CN113450405A - Method for positioning cylindrical part and hooking grapple of yard crane - Google Patents

Method for positioning cylindrical part and hooking grapple of yard crane Download PDF

Info

Publication number
CN113450405A
CN113450405A CN202111009348.3A CN202111009348A CN113450405A CN 113450405 A CN113450405 A CN 113450405A CN 202111009348 A CN202111009348 A CN 202111009348A CN 113450405 A CN113450405 A CN 113450405A
Authority
CN
China
Prior art keywords
grapple
pixel
image
cylinder
center
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.)
Granted
Application number
CN202111009348.3A
Other languages
Chinese (zh)
Other versions
CN113450405B (en
Inventor
杨文强
聂福全
杜留锋
陈永刚
杨之乐
李勇峰
徐君鹏
彭占磊
张栋华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Henan Institute of Science and Technology
Original Assignee
Henan Institute of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Henan Institute of Science and Technology filed Critical Henan Institute of Science and Technology
Priority to CN202111009348.3A priority Critical patent/CN113450405B/en
Publication of CN113450405A publication Critical patent/CN113450405A/en
Application granted granted Critical
Publication of CN113450405B publication Critical patent/CN113450405B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/136Segmentation; Edge detection involving thresholding
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • G06T7/66Analysis of geometric attributes of image moments or centre of gravity
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10004Still image; Photographic image
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30248Vehicle exterior or interior

Abstract

The invention discloses a method for positioning a cylindrical part of a yard crane and hooking a grapple. The method specifically comprises the following steps: A. firstly, acquiring a storage position of a cylindrical piece corresponding to a code; B. downward probing the grapple to ensure that the height difference between the industrial camera of the grapple and the target cylinder piece is H; C. starting an industrial camera of the grapple to acquire images; D. carrying out binarization on the acquired image; E. from top to bottom, the black-white pixel ratio is counted by scanning line by line, and two end points representing the projected boundary of the upper and lower surfaces of the target cylindrical piece on the image are found and are respectively marked as A (x)a,ya)、B(xb,yb) (ii) a F. Calculating to obtain the center coordinate C (x) of the target cylinder part on the imagec,yc) (ii) a G. ComputingThe actual distance of the grapple from the center of the target cylinder in the XOY plane.

