Agilawood grading processing device and method based on computer vision

Abstract

The invention discloses an agilawood grading processing device and method based on computer vision, and the method comprises the steps: collecting the image data of the cross sections of two sides of an agilawood block to be processed, obtaining an agilawood region above a clamping part based on an image processing technology, taking the maximum value of the heights of two sides as a cutting parameter, carrying out integral cutting on the agilawood section raw materials above the height; the machined part is rotated, the operation is repeated, and first-stage rough machining is achieved; in the second stage, the machined part is detected based on the computer vision technology, a hooking knife operation component perpendicular to the agilawood sections is used for conducting translation operation, a white wood area is hooked, the machined part is rotated according to the set fixed angle value after the current angle is completed, and the operation is repeated till machining of the agilawood sections is completed. Computer vision, automation and mechanical design are comprehensively utilized, the to-be-processed agilawood sections are subjected to automatic grading processing, and the agilawood section cutting and snagging processing efficiency can be effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of automated processing devices and methods for agarwood, and specifically relates to a device and method for grading and processing agarwood based on computer vision. Background Art

[0002] Agarwood is a plant of the genus Aquilaria Lam. and Gyrinops Gaertn. of the family Thymeleaeceae. When the plant is damaged by natural or human factors, the stems produce resin and continue to accumulate to form a resin-rich wood.

[0003] The primary processing of agarwood is the core issue in the secondary industry of agarwood. How to reduce the processing links, improve efficiency and reduce costs is a fundamental problem that needs to be solved urgently. Therefore, the research and development of automated and intelligent equipment for the primary processing of agarwood is crucial. Today, with the continuous expansion of the scale of artificial planting of agarwood trees, there will be a large number of artificial agarwood trees that need to be processed in the future. At present, the primary processing of agarwood is still in the stage of manual processing, which is costly, inefficient and dangerous. In addition to simple tools or equipment such as electric saws, table saws, semi-automatic guillotines, machetes, hook knives, razors, etc., there is a lack of efficient intelligent and automated processing equipment.

[0004] In recent years, with the emergence of primary processing problems, the number of applications for agarwood processing equipment patents has increased significantly, aiming to improve efficiency and reduce costs. However, although some related utility models and invention patents have been applied for and approved, they are difficult to implement and promote for various reasons. For example, patent CN117207294A discloses an automated agarwood wire-snapping processing equipment, which uses a three-axis linkage slide, a depth camera, a detection unit, a main control unit, multiple servo motors, a scraper, an ejector pin, etc., and uses a deep learning method to automatically identify the image of the agarwood material to be processed. It is necessary to manually mark the position coordinate information of the white wood area after image acquisition, and the CNN parameters need to be continuously adjusted during the training model process. The overall design is relatively complex and has a high reliance on training data, which will actually result in high manpower and material costs; and this method does not perform cutting in the rough processing of raw materials, but directly performs wire-snapping, which will result in low operating efficiency. For example, patent CN213732315U discloses a processing equipment for agarwood and sandalwood, which can saw, split and finely plan the wood segments, but still needs manual identification of agarwood and white wood, and cannot realize intelligent identification and automated splitting and cutting; for example, CN220362714U discloses a cutting device for agarwood processing, CN220661192U discloses a cutting device for agarwood raw materials, and CN218534921U discloses a cutting device for agarwood processing, which are all suitable for cutting larger agarwood, focusing on solving the problems of sample clamping stability, processing safety and cleaning of blades, and cannot realize further cutting, wire drawing and separation of white wood and agarwood layers and other fine processing, and are even more difficult to automate and intelligentize. Summary of the invention

[0005] The object of the present invention is to provide an agarwood grading and processing device based on computer vision.

[0006] The purpose of the present invention is also to provide a method for grading and processing agarwood based on the above-mentioned device.

