Method and system for measuring height of wood board higher than veneer and storage medium

Abstract

The invention discloses a method and system for measuring the height of a wood board higher than a veneer and a storage medium, and the method comprises the steps: obtaining a wood board image, and carrying out the preprocessing based on the wood board image to obtain a processed image; threshold segmentation is carried out on the basis of the processed image to obtain a target wood board area, and during threshold segmentation, adaptive threshold segmentation screening and large law threshold segmentation screening are carried out; performing equal-interval segmentation on the basis of the target wood board region to obtain a region of interest, and performing gradient threshold adaptive screening and edge extreme point calculation on the region of interest to determine wood board edge points; performing linear fitting on the edge points of the wood board to filter burr and sawdust interference to obtain effective edge points, and calculating the thickness of the wood board based on the effective edge points to judge whether the current wood board is higher than the veneer or not. According to the method, background areas can be effectively eliminated, effective areas of the planks are reserved, the edges of the planks are accurately segmented, and the influence of interference in the industrial field on higher facing measurement is effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and more specifically, to a method, system and storage medium for measuring a wooden board above a veneer. Background Art

[0002] The thickness of a board higher than the facing refers to whether the board is thicker than the front facing when viewed from the side. In the field of visual algorithms for measuring the thickness of a board higher than the facing, despite the continuous advancement of technology, existing technologies still have some problems and shortcomings. For example, AI segmentation and labeling are difficult and have poor accuracy, and traditional algorithms are not robust to complex environments. Especially in the industrial manufacturing field, the lighting effects are inconsistent, the craftsmanship of the boards is uneven, and the patterns are relatively diverse and complex. Conventional visual measurements of boards higher than the facing are not universal.

[0003] For example, when a wooden board moves on a conveyor belt, the lighting effects on different machines will be inconsistent, and it is easy for the conveyor belt part to be photographed. Conventional visual measurement algorithms are easily affected by the conveyor belt, and thus the edge of the conveyor belt is considered to be the edge of the wooden board. For example, the cutting process of wooden boards is uneven, and it is easy for edge banding residues to appear at the head and tail of the wooden board. It is difficult for general algorithms to filter out the interference of the residues, which will affect the positioning of the straight line of the wooden board edge. In addition, wooden boards have various patterns, and the edge light and dark imaging of each local area is inconsistent. Therefore, it is easy to produce deviations when setting a fixed threshold to find the edge. At present, the problem of high-robust measurement of wooden boards above the finish in the industrial field needs to be solved urgently. Summary of the invention

[0004] The purpose of the present invention is to provide a method, system and storage medium for measuring the height of a wooden board above a finish, which can effectively eliminate the background area and retain the effective area of ​​the wooden board to accurately segment the edge of the wooden board, and effectively solve the impact of interference in the industrial field on the measurement above the finish.

[0005] A first aspect of the present invention provides a method for measuring a wood board above a facing, comprising the following steps: Acquire a wooden board image, and perform preprocessing based on the wooden board image to obtain a processed image; Performing threshold segmentation based on the processed image to obtain a target wooden board area, wherein the threshold segmentation includes performing adaptive threshold segmentation screening and large law threshold segmentation screening; Based on the target wooden board area, an area of ​​interest is obtained by performing equal-interval segmentation, and the area of ​​interest is subjected to gradient threshold adaptive screening and edge extreme point calculation to determine the edge point of the wooden board; Linear fitting is performed on the edge points of the wooden board to filter out burrs and wood chips to obtain effective edge points, and the thickness of the wooden board is calculated based on the effective edge points to determine whether the current wooden board is higher than the veneer.

[0006] In this solution, the step of obtaining the wooden board image and performing preprocessing based on the wooden board image to obtain a processed image specifically includes: The wooden board image is normalized, grayscale scaled, and contrast adjusted to obtain an adjusted image; Gaussian filtering and noise removal are performed on the adjusted image to obtain the processed image.

[0007] In this solution, the target wooden board area is obtained by performing threshold segmentation based on the processed image, specifically including: Adaptive threshold segmentation and screening are performed based on the processed image to obtain a candidate wooden board area, wherein the processed image is traversed with a sliding window of a fixed size, and a segmentation threshold is dynamically calculated using a local pixel mean to obtain a binary wooden board image, and a closing operation is performed on the binary wooden board image to connect different areas of the wooden board; different areas of the connected domain are screened, and connected domains with an area larger than a preset area are collected to obtain the candidate wooden board area; Based on the processed image, a large-law threshold segmentation is performed to obtain a wooden board area to be selected, wherein the processed image is subjected to a large-law threshold segmentation to obtain a wooden board binary image, the wooden board binary image is subjected to a closing operation and an opening operation to fill and filter the gap area, and the largest area is screened to obtain the wooden board area to be selected; The target wooden board area is obtained by comparing and screening the wooden board candidate area and the wooden board candidate area, wherein when the width of the wooden board candidate area is less than a preset width threshold, the target wooden board area is obtained based on the wooden board candidate area; otherwise, the target wooden board area is obtained based on the intersection of the wooden board candidate area and the wooden board candidate area.

[0008] In this solution, the region of interest is obtained by performing equal-interval segmentation based on the target wooden board region, specifically including: Adjusting the width of the target wooden board area to eliminate invalid areas, and combining the processed image to intercept and obtain a valid target area; The effective target area is segmented cyclically using a fixed height to obtain the region of interest.

[0009] In this solution, the step of performing adaptive gradient threshold screening and edge extreme point calculation on the region of interest to determine the edge points of the board specifically includes: The left and right gradient thresholds are obtained based on the adaptive screening of the gradient threshold; The edge extreme points are calculated based on the projected edge points of the region of interest; The edge extreme points are filtered using the left and right gradient thresholds to obtain the edge points of the wooden board, wherein the edge points of the wooden board include left and right edge points.

