CN114166121B - Log rule checking method based on four-edge rule - Google Patents
Log rule checking method based on four-edge rule Download PDFInfo
- Publication number
- CN114166121B CN114166121B CN202111454867.0A CN202111454867A CN114166121B CN 114166121 B CN114166121 B CN 114166121B CN 202111454867 A CN202111454867 A CN 202111454867A CN 114166121 B CN114166121 B CN 114166121B
- Authority
- CN
- China
- Prior art keywords
- log
- grid
- scale
- coordinates
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012937 correction Methods 0.000 claims abstract description 12
- 239000003550 marker Substances 0.000 claims description 22
- 239000011159 matrix material Substances 0.000 claims description 22
- 230000011218 segmentation Effects 0.000 claims description 17
- 239000002023 wood Substances 0.000 claims description 14
- 238000007689 inspection Methods 0.000 claims description 10
- 240000004282 Grewia occidentalis Species 0.000 claims description 8
- 238000013213 extrapolation Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 2
- 230000009466 transformation Effects 0.000 abstract description 7
- 238000011179 visual inspection Methods 0.000 abstract 1
- 238000005259 measurement Methods 0.000 description 18
- 238000001514 detection method Methods 0.000 description 10
- 230000000007 visual effect Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000000691 measurement method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000011120 plywood Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
- G01B11/0608—Height gauges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/08—Measuring arrangements characterised by the use of optical techniques for measuring diameters
-
- G06T5/70—
-
- G06T5/80—
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a log checking method based on a four-edge scale. The four-edge ruler is used as an auxiliary tool, a handheld camera is used for collecting images of the log end face, the log images are corrected through a machine vision algorithm, and finally the diameter of the log end face is measured in the corrected images. The invention abandons the method that the traditional method usually uses a fixed camera and a calibration plate, and adopts a four-edge scale correction image method. The invention firstly uses a geodesic standard pole and a T-shaped connecting block to assemble a four-edge scale, acquires a snap image of the four-edge scale and the log end surface, detects the reference point of the four-edge scale frame, obtains a grid by an interpolation method, obtains a correction chart through perspective transformation of the grid, and finally calculates the diameter of the log end surface on the correction chart according to the size of the grid to finish the visual inspection of the log stack.
Description
Technical Field
The invention relates to the field of image processing and computer vision, in particular to a log ruler detection method based on a four-edge ruler.
Background
In the course of timber harvesting, timber volume measurement is one of the important tasks, and the sales and processing of timber also depends on the measurement of timber volume. The calculation of the volume is approximated by using the volume of the cylinder, and the calculation of the volume can be completed by only knowing the log gauge and gauge length or by referring to the log volume table according to the log volume calculation formula taught in the national standard log volume table (GB 4814-84).
For a long time, for wood processing enterprises and wood sales enterprises, the wood volume measurement work is completed by using a manual gauge, and the gauge length and the gauge diameter of the wood are directly measured by using tools such as a tape measure or a caliper. The manual inspection has a plurality of defects, wherein obvious defects are as follows: 1) high labor cost, low rule detection efficiency, 2) more complex rule detection rules, different types of logs with different rule detection rules, 3) high requirements on the working attitude and working experience of a rule detection staff for high-accuracy rule detection, 4) a certain height for stacking general wood, the rule detection staff often climbs up and down, and danger possibly occurs in the rule detection process.
At present, the manual log inspection method is that log numbers are firstly measured by a log inspector, then measurement data are recorded, so that the log inspection method cannot visualize the log inspection result, namely log images and the log inspection result are associated, and meanwhile, the log inspection situation cannot be traced back, so that an advanced visual wood measurement technology is urgently needed to replace the manual log inspection for adapting to the development trend of modern wood processing and sales, and the wood volume is efficiently acquired.