[0007] The above-mentioned first object of the present invention can be achieved by the following technical scheme: A computer vision-based agarwood grading and processing device, comprising a base provided with an embedded computing system for image processing and motor driving, a lower bracket arranged in the middle of the base, a left bracket and a right bracket arranged on both sides of the base, and an upper bracket arranged above the left bracket and the right bracket, the lower bracket is provided with a lower bracket motor and a lower bracket slide rail, the lower bracket slide rail is provided with a cutting telescopic mechanism that can move on the lower bracket slide rail, the cutting telescopic mechanism is provided with a cutting component on the top, the left bracket and the right bracket are relatively Clamping parts for clamping the agarwood section to be processed are respectively provided at the positions, a first industrial camera for photographing the first cross-section of the agarwood section to be processed is provided above the clamping part of the left bracket, and a second industrial camera for photographing the second cross-section of the agarwood section to be processed is provided at the corresponding position above the clamping part of the right bracket, an upper bracket motor and an upper bracket slide rail are provided on the upper bracket, a hook knife telescopic mechanism that can move on the upper bracket slide rail is provided on the upper bracket slide rail, a hook knife operating part is provided on the top of the hook knife telescopic mechanism, and a third industrial camera is provided on the upper bracket at the position of the agarwood section to be processed.

[0008] Optionally, the cutting telescopic mechanism is a cutting telescopic rod.

[0009] Optionally, the hook knife telescopic mechanism is a hook knife telescopic rod.

[0010] Optionally, the cutting component is a gear cutting tool.

[0011] Optionally, the hook cutter operating component includes a hook cutter connecting rod and a hook cutter head.

[0012] Optionally, the width of the hook cutter head of the hook cutter operating component is approximately in the range of 2 to 5 mm.

[0013] The above second object of the present invention can be achieved by the following technical solution: A method for grading and processing agarwood based on the above device comprises the following steps:

[0014] S1, using the first industrial camera and the second industrial camera to collect image information of the cross sections on both sides of the agarwood segment to be processed;

[0015] S2, using the embedded computing system in the base to calculate the image information obtained in S1 based on image processing technology to obtain cutting parameters;

[0016] S3, transmitting the cutting parameters to the cutting component, and driving the cutting component to cut the agarwood segment to be processed;

[0017] S4, using the clamping component to rotate the agarwood segment to be processed by a fixed angle, and repeating steps S1-S3 to achieve the first level of rough processing;

[0018] S5. The camera of the third industrial camera on the upper bracket is used to collect the image data of the rough-processed material, and the hook cutter operation area Q is marked according to the width of the hook cutter operation part. w ;

[0019] S6. Identify the hook cutter operation area based on computer vision technology Q w White wood area Q in b , according to the white wood area Q b Passing hook cutter operation parameters to the hook cutter operation component;

[0020] S7. According to the hooking requirements, according to the preset hook knife sinking parameter g, the hook knife sinks from the white wood area Q b The top position of the hook knife will be lowered to the white wood area Q b Use translation operation to achieve hooking of white wood area;

[0021] S8, after performing the wire hooking operation, repeat step S7 until no white wood area is detected in the current wire hooking operation area;

[0022] S9, rotating the workpiece by a fixed angle, and repeating steps S5-S8 to achieve the second level of fine processing.

[0023] In the above-mentioned agarwood grading and processing method:

[0024] Optionally, the image processing and motor drive in steps S1-S9 are controlled by an embedded computing system in the base, which is a lightweight embedded system using an ARM architecture and is equipped with an image processing module for processing image information of the cross sections on both sides of the agarwood segment to be processed. The operating parameters required in the calculation process are transmitted through a bus to the motors that control various operating components (such as the lower bracket slide rail, the upper bracket slide rail, the cutting telescopic mechanism, the hook knife telescopic mechanism, etc.), thereby driving each operating component to operate.

[0025] Optionally, in step S2, an embedded computing system in the base is used to calculate the image information obtained in S1 based on image processing technology to obtain cutting parameters, and the specific steps include:

[0026] S21, processing the cross-sectional image of one side of the agarwood segment to be processed, and obtaining the distance L1 between the highest point of the agarwood and the clamping component;

[0027] S21, processing the cross-sectional image of the other side of the agarwood segment to be processed, and obtaining the distance L2 between the highest point of the agarwood and the clamping component;

[0028] S23, calculating cutting parameters: L = Max (L1, L2);

[0029] The image processing technology includes identifying the agarwood part in the image information based on the threshold segmentation method in the CV image processing library, and then calculating the edge position of the agarwood part using the edge detection method, and calculating the cutting parameters according to the edge position parameters.