Description

Method for positioning cylindrical part and hooking grapple of yard crane
Technical Field
The invention belongs to the technical field of intelligent hoisting, and particularly relates to a method for positioning a cylindrical part and hooking a grapple of a yard crane.
Background
How to quickly position the cylindrical part and how to hook the grapple hook are key factors influencing the operating efficiency of the yard crane, however, the existing yard crane also basically adopts a manual operation mode to position the cylindrical part and the grapple hook, and the positioning accuracy and the efficiency of the grapple hook are greatly reduced by visual fatigue and human visual blind areas caused by continuous high-strength work, wherein the positioning mode and the grapple hook are mainly based on experience and human visual observation. In this regard, the level of intelligence of the crane needs to be further improved to meet the application requirements of the intelligent crane. Therefore, the method for quickly positioning the cylindrical part of the yard crane and hooking the grapple based on the machine vision is sought, so that the theoretical knowledge of the efficient operation of the crane is enriched, and the method has good practical application and engineering demonstration values.
In addition, when the target object is positioned, most of the conventional methods extract features by convolution and the like or compare an image with a corresponding template to determine a contour, a large amount of calculation is required, the execution efficiency is low, and for a related control component on a crane, the time consumption is relatively long, and the requirement is relatively high, so that the problem of the execution efficiency in positioning needs to be solved.
Disclosure of Invention
In order to solve the problems in the background art, the invention firstly provides a method for positioning a cylindrical piece of a yard crane and secondly provides a method for hooking a grapple.
A method for positioning a storage yard cylinder is used for a storage yard crane to find the center of a target cylinder stored in a storage yard so as to position the target cylinder.
The trolley of the crane is provided with a vertically movable grapple, the center of which is provided with a resolution ratio px×pyThe industrial camera of (2) specifies that the pixel at the leftmost upper corner of the image shot by the industrial camera is the origin of coordinates, the horizontal right direction on the image is the positive direction of an x axis, and the vertical downward direction on the image is the positive direction of a y axis.
The included angle between the placing angle of the cylinder pieces axially and horizontally stored in the storage yard and the y axis is any angle between 0 degrees and 5 degrees.
Pre-storing information of the cylindrical parts stored in a storage yard, wherein the information comprises individual information of the cylindrical parts and public information of the cylindrical parts; the individual information of the cylindrical pieces comprises the code of each cylindrical piece stored in the storage yard and the position of a storage position of the cylindrical piece corresponding to the code; the cylinder public information is used for storing the actual height D of a certain cylinder, the pixel number D corresponding to D in the binary image of the certain cylinder and the bottom surface excircle radius R of the certain cylinder; when acquiring a binary image of a certain cylindrical object, setting the resolution as px×pyThe uppermost left corner pixel of the image shot by the industrial camera is the origin of coordinates, the horizontal right direction on the image is the positive direction of an x axis, the vertical downward direction on the image is the positive direction of a y axis, the individual of a certain type of cylindrical parts is arranged horizontally in the axial direction, the axial direction is consistent with the direction of the y axis, the projection of the center of the image shot by the industrial camera and the projection of the center of the individual of the certain type of cylindrical parts on an XOY plane are kept to be superposed, the height difference between the individual of the industrial camera and the individual of the certain type of cylindrical parts is H, and the H ensures that p is the same as the height difference between the individual of the industrial camera and the individual of the certain type of cylindrical partsxThe actual length of the representation is smaller than 4R and larger than 2R, and after the image is collected, binarization is performed, and then d is obtained through statistics.
The method specifically comprises the following steps:
A. when a target cylindrical part with a certain code needs to be positioned, the position of a goods position where the cylindrical part corresponding to the code is stored is firstly obtained, and a cart and a trolley of a crane are driven, so that the grapple is moved to the position of the goods position.
B. And (4) downwards probing the grapple, so that the height difference between the industrial camera of the grapple and the target cylinder piece is H.
C. And starting the industrial camera of the grapple to acquire images.
D. And carrying out binarization on the acquired image.
E. And (3) counting the ratio of black and white pixels of the binary image by scanning line by line from top to bottom, and when the ratio of the number of the black and white pixels of the (i-1) th line is different from that of the (i) th line and the ratio of the number of the black and white pixels of the (i + 1) th line is the same as that of the (i) th line, considering that the (i) th line is a critical pixel line, finding two end points which are above the (i-1) th line and represent the projection boundary of the upper bottom surface of the target cylindrical part on the image, and respectively marking the two end points as A (x)a,ya)、B(xb,yb)。
