Visual precision positioning system applied to log splitter

Abstract

The invention belongs to the technical field of visual positioning, and particularly discloses a visual precision positioning system applied to a wood splitting machine, which comprises an image acquisition module, a wood type identification module, a positioning correction module and a material pushing and wood splitting module. According to the scheme, the local quality index image is obtained by calculating the local quality index, the image quality of any region is quantified, the negative effects of interference characteristics such as saw marks, cracks and dirt are reduced, the accuracy of the log splitter operation is improved, the deep learning model is more concerned on high-quality regions, low-quality regions are selectively ignored, and the log splitter operation efficiency is improved. Therefore, the reliability of feature extraction and wood species identification is improved; according to the wood type, the wood shear strength is determined, a linear regression model is used for obtaining a global shear strength image, the cutting angle of the wood splitting unit is adjusted, the pushing speed of the pushing unit is optimized, and the wood splitting machine is assisted to reduce energy consumption and save cost.

Description

Technical Field

[0001] The invention relates to the technical field of visual positioning, and in particular to a visual precision positioning system applied to a wood splitter. Background Art

[0002] The visual precision positioning system applied to wood splitters refers to a system that uses computer vision technology to optimize wood splitters.

[0003] Among the existing approximate solutions, for example, CN114820606B is a laser cutting equipment control system and method based on visual positioning. This solution addresses the technical problem that the prior art lacks a method for detecting the cutting effect of the cut material and adjusting the parameters of the laser cutting equipment according to the detection results. By performing HSV color space conversion on the section image, finding the main cutting seam, calculating the cut mark coefficient and the flatness of the cut surface, and adjusting the parameters of the laser cutting equipment, the cutting effect of the cut material is detected and the parameters of the laser cutting equipment are adjusted according to the detection results to ensure the subsequent material cutting accuracy. However, there is a technical problem that the negative impact of interference features such as cracks and saw marks that reduce the significance of important features in the cut material is not taken into account;

[0004] Knots in wood can reduce the strength of the wood, making it more susceptible to breakage or deformation. The internal grain structure of the wood also directly affects the pressure required by the pusher and the cutting angle of the splitter. Existing wood splitter systems do not yet have the technical problem of adjusting the operating accuracy of the pusher and splitter according to the strength of the wood. Summary of the invention

[0005] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a visual precision positioning system applied to a wood splitter. In view of the technical problem that the prior art does not take into account the negative impact of interfering features such as cracks and saw marks in the cutting material that reduce the significance of important features, this solution calculates the local quality index to obtain a local quality index image, quantifies the image quality of any area, reduces the negative impact of interfering features such as saw marks, cracks and dirt, improves the accuracy of the wood splitter operation, and makes the deep learning model pay more attention to high-quality areas and selectively ignore low-quality areas, thereby improving the reliability of feature extraction and wood species identification; in view of the technical problem that the existing wood splitter system does not have a solution for adjusting the operating accuracy of the pusher device and the firewood splitting device according to the strength of the wood, this solution determines the shear strength of the wood according to the wood type, uses a linear regression model to obtain a global shear strength image, adjusts the cutting angle of the firewood splitting unit, optimizes the pushing speed of the pusher unit, and assists the wood splitter to reduce energy consumption and save costs.

[0006] The technical solution adopted by the present invention is as follows: The present invention provides a visual precision positioning system applied to a wood splitter, the visual precision positioning system applied to a wood splitter comprises an image acquisition module, a wood species identification module, a positioning correction module and a material pushing and splitting module;

[0007] The image acquisition module uses an industrial camera to obtain a cross-sectional image of the wood;

[0008] The wood species identification module adopts a wood species identification method to analyze the cross-sectional texture according to the wood cross-sectional image and identify the wood species;

[0009] The positioning correction module adopts a positioning correction method to determine the global shear strength image of the wood according to the wood type:

[0010] The pushing and chopping wood module comprises a chopping wood unit and a pushing unit; the pushing and chopping wood module adjusts the cutting angle of the chopping wood unit and optimizes the pushing speed of the pushing unit according to the global shear strength image.