[0010] In this solution, the linear fitting of the edge points of the wooden board to filter out the interference of burrs and wood chips to obtain effective edge points, and the thickness of the wooden board is calculated based on the effective edge points to determine whether the current wooden board is higher than the veneer, specifically includes: Based on the edge extreme points, a random sampling consistency algorithm is used to fit a straight line to filter out burr and sawdust interference to obtain a valid point set; The thickness of the wooden board is calculated according to the valid edge point pairs in the valid point set, and whether the current wooden board is higher than the finish is determined based on the thickness of the wooden board and a preset thickness threshold, wherein if the thickness of the wooden board is greater than the thickness threshold, it indicates that the wooden board is higher than the finish, otherwise it indicates that the wooden board is lower than the finish.

[0011] The second aspect of the present invention further provides a system for measuring a wooden board higher than a veneer, comprising a memory and a processor, wherein the memory comprises a program for measuring a wooden board higher than a veneer, and when the program for measuring a wooden board higher than a veneer is executed by the processor, the following steps are implemented: Acquire a wooden board image, and perform preprocessing based on the wooden board image to obtain a processed image; Performing threshold segmentation based on the processed image to obtain a target wooden board area, wherein the threshold segmentation includes performing adaptive threshold segmentation screening and large law threshold segmentation screening; Based on the target wooden board area, an area of ​​interest is obtained by performing equal-interval segmentation, and the area of ​​interest is subjected to gradient threshold adaptive screening and edge extreme point calculation to determine the edge point of the wooden board; Linear fitting is performed on the edge points of the wooden board to filter out burrs and wood chips to obtain effective edge points, and the thickness of the wooden board is calculated based on the effective edge points to determine whether the current wooden board is higher than the veneer.

[0012] In this solution, the step of obtaining the wooden board image and performing preprocessing based on the wooden board image to obtain a processed image specifically includes: The wooden board image is normalized, grayscale scaled, and contrast adjusted to obtain an adjusted image; Gaussian filtering and noise removal are performed on the adjusted image to obtain the processed image.

[0013] In this solution, the target wooden board area is obtained by performing threshold segmentation based on the processed image, specifically including: Adaptive threshold segmentation and screening are performed based on the processed image to obtain a candidate wooden board area, wherein the processed image is traversed with a sliding window of a fixed size, and a segmentation threshold is dynamically calculated using a local pixel mean to obtain a binary wooden board image, and a closing operation is performed on the binary wooden board image to connect different areas of the wooden board; different areas of the connected domain are screened, and connected domains with an area larger than a preset area are collected to obtain the candidate wooden board area; Based on the processed image, a large-law threshold segmentation is performed to obtain a wooden board area to be selected, wherein the processed image is subjected to a large-law threshold segmentation to obtain a wooden board binary image, the wooden board binary image is subjected to a closing operation and an opening operation to fill and filter the gap area, and the largest area is screened to obtain the wooden board area to be selected; The target wooden board area is obtained by comparing and screening the wooden board candidate area and the wooden board candidate area, wherein when the width of the wooden board candidate area is less than a preset width threshold, the target wooden board area is obtained based on the wooden board candidate area; otherwise, the target wooden board area is obtained based on the intersection of the wooden board candidate area and the wooden board candidate area.

[0014] In this solution, the region of interest is obtained by performing equal-interval segmentation based on the target wooden board region, specifically including: Adjusting the width of the target wooden board area to eliminate invalid areas, and combining the processed image to intercept and obtain a valid target area; The effective target area is segmented cyclically using a fixed height to obtain the region of interest.

[0015] In this solution, the step of performing adaptive gradient threshold screening and edge extreme point calculation on the region of interest to determine the edge points of the board specifically includes: The left and right gradient thresholds are obtained based on the adaptive screening of the gradient threshold; The edge extreme points are calculated based on the projected edge points of the region of interest; The edge extreme points are filtered using the left and right gradient thresholds to obtain the edge points of the wooden board, wherein the edge points of the wooden board include left and right edge points.

[0016] In this solution, the linear fitting of the edge points of the wooden board to filter out the interference of burrs and wood chips to obtain effective edge points, and the thickness of the wooden board is calculated based on the effective edge points to determine whether the current wooden board is higher than the veneer, specifically includes: Based on the edge extreme points, a random sampling consistency algorithm is used to fit a straight line to filter out burr and sawdust interference to obtain a valid point set; The thickness of the wooden board is calculated according to the valid edge point pairs in the valid point set, and whether the current wooden board is higher than the finish is determined based on the thickness of the wooden board and a preset thickness threshold, wherein if the thickness of the wooden board is greater than the thickness threshold, it indicates that the wooden board is higher than the finish, otherwise it indicates that the wooden board is lower than the finish.

[0017] A third aspect of the present invention provides a computer-readable storage medium, which includes a program for a method for measuring a wooden board above a finish for a machine. When the program for measuring a wooden board above a finish is executed by a processor, the steps of a method for measuring a wooden board above a finish as described in any one of the above items are implemented.