F. Calculating to obtain the center coordinate C (x) of the target cylinder part on the imagec,yc) Thereby achieving the positioning of the center of the target cylinder on the image, wherein xc=(xa+xb)/2,yc=(ya+yb)/2+d/2。
G. Image center coordinate is (p)x/2,py/2), calculating C (x)c,yc) The difference between the number of pixels and the central coordinate of the image is expressed as Δ x = px/2-xc、Δy=py/2-ycAnd calculating the actual distance between the grapple and the center of the target cylinder on the XOY plane according to the actual distance represented by each pixel, and further moving a cart and a trolley of the crane so as to enable the industrial camera of the grapple to be aligned to the center of the target cylinder.
Further, in step D, when the image is binarized, the image is first subjected to the gradation processing and then to the binarization processing.
Further, in the graying processing, values of R, G, B three color channels of each pixel in the captured image are recorded as VR、VG、VBThe graying is performed by using a weighted average method, a maximum value method, a gamma correction method or an average value method.
When using the weighted average method, the weighting coefficients of R, G, B three color channels are set to WR、WG、WBThen the Gray value Gray = V of each pixel after grayingR×WR+VG×WG+VB×WB
When the maximum value method is used, the Gray value Gray of each pixel after the graying is V of the pixelR、VG、VBMaximum value of (2).
When the gamma correction method is used, the Gray value Gray = ((V) for each pixel after the grayingR 2.2+(1.5VG)2.2+(0.6VB)2.2)/(1+1.52.2+0.62.2))^(5/11)。
When the average value method is used, the Gray level value Gray = (V) of each pixel after the grayingR+VG+VB)/3。
Further, when using the weighted average method, WR=0.3、WG=0.59、WB=0.11。
Further, after graying processing, binarization is carried out by using a histogram bimodal method; and counting the grayed image to obtain a gray value distribution histogram, selecting a separation threshold value between two peaks of the gray value distribution histogram, setting the gray value which is greater than or equal to the separation threshold value to be 255, and setting the gray value which is smaller than the separation threshold value to be 0, thereby completing binarization.
Further, in step E, the method of finding two end points representing the boundary of the projection of the upper and lower surfaces of the target cylinder on the image is one of the following methods: E1. from the i-1 th line upwards, pixels are judged according to the rule from left to right line by line, and when a pixel with the first gray level replacement is met, the pixel is marked as A (x)a,ya) As one end point, the judgment of the current line is ended, and the subsequent judgment area is pxA/2 is a boundary with respect to xaAnd the other side of the one side is used for continuously judging the pixels in the previous row from left to right, if no pixel meeting the condition exists, judging the pixels in the next previous row in the judgment area, and when the pixel with the first gray level replacement is encountered again, recording the point as B (x)b,yb) As another endpoint; e2Looking for the first gray-level-changed pixel closest to the middle pixel of the row from the middle pixel to the left and right sides row by row from the i-1 th row upwards, and recording as A (x)a,ya) As an endpoint, x is determined simultaneouslyaAnd pxThe size relation of/2, then ending the judgment of the current line, starting the judgment of the pixel of the previous line, but judging the region as pxA/2 is a boundary with respect to xaIf there is no pixel meeting the condition, the other side of the side is used to judge the pixel of the next previous row, when the pixel with the first gray level replacement is encountered again, the point is marked as B (x)b,yb) As the other endpoint.
Further, in step G, when calculating the actual distance between the grapple and the center of the target cylinder on the XOY plane, the actual distance between the grapple and the center of the target cylinder on the x-axis is Δ x (D/D), and the actual distance between the grapple and the center of the target cylinder on the y-axis is Δ y (D/D).
Further, the center of the grapple is also provided with a ring embedded with a lighting lamp for ensuring the imaging brightness of the industrial camera.
The method for hooking the grapple further comprises the steps of obtaining the radius R of the inner circle of the bottom surface of the target cylindrical part in advance, driving the grapple to open for a distance of D/2 after an industrial camera of the grapple is aligned to the center of the target cylindrical part, then lowering the grapple to enable the grapple to descend for a height of H + (R-R), and finally retracting the grapple again to clamp the target cylindrical part, namely completing the grapple hooking action on the target cylindrical part.
When the included angle is 5 degrees, the length of the cylinder projected to the y axis is 0.996 times, which is within an acceptable error range, for example, when the included angle is 10 degrees, the length of the cylinder projected to the y axis becomes 0.985 times of the actual length, when the included angle is larger, the length of the cylinder projected to the y axis is only 0.94 times when the included angle is 20 degrees, and when the included angle is 30 degrees, the length of the cylinder projected to the y axis is only 0.866 times, which is larger in error. Thereby limiting the arrangement angle of the cylindrical member to be [0 DEG, 5 DEG ] with the y axis]Thereby ensuring the calculation of C (x)c,yc) When d/2 is added, the projection of the centre of the grapple, i.e. the centre of the camera and the cylinder, on the XOY plane does not show a large deviation.