[0030] Optionally, in step S3, the cutting parameters are transmitted to the cutting component, and the cutting component is driven to cut the agarwood segment to be processed. The specific steps include:

[0031] S31, according to the cutting parameter L, using the lower bracket motor to drive the height of the cutting telescopic mechanism;

[0032] S32. According to the adjusted height, the lower bracket motor is used to drive the cutting telescopic mechanism to translate through the lower bracket slide rail, and the cutting component is rotated at the same time to complete the cutting of the agarwood segment.

[0033] Optionally, in step S4 and step S8, the agarwood segment to be processed is rotated by a fixed angle using a clamping component, and the fixed angle is 40 to 60 degrees.

[0034] Optionally, in step S5, the camera of the third industrial camera of the upper bracket is used to collect image data of the rough-processed material, and the hook cutter operation area Q is marked according to the width of the hook cutter operation part. w Specifically, it includes: using the camera of the third industrial camera on the upper bracket to collect the top view image of the rough-processed material, and marking the hook cutter operation area Q according to the width of the hook cutter operation part w The width of the hook cutter operating component is between 2 and 5 mm.

[0035] Optionally, in step S6, the white wood area Q is identified based on computer vision technology. b , according to the white wood area Q b Pass hook cutter operation parameters to the hook cutter operation component, including:

[0036] S61. Identify the hook cutter operation area Q based on computer vision technology w The white wood area in the middle is marked as white wood area Q b ;

[0037] S62, according to the identified white wood area Q b Calculate hook cutter operation parameters and transmit the hook cutter operation parameters to the hook cutter operation component;

[0038] The computer vision technology includes using a convolutional neural network method to extract the hook cutter operation area Q w Middle Agarwood Area and White Wood Area Q bThe image features of the agarwood area and the white wood area are mainly extracted by extracting color features and texture features. On this basis, the lightweight convolutional neural network model EfficientNet with an attention mechanism is trained and learned to construct the Q b The binary classification model identifies the hook cutter operation area Q w White wood area Q in b .

[0039] Optionally, in step S7, according to the hooking requirement, the hook knife sinking parameter g is set from the white wood area Q b The top position of the hook knife will be lowered to the white wood area Q b The translation operation is used to realize the hooking of the white wood area. The specific steps include:

[0040] S71, according to the obtained hook knife operation parameters, use the upper bracket motor and the upper bracket slide rail to align the hook knife operation component in the vertical direction with the white wood area Q b The right edge position;

[0041] S72, using the hook knife telescopic mechanism to lower the hook knife operating component to the current highest position of the agarwood section, and further lowering it according to the hook knife sinking parameter g;

[0042] S73, use hook knife operation parts to white wood area Q b Perform wire hooking operation;

[0043] S74, when there are multiple white wood areas Q in step S52 b After finishing the hooking of each white wood area, raise the hooking knife operation part to the highest point of the agarwood segment, and then move it to the next white wood area Q b The right edge of the wire is lowered and the wire hooking operation is performed.

[0044] Optionally, the hook cutter sinking parameter g is 0.05-0.1 mm.

[0045] The present invention has the following advantages: the device and method of the present invention comprehensively utilize computer vision, automation and mechanical design to automatically grade the agarwood segment raw materials to be processed, which can effectively improve the processing efficiency of agarwood segment cutting and wire drawing. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings:

[0047] Figure 1 It is a front view of the agarwood grading and processing device based on computer vision in Example 1 of the present invention;

[0048] Figure 2The cutting component used for the first-level rough machining in Example 1 of the present invention;

[0049] Figure 3 This is a cross section of one side of the agarwood segment raw material to be processed in Example 2 of the present invention;

[0050] Figure 4 The cross-sectional image of one side of the agarwood segment raw material to be processed in Example 2 of the present invention is processed to obtain the distance L1 between the highest point of the agarwood and the clamping component;

[0051] Figure 5 The cross-sectional image of the agarwood segment raw material to be processed after being cut according to step S3 in Example 2 of the present invention;

[0052] Figure 6 In the second embodiment of the present invention, according to step S4 Figure 4 The cross-sectional image of the agarwood segment after it is rotated once and then cut;

[0053] Figure 7 This is a schematic diagram of the hook cutter operation components in Example 1 of the present invention;

