A detection method for automatically judging whether there are missing nails in the processing process based on the wooden board image

Abstract

The present invention provides a detection method for automatically judging whether there are missing nails in the processing process according to the wooden board image, which relates to the technical field of image data processing. This method takes the nail position detection algorithm in the single-chip microcomputer as the core, realizes the bidirectional communication between the PLC and the single-chip microcomputer through the RS-485 serial port, and transmits the relevant parameters of the wooden board processing to the single-chip microcomputer at the initial stage to complete the initialization of the internal program of the single-chip microcomputer. When the detection system starts, the camera captures the image data of the processed wooden board on the production line and transmits it to the single-chip microcomputer, and the nail position detection algorithm of the wooden board is used for detection, and the result is then returned to the PLC. The present invention can replace the cumbersome manual detection link, has high work efficiency and detection accuracy, and can effectively screen out the defective products with missing nails according to the wooden board image information.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and particularly to a detection method for automatically judging whether there are missing nails in the processing process according to a wooden board image. Background Art

[0002] As is well known, the processing of wooden boards is very common in life, and various wooden board processing factories cannot do without the processes of docking wooden boards and fixing them with nails. Under the conditions of today's fully automatic production line processing, it has become particularly important to be able to quickly and accurately inspect the processed products. However, due to the small size of nails and the different numbers in different processing schemes, it has caused great difficulties in automatic detection. Nowadays, many wooden board processing factories still use traditional manual detection, which requires workers to continuously pay attention to and inspect the processed products, which is not only quite time-consuming and laborious, but also has very low detection efficiency.

[0003] Therefore, it is necessary to design a detection system for automatically judging whether there are missing nails in the processing process according to a wooden board image to solve the above problems. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a detection method for automatically judging whether there are missing nails in the processing process according to a wooden board image.

[0005] A detection method for automatically judging whether there are missing nails in the processing process according to a wooden board image includes the following steps:

[0006] Step 1: Connect the PLC and the AT32 single-chip microcomputer through the serial port, and connect the camera of the shooting device to the pins of the AT32 single-chip microcomputer through the power cord, data line, and control line;

[0007] Step 2: Initialize the serial port of the single-chip microcomputer; configure the pins used for serial communication, enable the clock, set the working mode of the pins, and set the baud rate, data format, parity bit, and sending and receiving mode of the serial communication;

[0008] Step 3: Use the PLC to set the wooden board processing scheme on the production line, including the positions where the wooden board needs to be processed, and the number and shape of nails to be processed at each position; at the same time, transmit the set parameters to the single-chip microcomputer through the serial port, and after the single-chip microcomputer receives the parameters, assign them to each variable. If no new parameters are transmitted, the previous parameters are used by default without change;

[0009] Step 4: After the processing of the wooden board starts, the wooden board will be sent to the nail gun for processing in turn under the control of the PLC through the conveyor belt, and the processed product will be sent to the camera by the conveyor belt. The camera will collect the image of the processed product of the wooden board and transmit the collected image data to the single-chip microcomputer for waiting for detection;

[0010] Step 5: After receiving the image, the single-chip microcomputer will perform detection through the nail position detection algorithm for the wooden board, and based on the detection results, determine whether there are missing or missed nails on the wooden board. Then, the detection results will be transmitted to the PLC through the serial port and displayed by the PLC. The staff will judge whether there are missing nails on the wooden board according to the displayed detection situation. If there are missing nails, they will be replenished.

[0011] The steps of the nail position detection algorithm for the wooden board are as follows:

[0012] Step S1: The wooden board image is first grayscaled and then binarized, changing all pixel values in the image to 0 and 255, where 0 is black and 255 is white.

[0013] Step S2: According to the specifications and characteristics of the wooden board, image preprocessing is carried out. The wooden boards are divided into three types: standard, uneven surface, and multi-ribbed. For those with a flat surface and consisting of only one wooden board, they are classified as the standard wooden board type; for those with surfaces that are not all at the same horizontal plane, they are classified as the wooden board type with an uneven surface; for those composed of multiple wooden ribs spliced together, they are classified as the multi-ribbed wooden board type.

[0014] For the wooden board type with an uneven surface, screening limit conditions are set to remove the boundaries of the uneven surface and fill them with the pixel values of the standard wooden board plane. For the multi-ribbed wooden board type, void detection is carried out to fill the voids between the ribs of the wooden board.

[0015] Step S3: A wooden board edge extraction algorithm is set to find the edge position of the wooden board from the picture.

[0016] The wooden board edge extraction algorithm is as follows: The jumps of the picture pixels from black to white and from white to black are used as key information to judge the positions of the wooden board boundary pixels. If for a certain pixel, it and the n pixels on the left are all black, while the n pixels on the right are all white, it is regarded as a candidate point for the left boundary of the wooden board; if for a certain pixel, it and the n pixels on the right are all black, while the n pixels on the left are all white, it is regarded as a candidate point for the right boundary of the wooden board; if for a certain pixel, it and the n pixels above are all black, while the n pixels below are all white, it is regarded as a candidate point for the upper boundary of the wooden board; if for a certain pixel, it and the n pixels below are all black, while the n pixels above are all white, it is regarded as a candidate point for the lower boundary of the wooden board; if among the above left and right boundary candidate points, the m pixels above and below them are not black, they are regarded as noise points caused by uneven boundaries and are excluded from the candidate points; similarly, if among the above upper and lower boundary candidate points, the m pixels on the left and right are not black, they will also be excluded; the above m and n are both set parameters.