In the actual use process, the cart and the trolley are manually or automatically moved to the vicinity of the target cylindrical part, so that the center of the industrial camera is approximately positioned at the target cylindrical part, and then the positioning method disclosed by the invention can replace manual fine adjustment to realize more accurate positioning.
Compared with the prior art, the invention has the beneficial effects that: the binary image is scanned from top to bottom line by line to count the ratio of black and white pixels, and a critical pixel line with the first ratio of the number of black and white pixels changing from constant to constant is found, so that the boundary of one end of the target cylinder part on the image is determined. From the in-service use effect, it can avoid the inaccurate and problem of the fish tail of scraping of article scraping that brings from this of location that manual operation brought, has reduced the operating cost, has improved the hoist and mount efficiency and the economic benefits of hoist.
Drawings
FIG. 1: the size and position of the grab hook and the target cylinder piece of the yard crane are shown schematically.
FIG. 2: the grayed image in example 1.
FIG. 3: the binarized image in example 1.
In the figure: 1. industrial camera, 2. grapple, 3. ring embedded with lighting lamp.
Detailed Description
The present invention is explained, but not limited to, and the technical solutions obtained in the light of the idea of the present invention should be included in the scope of protection of the present patent.
Example 1
As shown in fig. 1-3.
A method for positioning a storage yard cylinder is used for a storage yard crane to find the center of a target cylinder stored in a storage yard so as to position the target cylinder.
The trolley of the crane is provided with a grab hook 2 capable of moving vertically, and the center of the grab hook 2 is provided with a resolution ratio px×pyThe industrial camera 1 of (1) specifies the pixel at the uppermost left corner of the image taken by the industrial camera 1 as the origin of coordinates,the horizontal direction on the image is the positive direction of the x axis, and the vertical direction on the image is the positive direction of the y axis.
The included angle between the placing angle of the cylinder pieces axially and horizontally stored in the storage yard and the y axis is any angle between 0 degrees and 5 degrees.
Pre-storing information of the cylindrical parts stored in a storage yard, wherein the information comprises individual information of the cylindrical parts and public information of the cylindrical parts; the individual information of the cylindrical pieces comprises the code of each cylindrical piece stored in the storage yard and the position of a storage position of the cylindrical piece corresponding to the code; the cylinder common information is used for storing the actual height D of a certain cylinder (in this embodiment, D =15.6 cm), the number of pixels D corresponding to D in the binarized image of a certain cylinder (in this embodiment, D = 780), and the bottom outer circle radius R of a certain cylinder (in this embodiment, R =5.5 cm); when acquiring a binary image of a certain cylindrical object, setting the resolution as px×py(in this example px=1080,py= 1056), the pixel at the uppermost left corner of the image shot by the industrial camera 1 is the origin of coordinates, the pixel at the uppermost left corner of the image is the x-axis forward direction, the pixel at the uppermost left corner of the image is the y-axis forward direction, the individual of a certain type of cylindrical member is arranged horizontally in the axial direction, the axial direction of the individual is consistent with the y-axis direction, the center of the image shot by the industrial camera 1 is kept to be superposed with the projection of the center of the individual of the certain type of cylindrical member on the XOY plane, the height difference between the industrial camera 1 and the individual of the certain type of cylindrical member is H (H =22cm in the embodiment), and the H ensures that p isxThe actual length of the representation is smaller than 4R and larger than 2R, and after the image is collected, binarization is performed, and then d is obtained through statistics.
The method specifically comprises the following steps:
A. when a target cylindrical part with a certain code needs to be positioned, the position of a goods position where the cylindrical part corresponding to the code is stored is firstly obtained, and a cart and a trolley of the crane are driven, so that the grapple 2 is moved to the position of the goods position.
B. The grapple 2 is lowered so that the height difference between the industrial camera 1 of the grapple 2 and the target cylinder is H.
C. The industrial camera 1 of the grapple 2 is activated for image acquisition.