The method is characterized in that images of objects to be detected are collected, the sizes of the objects are measured by a computer vision technology, and the automatic detection of a plurality of industrial products, such as metal workpieces, plastic products, electronic products and the like, is almost successfully realized, however, the traditional computer vision measurement technology is difficult to directly apply to a log pile inspection ruler, and the reasons are as follows: 1) In general, before implementation, a Calibration (Calibration) process is required, a plurality of images are acquired by using a Calibration board, camera parameters are calculated by a Calibration algorithm, and because of the log pile images required to be acquired, the field of view is quite large, a large Calibration board is required, and outdoor operation is easy to influence by weather, so that the implementation of the Calibration process is difficult. 2) Conventional measurement techniques often require fixing the camera and then calibrating, then capturing an image of the object to be measured, and recalculating the measurement data based on the camera parameters, however, such calibration measurement techniques require recalibration once the camera is moved or the focal length is adjusted. Maintaining a fixed position and attitude of the camera, achieving the required facilities, appliances and techniques in an outdoor environment is much more difficult and costly than in an indoor environment. 3) The log collecting area is large in range, logs are conveyed to the gauge station in a centralized mode, time and transportation cost are consumed, measurement equipment carried by a gauge operator is dispersed to a collecting point gauge, on one hand, transportation cost is saved, on the other hand, influence of gauge operation on log cutting operation can be reduced, therefore, a correction-free process is designed, a hand-held camera can be used, measurement equipment is easy to carry, log pile gauge work is completed, and the log pile gauge is worthy of study.
In many signboards, the rectangle is one of the most common shapes, the imaged signboard image is distorted (display) due to the visual angle factor of the camera, as shown in fig. 1 (a) - (b), the shape of the rectangular license plate is changed into any quadrangle in the image, meanwhile, the sizes of letters and numbers in the license plate are changed, the sizes of letters and numbers close to the camera are larger, the sizes of letters and numbers close to the camera are smaller, in the actual license plate, all the letters and numbers are the same size, the any quadrangle can be corrected back into the rectangle through perspective transformation (Perspective transformation), the license plate shape is corrected back into the rectangle of the front visual angle as shown in fig. 1 (c) - (d), and the letters and numbers in the license plate are restored to the same size, so the rectangle with the known size is the characteristic of being capable of correcting the distorted image.
Disclosure of Invention
The invention aims to develop a visual measurement algorithm without a correction flow by taking a four-side scale as an auxiliary tool for the end face of a log pile, and particularly provides a log checking method based on the four-side scale.
To achieve the above object, it is divided into two parts: 1) The four-side scale design utilizes a detachable red-white alternate geodetic standard pole and a T-shaped connecting block which are currently marketed, a rectangular frame is formed by combining a left vertical rod, a right vertical rod, an upper cross rod and a lower cross rod, and red-white alternate bars form fixed length scales and are used as reference points for image correction. 2) The visual measurement algorithm inputs the image of the log end face in the four-side scale frame, detects the reference point of the four-side scale frame, obtains the Grid (Grid) by interpolation method, corrects the square Grid into square by perspective transformation one by one, and obtains the correction chart after a series of perspective transformations of the image, based on the assumption that the log end face and the Grid are in the same plane, on the correction chart, the diameter of the log end face can be calculated by the Grid with known size.
In order to achieve the above purpose, the technical scheme of the invention is as follows: a log scale detection method based on a four-edge scale comprises the following steps:
s1, placing the end face side of a log stack, enabling the end face of the log stack to be framed by a four-side ruler, enabling a rectangular frame of the four-side ruler and the end face of the log stack to be on the same plane, and collecting images containing the four-side ruler and the log stack;
s2, inputting a test image, and manually dragging an arbitrary quadrangle on a program user interface to enable the quadrangle to be matched with a quadrangle scale;
s3, after any quadrilateral is pulled to fit with a quadrilateral scale, four edges of the any quadrilateral are attached to a marker post, sub-sampling is carried out on gray scale images along the four edges to form one-dimensional signals, the one-dimensional signals approximate to square wave signals due to the fact that the marker post is painted in red-white phase, noise is removed through smooth filtering, then a first derivative is obtained on the smoothed signals, a local maximum value, where the first derivative is larger than a threshold value, and a local minimum value, where the first derivative is smaller than the threshold value, are selected, and the red-white boundary point positions of the marker post are obtained through the positions of the local maximum value and the local minimum value;
s4, detecting red and white boundary points on the marker post to obtain four groups of segmentation points of the upper side, the lower side, the left side and the right side, obtaining four corner points by an extrapolation method according to the segmentation points, obtaining grid points in a frame by an interpolation method, and forming a complete grid by adding four segmentation points and the four corner points to the interpolated grid points;
s5, after grid generation, converting each grid into rectangles with the same size, calculating a homography matrix of each grid for each grid, and converting each grid into new coordinates to generate a correction image;
and S6, for each log in the corrected image, manually dragging a straight line mode on a program user interface, passing through a wood core from one point of the outline to another point of the outline, measuring the log diameter, converting the image coordinates into real world coordinates by a scale, and finally calculating the log diameter from the two-point distance.
