Timber segmentation method based on machine vision

Abstract

The invention discloses a timber segmentation method based on machine vision. The timber segmentation method comprises the following steps that S1, timber is conveyed into a visual scanner through a feeding table chain to be recognized; s2, a user sets parameters related to wood segmentation and determines the corresponding value of wood according to the set parameters; and S3, determining the priority of wood segmentation types and carrying out wood segmentation. According to the invention, comprehensive analysis can be carried out on wood samples through the visual scanner, identification and detection of a plurality of targets such as wood types, quality, sizes and the like are realized, and the efficiency and precision of wood processing are greatly improved; the wood is accurately identified and classified, so that material optimization and value maximization in the furniture manufacturing process are realized; and the wood utilization rate can be maximized, so that the production cost is reduced, and the production efficiency is improved.

Description

Technical Field

[0001] The invention relates to the technical field of machine vision, and in particular to a wood segmentation method based on machine vision. Background Art

[0002] In the current domestic sawn timber processing market, wood debarking and optimized sawing of boards are mainly achieved by longitudinal optimal saws, and the wood feeding problem is the biggest problem that bothers manufacturers. At present, most manufacturers use two feeding methods. One is that workers manually load the wood and then manually adjust the laser marking, manually adjust the position of the wood, and then feed it to the optimal saw for sawing; the other is to use an automatic feeder to send the wood to the specified position and then manually adjust the laser marking, manually adjust the position of the wood, and then feed it to the optimal saw for sawing. The second method has the advantage of the first method that it does not require manual loading and reduces labor, but these two methods still have great defects, such as both require manual intervention, and the wood must be aligned by the naked eye, resulting in low processing accuracy and low efficiency. Summary of the invention

[0003] In order to solve the above problems, the present invention provides a wood segmentation method based on machine vision, comprising the following steps: S1. The wood is transported into a visual scanner through a loading platform chain for identification; S2. The user sets the relevant parameters for wood segmentation and determines the corresponding value of the wood according to the set parameters; S3. Determine the priority of the wood segmentation type and perform wood segmentation; also includes an equipment preparation step: S0. Set and install relevant equipment to achieve wood segmentation; wherein the relevant equipment in step S0 specifically includes: a visual scanner, a loading platform, a CNC positioning platform, a longitudinal cutting optimal saw, and a host computer; the visual scanner is used to collect and analyze the pattern of the wood; the loading platform is used to transport the wood; the CNC positioning platform is used to fix the position of the wood and adjust the position of the wood; there are multiple longitudinal cutting optimal saws, which are used to segment the wood according to the parameters set by the user; the host computer is used to set the wood segmentation plan and monitor the status of the visual scanner, the loading platform, the CNC positioning platform, and the longitudinal cutting optimal saw.

[0004] Furthermore, the wood segmentation-related parameters in step S2 specifically include: sawing width, required quantity, segmentation priority, and whether quantity priority is enabled.

[0005] Furthermore, the S3 step specifically includes the following sub-steps: S31. Determine the wood splitting plan according to the wood splitting related parameters set by the user and the scanning data of the visual scanner; S32. Send the wood to the CNC positioning table for sawing positioning adjustment; S33. The longitudinal cutting optimal saw adjusts the moving saw blade to the splitting position according to the wood splitting related parameters set by the user; S34. Transmit the wood horizontally into the longitudinal cutting optimal saw for optimal sawing.

[0006] Furthermore, the step S31 specifically includes the following sub-steps: S311. Start multiple longitudinal cutting preferred saws and calculate the remainder of the wood after segmentation; S312. Select the combination with the smallest remainder and determine whether to enable quantity priority; S313. Calculate the total value corresponding to the combination with the smallest remainder and sort them, and select the combination with the largest total value.

[0007] Furthermore, the calculation formula for the remainder of the wood after splitting is: remainder = net width of wood - (planned dimension 1 + planned dimension 2 +... + planned dimension n) - (longitudinal sectioning preferred saw mobile link 1 + longitudinal sectioning preferred saw mobile link 2 +... + longitudinal sectioning preferred saw mobile link n-1), where n represents the number of longitudinal sectioning preferred saws used.

[0008] Furthermore, the step S312 specifically includes: when quantity priority is enabled, counting and sorting the required quantity of each size in the combination with the smallest margin, and selecting the combination with the smallest required quantity; when quantity priority is not enabled, executing step S313.