D. And carrying out binarization on the acquired image. When binarizing an image, first, gradation is performedPerforming binarization treatment, and performing binarization treatment; when graying is performed, the values of R, G, B three color channels of each pixel in the acquired image are recorded as VR、VG、VBCarrying out graying treatment by using a weighted average value method or a maximum value method or a gamma correction method or an average value method: when using the weighted average method, the weighting coefficients of R, G, B three color channels are set to WR、WG、WBThen the Gray value Gray = V of each pixel after grayingR×WR+VG×WG+VB×WBFurther, when using the weighted average method, WR=0.3、WG=0.59、WB= 0.11; when the maximum value method is used, the Gray value Gray of each pixel after the graying is V of the pixelR、VG、VBMaximum value of (1); when the gamma correction method is used, the Gray value Gray = ((V) for each pixel after the grayingR 2.2+(1.5VG)2.2+(0.6VB)2.2)/(1+1.52.2+0.62.2) Lambada (5/11); when the average value method is used, the Gray level value Gray = (V) of each pixel after the grayingR+VG+VB)/3. In this embodiment, a weighted average method is used for processing, and those skilled in the art can flexibly adjust the graying method as needed. Further, after graying processing, binarization is carried out by using a histogram bimodal method; the grayed image is counted to obtain a gray value distribution histogram, a separation threshold is selected between two peaks of the gray value distribution histogram, the gray value greater than or equal to the separation threshold is set to 255, and the gray value smaller than the separation threshold is set to 0, so that binarization is completed, in this embodiment, threshold selection is 127.
E. And for the binary image, scanning and counting the ratio of black and white pixels line by line from top to bottom, and when the ratio of the number of the black and white pixels of the (i-1) th line is different from that of the (i) th line and the ratio of the number of the black and white pixels of the (i + 1) th line is the same as that of the (i) th line, considering that the (i) th line is a critical pixel line, and finding two boundaries which are above the (i-1) th line and represent the projection of the upper bottom surface of the target cylindrical part on the imageThe endpoints, respectively, are denoted as A (x)a,ya)、B(xb,yb)。
Further, in step E, the method of finding two end points representing the boundary of the projection of the upper and lower surfaces of the target cylinder on the image is one of the following methods:
E1. from the i-1 th line upwards, pixels are judged according to the rule from left to right line by line, and when a pixel with the first gray level replacement is met, the pixel is marked as A (x)a,ya) As one end point, the judgment of the current line is ended, and the subsequent judgment area is pxA/2 is a boundary with respect to xaAnd the other side of the one side is used for continuously judging the pixels in the previous row from left to right, if no pixel meeting the condition exists, judging the pixels in the next previous row in the judgment area, and when the pixel with the first gray level replacement is encountered again, recording the point as B (x)b,yb) As another endpoint;
E2. looking for the pixels with the first gray level replacement closest to the middle pixels of the row from the middle pixels to the left and right sides row by row from the i-1 th row upwards, and marking the pixels as A (x)a,ya) As an endpoint, x is determined simultaneouslyaAnd pxThe size relation of/2, then ending the judgment of the current line, starting the judgment of the pixel of the previous line, but judging the region as pxA/2 is a boundary with respect to xaIf there is no pixel meeting the condition, the other side of the side is used to judge the pixel of the next previous row, when the pixel with the first gray level replacement is encountered again, the point is marked as B (x)b,yb) As the other endpoint.
In this embodiment, the critical pixels behave as a (x) found from top to bottom row 120, using method E1a,ya) Is (813,119), B (x)b,yb) Is (263,108).
F. Calculating to obtain the center coordinate C (x) of the target cylinder part on the imagec,yc) Thereby achieving the positioning of the center of the target cylinder on the image, wherein xc=(xa+xb)/2,yc=(ya+yb) 2+ d/2, C is (538, 503.5),since C does not represent an actual pixel, but is only needed for calculation, 503.5 need not be rounded.
G. Image center coordinate is (p)x/2,py/2), calculating C (x)c,yc) The difference between the number of pixels and the central coordinate of the image is expressed as Δ x = px/2-xc=2、Δy=py/2-ycAnd =24.5, calculating the actual distance between the grapple 2 and the center of the target cylinder on the XOY plane according to the actual distance represented by each pixel, and further moving the cart and the trolley of the crane, so that the industrial camera 1 of the grapple 2 is aligned with the center of the target cylinder.
Further, in step G, when calculating the actual distance between the grapple 2 and the center of the target cylinder on the XOY plane, the actual distance between the grapple 2 and the center of the target cylinder on the x axis is Δ x (D/D) =0.04cm, and the actual distance between the grapple 2 and the center of the target cylinder on the y axis is Δ y x (D/D) =0.49 cm.
Further, the center of the grapple 2 is provided with a ring 3 embedded with an illumination lamp for securing the imaging brightness of the industrial camera 1.
A grapple hooking method also comprises the steps of obtaining the radius R =2.5cm of the inner circle of the bottom surface of a target cylinder in advance, driving a grapple 2 to open for a distance of D/2=7.8cm after an industrial camera 1 of the grapple 2 is aligned with the center of the target cylinder, lowering the grapple 2 until the height of the grapple 2 is H + (R-R) =25cm, and finally retracting the grapple 2 again to clamp the target cylinder, namely completing the grapple hooking action of the target cylinder.