[0011] The wood species identification module adopts a wood species identification method, and the wood species identification method specifically includes the following steps:

[0012] Step S1: cross-section optimization, used to reduce the influence of interference features and extract local structures. The interference features refer to cracks and saw marks of wood. The specific operation is as follows;

[0013] Step S11: obtaining a filter map, specifically, using a group of filters with different directional characteristics, the filter includes a zero-mean Gaussian function, adjusting the directional characteristics of the filter by changing the variance of the filter in the horizontal direction and the vertical direction, and applying the group of filters to the wood cross-sectional image, respectively, to obtain a group of filter maps, the filter maps are used to highlight the texture of the wood cross-sectional image corresponding to the directional characteristics of the filter;

[0014] Step S12: reducing noise, specifically, using a majority voting method to smooth the filter graph;

[0015] Step S13: Calculate the response value, specifically, traverse all the pixels in the filter map, perform convolution operations on the pixel values ​​of the neighboring pixels around each pixel with all filters respectively, obtain the response value of each pixel under the corresponding filter, record the direction of the filter with the largest response value as the dominant direction of the pixel, record the dominant directions of all pixels, and obtain a direction map;

[0016] Step S2: Quality assessment, used to construct a local quality map, the specific operation is as follows;

[0017] Step S21: Eliminate discontinuity, which is used to eliminate the discontinuity caused by the directional angles of 0° and 180°. Specifically, the local directional consistency of each pixel point in the directional map and the surrounding neighboring pixel points is calculated. The smaller the local directional consistency, the more consistent the direction of the pixel point and the surrounding neighboring pixel points, and the clearer the texture of the annual ring. The calculation formula of the local directional consistency is as follows: ;

[0018] In the formula, represents local directional consistency, represents the dominant direction of each pixel in the direction map, It represents the directional diagram after rotating 90°. represents the operation of calculating the standard deviation, Indicates the minimum value operation;

[0019] Step S22: Calculate the local direction matching degree for evaluating the wood texture. Specifically, use a computer vision algorithm to obtain the line from each pixel to the wood pith, and calculate the local direction matching degree between the line and the dominant direction of the pixel in the direction map. The smaller the local direction matching degree, the more the direction of the pixel matches the texture direction of the annual ring. The calculation formula of the local direction matching degree is as follows: ;

[0020] In the formula, represents the local direction matching degree, represents the direction of the line, Indicates the direction of the line after rotating 90°. Represents a modulo operation;

[0021] Step S23: Calculate a local quality index for evaluating annual ring visibility and regional quality. Specifically, perform element-wise multiplication operation on the local direction consistency and local direction matching of all pixels to obtain a local quality index. The higher the local quality index, the higher the weight of the pixel for wood species identification. A local quality map is constructed based on the local quality index.

[0022] Step S3: Species output, which is used to identify the wood species using a convolutional neural network. Specifically, the local quality index in the local quality map is used as the weight of the wood cross-section image, and the local quality map is used as an additional channel to be embedded in the wood cross-section image used as input data in the convolutional neural network. The convolutional neural network outputs the wood species.

[0023] The positioning correction module adopts a positioning correction method, and the positioning correction method specifically includes the following steps:

[0024] Step M1: determining the shear strength, specifically, determining the wood density and initial shear strength according to the type of wood;

[0025] Step M2: determine the internal structure, specifically, use a laser scanner to obtain wood surface point cloud data, and reconstruct the internal texture structure of the wood based on wood science knowledge;

[0026] Step M3: Determine the stiffness coefficient, specifically, use a stress wave propagation device to measure the acoustic wave propagation speed of the stress wave in the wood, and calculate the stiffness coefficient of the wood. The formula used is as follows: ;

[0027] In the formula, represents the stiffness coefficient, is the speed of sound wave propagation, Indicates the density of the wood;

[0028] Step M4: Stiffness correction, used to correct the initial shear strength using a linear regression model. Specifically, the presence of knots will affect the shear strength of the wood. Computer vision technology is used to identify the position and shape of the scars in the wood cross-sectional image. The weight of the wood cross-sectional image is adjusted according to the position and shape of the scars. The position and shape of the scars, the initial shear strength and the local quality map are used as three additional channels and embedded into the internal texture structure of the wood and the wood cross-sectional image as input data of the linear regression model. The linear regression model outputs a global shear strength image.