In one embodiment of the present invention, in step S3, the red-white boundary points of the marker post are as follows:
wherein, (x) i ，y i ) Is the coordinate of the red and white boundary point of the marker post, (x) 0 ，y 0 ) Is the coordinates of the starting end point of the edge, θ is the bevel angle of the edge, l i Is the value on the x-axis of the local maximum and local minimum.
In an embodiment of the present invention, step S5 is specifically implemented as follows:
after grid generation, each grid is converted into a rectangle with the same size, for each grid, the original (x, y) coordinates are transformed into (u, v) coordinates, the homography matrix is transformed according to the formula (2), 4 corresponding points are needed for calculating the homography matrix H, and the (x) coordinates are transformed into the homography matrix H 1 ，y 1 )→(u 1 ， v 1 )、(x 2 ，y 2 )→(u 2 ，v 2 )、(x 3 ，y 3 )→(u 3 ，v 3 )、(x 4 ，y 4 )→(u 4 ，v 4 ) Wherein (u) 1 ，v 1 )～(u 4 ，v 4 ) For the four-corner coordinates of the rectangle, the homography matrix H is acted on the corresponding points to obtain equation (3), and the least square solution of H can be found by using SVD algorithm
Wherein the H homography matrix is a 3×3 matrix, H 1 ,h 2 ,…,h 8 The first 8 elements of the matrix and the last 1 element is 1, as in the (2) equation arrangement.
In an embodiment of the present invention, step S6 is specifically implemented as follows:
each grid is converted to obtain a corrected image, and for each log in the corrected image, the log diameter is measured by manually dragging a straight line from one point of the profile through the wood core to another point of the profile on the program user interface, and the image coordinates (x A ，y A ) And (x) B ，y B ) Converting image coordinates into real world coordinates with a scale, x-direction scale(s) x ) For the actual length of the marker post/grid image width, the y-scale(s) y ) For the actual length of the marker post/grid image height, finally, calculating the log diameter by calculating A, B two-point distance according to the formula (4):
wherein dist (A, B) is A, B two-point distance, i.e. log diameter.
Compared with the prior art, the invention has the following beneficial effects: compared with the traditional method, the method is characterized in that the four-side ruler is used, a correction process is not needed, a camera is not needed to be fixed, the operation steps of the method are quite simple and convenient, the training difficulty of the technology used by the gauge inspector is low, in addition, the whole set of equipment is easy to carry, and the equipment can move around in a collection area and a scattered field to implement the log pile gauge operation.
Drawings
FIG. 1 is a correction of license plate images;
FIG. 2 is a geodesic stick and four-sided ruler;
fig. 3 is a snap image of a log model and a four-sided ruler;
FIG. 4 is a drag of arbitrary quadrilaterals;
FIG. 5 is a one-dimensional signal processing;
FIG. 6 is a grid generation;
FIG. 7 is a grid coordinate transformation;
fig. 8 is a corrected image.
Detailed Description
The technical scheme of the invention is specifically described below with reference to the accompanying drawings.
The technical scheme of the present invention will be clearly and completely described in the following examples.