Claims (9)

1. A method for positioning a storage yard cylinder, which is used for a storage yard crane to find the center of a target cylinder stored in a storage yard so as to position the target cylinder, and is characterized in that:
the trolley of the crane is provided with a vertically movable grapple (2), and the center of the grapple (2) is provided with a resolution ratio px×pyThe industrial camera (1) is specified, the pixel at the uppermost left corner of the image shot by the industrial camera (1) is taken as the origin of coordinates, the horizontal right direction on the image is the positive direction of an x axis, and the vertical downward direction on the image is the positive direction of a y axis;
the included angle between the placing angle of the cylindrical pieces axially and horizontally stored in the storage yard and the y axis is any angle between 0 degrees and 5 degrees;
pre-storing information of the cylindrical parts stored in a storage yard, wherein the information comprises individual information of the cylindrical parts and public information of the cylindrical parts; the individual information of the cylindrical pieces comprises the code of each cylindrical piece stored in the storage yard and the position of a storage position of the cylindrical piece corresponding to the code; the cylinder public information is used for storing the actual height D of a certain cylinder, the pixel number D corresponding to D in the binary image of the certain cylinder and the bottom surface excircle radius R of the certain cylinder; when acquiring a binary image of a certain cylindrical object, setting the resolution as px×pyThe pixel at the leftmost upper corner of the image shot by the industrial camera (1) is a coordinate origin, the pixel at the upper horizontal right side of the image is an x-axis positive direction, the pixel at the upper vertical lower side of the image is a y-axis positive direction, the individual of a certain type of cylinder piece is arranged horizontally in the axial direction, the axial direction is consistent with the y-axis direction, the center of the image shot by the industrial camera (1) is kept to be superposed with the projection of the center of the individual of the certain type of cylinder piece on an XOY plane, the height difference between the industrial camera (1) and the individual of the certain type of cylinder piece is H, and the H ensures that p is the same as the height difference between the industrial camera (1) and the individual of the certain type of cylinder piecexThe represented actual length is smaller than 4R and larger than 2R, and after the image is collected, binaryzation is carried out, so that d is obtained through statistics;
the method specifically comprises the following steps:
A. when a target cylindrical part with a certain code needs to be positioned, firstly, a goods position where the cylindrical part corresponding to the code is stored is obtained, and a cart and a trolley of a crane are driven, so that the grapple (2) moves to the goods position;
B. downwards exploring the grapple (2) to ensure that the height difference between the industrial camera (1) of the grapple (2) and the target cylinder piece is H;
C. starting an industrial camera (1) of the grapple (2) to acquire images;
D. carrying out binarization on the acquired image;
E. for the binary image, scanning line by line from top to bottom to count the ratio of black and white pixels, when the ratio of the number of black and white pixels of the (i-1) th line is different from that of the (i) th line and the ratio of the number of black and white pixels of the (i + 1) th line is the same as that of the (i) th line, considering the (i) th line as a critical pixel line, and finding out the (i-1) th line as a critical pixel lineAs described above, the two end points of the boundary representing the projection of the upper and lower surfaces of the target cylinder on the image are denoted by A (x)a,ya)、B(xb,yb);
F. Calculating to obtain the center coordinate C (x) of the target cylinder part on the imagec,yc) Thereby achieving the positioning of the center of the target cylinder on the image, wherein xc=(xa+xb)/2,yc=(ya+yb)/2+d/2;
G. Image center coordinate is (p)x/2,py/2), calculating C (x)c,yc) The difference between the number of pixels and the central coordinate of the image is expressed as Δ x = px/2-xc、Δy=py/2-ycAnd then, calculating the actual distance between the grapple (2) and the center of the target cylinder piece on the XOY plane according to the actual distance represented by each pixel, and further moving a cart and a trolley of the crane so as to align the industrial camera (1) of the grapple (2) to the center of the target cylinder piece.
2. A yard cylinder positioning method according to claim 1, characterized in that: in step D, when the image is binarized, the image is first subjected to the graying process and then to the binarization process.