[0054] Figure 8 This is the hook cutter operation area processing based on computer vision recognition in Example 2 of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] like Figure 1As shown, the agarwood grading and processing device based on computer vision provided in this embodiment includes a base 1 provided with an embedded computing system for image processing and motor driving, a lower bracket 2 arranged in the middle of the base 1, a left bracket 3 and a right bracket 4 arranged on both sides of the base 1, and an upper bracket 5 arranged above the left bracket 3 and the right bracket 4, a lower bracket motor and a lower bracket slide rail (conventional design, not shown in the figure) are arranged on the lower bracket 2, a cutting telescopic mechanism 6 movable on the lower bracket slide rail is arranged on the lower bracket slide rail, a cutting component 7 is arranged on the top of the cutting telescopic mechanism 6, and a clamp for clamping the agarwood segment 14 to be processed is respectively arranged at the relative positions of the left bracket 3 and the right bracket 4. A first industrial camera 9 for photographing the first cross section of the agarwood section to be processed is provided above the clamping component 8 of the left bracket 3 (a conventional clamping component that can clamp and rotate the agarwood section), and a second industrial camera 10 for photographing the second cross section of the agarwood section to be processed is provided at a corresponding position above the clamping component 8 of the right bracket 4. An upper bracket motor and an upper bracket slide rail (conventional design, not shown in the figure) are provided on the upper bracket 5. A hook knife telescopic mechanism 11 that can move on the upper bracket slide rail is provided on the upper bracket slide rail, and a hook knife operating component 12 is provided on the top of the hook knife telescopic mechanism 11. A third industrial camera 13 is provided on the upper bracket 5 at a position opposite to the agarwood section to be processed.

[0057] in:

[0058] The embedded computing system is a lightweight embedded system that adopts the conventional ARM architecture. It is equipped with an image processing module for image processing of the cross-sections on both sides of the agarwood raw material to be processed. The operating parameters required in the calculation process are transmitted to the motors that control each operating component through the bus, thereby driving each operating component to perform the operation.

[0059] The cutting telescopic mechanism 6 is a cutting telescopic rod.

[0060] The hook knife telescopic mechanism 11 is a hook knife telescopic rod.

[0061] The cutting part 7 is a gear cutting tool, and its structure is as follows: Figure 2 shown.

[0062] The structural diagram of the hook cutter operation component 12 is as follows Figure 7 As shown, it includes a hook knife connecting rod 121 and a hook knife head 122.

[0063] The width of the hook cutter head 122 of the hook cutter working component 12 is generally in the range of 2 to 5 mm.

[0064] Example 2

[0065] The agarwood grading and processing method based on the device in Example 1 comprises the following steps:

[0066] S1, using the first industrial camera 9 and the second industrial camera 10 to collect image information of the cross section of both sides of the agarwood segment to be processed of a fixed length (eg, 100 mm), such as Figure 3 As shown;

[0067] S2, using the embedded computing system in the base 1 to calculate the image information obtained in S1 based on image processing technology to obtain cutting parameters;

[0068] S3, transmitting the cutting parameters to the cutting component 7, driving the cutting component 7 to cut the agarwood segment raw material;

[0069] S4, using the clamping member 8 to rotate the workpiece by a fixed angle, and repeating steps S1-S3 to achieve the first level of rough machining;

[0070] S5, obtain the image data of the rough-processed material collected by the industrial camera of the third industrial camera 13 of the upper bracket 5, and mark the hook cutter operation area Q according to the width of the hook cutter operation part w ;

[0071] S6. Identify the hook cutter operation area based on computer vision technology Q w White wood area Q in b , according to the white wood area Q b Pass hook cutter operation parameters to the hook cutter component;

[0072] S7. According to the hooking requirements, according to the preset hook knife sinking parameter g, the hook knife sinks from the white wood area Q b The top position of the hook knife will be lowered to the white wood area Q b Use translation operation to achieve hooking of white wood area;

[0073] S8, after performing the wire hooking operation, repeat step S7 until no white wood area is detected in the current wire hooking operation area;

[0074] S9, rotating the workpiece by a fixed angle, and repeating steps S5-S8 to achieve second-level fine processing;

[0075] The image processing and motor driving in Example 1 and the method of this embodiment are all controlled by the embedded computing system in the base.

[0076] The image processing and motor drive in steps S1-S9 are controlled by an embedded computing system in the base. The embedded computing system is a lightweight embedded system using a conventional ARM architecture and is equipped with an image processing function module. The operating parameters required in the calculation process are transmitted to the motors that control each operating component through the bus, thereby driving each operating component to perform the operation.