The invention aims to develop a vision measurement algorithm without correction flow by taking a four-edge scale as an auxiliary tool for the end face of a log pile.
[ assembled four-sided ruler ]
Two groups of geodetic standard poles are purchased, 1 group has 5 removable connection short bars, 1 short bar is 100 cm long, 1 short bar has 5 red and white sections, each section is 20 cm long, as shown in fig. 2 (a), four-side scales are assembled by using 4T-shaped connecting blocks, as shown in fig. 2 (b), left and right vertical rods are assembled firstly, the T-shaped connecting blocks penetrate through the T-shaped connecting blocks, and then upper and lower cross bars are assembled, the T-shaped connecting blocks are adjusted at the positions where the sections are alternated, so that the height and the width of an inner frame of the four-side scales can be integer multiples of the length of the sections, as shown in fig. 2 (b), the height of the inner frame is 140 cm and is 7 sections, and the width of the inner frame is 100 cm and is 5 sections.
[ Vision measurement method ]
Placing the end face side of the log pile, enabling the end face of the log pile to be framed by the four-side staff gauge, enabling the rectangular frame of the four-side staff gauge and the end face of the log pile to be approximately on the same plane, and collecting images containing the four-side staff gauge and the log pile.
For verification, in a laboratory, a log model is made, several logs of different diameters are sawn, a plywood is mounted, the log is placed on the floor, the collected image is framed with four-sided scales, as shown in fig. 3, the logs are dispersed in the four-sided scale frames, and the four-sided scales and the end faces of the logs are at a near level.
Step two, inputting a test image, manually dragging an arbitrary quadrangle on a program user interface to enable the quadrangle to be matched with a quadrangle scale, as shown in fig. 3, wherein in fig. 3, a quadrangle is added on an original image, dragging control squares are arranged on four corners, a T-shaped connecting block is respectively clicked to drag the control squares, after four times of dragging are completed, the quadrangle can be matched with the quadrangle scale, and fig. 4 is the situation that the arbitrary quadrangle is dragged.
Step three, after any quadrilateral is pulled to fit with a quadrilateral scale, four edges of any quadrilateral are attached to a marker post, subsampling (Subsampling) is carried out on a gray scale image along the four edges respectively to form a one-dimensional signal, as shown in fig. 5 (a), an x-axis is the position of the edge, a y-axis is the gray scale value of Subsampling, as the marker post is painted in red and white, the one-dimensional signal approximates a square wave signal, noise is removed through smoothing filtering, then a first derivative is obtained on the smoothed signal, as shown in fig. 5 (b), a Local maximum value (Local maximum) with the first derivative being larger than a threshold value and a Local minimum value (Local minimum) being smaller than the threshold value are selected, the 2 threshold values are respectively set at 6.0 and-6.0, the Local maximum value and the Local minimum value are exactly located at the red and white boundary point of the marker post, and finally, the Local maximum value and the Local minimum value are located at the x-axis value (l) i ) Converted into the coordinates (x) of the red and white boundary point of the marker post by the method of 1 i ,y i ) Wherein (x) 0 ,y 0 ) Is the coordinates of the starting end point of the edge, θ is the bevel angle of the edge.
Step four, the detected red and white boundary points on the marker post can be regarded as segmentation points (Segment points) on four sides, and four sides obtain four groups of segmentation points: the upper, lower, left and right sides are then complemented with four corner points as shown in fig. 6 (a), the two-point straight line of the 1 st and 2 nd segmentation points is obtained by using the existing equal division point extrapolation (Extrainterpolation), the two-point straight line of the 1 st and 2 nd segmentation points is intersected with the two-point straight line of the 1 st and 2 nd segmentation points, the left upper corner point is obtained by extending the two straight lines, the two-point straight line of the 1 st and 2 nd segmentation points is intersected with the two-point straight line of the 1 st and 2 nd equal division points, the right upper corner point is obtained by extending the two straight lines, and the left lower corner point and the right lower corner point are also calculated by the method.