3. A yard cylinder positioning method according to claim 2, characterized in that: when graying is performed, the values of R, G, B three color channels of each pixel in the acquired image are recorded as VR、VG、VBCarrying out graying treatment by using a weighted average value method or a maximum value method or a gamma correction method or an average value method;
when using the weighted average method, the weighting coefficients of R, G, B three color channels are set to WR、WG、WBThen the Gray value Gray = V of each pixel after grayingR×WR+VG×WG+VB×WB
When the maximum value method is used, the Gray value Gray of each pixel after the graying is the Gray value of the pixelVR、VG、VBMaximum value of (1);
when the gamma correction method is used, the Gray value Gray = ((V) for each pixel after the grayingR 2.2+(1.5VG)2.2+(0.6VB)2.2)/(1+1.52.2+0.62.2))^(5/11);
When the average value method is used, the Gray level value Gray = (V) of each pixel after the grayingR+VG+VB)/3。
4. A yard cylinder positioning method according to claim 3, wherein: using a weighted average method, WR=0.3、WG=0.59、WB=0.11。
5. A yard cylinder positioning method according to claim 2, characterized in that: after graying processing, binaryzation is carried out by using a histogram bimodal method; and counting the grayed image to obtain a gray value distribution histogram, selecting a separation threshold value between two peaks of the gray value distribution histogram, setting the gray value which is greater than or equal to the separation threshold value to be 255, and setting the gray value which is smaller than the separation threshold value to be 0, thereby completing binarization.
6. A yard cylinder positioning method according to claim 1, characterized in that: in step E, the method of finding the two end points of the boundary representing the projection of the upper bottom surface of the target cylinder on the image is one of the following methods:
E1. from the i-1 th line upwards, pixels are judged according to the rule from left to right line by line, and when a pixel with the first gray level replacement is met, the pixel is marked as A (x)a,ya) As one end point, the judgment of the current line is ended, and the subsequent judgment area is pxA/2 is a boundary with respect to xaAnd the other side of the side is used for continuously judging the pixels in the previous row from left to right, if no pixel meeting the condition exists, judging the pixels in the next previous row in the judgment area, and when the first gray is met againThe pixel with the degree of replacement is marked as B (x)b,yb) As another endpoint;
E2. looking for the pixels with the first gray level replacement closest to the middle pixels of the row from the middle pixels to the left and right sides row by row from the i-1 th row upwards, and marking the pixels as A (x)a,ya) As an endpoint, x is determined simultaneouslyaAnd pxThe size relation of/2, then ending the judgment of the current line, starting the judgment of the pixel of the previous line, but judging the region as pxA/2 is a boundary with respect to xaIf there is no pixel meeting the condition, the other side of the side is used to judge the pixel of the next previous row, when the pixel with the first gray level replacement is encountered again, the point is marked as B (x)b,yb) As the other endpoint.
7. A yard cylinder positioning method according to claim 1, characterized in that: in the step G, when the actual distance between the grapple (2) and the center of the target cylinder piece on the XOY plane is calculated, the actual distance between the grapple (2) and the center of the target cylinder piece on the x axis is delta x (D/D), and the actual distance between the grapple (2) and the center of the target cylinder piece on the y axis is delta y x (D/D).
8. A yard cylinder positioning method according to claim 1, characterized in that: the center of the grapple (2) is also provided with a ring (3) which is used for ensuring the imaging brightness of the industrial camera (1) and is embedded with a lighting lamp.
9. A grapple hooking method based on the method for positioning a drum of a yard crane according to any one of claims 1 to 8, characterized in that: the method comprises the steps of obtaining the radius R of the inner circle of the bottom surface of a target cylinder piece in advance, driving a grapple (2) to open a distance D/2 after an industrial camera (1) of the grapple (2) is aligned to the center of the target cylinder piece, then descending the grapple (2), enabling the descending height of the grapple (2) to be H + (R-R), and finally contracting the grapple (2) again to clamp the target cylinder piece, namely completing the grapple and hook action on the target cylinder piece.
CN202111009348.3A 2021-08-31 2021-08-31 Method for positioning cylindrical part and hooking grapple of yard crane Active CN113450405B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111009348.3A CN113450405B (en) 2021-08-31 2021-08-31 Method for positioning cylindrical part and hooking grapple of yard crane