[0009] The present invention provides a wood segmentation method based on machine vision, which has the following beneficial effects: The present invention can conduct a comprehensive analysis of wood samples through a visual scanner, realize the identification and detection of multiple targets such as wood type, quality, size, etc., greatly improving the efficiency and accuracy of wood processing; and accurately identify and classify wood, thereby realizing material optimization and value maximization in the furniture manufacturing process; and can maximize the utilization rate of wood, thereby reducing production costs and improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0011] Figure 1 The present invention provides a flow chart of the method. DETAILED DESCRIPTION

[0012] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0013] The following is a detailed description of the implementation method of the present invention in conjunction with the accompanying drawings. Only some embodiments are described, not all embodiments. For the purpose of clarity, representations and descriptions that are not related to the present invention are omitted in the drawings and descriptions.

[0014] In order to have a clearer understanding of the technical features, purposes and beneficial effects of the present invention, the technical solution of the present invention is now described in detail below. Obviously, the implementation cases described are part of the embodiments of the present invention, not all of the embodiments, and cannot be understood as limiting the scope of the implementation of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the protection scope of the present invention.

[0015] like Figure 1 As shown, the present invention provides a wood segmentation method based on machine vision, comprising the following steps: S1. The wood is transported into a visual scanner through a loading platform chain for identification; S2. The user sets relevant parameters for wood segmentation and determines the corresponding value of the wood according to the set parameters; S3. Determine the priority of the wood segmentation type and perform wood segmentation; also includes an equipment preparation step: S0. Set and install relevant equipment to achieve wood segmentation; wherein the relevant equipment in step S0 specifically includes: a visual scanner, a loading platform, a CNC positioning platform, a longitudinal cutting preferred saw, and a host computer; the visual scanner is used to collect and analyze patterns of the wood; the loading platform is used to transport the wood; the CNC positioning platform is used to fix the position of the wood and adjust the position of the wood; there are multiple longitudinal cutting preferred saws, which are used to segment the wood according to the parameters set by the user; the host computer is used to set the wood segmentation plan and monitor the status of the visual scanner, the loading platform, the CNC positioning platform, and the longitudinal cutting preferred saw.

[0016] The wood segmentation-related parameters in step S2 specifically include: sawing width, required quantity, segmentation priority, and whether quantity priority is enabled.

[0017] Step S3 specifically includes the following sub-steps: S31. Determine the wood splitting plan based on the wood splitting related parameters set by the user and the scanning data of the visual scanner; S32. Send the wood to the CNC positioning table for sawing positioning adjustment; S33. The longitudinal cutting optimal saw adjusts the moving saw blade to the splitting position according to the wood splitting related parameters set by the user; S34. Transmit the wood horizontally into the longitudinal cutting optimal saw for optimal sawing.

[0018] Step S31 specifically includes the following sub-steps: S311. Start multiple longitudinal cutting optimal saws and calculate the remaining amount of wood after segmentation; S312. Select the combination with the smallest remaining amount and determine whether to enable quantity priority; S313. Calculate the total value corresponding to the combination with the smallest remaining amount and sort them, and select the combination with the largest total value.

[0019] The calculation formula for the remainder of the wood after splitting is: remainder = net width of the wood - (planned dimension 1 + planned dimension 2 +... + planned dimension n) - (longitudinal sectioning optimal saw mobile link 1 + longitudinal sectioning optimal saw mobile link 2 +... + longitudinal sectioning optimal saw mobile link n-1), where n represents the number of longitudinal sectioning optimal saws used.

[0020] Step S312 specifically includes: when quantity priority is enabled, counting and sorting the required quantities of each size in the combination with the smallest margin, and selecting the combination with the smallest required quantity; when quantity priority is not enabled, executing step S313.

[0021] Embodiment: A wood sample analysis and optimal sawing method based on machine vision, including a visual scanner, a loading table, a CNC positioning table, and a longitudinal cutting optimal saw, the main steps of which are as follows: Step 1: The wood is transported into the visual scanner through the loading table chain and is ready for identification.

[0022] Step 2: Collect patterns of wood samples and analyze images.

[0023] Step 3: Send the analysis results to the host computer, and perform process processing such as value optimization, quantity optimization, grade optimization, and maximum yield optimization according to customer needs. The customer first enters the size, quantity, priority, and whether to enable quantity priority on the master control terminal.