[0018] The present invention discloses a method, system and storage medium for measuring the height of a wooden board above a finish, which can effectively eliminate the background area and retain the effective area of ​​the wooden board so as to accurately segment the edge of the wooden board, and effectively solve the influence of interference in the industrial field on the measurement of the height above the finish. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flow chart showing a method for measuring a wood board higher than a facing surface according to the present invention is shown; Figure 2 A comparison diagram of the pre-processing of a method for measuring a wood board higher than a veneer surface according to the present invention is shown; Figure 3 The binary image after local adaptive segmentation of a method for measuring a wood board higher than a facing surface according to the present invention is shown; Figure 4 A schematic diagram of a wooden board candidate area in a method for measuring a wooden board higher than a facing surface according to the present invention is shown; Figure 5 A schematic diagram of a binary image after large-scale threshold segmentation according to a method for measuring a wood board higher than a veneer surface according to the present invention is shown; Figure 6 A schematic diagram of a wooden board candidate area in a method for measuring a wooden board higher than a facing surface according to the present invention is shown; Figure 7 A schematic diagram of a target wood board area of ​​a method for measuring a wood board higher than a facing surface according to the present invention is shown; Figure 8 The invention shows a method for measuring a wood board higher than a facing, which relaxes the effective wood board area; Fig. 9 A schematic diagram showing the region of interest of a method for measuring a wood board above a veneer surface according to the present invention; Fig.10 A schematic diagram showing the method for measuring a wood board higher than a facing surface after adaptive threshold segmentation according to the present invention is shown; Fig.11 A schematic diagram showing the segmentation of the region of interest in a method for measuring a wood board higher than a facing surface according to the present invention; Fig.12 A schematic diagram of residual tape interference in a method for measuring a wood board higher than a facing surface according to the present invention is shown; Fig.13 A schematic diagram of burr interference in a method for measuring a wooden board higher than a veneer surface according to the present invention is shown; Fig.14 A diagram showing the burr filtering effect of a method for measuring a wooden board higher than a facing surface according to the present invention is shown; Fig.15 A block diagram of a system for measuring a wood board above a facing surface according to the present invention is shown. DETAILED DESCRIPTION

[0020] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0022] Figure 1 A flow chart of a method for measuring a wooden board above a facing surface according to the present application is shown.

[0023] like Figure 1 As shown, the present application discloses a method for measuring the height of a wooden board above a facing, comprising the following steps: S102, acquiring a wooden board image, and performing preprocessing based on the wooden board image to obtain a processed image; S104, performing threshold segmentation based on the processed image to obtain a target wooden board area, wherein the threshold segmentation includes performing adaptive threshold segmentation screening and large law threshold segmentation screening; S106, performing equal-interval segmentation based on the target wooden board area to obtain an area of ​​interest, and performing gradient threshold adaptive screening and edge extreme point calculation on the area of ​​interest to determine the edge points of the wooden board; S108, performing straight line fitting on the edge points of the wooden board to filter out the interference of burrs and wood chips to obtain effective edge points, and calculating the thickness of the wooden board based on the effective edge points to determine whether the current wooden board is higher than the veneer.

[0024] It should be noted that, in this embodiment, a wooden board segmentation method is provided to address the visual interference of the conveyor belt introduced due to inconsistent lighting effects. The method can effectively eliminate the background area and retain only the effective area of ​​the wooden board, wherein the effective area of ​​the wooden board corresponds to the target wooden board area. Specifically, it is necessary to first obtain the wooden board image and pre-process it to obtain a processed image, and then perform threshold segmentation on the processed image to obtain the target wooden board area. Specifically, in view of the various patterns of wooden boards and the inability to stably extract the edges of wooden boards, adaptive threshold segmentation screening and large-law threshold segmentation screening are applied to accurately segment the foreground and background of the wooden board edge, calculate the gradient adaptive threshold of the area based on the foreground and background, and then screen the wooden board edge points to obtain effective edge points for the interference of "residual belts" and "no wooden board areas" on the wooden board, which can effectively filter out the influence. Finally, the thickness of the wooden board is calculated based on the effective edge points to determine whether the current wooden board is higher than the veneer. Specifically, the thickness of the wooden board is calculated based on the left and right edge points and compared with the preset thickness threshold to determine whether the wooden board is higher than the veneer.

[0025] According to an embodiment of the present invention, the acquiring of the wooden board image and the preprocessing of the wooden board image to obtain the processed image specifically include: The wooden board image is normalized, grayscale scaled, and contrast adjusted to obtain an adjusted image; Gaussian filtering and noise removal are performed on the adjusted image to obtain the processed image.

[0026] It should be noted that, in this embodiment, Figure 2 As shown, it is shown as a pre-processing comparison diagram, wherein the wooden board image is normalized, grayscale value is scaled and contrast is adjusted to obtain an adjusted image. Specifically, the image is normalized, the grayscale value range is scaled to the "0-255" area, the contrast is enhanced, and the darkening of the wooden board area caused by poor lighting is prevented. The adjusted image is then Gaussian filtered and noise is removed to obtain the processed image. Specifically, the image is Gaussian filtered. Since the noise will be amplified after the image is normalized, it is necessary to remove the influence of small Gaussian noise. Figure 2 The left picture is the wooden board image. Figure 2 The right image is the processed image.

[0027] According to an embodiment of the present invention, performing threshold segmentation based on the processed image to obtain the target wooden board area specifically includes: Adaptive threshold segmentation and screening are performed based on the processed image to obtain a candidate wooden board area, wherein the processed image is traversed with a sliding window of a fixed size, and a segmentation threshold is dynamically calculated using a local pixel mean to obtain a binary wooden board image, and a closing operation is performed on the binary wooden board image to connect different areas of the wooden board; different areas of the connected domain are screened, and connected domains with an area larger than a preset area are collected to obtain the candidate wooden board area; Based on the processed image, a large-law threshold segmentation is performed to obtain a wooden board area to be selected, wherein the processed image is subjected to a large-law threshold segmentation to obtain a wooden board binary image, the wooden board binary image is subjected to a closing operation and an opening operation to fill and filter the gap area, and the largest area is screened to obtain the wooden board area to be selected; The target wooden board area is obtained by comparing and screening the wooden board candidate area and the wooden board candidate area, wherein when the width of the wooden board candidate area is less than a preset width threshold, the target wooden board area is obtained based on the wooden board candidate area; otherwise, the target wooden board area is obtained based on the intersection of the wooden board candidate area and the wooden board candidate area.