In order to implement grid correction (Grid rectification) to eliminate image distortion, interpolation is used to obtain grid points in the frame, the segmentation points on the upper side and the lower side are one-to-one correspondence, and the segmentation points on the left side and the right side are one-to-one correspondence, so that vertical connection lines of the segmentation points on the upper side and the lower side and horizontal connection lines of the segmentation points on the left side and the right side are drawn, grid points are obtained at the intersection points of the connection lines in two directions, and the interpolation grid points are added with four segmentation points and four corner points to form a complete grid, as shown in fig. 6 (b), and finally, a 5×7 grid is generated.
Step five, after grid generation, each grid is converted into a rectangle with the same size, for each grid, the original (x, y) coordinates are transformed into (u, v) coordinates, the homography matrix transformation is carried out according to the formula 2, 4 corresponding points are needed for calculating the homography matrix H, (x) 1 ,y 1 )→ (u 1 ,v 1 )、(x 2 ,y 2 )→(u 2 ,v 2 )、(x 3 ,y 3 )→(u 3 ,v 3 )、(x 4 ,y 4 )→(u 4 ,v 4 ) Wherein (u) 1 ,v 1 )～(u 4 ,v 4 ) As shown in fig. 7, the homography matrix H is applied to the corresponding points to obtain equation 3, and the least squares solution of H can be found using SVD algorithm.
Wherein the H homography matrix is a 3×3 matrix, H 1 ,h 2 ,…,h 8 For the first 8 elements of the matrix, the last 1 element is 1, e.g., (2) equationAnd (5) arrangement.
Step six, obtaining corrected images after each grid conversion, as shown in fig. 8 (a), for each log in the corrected images, measuring the log diameter by manually dragging a straight line from one point of the profile through the wood core to another point of the profile on the user interface, as shown in fig. 8 (B), taking the coordinates (x A ,y A ) And (x) B ,y B ) Converting image coordinates into real world coordinates with a scale, x-direction scale(s) x ) For the actual length of the marker post/grid image width, the y-scale(s) y ) The actual length of the marker post/the height of the grid image is expressed in mm/pixel, and finally, the distance between the points A and B is calculated by calculating the distance between the points A and B by using the method of 4, and the diameter (mm) of the raw wood is calculated.
Taking 3 photographs of 12 log models in a laboratory, taking 3 visual measurements of each log, the results are shown in Table 1, comparing the visual measurement with the manual measurement, and comparing the errors of the visual measurement with the errors of the manual measurement, wherein the errors of the 4 large-size logs are-8.32-14.51 mm, the rest of the errors are-4.95-0.62 mm, the standard deviation of the 3 measurements is less than 2.03 except that 1 log standard deviation is 4.18, the rest of the standard deviation is 5.29 percent at maximum from the absolute error, and the average is 2.35 percent.
Table 1 results of experiments (mm)
The described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The above is a preferred embodiment of the present invention, and all changes made according to the technical solution of the present invention belong to the protection scope of the present invention when the generated functional effects do not exceed the scope of the technical solution of the present invention.
Claims (4)
1. The log checking method based on the four-edge scale is characterized by comprising the following steps of:
s1, placing the end face side of a log stack, enabling the end face of the log stack to be framed by a four-side ruler, enabling a rectangular frame of the four-side ruler and the end face of the log stack to be on the same plane, and collecting images containing the four-side ruler and the log stack;
s2, inputting a test image, and manually dragging an arbitrary quadrangle on a program user interface to enable the quadrangle to be matched with a quadrangle scale;
s3, after any quadrilateral is pulled to fit with a quadrilateral scale, four edges of the any quadrilateral are attached to a marker post, sub-sampling is carried out on gray scale images along the four edges to form one-dimensional signals, the one-dimensional signals approximate to square wave signals due to the fact that the marker post is painted in red-white phase, noise is removed through smooth filtering, then a first derivative is obtained on the smoothed signals, a local maximum value, where the first derivative is larger than a threshold value, and a local minimum value, where the first derivative is smaller than the threshold value, are selected, and the red-white boundary point positions of the marker post are obtained through the positions of the local maximum value and the local minimum value;
s4, detecting red and white boundary points on the marker post to obtain four groups of segmentation points of the upper side, the lower side, the left side and the right side, obtaining four corner points by an extrapolation method according to the segmentation points, obtaining grid points in a frame by an interpolation method, and forming a complete grid by adding four segmentation points and the four corner points to the interpolated grid points;
s5, after grid generation, converting each grid into rectangles with the same size, calculating a homography matrix of each grid for each grid, and converting each grid into new coordinates to generate a correction image;
and S6, for each log in the corrected image, manually dragging a straight line mode on a program user interface, passing through a wood core from one point of the outline to another point of the outline, measuring the log diameter, converting the image coordinates into real world coordinates by a scale, and finally calculating the log diameter from the two-point distance.