[0024] According to the user list, the best cutting plan is found with the highest value while ensuring the maximum output. After analyzing and identifying that the current net width of the wood is W (after removing the edge bark), the host computer automatically finds the combinations that meet the requirements when 1 mobile saw (i.e., the preferred saw for longitudinal cutting) is enabled, 2 mobile saws are enabled, 3 mobile saws are enabled, and 4 mobile saws are enabled, and the margins of these combinations are calculated respectively.

[0025] Enable 1 mobile saw (no need to consider the saw path): allowance = net width of wood W - planned size 1.

[0026] Enable 2 mobile saws (the sawing path of the first mobile saw needs to be considered): allowance = net width of wood W - planned size 1 - planned size 2 - sawing path of the first mobile saw.

[0027] Activate 3 mobile saws (the sawing paths of the 1st and 2nd mobile saws need to be considered): allowance = net width of wood W - planned size 1 - planned size 2 - planned size 3 - sawing path of the 1st mobile saw - sawing path of the 2nd mobile saw.

[0028] Activate 4 mobile saws (the sawing paths of the 1st, 2nd and 3rd mobile saws need to be considered): allowance = net width of wood W - planned size 1 - planned size 2 - planned size 3 - planned size 4 - sawing path of the 1st mobile saw - sawing path of the 2nd mobile saw - sawing path of the 3rd mobile saw.

[0029] By comparing the size of the surplus, find the combination with the smallest surplus. There may be one or more combinations with the smallest surplus (this step ensures the maximum material output and reduces wood waste). Then take out the combination with the smallest surplus for the next step.

[0030] After obtaining the combination with the smallest margin, determine whether the quantity priority mode is enabled. If the quantity priority mode is not enabled, calculate the sum of the values ​​corresponding to the combination with the smallest margin, then sort the total values, and select the combination with the largest total value for sawing. The value is calculated based on the user's customized calculation of different grades of boards; increasing the priority can increase the value of the corresponding size.

[0031] If the quantity priority mode is enabled, the required quantity of each size in the combination with the smallest margin is counted, the required quantity is sorted, and the one with the smallest required quantity is selected for sawing.

[0032] For example: recognizing that the net width of the current wood is 187mm (after removing the edge bark), the upper computer automatically finds the following combination: The combination obtained when using 1 mobile saw: 140+0+0+0, with a margin of 47mm.

[0033] When using two mobile saws (the sawing path of the middle mobile saw is 3mm), the combinations obtained are: 130+50+0+0+3, with a margin of 4mm; 120+60+0+0+3, with a margin of 4mm; 110+70+0+0+3, with a margin of 4mm; 100+80+0+0+3, with a margin of 4mm; 90+90+0+0+3, with a margin of 4mm.

[0034] When using 3 mobile saws (the sawing path of the middle mobile saw is 3mm+3mm): 80+50+50+0+3+3, the margin is 1mm; 70+60+50+0+3+3, the margin is 1mm; 60+60+60+0+3+3, the margin is 1mm.

[0035] When using 4 mobile saws (the sawing path of the middle mobile saw is 3mm+3mm+3mm): it is impossible to find a combination that meets the requirements. The minimum combination is 50+50+50+50+3+3+3. Four mobile saws can be used for sawing only when the net width of the wood is at least 209mm.

[0036] By comparison, the combinations with the smallest margin are: 80+50+50+0+3+3, with a margin of 1mm; 70+60+50+0+3+3, with a margin of 1mm; 60+60+60+0+3+3, with a margin of 1mm.

[0037] Then determine whether the quantity priority mode is enabled. If the quantity priority mode is not enabled, continue to calculate the total value of the three combinations with the smallest remainder: 80+50+50+3+3: 1068+760+760=2588; 70+60+50+3+3: 972+852+760=2584; 60+60+60+3+3: 852+852+852=2556.

[0038] Sort the total value and select the combination with the largest value, that is, the combination of 80+50+50+3+3. Use 3 mobile saws for sawing, and finally cut out 1 sheet with a width of 80mm and 2 sheets with a width of 50mm.

[0039] If the quantity priority mode is enabled, the combination with the smallest margin will be judged, and the size with the smallest demand will be sawed first: if the demand quantity of size 80 is the smallest, the combination of 80+50+50+3+3 will be selected; if the demand quantity of size 70 is the smallest, the combination of 70+60+50+3+3 will be selected; if the demand quantity of size 60 is the smallest, the combination of 60+60+60+3+3 will be selected; if the demand quantity of size 50 is the smallest, the combination of 80+50+50+3+3 will be selected.