[0028] It should be noted that, in this embodiment, adaptive threshold segmentation and screening are performed based on the processed image to obtain the candidate wooden board area, wherein the processed image is traversed with a sliding window of a fixed size, and the segmentation threshold is dynamically calculated using the local pixel mean to obtain a binary wooden board image, wherein, Figure 3 As shown, it is a binary image after local adaptive segmentation. A closing operation is performed on the binary image of the wooden board to connect different areas of the wooden board as much as possible. Finally, different areas of the connected domain are screened, and connected domains with an area larger than a preset area are collected to obtain the wooden board candidate area connected1, where Figure 4 As shown, a schematic diagram of the candidate area for the wooden board is shown.

[0029] Further, based on the processed image, the large law threshold segmentation is performed to obtain the selected wooden board area, wherein the large law threshold segmentation is performed on the processed image to obtain the wooden board binary image, and the brighter area binary image is specifically selected, such as Figure 5 As shown, it is a schematic diagram of a binary image after the large law threshold segmentation, and then the binary image of the wooden board is closed and opened to fill and filter the gap area, and the largest area is selected to obtain the wooden board candidate area connected2, where, Figure 6 As shown, a schematic diagram of the candidate area for the wooden board is shown.

[0030] Furthermore, the target wooden board area is obtained by comparison and screening based on the wooden board candidate area and the wooden board candidate area. The purpose of this step is to obtain the area of ​​the wooden board in the vertical direction, reduce the scope of the entire image, filter out the influence of the conveyor belt, and facilitate the subsequent extraction of wooden board edge points. The screening rules are as follows: When the width of the wooden board candidate area connected2 is less than the preset width threshold, the target wooden board area is obtained based on the wooden board candidate area connected1 to eliminate the conveyor belt area that is mistakenly identified as too bright by the Otsu method; otherwise, the target wooden board area is obtained based on the intersection of the wooden board candidate area connected1 and the wooden board candidate area connected2 to eliminate the conveyor belt background area, wherein, as Figure 7 As shown, a schematic diagram of the target wooden board area is shown.

[0031] According to an embodiment of the present invention, the step of performing equal-interval segmentation based on the target wooden board area to obtain the region of interest specifically includes: Adjusting the width of the target wooden board area to eliminate invalid areas, and combining the processed image to intercept and obtain a valid target area; The effective target area is segmented cyclically using a fixed height to obtain the region of interest.

[0032] It should be noted that, in this embodiment, the target wooden board area is close to the edge of the wooden board, so a small range is relaxed in the vertical direction to remove the invalid area, and the effective wooden board area can be obtained by combining the processed image after preprocessing, reducing the interference of the conveyor belt and facilitating the subsequent wooden board edge extraction. Figure 8 As shown, the effective plank area is shown as relaxed.

[0033] Furthermore, in order to accurately extract the edge points of the wooden board, the wooden board is segmented by cyclic traversal at a fixed height to obtain the local ROI area (Region Of Interest) of the wooden board. The purpose is to more effectively obtain the edge points of the wooden board and avoid the influence of different lighting and textures. Fig. 9 As shown, a schematic diagram of the region of interest is shown.

[0034] According to an embodiment of the present invention, the step of performing adaptive gradient threshold screening and edge extreme point calculation on the region of interest to determine the edge points of the wooden board specifically includes: The left and right gradient thresholds are obtained based on the adaptive screening of the gradient threshold; The edge extreme points are calculated based on the projected edge points of the region of interest; The edge extreme points are filtered using the left and right gradient thresholds to obtain the edge points of the wooden board, wherein the edge points of the wooden board include left and right edge points.

[0035] It should be noted that, in this embodiment, the steps of obtaining the left and right gradient thresholds based on the gradient threshold adaptive screening include the following steps: (1) Adaptive threshold segmentation to obtain edge change areas, where Fig.10 As shown, it is a schematic diagram after adaptive threshold segmentation; (2) Locate the outermost edge area of ​​the board based on the binary area, including the leftmost and rightmost boundaries; (3) According to the left and right boundaries, the small ROI division can be performed to segment the background area and the board area near the edge of the board, that is, the background area on the left side of the board, the foreground area on the left side of the board, the foreground area on the right side of the board, and the background area on the right side of the board. The schematic diagram after segmentation is shown in the figure below. Fig.11 As shown; (4) The contrast can be calculated based on the pixel values ​​of the foreground and background areas, and the optimal gradient change thresholds TL and TR on the left and right sides can be obtained respectively.

[0036] Furthermore, the edge extreme points are calculated based on the projected edge points of the region of interest, specifically including: projecting the wooden board ROI in the vertical direction as a one-dimensional vector to facilitate the positioning of the outermost edge points of the wooden board ROI, and then calculating the first-order derivative to obtain the extreme points of the edge change and determine the direction of the extreme change, the left edge direction of the wooden board is from dark to light, the right edge direction of the wooden board is from light to dark, and non-maximum suppression, and eliminating invalid edge points to obtain the edge extreme points.

[0037] Furthermore, in this embodiment, the edge extreme value points are filtered using the obtained left and right gradient thresholds to obtain the best edge point position of the ROI. By performing the operation and calculation for each ROI in this way, a series of left and right edge points can be collected. In an actual factory environment, the cutting process of wooden boards is uneven, which may cause residual tapes at the head and tail of the wooden boards. The residual tape area may be mistakenly identified as the edge area of ​​the wooden board. In addition, in the "no wooden board" area, it is interfered by the background conveyor belt, which may easily cause various misjudgments, such as Fig.12 As shown, it is a schematic diagram of residual band interference, so the "edge point pair" idea is added for filtering.

[0038] (1) For the left edge point of the wooden board, if the grayscale mean value of a certain range on the right side is less than the threshold, the edge point within the ROI is judged to be invalid.

[0039] (2) For the right edge point of the wooden board, if the grayscale mean value of a certain range on the left side is less than the threshold, the edge point within the ROI is judged to be invalid.

[0040] (3) If the distance between the left and right edge points exceeds or is less than a certain range, the edge points within the ROI are judged to be invalid. Finally, after the above steps, the interference of residual tape and non-wooden area can be filtered out.