[0077] In step S2, the embedded computing system in the base is used to calculate the image information based on image processing technology to obtain cutting parameters. The specific steps include:

[0078] S21, such as Figure 4 As shown, the cross-sectional image of one side of the agarwood segment raw material to be processed is processed to obtain the distance L1 between the highest point of the agarwood and the clamping component;

[0079] S21, processing the cross-sectional image of the other side of the agarwood segment to be processed, and obtaining the distance L2 between the highest point of the agarwood and the clamping component;

[0080] S23, calculating cutting parameters: L = Max (L1, L2);

[0081] The image processing technology includes identifying the agarwood part in the image information based on the threshold segmentation method in the CV image processing library, and then calculating the edge position of the agarwood part using the edge detection method, and calculating the cutting parameters according to the edge position parameters.

[0082] In step S3, the cutting parameters are transmitted to the cutting component to cut the agarwood segment raw material to be processed. The specific steps include:

[0083] S31, according to the cutting parameter L, using the lower bracket motor to drive the height of the telescopic rod to be cut;

[0084] S32, according to the adjusted height, the lower bracket motor is used to drive the cutting telescopic rod to move horizontally through the lower bracket slide rail, and the cutting component is rotated at the same time to complete the cutting of the agarwood section. The cross section of one side after cutting is as follows Figure 5 shown.

[0085] In step S4 and step S8, the agarwood segment to be processed is rotated by a clamping member to a fixed angle, wherein the fixed angle is 40 to 60°. In this embodiment, 60° is recommended.

[0086] According to step S4 Figure 4 The cross-sectional image of the agarwood segment after it is rotated once and then cut is as follows: Figure 6 shown.

[0087] In step S5, the camera of the third industrial camera of the upper bracket is used to collect image data of the rough-processed material, and the hook cutter operation area Q is marked according to the width of the hook cutter operation part. w Specifically, it includes: using the camera of the third industrial camera on the upper bracket to collect the top view image of the rough-processed material, and marking the hook cutter operation area Q according to the width of the hook cutter operation part w , the width of the hook cutter operating part is between 2 and 5 mm; mark the hook cutter operating area as follows Figure 8 The dotted box part Q w .

[0088] In step S6, the white wood area Q is identified based on computer vision technology. b , according to the white wood area Q b Pass hook cutter operation parameters to the hook cutter operation component, including:

[0089] S61. Identify the hook cutter operation area Q based on computer vision technology w The white wood area in the middle is marked as white wood area Q b , there may actually be multiple whitewood areas;

[0090] S62, according to the identified white wood area Q b Calculate hook cutter operation parameters and transmit the hook cutter operation parameters to the hook cutter operation component;

[0091] The computer vision technology includes using a convolutional neural network method to extract the hook cutter operation area Q w Middle Agarwood Area( Figure 8 The image features of the agarwood area (the shaded part in the middle) and the white wood area Qb are extracted based on the color and texture differences between the agarwood area and the white wood area. Therefore, the color features and texture features have the largest weight in the extracted image features. On this basis, the lightweight convolutional neural network model EfficientNet with an attention mechanism is further trained and learned to construct a binary classification model of the agarwood area and the white wood area Qb, and the hook knife operation area Q w White wood area Q in b .

[0092] Among them, the white wood area Q b It is the hook cutter operation area Q w The agarwood area in Central Africa is Figure 8 Middle shaded area.

[0093] Hook cutter operation area Q w The width is one of the hook knife operating parameters, that is, the width of the hook knife operating part, which ranges roughly between 2-5mm.

[0094] In step S7, according to the wire hooking requirements, the hook knife sinking parameter g is set from the white wood area Q b The top position of the hook knife will be lowered to the white wood area Q b The translation operation is used to realize the hooking of the white wood area. The specific steps include:

[0095] S71, according to the obtained hook knife operation parameters, use the upper bracket motor and the slide rail to align the hook knife operation component in the vertical direction with the white wood area Q b The right edge position;

[0096] S72, using the hook knife telescopic rod to lower the hook knife operating component to the current highest position of the agarwood section, and further lower it according to the hook knife sinking parameter g (such as: 0.1mm);

[0097] S73, basis Figure 8 The hook cutter operation shown is used to hook the whitewood area;

[0098] S74, if there are multiple white wood areas in step S52, after completing the wire hooking of each white wood area, raise the hook knife operating component to the current highest point of the agarwood segment, and then move horizontally to the right edge of the next white wood area to descend and perform the wire hooking operation.