[0029] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0030] (1) In view of the technical problem that the existing technology does not take into account the negative impact of interfering features such as cracks and saw marks in the cut material that reduce the significance of important features, this solution calculates the local quality index to obtain a local quality index image, quantifies the image quality of any area, reduces the negative impact of interfering features such as saw marks, cracks and dirt, improves the accuracy of the wood splitter operation, and enables the deep learning model to pay more attention to high-quality areas and selectively ignore low-quality areas, thereby improving the reliability of feature extraction and wood species identification;

[0031] (2) In view of the technical problem that the existing wood splitter system does not have a solution to adjust the operating accuracy of the pusher and chopping device according to the strength of the wood, this solution determines the shear strength of the wood according to the type of wood, uses a linear regression model to obtain a global shear strength image, adjusts the cutting angle of the chopping unit, optimizes the pushing speed of the pusher unit, and assists the wood splitter in reducing energy consumption and saving costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1A module connection diagram of a visual precision positioning system applied to a wood splitter provided by the present invention;

[0033] Figure 2 is a flow chart of a wood species identification method;

[0034] Figure 3 is a schematic diagram of step S1;

[0035] Figure 4 is a schematic diagram of step S2;

[0036] Figure 5 Schematic diagram of the flow of the positioning correction method.

[0037] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0039] Example 1: See Figures 1 to 5 , this embodiment provides a visual precision positioning system applied to a wood splitter, the visual precision positioning system applied to a wood splitter includes an image acquisition module, a wood species identification module, a positioning correction module and a pushing and splitting module;

[0040] The image acquisition module uses an industrial camera to obtain a cross-sectional image of the wood;

[0041] The wood species identification module adopts a wood species identification method to analyze the cross-sectional texture according to the wood cross-sectional image and identify the wood species;

[0042] The positioning correction module adopts a positioning correction method to determine the global shear strength image of the wood according to the wood type:

[0043] The pushing and chopping wood module comprises a chopping wood unit and a pushing unit; the pushing and chopping wood module adjusts the cutting angle of the chopping wood unit and optimizes the pushing speed of the pushing unit according to the global shear strength image.

[0044] Example 2: See Figures 1 to 4 This embodiment is based on the above embodiment. The wood species identification module adopts a wood species identification method. The wood species identification method specifically includes the following steps:

[0045] Step S1: cross-section optimization, used to reduce the influence of interference features and extract local structures. The interference features refer to cracks and saw marks of wood. The specific operation is as follows;

[0046] Step S11: obtaining a filter map, specifically, using a group of filters with different directional characteristics, the filter includes a zero-mean Gaussian function, adjusting the directional characteristics of the filter by changing the variance of the filter in the horizontal direction and the vertical direction, and applying the group of filters to the wood cross-sectional image, respectively, to obtain a group of filter maps, the filter maps are used to highlight the texture of the wood cross-sectional image corresponding to the directional characteristics of the filter;

[0047] Step S12: reducing noise, specifically, using a majority voting method to smooth the filter graph;

[0048] Step S13: Calculate the response value, specifically, traverse all the pixels in the filter map, perform convolution operations on the pixel values ​​of the neighboring pixels around each pixel with all filters respectively, obtain the response value of each pixel under the corresponding filter, record the direction of the filter with the largest response value as the dominant direction of the pixel, record the dominant directions of all pixels, and obtain a direction map;

[0049] Step S2: Quality assessment, used to construct a local quality map, the specific operation is as follows;

[0050] Step S21: Eliminate discontinuity, which is used to eliminate the discontinuity caused by the directional angles of 0° and 180°. Specifically, the local directional consistency of each pixel point in the directional map and the surrounding neighboring pixel points is calculated. The smaller the local directional consistency, the more consistent the direction of the pixel point and the surrounding neighboring pixel points, and the clearer the texture of the annual ring. The calculation formula of the local directional consistency is as follows: ;