[0041] According to an embodiment of the present invention, performing straight line fitting on the edge points of the wooden board to filter out burr and sawdust interference to obtain effective edge points, and calculating the thickness of the wooden board based on the effective edge points to determine whether the current wooden board is higher than the veneer, specifically includes: Based on the edge extreme points, a random sampling consistency algorithm is used to fit a straight line to filter out burr and sawdust interference to obtain a valid point set; The thickness of the wooden board is calculated according to the valid edge point pairs in the valid point set, and whether the current wooden board is higher than the finish is determined based on the thickness of the wooden board and a preset thickness threshold, wherein if the thickness of the wooden board is greater than the thickness threshold, it indicates that the wooden board is higher than the finish, otherwise it indicates that the wooden board is lower than the finish.

[0042] It should be noted that, in this embodiment, Fig.13 As shown, it is a schematic diagram of burr interference. When burrs and sawdust appear on the edge of the wooden board, the edge points within the ROI must appear in the burr and sawdust area. Therefore, it is easy to determine that the width of the wooden board in this area is greater than the standard wooden board thickness, that is, higher than the finish. Therefore, in order to eliminate the misjudgment caused by such abrupt burrs and sawdust, a straight line fitting is added to filter the extreme points.

[0043] Specifically, a random sampling consistency algorithm is used to fit a straight line based on the edge extreme points to filter out the interference of burrs and wood chips to obtain a valid point set, wherein a random sampling consistency algorithm is used to fit a straight line, and when the number of fitted straight line point sets exceeds "60%" of the total number of point sets, the straight line is considered valid, and the straight line angle range is fixed to be 75°-105° in the vertical direction, and the distance between the fixed extreme edge point and the fitted straight line is within twenty pixels. After the above operation, the abrupt burrs and wood chip interference can be completely filtered out, and the slowly changing area above the facing of the wooden board edge can be retained, as shown in Figure 13. The local image of the burr interference after rotating 90° counterclockwise and enlarging is as shown in Figure 13 Fig.14 As shown, Fig.14 The image shows the burr filtering effect. The pink and orange lines are fitted edge lines, and the blue points on the fitted lines are the valid point sets of the actual wooden board edges. The actual maximum and minimum thicknesses of the wooden board are found based on the valid edge pair sets.

[0044] Furthermore, the thickness of the wooden board is calculated based on the valid edge point pairs in the valid point set, and whether the current wooden board is higher than the finish is determined based on the thickness of the wooden board combined with a preset thickness threshold, wherein if the thickness of the wooden board is greater than the thickness threshold, it indicates that the wooden board is higher than the finish, otherwise it indicates that the wooden board is lower than the finish.

[0045] Fig.15 A block diagram of a system for measuring a wood board above a facing surface according to the present invention is shown.

[0046] like Fig.15 As shown, the present invention discloses a system for measuring a wooden board higher than a veneer, comprising a memory and a processor, wherein the memory comprises a program for measuring a wooden board higher than a veneer, and when the program for measuring a wooden board higher than a veneer is executed by the processor, the following steps are implemented: Acquire a wooden board image, and perform preprocessing based on the wooden board image to obtain a processed image; Performing threshold segmentation based on the processed image to obtain a target wooden board area, wherein the threshold segmentation includes performing adaptive threshold segmentation screening and large law threshold segmentation screening; Based on the target wooden board area, an area of ​​interest is obtained by performing equal-interval segmentation, and the area of ​​interest is subjected to gradient threshold adaptive screening and edge extreme point calculation to determine the edge point of the wooden board; Linear fitting is performed on the edge points of the wooden board to filter out burrs and wood chips to obtain effective edge points, and the thickness of the wooden board is calculated based on the effective edge points to determine whether the current wooden board is higher than the veneer.

[0047] It should be noted that, in this embodiment, a wooden board segmentation method is provided to address the visual interference of the conveyor belt introduced due to inconsistent lighting effects. The method can effectively eliminate the background area and retain only the effective area of ​​the wooden board, wherein the effective area of ​​the wooden board corresponds to the target wooden board area. Specifically, it is necessary to first obtain the wooden board image and pre-process it to obtain a processed image, and then perform threshold segmentation on the processed image to obtain the target wooden board area. Specifically, in view of the various patterns of wooden boards and the inability to stably extract the edges of wooden boards, adaptive threshold segmentation screening and large-law threshold segmentation screening are applied to accurately segment the foreground and background of the wooden board edge, calculate the gradient adaptive threshold of the area based on the foreground and background, and then screen the wooden board edge points to obtain effective edge points for the interference of "residual belts" and "no wooden board areas" on the wooden board, which can effectively filter out the influence. Finally, the thickness of the wooden board is calculated based on the effective edge points to determine whether the current wooden board is higher than the veneer. Specifically, the thickness of the wooden board is calculated based on the left and right edge points and compared with the preset thickness threshold to determine whether the wooden board is higher than the veneer.

[0048] According to an embodiment of the present invention, the acquiring of the wooden board image and the preprocessing of the wooden board image to obtain the processed image specifically include: The wooden board image is normalized, grayscale scaled, and contrast adjusted to obtain an adjusted image; Gaussian filtering and noise removal are performed on the adjusted image to obtain the processed image.

[0049] It should be noted that, in this embodiment, Figure 2 As shown, it is shown as a pre-processing comparison diagram, wherein the wooden board image is normalized, grayscale value is scaled and contrast is adjusted to obtain an adjusted image. Specifically, the image is normalized, the grayscale value range is scaled to the "0-255" area, the contrast is enhanced, and the darkening of the wooden board area caused by poor lighting is prevented. The adjusted image is then Gaussian filtered and noise is removed to obtain the processed image. Specifically, the image is Gaussian filtered. Since the noise will be amplified after the image is normalized, it is necessary to remove the influence of small Gaussian noise. Figure 2 The left picture is the wooden board image. Figure 2 The right image is the processed image.