[0040] Finally, the main control outputs the optimization result and gives it to the mobile saw blade for positioning.

[0041] Step 4: The identified wood enters the CNC positioning table at the back for sawing and positioning adjustment. The positioning accuracy of the positioning system at the back is 0.1mm.

[0042] Step 5: The longitudinal section optimization saw adjusts and moves the saw blade to the corresponding position according to the optimization result. The saw blade movement accuracy is 0.1mm.

[0043] Step 6: After the adjustment is completed, the wood is transferred horizontally into the longitudinal cutting optimization sawing equipment for optimal sawing.

[0044] The present invention can conduct a comprehensive analysis of wood samples through a visual scanner, realize the identification and detection of multiple targets such as wood type, quality, size, etc., greatly improving the efficiency and accuracy of wood processing; and accurately identify and classify wood, thereby realizing material optimization and value maximization in the furniture manufacturing process; and can maximize the utilization rate of wood, thereby reducing production costs and improving production efficiency.

[0045] The above is only a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications and environments, and can be modified within the scope of the concept described herein through the above teachings or the technology or knowledge of the relevant field. The changes and modifications made by those skilled in the art shall not deviate from the spirit and scope of the present invention, and shall be within the scope of protection of the claims attached to the present invention.

Claims

1. A wood segmentation method based on machine vision, characterized in that: The following steps are involved: S1. The wood is transported through the loading platform chain into the visual scanner for identification; S2. The user sets the parameters related to wood segmentation and determines the corresponding value of the wood according to the set parameters; S3. Determine the priority of wood segmentation type and perform wood segmentation; It also includes equipment preparation steps: S0. Setting and installing relevant equipment to achieve wood splitting; The relevant equipment in step S0 specifically includes: a visual scanner, a loading table, a CNC positioning table, a longitudinal sectioning optimization saw, and a host computer; The visual scanner is used to collect and analyze the wood pattern; The loading platform is used to transport wood; The numerical control positioning table is used to fix the position of the wood and adjust the position of the wood; The longitudinal splitting preferred saw has multiple parts, which are used to split the wood according to the parameters set by the user; The host computer is used to set the wood splitting plan and monitor the status of the visual scanner, the loading platform, the CNC positioning platform, and the longitudinal splitting optimal saw.

2. The method for wood segmentation based on machine vision according to claim 1, characterized in that: The wood segmentation-related parameters in step S2 specifically include: sawing width, required quantity, segmentation priority, and whether quantity priority is enabled.

3. The wood segmentation method based on machine vision according to claim 1, characterized in that: The S3 step specifically includes the following sub-steps: S31. Determine the wood segmentation scheme according to the wood segmentation parameters set by the user and the visual scanner scan data; S32. The wood is fed into the CNC positioning table for sawing positioning adjustment; S33. The longitudinal cutting optimal saw adjusts the moving saw blade to the cutting position according to the wood cutting related parameters set by the user; S34. The wood is transferred transversely to the longitudinal cutting optimization saw for optimal sawing.

4. The wood segmentation method based on machine vision according to claim 3 is characterized in that: The step S31 specifically includes the following sub-steps: S311. Start multiple longitudinal cutting optimal saws and calculate the remaining amount of wood after splitting; S312. Select the combination with the smallest margin and determine whether to enable quantity priority; S313. Calculate the sum of the corresponding values ​​of the combinations with the smallest remainder and sort them, and select the combination with the largest total value.

5. The method for wood segmentation based on machine vision according to claim 4, characterized in that: The calculation formula for the remainder of the wood after splitting is: remainder = net width of wood - (planned dimension 1 + planned dimension 2 +... + planned dimension n) - (longitudinal sectioning preferred saw mobile link 1 + longitudinal sectioning preferred saw mobile link 2 +... + longitudinal sectioning preferred saw mobile link n-1), where n represents the number of longitudinal sectioning preferred saws used.

6. The method for wood segmentation based on machine vision according to claim 4, characterized in that: The step S312 specifically includes: when quantity priority is enabled, counting and sorting the required quantities of each size in the combination with the smallest margin, and selecting the combination with the smallest required quantity; when quantity priority is not enabled, executing step S313.

Images