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111009348.3A CN113450405B (en) 2021-08-31 2021-08-31 Method for positioning cylindrical part and hooking grapple of yard crane

Publications (2)

Publication Number Publication Date
CN113450405A true CN113450405A (en) 2021-09-28
CN113450405B CN113450405B (en) 2021-11-12

Family

ID=77819335

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111009348.3A Active CN113450405B (en) 2021-08-31 2021-08-31 Method for positioning cylindrical part and hooking grapple of yard crane

Country Status (1)

Country Link
CN (1) CN113450405B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115115636A (en) * 2022-08-30 2022-09-27 南通长石科技有限公司 Intelligent control system and control method for unmanned material grabbing machine

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103752534A (en) * 2014-01-14 2014-04-30 温州中波电气有限公司 Intelligent-vision-based image intelligent recognizing-sorting device and method
CN204021915U (en) * 2013-01-25 2014-12-17 德马格起重机及部件有限公司 For capturing the mechanical load-engaging device of transporting cargo
CN106934813A (en) * 2015-12-31 2017-07-07 沈阳高精数控智能技术股份有限公司 A kind of industrial robot workpiece grabbing implementation method of view-based access control model positioning
US20180141787A1 (en) * 2016-11-22 2018-05-24 Manitowoc Crane Companies, Llc Optical detection and analysis of crane hoist and rope
CN111080599A (en) * 2019-12-12 2020-04-28 哈尔滨市科佳通用机电股份有限公司 Fault identification method for hook lifting rod of railway wagon
CN112150544A (en) * 2020-09-24 2020-12-29 西门子(中国)有限公司 Hook in-place detection method and device and computer readable medium
CN112884422A (en) * 2021-04-28 2021-06-01 河南科技学院 Automatic crane operation system for storage yard storage

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN204021915U (en) * 2013-01-25 2014-12-17 德马格起重机及部件有限公司 For capturing the mechanical load-engaging device of transporting cargo
CN103752534A (en) * 2014-01-14 2014-04-30 温州中波电气有限公司 Intelligent-vision-based image intelligent recognizing-sorting device and method
CN106934813A (en) * 2015-12-31 2017-07-07 沈阳高精数控智能技术股份有限公司 A kind of industrial robot workpiece grabbing implementation method of view-based access control model positioning
US20180141787A1 (en) * 2016-11-22 2018-05-24 Manitowoc Crane Companies, Llc Optical detection and analysis of crane hoist and rope
CN111080599A (en) * 2019-12-12 2020-04-28 哈尔滨市科佳通用机电股份有限公司 Fault identification method for hook lifting rod of railway wagon
CN112150544A (en) * 2020-09-24 2020-12-29 西门子(中国)有限公司 Hook in-place detection method and device and computer readable medium
CN112884422A (en) * 2021-04-28 2021-06-01 河南科技学院 Automatic crane operation system for storage yard storage

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
MASAHIRO IZUMI 等: "Automatic Hook Crane With Robotic Arm", 《2011 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS》 *
董富祥 等: "一种可伸缩长度可调中心距的取桩吊具", 《起重运输机械》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115115636A (en) * 2022-08-30 2022-09-27 南通长石科技有限公司 Intelligent control system and control method for unmanned material grabbing machine

Also Published As

Publication number Publication date
CN113450405B (en) 2021-11-12

Similar Documents

Publication Publication Date Title
CN106067023B (en) Container number and truck number identification system and method based on image processing
CN113450405B (en) Method for positioning cylindrical part and hooking grapple of yard crane
CN108133216B (en) Nixie tube reading identification method capable of realizing decimal point reading based on machine vision
CN105678749B (en) A kind of fresh fish discriminating direction method of view-based access control model
CN112194011A (en) Tower crane automatic loading method based on binocular vision
CN107014291B (en) A kind of vision positioning method of material precision transfer platform
CN1667355A (en) Image recognition method and image recognition apparatus
CN108890692A (en) A kind of material color identification method for industrial robot vision's sorting
CN112304954A (en) Part surface defect detection method based on line laser scanning and machine vision
CN107301634A (en) A kind of robot automatic sorting method and system
CN109548489A (en) A kind of apple picking robot based on yolo vision
JP2004055658A (en) Electronic component loading apparatus and method of recognizing images
CN104392210A (en) Gesture recognition method
CN109225941B (en) Automatic detection and sorting system and method for internal thread tapping condition
CN108480223A (en) A kind of workpiece sorting system and its control method
CN114881965A (en) Wood board joint detection method based on artificial intelligence and image processing
JP6642776B1 (en) Inspection device and inspection method
CN108896561B (en) Textile fabric detection method based on multi-thread machine vision
JP4987323B2 (en) Color filter defect correcting apparatus and color filter defect correcting method
CN111815542A (en) Tree ring image medullary center positioning and ring measuring method
CN107578379A (en) A kind of processing method of chess robot to checkerboard image
CN213196231U (en) Welding seam tracking robot
CN114842335A (en) Slotting target identification method and system for construction robot
CN1542697A (en) Words and image dividing method on the basis of adjacent edge point distance statistics
CN110827272B (en) Tire X-ray image defect detection method based on image processing

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