[0050] According to an embodiment of the present invention, performing threshold segmentation based on the processed image to obtain the target wooden board area specifically includes: Adaptive threshold segmentation and screening are performed based on the processed image to obtain a candidate wooden board area, wherein the processed image is traversed with a sliding window of a fixed size, and a segmentation threshold is dynamically calculated using a local pixel mean to obtain a binary wooden board image, and a closing operation is performed on the binary wooden board image to connect different areas of the wooden board; different areas of the connected domain are screened, and connected domains with an area larger than a preset area are collected to obtain the candidate wooden board area; Based on the processed image, a large-law threshold segmentation is performed to obtain a wooden board area to be selected, wherein the processed image is subjected to a large-law threshold segmentation to obtain a wooden board binary image, the wooden board binary image is subjected to a closing operation and an opening operation to fill and filter the gap area, and the largest area is screened to obtain the wooden board area to be selected; The target wooden board area is obtained by comparing and screening the wooden board candidate area and the wooden board candidate area, wherein when the width of the wooden board candidate area is less than a preset width threshold, the target wooden board area is obtained based on the wooden board candidate area; otherwise, the target wooden board area is obtained based on the intersection of the wooden board candidate area and the wooden board candidate area.

[0051] It should be noted that, in this embodiment, adaptive threshold segmentation and screening are performed based on the processed image to obtain the candidate wooden board area, wherein the processed image is traversed with a sliding window of a fixed size, and the segmentation threshold is dynamically calculated using the local pixel mean to obtain a binary wooden board image, wherein, Figure 3 As shown, it is a binary image after local adaptive segmentation. A closing operation is performed on the binary image of the wooden board to connect different areas of the wooden board as much as possible. Finally, different areas of the connected domain are screened, and connected domains with an area larger than a preset area are collected to obtain the wooden board candidate area connected1, where Figure 4As shown, a schematic diagram of the candidate area for the wooden board is shown.

[0052] Further, based on the processed image, the large law threshold segmentation is performed to obtain the selected wooden board area, wherein the large law threshold segmentation is performed on the processed image to obtain the wooden board binary image, and the brighter area binary image is specifically selected, such as Figure 5 As shown, it is a schematic diagram of a binary image after the large law threshold segmentation, and then the binary image of the wooden board is closed and opened to fill and filter the gap area, and the largest area is selected to obtain the wooden board candidate area connected2, where, Figure 6 As shown, a schematic diagram of the candidate area for the wooden board is shown.

[0053] Furthermore, the target wooden board area is obtained by comparison and screening based on the wooden board candidate area and the wooden board candidate area. The purpose of this step is to obtain the area of ​​the wooden board in the vertical direction, reduce the scope of the entire image, filter out the influence of the conveyor belt, and facilitate the subsequent extraction of wooden board edge points. The screening rules are as follows: When the width of the wooden board candidate area connected2 is less than the preset width threshold, the target wooden board area is obtained based on the wooden board candidate area connected1 to eliminate the conveyor belt area that is mistakenly identified as too bright by the Otsu method; otherwise, the target wooden board area is obtained based on the intersection of the wooden board candidate area connected1 and the wooden board candidate area connected2 to eliminate the conveyor belt background area, wherein, as Figure 7 As shown, a schematic diagram of the target wooden board area is shown.

[0054] According to an embodiment of the present invention, the step of performing equal-interval segmentation based on the target wooden board area to obtain the region of interest specifically includes: Adjusting the width of the target wooden board area to eliminate invalid areas, and combining the processed image to intercept and obtain a valid target area; The effective target area is segmented cyclically using a fixed height to obtain the region of interest.

[0055] It should be noted that, in this embodiment, the target wooden board area is close to the edge of the wooden board, so a small range is relaxed in the vertical direction to remove the invalid area, and the effective wooden board area can be obtained by combining the processed image after preprocessing, reducing the interference of the conveyor belt and facilitating the subsequent wooden board edge extraction. Figure 8 As shown, the effective plank area is shown as relaxed.

[0056] Furthermore, in order to accurately extract the edge points of the wooden board, the wooden board is segmented by cyclic traversal at a fixed height to obtain the local ROI area (Region Of Interest) of the wooden board. The purpose is to more effectively obtain the edge points of the wooden board and avoid the influence of different lighting and textures. Fig. 9 As shown, a schematic diagram of the region of interest is shown.

[0057] According to an embodiment of the present invention, the step of performing adaptive gradient threshold screening and edge extreme point calculation on the region of interest to determine the edge points of the wooden board specifically includes: The left and right gradient thresholds are obtained based on the adaptive screening of the gradient threshold; The edge extreme points are calculated based on the projected edge points of the region of interest; The edge extreme points are filtered using the left and right gradient thresholds to obtain the edge points of the wooden board, wherein the edge points of the wooden board include left and right edge points.

[0058] It should be noted that, in this embodiment, the steps of obtaining the left and right gradient thresholds based on the gradient threshold adaptive screening include the following steps: (1) Adaptive threshold segmentation to obtain edge change areas, where Fig.10 As shown, it is a schematic diagram after adaptive threshold segmentation; (2) Locate the outermost edge area of ​​the board based on the binary area, including the leftmost and rightmost boundaries; (3) According to the left and right boundaries, the small ROI division can be performed to segment the background area and the board area near the edge of the board, that is, the background area on the left side of the board, the foreground area on the left side of the board, the foreground area on the right side of the board, and the background area on the right side of the board. The schematic diagram after segmentation is shown in the figure below. Fig.11 As shown; (4) The contrast can be calculated based on the pixel values ​​of the foreground and background areas, and the optimal gradient change thresholds TL and TR on the left and right sides can be obtained respectively.