[0099] In summary, the method of the present invention includes collecting image data of cross sections on both sides of a fixed length of agarwood segment to be processed, obtaining the agarwood area above the fixed axis based on computer vision technology, and calculating the height of the highest point in the area; taking the maximum value of the heights on both sides as the cutting parameter, and using a rotary cutter to perform overall cutting of the agarwood segment raw material above the height according to the parameter; rotating the workpiece according to a set fixed angle value, repeating the above operation, and realizing the first level of rough processing; in the second level, using a hook knife perpendicular to the rough-processed agarwood segment to perform a translation operation, and performing a wire-hooking operation to achieve more refined processing, and gradually sinking the hook knife according to a fixed step length set in the vertical direction, and at the same time, detecting the workpiece based on computer vision technology, and performing wire-hooking on white wood, and the part that detects the dark threshold is considered to be agarwood, then stopping the wire-hooking for this area, and rotating the workpiece according to the set fixed angle value after the current angle is completed, and repeating the above operation until the processing of the agarwood segment is completed.

[0100] Although the 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. The scope of the present invention is defined by the appended claims and their equivalents, and all should be included within the scope of protection of the present invention.

Claims

1. A device for grading and processing agarwood based on computer vision, characterized in that: The invention comprises a base provided with an embedded computing system for image processing and motor driving, a lower bracket provided in the middle of the base, a left bracket and a right bracket provided at both sides of the base, and an upper bracket provided above the left bracket and the right bracket, the lower bracket being provided with a lower bracket motor and a lower bracket slide rail, the lower bracket slide rail being provided with a cutting telescopic mechanism movable on the lower bracket slide rail, a cutting component being provided on the top of the cutting telescopic mechanism, clamping components for clamping a to-be-processed agarwood section being provided at relative positions of the left bracket and the right bracket, a first industrial camera for photographing a first cross section of the to-be-processed agarwood section being provided above the clamping components of the left bracket, a second industrial camera for photographing a second cross section of the to-be-processed agarwood section being provided at a corresponding position above the clamping components of the right bracket, an upper bracket motor and an upper bracket slide rail being provided on the upper bracket, a hook knife telescopic mechanism movable on the upper bracket slide rail being provided on the upper bracket slide rail, a hook knife operating component being provided on the top of the hook knife telescopic mechanism, and a third industrial camera being provided at a position of the upper bracket facing the to-be-processed agarwood section.

2. A method for grading and processing agarwood based on the device according to claim 1, characterized in that: The following steps are involved: S1, using the first industrial camera and the second industrial camera to collect image information of the cross sections on both sides of the agarwood segment to be processed; S2, using the embedded computing system in the base to calculate the image information obtained in S1 based on image processing technology to obtain cutting parameters; S3, transmitting the cutting parameters to the cutting component, and driving the cutting component to cut the agarwood segment to be processed; S4, using the clamping component to rotate the agarwood segment to be processed by a fixed angle, and repeating steps S1-S3 to achieve the first level of rough processing; S5. The camera of the third industrial camera on the upper bracket is used to collect the image data of the rough-processed material, and the hook cutter operation area Q is marked according to the width of the hook cutter operation part. w ; S6. Identify the hook cutter operation area based on computer vision technology Q w White wood area Q in b , according to the white wood area Q b Passing hook cutter operation parameters to the hook cutter operation component; S7. According to the hooking requirements, according to the preset hook knife sinking parameter g, the hook knife sinks from the white wood area Q b The top position of the hook knife will be lowered to the white wood area Q b Use translation operation to achieve hooking of white wood area; S8, after performing the wire hooking operation, repeat step S7 until no white wood area is detected in the current wire hooking operation area; S9, rotating the workpiece by a fixed angle, and repeating steps S5-S8 to achieve the second level of fine processing.

3. The computer vision-based agarwood grading and processing method according to claim 1, characterized in that: The image processing and motor driving in steps S1-S9 are controlled by an embedded computing system in the base. The embedded computing system is a lightweight embedded system using an ARM architecture, and is equipped with an image processing module for processing image information of the cross sections on both sides of the agarwood segment to be processed. The operating parameters required in the calculation process are transmitted to the motors that control each operating component through the bus, thereby driving each operating component to perform the operation.