[0051] In the formula, represents local directional consistency, represents the dominant direction of each pixel in the direction map, It represents the directional diagram after rotating 90°. represents the operation of calculating the standard deviation, Indicates the minimum value operation;

[0052] Step S22: Calculate the local direction matching degree for evaluating the wood texture. Specifically, use a computer vision algorithm to obtain the line from each pixel to the wood pith, and calculate the local direction matching degree between the line and the dominant direction of the pixel in the direction map. The smaller the local direction matching degree, the more the direction of the pixel matches the texture direction of the annual ring. The calculation formula of the local direction matching degree is as follows: ;

[0053] In the formula, represents the local direction matching degree, represents the direction of the line, Indicates the direction of the line after rotating 90°. Represents a modulo operation;

[0054] Step S23: Calculate a local quality index for evaluating annual ring visibility and regional quality. Specifically, perform element-wise multiplication operation on the local direction consistency and local direction matching of all pixels to obtain a local quality index. The higher the local quality index, the higher the weight of the pixel for wood species identification. A local quality map is constructed based on the local quality index.

[0055] Step S3: Species output, which is used to identify the wood species using a convolutional neural network. Specifically, the local quality index in the local quality map is used as the weight of the wood cross-section image, and the local quality map is used as an additional channel to be embedded in the wood cross-section image used as input data in the convolutional neural network. The convolutional neural network outputs the wood species.

[0056] Example 3: See Figures 1 to 5 This embodiment is based on the above embodiment. The positioning correction module adopts a positioning correction method. The positioning correction method specifically includes the following steps:

[0057] Step M1: determining the shear strength, specifically, determining the wood density and initial shear strength according to the type of wood;

[0058] Step M2: determine the internal structure, specifically, use a laser scanner to obtain wood surface point cloud data, and reconstruct the internal texture structure of the wood based on wood science knowledge;

[0059] Step M3: Determine the stiffness coefficient, specifically, use a stress wave propagation device to measure the acoustic wave propagation speed of the stress wave in the wood, and calculate the stiffness coefficient of the wood. The formula used is as follows: ;

[0060] In the formula, represents the stiffness coefficient, is the speed of sound wave propagation, Indicates the density of the wood;

[0061] Step M4: Stiffness correction, used to correct the initial shear strength using a linear regression model. Specifically, the presence of knots will affect the shear strength of the wood. Computer vision technology is used to identify the position and shape of the scars in the wood cross-sectional image. The weight of the wood cross-sectional image is adjusted according to the position and shape of the scars. The position and shape of the scars, the initial shear strength and the local quality map are used as three additional channels and embedded into the internal texture structure of the wood and the wood cross-sectional image as input data of the linear regression model. The linear regression model outputs a global shear strength image.

[0062] Example 4: See Figures 1 to 5 , this embodiment is based on the above embodiment, and the firewood splitting unit is a cross knife.

[0063] Example 5: See Figures 1 to 5 This embodiment is based on the above embodiment, and the firewood splitting unit is a straight knife.

[0064] Example 6: See Figures 1 to 5 This embodiment is based on the above embodiment. In step S11, the group of filters with different directional characteristics includes 4 different filter sizes (5x5, 7x7, 9x9 and 11x11), each size corresponds to 12 different directions (0°, 15°, 30°, 45°, 60°, 75°, 90°, 105°, 120°, 135°, 150° and 165°), and a total of 48 direction-sensitive zero-mean Gaussian filters are used.

[0065] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0066] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0067] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A visual precision positioning system for a wood splitter, characterized in that: It includes image acquisition module, wood species identification module, positioning correction module and material pushing and chopping module; The image acquisition module uses an industrial camera to obtain a cross-sectional image of the wood; The wood species identification module adopts a wood species identification method to analyze the cross-sectional texture according to the wood cross-sectional image and identify the wood species; The positioning correction module adopts a positioning correction method to determine the global shear strength image of the wood according to the wood type: The pushing and chopping wood module comprises a chopping wood unit and a pushing unit; the pushing and chopping wood module adjusts the cutting angle of the chopping wood unit and optimizes the pushing speed of the pushing unit according to the global shear strength image.