2. The log marking method based on four-edge scale according to claim 1, wherein in step S3, the red-white boundary points of the marking post are as follows:
wherein, (x) i ，y i ) Is the coordinate of the red and white boundary point of the marker post, (x) 0 ，y 0 ) Is the coordinates of the starting end point of the edge, θ is the bevel angle of the edge, l i Is the value on the x-axis of the local maximum and local minimum.
3. The log inspection method based on the four-edge scale according to claim 1, wherein step S5 is specifically implemented as follows:
after grid generation, each grid is converted into a rectangle with the same size, for each grid, the original (x, y) coordinates are transformed into (u, v) coordinates, the homography matrix is transformed according to the formula (2), 4 corresponding points are needed for calculating the homography matrix H, and the (x) coordinates are transformed into the homography matrix H 1 ，y 1 )→(u 1 ，v 1 )、(x 2 ，y 2 )→(u 2 ，v 2 )、(x 3 ，y 3 )→(u 3 ，v 3 )、(x 4 ，y 4 )→(u 4 ，v 4 ) Wherein (u) 1 ，v 1 )～(u 4 ，v 4 ) For four-corner coordinates of a rectangle, a homography matrix H is acted on the corresponding points to obtain a formula (3) equation, and a least squares solution of H is found by using an SVD algorithm
Wherein the H homography matrix is a 3×3 matrix, H 1 ,h 2 ,…,h 8 The first 8 elements of the matrix and the last 1 element is 1, as in the (2) equation arrangement.
4. The log inspection method based on the four-edge scale according to claim 1, wherein step S6 is specifically implemented as follows:
each grid is converted to obtain a corrected image, and for each log in the corrected image, the log diameter is measured by manually dragging a straight line from one point of the profile through the wood core to another point of the profile on the program user interface, and the image coordinates (x A ，y A ) And (x) B ，y B ) Converting image coordinates into real world coordinates with a scale, x-direction scale(s) x ) For the actual length of the marker post/grid image width, the y-scale(s) y ) For the actual length of the marker post/grid image height, finally, calculating the log diameter by calculating A, B two-point distance according to the formula (4):
wherein dist (A, B) is A, B two-point distance, i.e. log diameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111454867.0A CN114166121B (en) | 2021-12-01 | 2021-12-01 | Log rule checking method based on four-edge rule |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111454867.0A CN114166121B (en) | 2021-12-01 | 2021-12-01 | Log rule checking method based on four-edge rule |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114166121A CN114166121A (en) | 2022-03-11 |
| CN114166121B true CN114166121B (en) | 2023-05-12 |
Family
ID=80482174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111454867.0A Active CN114166121B (en) | 2021-12-01 | 2021-12-01 | Log rule checking method based on four-edge rule |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114166121B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE202005002818U1 (en) * | 2005-02-22 | 2005-05-25 | Simmler, Franz | Foldable wooden frame to be used for precise positioning of picture, comprising level gauge and scale |
| CN104224217A (en) * | 2013-06-24 | 2014-12-24 | 株式会社东芝 | Method of, and apparatus for, processing medical image |
| CN109631766A (en) * | 2018-12-11 | 2019-04-16 | 南京第五十五所技术开发有限公司 | A kind of wood plank dimension measurement method based on image |
| CN113610933A (en) * | 2021-08-20 | 2021-11-05 | 苏州欧朗德智能科技有限公司 | Log stacking dynamic scale detecting system and method based on binocular region parallax |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3404648A4 (en) * | 2016-01-13 | 2019-01-23 | Ricoh Company, Ltd. | Projection system, image processing device, projection method, and program |
