3, wherein in the adaptive thresholding process of step 1, to prevent artifacts from occurring between pixel arrays with large extremum differences, grayscale extrema of each tile are calculated, and letP max —P min =， P max Is the gray maximum of the tile, P min is the gray minimum of said block ifNot less than 10, judging the pixel array contrast is obvious, and utilizing the pixel threshold valueP’=(P max —P min ) And/2 to assign the pixel array black and white effect.
5. The target recognition method of claim 4, wherein the step of detecting the presence of the target in the sample is performed if<And 10, judging that the contrast of the pixel array is insufficient, deleting the pixel array to save the calculation time, and acquiring an adaptive threshold map.
6. The target identification method of claim 4, wherein the ring mark and the inner and outer portions of the ring mark are made of a first polarizer and a second polarizer, the polarization directions of the first polarizer and the second polarizer are perpendicular to each other, a third polarizer is behind the ring mark and is driven to rotate by a rotating device, a background light is arranged behind the third polarizer, the third polarizer is rotated to enable the polarization direction of the third polarizer to be the same as that of the first polarizer and to be opposite to that of the second polarizer, so that the ring is transparent white, and the other portions are opaque black, and the steps 1 to 6 are repeated to obtain new data of point coordinates of A ', B', C ', D', and E ', wherein the new data is the same as the new data of point coordinates of A', B ', C', D ', and D' measured before the third polarizer rotates, And comparing the new data of the coordinates of the E' point, mutually verifying, and if the two groups of data have obvious difference, indicating that the identification is not accurate and the problem needs to be found out by manual treatment.
7. The method of claim 6, wherein the ring is made transparent white and other parts are opaque black when the ambient light is dark, and the ring is made transparent black and other parts are opaque white when the ambient light is bright.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010891587.5A CN111814918B (en) | 2020-08-31 | 2020-08-31 | Cooperative target and target identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010891587.5A CN111814918B (en) | 2020-08-31 | 2020-08-31 | Cooperative target and target identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111814918A CN111814918A (en) | 2020-10-23 |
| CN111814918B true CN111814918B (en) | 2020-12-29 |
Family
ID=72860289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010891587.5A Active CN111814918B (en) | 2020-08-31 | 2020-08-31 | Cooperative target and target identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111814918B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113894799B (en) * | 2021-12-08 | 2022-04-08 | 北京云迹科技有限公司 | Robot and marker identification method and device for assisting environment positioning |
| CN118111403A (en) * | 2024-04-30 | 2024-05-31 | 上海大学 | Mode target for anti-interference measurement and positioning method thereof |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145897A (en) * | 2018-07-26 | 2019-01-04 | 中国船舶重工集团公司第七〇九研究所 | Spacecraft cooperation target and its recognition methods and identification device |
| CN110689579A (en) * | 2019-10-18 | 2020-01-14 | 华中科技大学 | Rapid monocular vision pose measurement method and measurement system based on cooperative target |
| CN111598952A (en) * | 2020-05-21 | 2020-08-28 | 华中科技大学 | Multi-scale cooperative target design and online detection and identification method and system |
-
2020
- 2020-08-31 CN CN202010891587.5A patent/CN111814918B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145897A (en) * | 2018-07-26 | 2019-01-04 | 中国船舶重工集团公司第七〇九研究所 | Spacecraft cooperation target and its recognition methods and identification device |
| CN110689579A (en) * | 2019-10-18 | 2020-01-14 | 华中科技大学 | Rapid monocular vision pose measurement method and measurement system based on cooperative target |
| CN111598952A (en) * | 2020-05-21 | 2020-08-28 | 华中科技大学 | Multi-scale cooperative target design and online detection and identification method and system |
Non-Patent Citations (2)
| Title |
|---|
| 空间机械臂位姿测量中合作靶标的识别及定位;何龙等;《现代电子技术》;20180701;第41卷(第13期);第106页-第114页 * |
| 空间站机械臂位姿测量中合作靶标的快速识别;温卓漫等;《航空学报》;20150425;第36卷(第4期);1330-1337页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111814918A (en) | 2020-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111243032B (en) | Full-automatic detection method for checkerboard corner points | |
| CN100380393C (en) | Precise location method of QR code image symbol region at complex background | |
| US7398928B2 (en) | Coded target and photogrammetry method using such targets | |
| CN111814918B (en) | Cooperative target and target identification method | |
| CN112257676B (en) | Pointer type instrument reading method and system and inspection robot | |
| CN108007388A (en) | A kind of turntable angle high precision online measuring method based on machine vision | |
| CN111260731A (en) | Checkerboard sub-pixel level corner point self-adaptive detection method | |
| CN108960231B (en) | Machine vision-based thin pointer dial identification reading method | |
| CN107063261B (en) | Multi-feature information landmark detection method for precise landing of unmanned aerial vehicle | |
| CN112614188B (en) | Dot-matrix calibration board based on cross ratio invariance and identification method thereof | |
| CN110288612B (en) | Nameplate positioning and correcting method and device | |
| US8548221B2 (en) | Microbead automatic recognition method and microbead | |
| CN109064481B (en) | Machine vision positioning method | |
| CN112308916A (en) | Target pose identification method based on image target | |
| CN113049184A (en) | Method, device and storage medium for measuring mass center | |
| CN115609591A (en) | 2D Marker-based visual positioning method and system and composite robot | |
| CN114972531B (en) | Corner detection method, equipment and readable storage medium | |
| CN117496401A (en) | Full-automatic identification and tracking method for oval target points of video measurement image sequences | |
| CN112036391A (en) | Electronic inspection method and system based on shale gas field production station | |
| CN114792343B (en) | Calibration method of image acquisition equipment, method and device for acquiring image data | |
| US20240013437A1 (en) | Method for providing calibration data for calibrating a camera, method for calibrating a camera, method for producing at least one predefined point-symmetric region, and device | |
| CN105741268B (en) | A kind of vision positioning method based on colored segment and its topological relation | |
| CN113554688A (en) | Monocular vision-based O-shaped sealing ring size measurement method | |
| CN113989368A (en) | High-precision positioning method and system for object surface | |
| CN113298880B (en) | Camera calibration board, camera calibration 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 |