2. A visual precision positioning system for a wood splitter according to claim 1, characterized in that: The wood species identification module adopts a wood species identification method, and the wood species identification method specifically includes the following steps: Step S1: cross-section optimization, used to extract local structure, the specific operation is as follows; Step S11: obtaining a filter map, specifically, using a group of filters with different directional characteristics, the filter includes a zero-mean Gaussian function, adjusting the directional characteristics of the filter by changing the variance of the filter in the horizontal direction and the vertical direction, and applying the group of filters to the wood cross-sectional image, respectively, to obtain a group of filter maps, the filter maps are used to highlight the texture of the wood cross-sectional image corresponding to the directional characteristics of the filter; Step S12: reducing noise, specifically, using a majority voting method to smooth the filter graph; Step S13: Calculate the response value, specifically, traverse all the pixels in the filter map, perform convolution operations on the pixel values ​​of the neighboring pixels around each pixel with all filters respectively, obtain the response value of each pixel under the corresponding filter, record the direction of the filter with the largest response value as the dominant direction of the pixel, record the dominant directions of all pixels, and obtain a direction map; Step S2: Quality assessment, used to construct a local quality map, the specific operation is as follows; Step S21: Eliminate discontinuity, which is used to eliminate the discontinuity caused by the directional angles of 0° and 180°. Specifically, the local directional consistency of each pixel point in the directional map and the surrounding neighboring pixel points is calculated. The smaller the local directional consistency, the more consistent the direction of the pixel point and the surrounding neighboring pixel points, and the clearer the texture of the annual ring. The calculation formula of the local directional consistency is as follows: ； In the formula, represents local directional consistency, represents the dominant direction of each pixel in the direction map, It represents the directional diagram after rotating 90°. Indicates the operation of calculating the standard deviation. Indicates the minimum value operation; Step S22: Calculate the local direction matching degree for evaluating the wood texture. Specifically, use a computer vision algorithm to obtain the line from each pixel to the wood pith, and calculate the local direction matching degree between the line and the dominant direction of the pixel in the direction map. The smaller the local direction matching degree, the more the direction of the pixel matches the texture direction of the annual ring. The calculation formula of the local direction matching degree is as follows: ； In the formula, represents the local direction matching degree, represents the direction of the line, Indicates the direction of the line after rotating 90°. Represents a modulo operation; Step S23: Calculate a local quality index for evaluating annual ring visibility and regional quality. Specifically, perform element-wise multiplication operation on the local direction consistency and local direction matching of all pixels to obtain a local quality index. The higher the local quality index, the higher the weight of the pixel for wood species identification. A local quality map is constructed based on the local quality index. Step S3: Species output, which is used to identify the wood species using a convolutional neural network. Specifically, the local quality index in the local quality map is used as the weight of the wood cross-section image, and the local quality map is used as an additional channel to be embedded in the wood cross-section image used as input data in the convolutional neural network. The convolutional neural network outputs the wood species.

3. A visual precision positioning system for a wood splitter according to claim 2, characterized in that: The positioning correction module adopts a positioning correction method, and the positioning correction method specifically includes the following steps: Step M1: determining the shear strength, specifically, determining the wood density and initial shear strength according to the type of wood; Step M2: determine the internal structure, specifically, use a laser scanner to obtain wood surface point cloud data, and reconstruct the internal texture structure of the wood based on wood science knowledge; Step M3: Determine the stiffness coefficient, specifically, use a stress wave propagation device to measure the acoustic wave propagation speed of the stress wave in the wood, and calculate the stiffness coefficient of the wood. The formula used is as follows: ； In the formula, represents the stiffness coefficient, represents the speed of sound wave propagation, Indicates the density of the wood; Step M4: Stiffness correction, used to correct the initial shear strength using a linear regression model. Specifically, the presence of knots will affect the shear strength of the wood. Computer vision technology is used to identify the position and shape of the scars in the wood cross-sectional image. The weight of the wood cross-sectional image is adjusted according to the position and shape of the scars. The position and shape of the scars, the initial shear strength and the local quality map are used as three additional channels and embedded into the internal texture structure of the wood and the wood cross-sectional image as input data of the linear regression model. The linear regression model outputs a global shear strength image.

Images