| CA3082445A1 (en) * | 2017-11-17 | 2019-05-23 | C 3 Limited | Object measurement system |
-
2021
- 2021-12-01 CN CN202111454867.0A patent/CN114166121B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE202005002818U1 (en) * | 2005-02-22 | 2005-05-25 | Simmler, Franz | Foldable wooden frame to be used for precise positioning of picture, comprising level gauge and scale |
| CN104224217A (en) * | 2013-06-24 | 2014-12-24 | 株式会社东芝 | Method of, and apparatus for, processing medical image |
| CN109631766A (en) * | 2018-12-11 | 2019-04-16 | 南京第五十五所技术开发有限公司 | A kind of wood plank dimension measurement method based on image |
| CN113610933A (en) * | 2021-08-20 | 2021-11-05 | 苏州欧朗德智能科技有限公司 | Log stacking dynamic scale detecting system and method based on binocular region parallax |
Non-Patent Citations (3)
| Title |
|---|
| Automatic detection of fractures and breakouts patterns in acoustic borehole image logs using fast-region convolutional neural networks;Dias, L.O等;《Journal of Petroleum Science and Engineering》;第191卷(第0期);第1-11页 * |
| 双目视觉的原木径级快速检测算法;陈广华等;《北京交通大学学报》;第42卷(第02期);第22-30页 * |
| 多激光扫描仪三维重建技术研究及其在木材检测中的应用;倪海明等;《中国博士学位论文全文数据库 农业科技辑》(第02期);第D049-46页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114166121A (en) | 2022-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111879241B (en) | Mobile phone battery size measuring method based on machine vision | |
| CN104089575B (en) | Intelligent plane detector and detection method | |
| WO2016155585A1 (en) | Device, method and apparatus for measuring size of object | |
| CN104463845B (en) | A kind of choosing method and system of flame forming plate feature registration point | |
| CN109978940B (en) | Visual measurement method for SAB safety airbag size | |
| CN108489383A (en) | A kind of measuring device and method of H-type cross dimensions | |
| CN110695520B (en) | Vision-based full-automatic galvanometer field calibration system and calibration method thereof | |
| CN109631766A (en) | A kind of wood plank dimension measurement method based on image | |
| CN114018932A (en) | Pavement disease index measuring method based on rectangular calibration object | |
| CN104931027B (en) | A kind of projection line-putting method of decorative pattern | |
| CN111161339A (en) | Distance measuring method, device, equipment and computer readable medium | |
| CN107328358B (en) | The measuring system and measurement method of aluminium cell pose | |
| CN114166121B (en) | Log rule checking method based on four-edge rule | |
| CN112815924B (en) | Quantitative evaluation method for verticality of building structure | |
| CN105423975A (en) | Calibration system and method of large-size workpiece | |
| CN112884823B (en) | Guiding rule simulation point cloud selection and calculation method for actual measurement actual quantity application | |
| CN108053485B (en) | Potato three-dimensional modeling method based on contour image | |
| CN116524002A (en) | Log diameter measurement method based on deep learning and binocular camera | |
| CN114549780B (en) | Intelligent detection method for large complex component based on point cloud data | |
| CN114092749B (en) | Automatic judgment method and device for working gear of J-shaped handle and storage medium | |
| CN102013087A (en) | Method for digitalizing cutting template | |
| JP3894420B2 (en) | 3D model generation method and apparatus | |
| CN110986891A (en) | System for accurately and rapidly measuring crown width of tree by using unmanned aerial vehicle | |
| CN114119488B (en) | Intelligent detection method for dimension quality of prefabricated laminated slab for factory | |
| CN114119488A (en) | Intelligent size and quality detection method for prefabricated laminated plate facing factory |
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 |