[0059] Furthermore, the edge extreme points are calculated based on the projected edge points of the region of interest, specifically including: projecting the wooden board ROI in the vertical direction as a one-dimensional vector to facilitate the positioning of the outermost edge points of the wooden board ROI, and then calculating the first-order derivative to obtain the extreme points of the edge change and determine the direction of the extreme change, the left edge direction of the wooden board is from dark to light, the right edge direction of the wooden board is from light to dark, and non-maximum suppression, and eliminating invalid edge points to obtain the edge extreme points.

[0060] Furthermore, in this embodiment, the edge extreme value points are filtered using the obtained left and right gradient thresholds to obtain the best edge point position of the ROI. By performing the operation and calculation for each ROI in this way, a series of left and right edge points can be collected. In an actual factory environment, the cutting process of wooden boards is uneven, which may cause residual tapes at the head and tail of the wooden boards. The residual tape area may be mistakenly identified as the edge area of ​​the wooden board. In addition, in the "no wooden board" area, it is interfered by the background conveyor belt, which may easily cause various misjudgments, such as Fig.12 As shown, it is a schematic diagram of residual band interference, so the "edge point pair" idea is added for filtering.

[0061] (1) For the left edge point of the wooden board, if the grayscale mean value of a certain range on the right side is less than the threshold, the edge point within the ROI is judged to be invalid.

[0062] (2) For the right edge point of the wooden board, if the grayscale mean value of a certain range on the left side is less than the threshold, the edge point within the ROI is judged to be invalid.

[0063] (3) If the distance between the left and right edge points exceeds or is less than a certain range, the edge points within the ROI are judged to be invalid. Finally, after the above steps, the interference of residual tape and non-wooden area can be filtered out.

[0064] According to an embodiment of the present invention, performing straight line fitting on the edge points of the wooden board to filter out burr and sawdust interference to obtain effective edge points, and calculating the thickness of the wooden board based on the effective edge points to determine whether the current wooden board is higher than the veneer, specifically includes: Based on the edge extreme points, a random sampling consistency algorithm is used to fit a straight line to filter out burr and sawdust interference to obtain a valid point set; The thickness of the wooden board is calculated according to the valid edge point pairs in the valid point set, and whether the current wooden board is higher than the finish is determined based on the thickness of the wooden board and a preset thickness threshold, wherein if the thickness of the wooden board is greater than the thickness threshold, it indicates that the wooden board is higher than the finish, otherwise it indicates that the wooden board is lower than the finish.

[0065] It should be noted that, in this embodiment, Fig.13 As shown, it is a schematic diagram of burr interference. When burrs and sawdust appear on the edge of the wooden board, the edge points within the ROI must appear in the burr and sawdust area. Therefore, it is easy to determine that the width of the wooden board in this area is greater than the standard wooden board thickness, that is, higher than the finish. Therefore, in order to eliminate the misjudgment caused by such abrupt burrs and sawdust, a straight line fitting is added to filter the extreme points.

[0066] Specifically, a random sampling consistency algorithm is used to fit a straight line based on the edge extreme points to filter out the interference of burrs and wood chips to obtain a valid point set, wherein a random sampling consistency algorithm is used to fit a straight line, and when the number of fitted straight line point sets exceeds "60%" of the total number of point sets, the straight line is considered valid, and the straight line angle range is fixed to be 75°-105° in the vertical direction, and the distance between the fixed extreme edge point and the fitted straight line is within twenty pixels. After the above operation, the abrupt burrs and wood chip interference can be completely filtered out, and the slowly changing area above the facing of the wooden board edge can be retained, as shown in Figure 13. The local image of the burr interference after rotating 90° counterclockwise and enlarging is as shown in Figure 13 Fig.14 As shown, Fig.14 The image shows the burr filtering effect. The pink and orange lines are fitted edge lines, and the blue points on the fitted lines are the valid point sets of the actual wooden board edges. The actual maximum and minimum thicknesses of the wooden board are found based on the valid edge pair sets.

[0067] Furthermore, the thickness of the wooden board is calculated based on the valid edge point pairs in the valid point set, and whether the current wooden board is higher than the finish is determined based on the thickness of the wooden board combined with a preset thickness threshold, wherein if the thickness of the wooden board is greater than the thickness threshold, it indicates that the wooden board is higher than the finish, otherwise it indicates that the wooden board is lower than the finish.

[0068] A third aspect of the present invention provides a computer-readable storage medium, which includes a program for a method for measuring a wooden board above a finish. When the program for measuring a wooden board above a finish is executed by a processor, the steps of a method for measuring a wooden board above a finish as described in any one of the above items are implemented.

[0069] The present invention discloses a method, system and storage medium for measuring the height of a wooden board above a finish, which can effectively eliminate the background area and retain the effective area of ​​the wooden board so as to accurately segment the edge of the wooden board, and effectively solve the influence of interference in the industrial field on the measurement of the height above the finish.

[0070] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0071] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0072] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0073] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0074] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A method for measuring the height of a wooden board above a facing, characterized in that: The following steps are involved: Acquire a wooden board image, and perform preprocessing based on the wooden board image to obtain a processed image; Performing threshold segmentation based on the processed image to obtain a target wooden board area, wherein the threshold segmentation includes performing adaptive threshold segmentation screening and large law threshold segmentation screening; Based on the target wooden board area, an area of ​​interest is obtained by performing equal-interval segmentation, and the area of ​​interest is subjected to gradient threshold adaptive screening and edge extreme point calculation to determine the edge point of the wooden board; Linear fitting is performed on the edge points of the wooden board to obtain effective edge points, and the thickness of the wooden board is calculated based on the effective edge points to determine whether the current wooden board is higher than the veneer.

2. A method for measuring the height of a wooden board above a facing according to claim 1, characterized in that: The obtaining of the wooden board image and performing preprocessing based on the wooden board image to obtain a processed image specifically includes: The wooden board image is normalized, grayscale scaled, and contrast adjusted to obtain an adjusted image; Gaussian filtering and noise removal are performed on the adjusted image to obtain the processed image.