4. The computer vision-based agarwood grading and processing method according to claim 3, characterized in that: In step S2, the embedded computing system in the base is used to calculate the image information obtained in S1 based on image processing technology to obtain cutting parameters. The specific steps include: S21, processing the cross-sectional image of one side of the agarwood segment to be processed, and obtaining the distance L1 between the highest point of the agarwood and the clamping component; S21, processing the cross-sectional image of the other side of the agarwood segment to be processed, and obtaining the distance L2 between the highest point of the agarwood and the clamping component; S23, calculating cutting parameters: L = Max (L1, L2); The image processing technology includes identifying the agarwood part in the image information based on the threshold segmentation method in the CV image processing library, and then calculating the edge position of the agarwood part using the edge detection method, and calculating the cutting parameters according to the edge position parameters.

5. The computer vision-based agarwood grading and processing method according to claim 4, characterized in that: In step S3, the cutting parameters are transmitted to the cutting component, and the cutting component is driven to cut the agarwood segment to be processed. The specific steps include: S31, according to the cutting parameter L, using the lower bracket motor to drive the height of the cutting telescopic mechanism; S32. According to the adjusted height, the lower bracket motor is used to drive the cutting telescopic mechanism to translate through the lower bracket slide rail, and the cutting component is rotated at the same time to complete the cutting of the agarwood segment.

6. The computer vision-based agarwood grading and processing method according to claim 2, characterized in that: In step S4 and step S8, the agarwood segment to be processed is rotated by a fixed angle using a clamping component, and the fixed angle is 40 to 60 degrees.

7. The computer vision-based agarwood grading and processing method according to claim 2, characterized in that: In step S5, the camera of the third industrial camera of the upper bracket is used to collect image data of the rough-processed material, and the hook cutter operation area Q is marked according to the width of the hook cutter operation part. w Specifically, it includes: using the camera of the third industrial camera on the upper bracket to collect the top view image of the rough-processed material, and marking the hook cutter operation area Q according to the width of the hook cutter operation part w The width of the hook cutter operating component is between 2 and 5 mm.

8. The computer vision-based agarwood grading and processing method according to claim 2, characterized in that: In step S6, the hook cutter operation area Q is identified based on computer vision technology. w White wood area Q in b , according to the white wood area Q b Pass hook cutter operation parameters to the hook cutter operation component, including: S61. Identify the hook cutter operation area Q based on computer vision technology w The white wood area in the middle is marked as white wood area Q b ; S62, according to the identified white wood area Q b Calculate hook cutter operation parameters and transmit the hook cutter operation parameters to the hook cutter operation component; The computer vision technology includes using a convolutional neural network method to extract the hook cutter operation area Q w Middle Agarwood Area and White Wood Area Q b The image features of the agarwood area and the white wood area are mainly extracted by extracting color features and texture features. On this basis, the lightweight convolutional neural network model EfficientNet with an attention mechanism is trained and learned to construct the Q b The binary classification model identifies the hook cutter operation area Q w White wood area Q in b .

9. The computer vision-based agarwood grading and processing method according to claim 2, characterized in that: In step S7, according to the hooking requirement, the hook knife sinking parameter g is set from the white wood area Q b The top position of the hook knife will be lowered to the white wood area Q b The translation operation is used to realize the hooking of the white wood area. The specific steps include: S71, according to the obtained hook knife operation parameters, use the upper bracket motor and the upper bracket slide rail to align the hook knife operation component in the vertical direction with the white wood area Q b The right edge position; S72, using the hook knife telescopic mechanism to lower the hook knife operating component to the current highest position of the agarwood section, and further lowering it according to the hook knife sinking parameter g; S73, use hook knife operation parts to white wood area Q b Perform wire hooking operation; S74, when there are multiple white wood areas Q in step S52 b After finishing the hooking of each white wood area, raise the hooking knife operation part to the highest point of the agarwood segment, and then move it to the next white wood area Q b The right edge of the wire is lowered and the wire hooking operation is performed.

10. The computer vision-based agarwood grading and processing method according to claim 9, characterized in that: The hook cutter sinking parameter g is 0.05-0.1 mm.

Images