3. A method for measuring the height of a wooden board above a facing according to claim 2, characterized in that: The step of performing threshold segmentation based on the processed image to obtain the target wooden board area specifically includes: Adaptive threshold segmentation and screening are performed based on the processed image to obtain a candidate wooden board area, wherein the processed image is traversed with a sliding window of a fixed size, and a segmentation threshold is dynamically calculated using a local pixel mean to obtain a binary wooden board image, and a closing operation is performed on the binary wooden board image to connect different areas of the wooden board; different areas of the connected domain are screened, and connected domains with an area larger than a preset area are collected to obtain the candidate wooden board area; Based on the processed image, a large-law threshold segmentation is performed to obtain a wooden board area to be selected, wherein the processed image is subjected to a large-law threshold segmentation to obtain a wooden board binary image, the wooden board binary image is subjected to a closing operation and an opening operation to fill and filter the gap area, and the largest area is screened to obtain the wooden board area to be selected; The target wooden board area is obtained by comparing and screening the wooden board candidate area and the wooden board candidate area, wherein when the width of the wooden board candidate area is less than a preset width threshold, the target wooden board area is obtained based on the wooden board candidate area; otherwise, the target wooden board area is obtained based on the intersection of the wooden board candidate area and the wooden board candidate area.

4. A method for measuring the height of a wooden board above a facing according to claim 3, characterized in that: The step of performing equal-interval segmentation based on the target wooden board area to obtain the region of interest specifically includes: Adjusting the width of the target wooden board area to eliminate invalid areas, and combining the processed image to intercept and obtain a valid target area; The effective target area is segmented cyclically using a fixed height to obtain the region of interest.

5. A method for measuring the height of a wooden board above a facing according to claim 4, characterized in that: The step of performing adaptive gradient threshold screening and edge extreme point calculation on the region of interest to determine the edge points of the wooden board specifically includes: The left and right gradient thresholds are obtained based on the adaptive screening of the gradient threshold; The edge extreme points are calculated based on the projected edge points of the region of interest; The edge extreme points are filtered using the left and right gradient thresholds to obtain the edge points of the wooden board, wherein the edge points of the wooden board include left and right edge points.

6. A method for measuring the height of a wooden board above a facing according to claim 5, characterized in that: The performing straight line fitting on the edge points of the wooden board to filter out the interference of burrs and wood chips to obtain effective edge points, and calculating the thickness of the wooden board based on the effective edge points to determine whether the current wooden board is higher than the veneer specifically includes: Based on the edge extreme points, a random sampling consistency algorithm is used to fit a straight line to filter out burr and sawdust interference to obtain a valid point set; The thickness of the wooden board is calculated according to the valid edge point pairs in the valid point set, and whether the current wooden board is higher than the finish is determined based on the thickness of the wooden board and a preset thickness threshold, wherein if the thickness of the wooden board is greater than the thickness threshold, it indicates that the wooden board is higher than the finish, otherwise it indicates that the wooden board is lower than the finish.

7. A system for measuring the height of a wooden board above the veneer, characterized in that: The method comprises a memory and a processor, wherein the memory comprises a method program for measuring a wooden board higher than a veneer, and when the method program for measuring a wooden board higher than a veneer is executed by the processor, the following steps are implemented: Acquire a wooden board image, and perform preprocessing based on the wooden board image to obtain a processed image; Performing threshold segmentation based on the processed image to obtain a target wooden board area, wherein the threshold segmentation includes performing adaptive threshold segmentation screening and large law threshold segmentation screening; Based on the target wooden board area, an area of ​​interest is obtained by performing equal-interval segmentation, and the area of ​​interest is subjected to gradient threshold adaptive screening and edge extreme point calculation to determine the edge point of the wooden board; Linear fitting is performed on the edge points of the wooden board to filter out burrs and wood chips to obtain effective edge points, and the thickness of the wooden board is calculated based on the effective edge points to determine whether the current wooden board is higher than the veneer.

8. A system for measuring the height of a wooden board above the veneer according to claim 7, characterized in that: The obtaining of the wooden board image and performing preprocessing based on the wooden board image to obtain a processed image specifically includes: The wooden board image is normalized, grayscale scaled, and contrast adjusted to obtain an adjusted image; Gaussian filtering and noise removal are performed on the adjusted image to obtain the processed image.

9. A system for measuring the height of a wooden board above the veneer according to claim 8, characterized in that: The step of performing threshold segmentation based on the processed image to obtain the target wooden board area specifically includes: Adaptive threshold segmentation and screening are performed based on the processed image to obtain a candidate wooden board area, wherein the processed image is traversed with a sliding window of a fixed size, and a segmentation threshold is dynamically calculated using a local pixel mean to obtain a binary wooden board image, and a closing operation is performed on the binary wooden board image to connect different areas of the wooden board; different areas of the connected domain are screened, and connected domains with an area larger than a preset area are collected to obtain the candidate wooden board area; Based on the processed image, a large-law threshold segmentation is performed to obtain a wooden board area to be selected, wherein the processed image is subjected to a large-law threshold segmentation to obtain a wooden board binary image, the wooden board binary image is subjected to a closing operation and an opening operation to fill and filter the gap area, and the largest area is screened to obtain the wooden board area to be selected; The target wooden board area is obtained by comparing and screening the wooden board candidate area and the wooden board candidate area, wherein when the width of the wooden board candidate area is less than a preset width threshold, the target wooden board area is obtained based on the wooden board candidate area; otherwise, the target wooden board area is obtained based on the intersection of the wooden board candidate area and the wooden board candidate area.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a method program for measuring a wooden board above a finish. When the method program for measuring a wooden board above a finish is executed by a processor, the steps of a method for measuring a wooden board above a finish as described in any one of claims 1 to 6 are implemented.

Images