[0017] Step S4: Traverse the entire wooden board image through the wooden board edge extraction algorithm to obtain the coordinate sequences of candidate points on each boundary of the wooden board; take the minimum ordinate of the upper boundary sequence, the minimum abscissa of the left boundary sequence, the maximum ordinate of the lower boundary sequence, and the maximum abscissa of the right boundary sequence as the boundary reference values;

[0018] Step S5: According to the four boundary reference values obtained in Step S4, form the maximum circumscribed rectangle of the wooden board, and crop the image data outside the rectangle, only retaining the pixel information inside the rectangle;

[0019] Step S6: Fill the gaps between the wooden board boundary and the image boundary with white;

[0020] Step S7: Eliminate the interference points where the color of the wooden board is similar to that of the nails, and set the pixel features of the nails; regard the nail as a connected domain with a pixel number less than d, where d depends on the fixed position of the camera and the size of the nail itself, and limit the area of this connected domain and the length and width of the circumscribed rectangle of the connected domain: if the area of a certain connected domain on the wooden board, that is, the number of pixels is less than the area threshold s and the length and width of the circumscribed rectangle are both less than the length and width threshold t, then this connected domain is regarded as a nail; otherwise, if any one of the area or the length and width of the circumscribed rectangle does not meet the requirements, it is regarded as an interference point on the wooden board and is uniformly filled with white.

[0021] Step S8: Perform partitioning and in-region detection on the image obtained in Step S7;

[0022] The partitioning is as follows: the partitioning width is determined by the number of nail guns in the processing plan, and the partitioning length is obtained by converting the processing intervals of each region in the PLC processing plan through the scale corresponding to the image size and the actual wooden board size. The number of partitions that the wooden board image should be divided into is equal to the product of the number of nail guns on the horizontal axis and the number of processing positions on the vertical axis;

[0023] The in-region detection is as follows: the coordinate starting point of each partition corresponds to the wooden board processing position in the PLC set parameters, and zero-point correction is determined by comparing the starting point of the nailing area during the processing and the starting point of the wooden board boundary on the image.

[0024] Step S9: Perform connected domain detection on each partition in Step S8 separately to obtain the connected domain information in each partition, including the area of each connected domain, the length and width of the circumscribed rectangle, and the center coordinates. The number of connected domains that meet the nail connected domain characteristics is the number of nails detected in this partition;

[0025] Step S10: Summarize the detection results of all partitions, and judge whether there are missing nails in this partition according to the number of nails detected in each partition and the number of nails set for processing in each partition, and send the final detection result to the PLC through the serial port for display.

[0026] The beneficial effects of adopting the above technical solution are as follows:

[0027] The present invention provides a detection method for automatically judging whether there are missing nails in the processing process according to the wooden board image. The present invention can perform nail position detection on different types of wooden boards under the conditions of three-nail guns and five-nail guns. By taking pictures and performing image recognition on the processed wooden boards, the number of nails in each area of the wooden board is automatically detected, and the set value is compared to judge whether there are missing or leaking nails. During operation, no manual operation is required, which can replace the traditional cumbersome manual detection link, saving the time and energy of the staff and greatly improving work efficiency. In addition, since the processing parameters of the wooden board have been initialized into the AT32 single-chip microcomputer, different wooden boards and different processing schemes can be detected, and the compatibility and versatility are greatly improved. Brief Description of the Drawings

[0028] Figure 1 It is a flow chart of the method for detecting missing nails in the embodiment of the present invention.

[0029] Figure 2 It is a schematic diagram of the processing position and processing scheme of the wooden board by the PLC in the embodiment of the present invention.

[0030] Figure 3 It is a work flow chart of the wooden board nail position detection algorithm in the embodiment of the present invention.

[0031] Figure 4 It is a work flow chart of the wooden board edge extraction algorithm in the embodiment of the present invention.

[0032] Figure 5 It is the original wooden board image and the processed image in the embodiment of the present invention. Detailed Embodiments

[0033] The following combines the drawings and embodiments to further describe in detail the specific embodiments of the present invention. The following embodiments are used to illustrate the present invention, but not to limit the scope of the present invention.

[0034] A detection method for automatically judging whether there are missing nails in the processing process according to the wooden board image, as Figure 1 shown, includes the following steps:

[0035] Step 1: The hardware of this system consists of an S7-1500 type PLC, a shooting device, and an AT32 single-chip microcomputer; the S7-1500 type PLC and the AT32 single-chip microcomputer are connected through an RS-485 serial port, and the shooting device connects the camera to the pins of the AT32 single-chip microcomputer through a power line, a data line, and a control line. The shooting device is located above the outlet of the assembly line. After the detection system starts, it is responsible for capturing the image information of the processed wooden board and sending it to the single-chip microcomputer through the data line. For the transmission of the wooden board image.

[0036] Step 2: Initialize the serial port of the AT32 microcontroller; configure the pins used for serial communication, enable the clock, and set the working mode of the pins and set the baud rate, data format, parity bit, and transceiver mode of serial communication;

[0037] Use a two-way communication program to be responsible for the data exchange between the S7-1500 PLC and the AT32 microcontroller, mainly including the reception and transmission of internal data of the microcontroller. When the PLC sets parameters to be transmitted to the microcontroller through the RS-485 serial port, first the PLC sends a start bit to the serial port. When the microcontroller receives the start signal, if there is no higher-priority program being executed, it responds through the serial port interrupt to execute the interrupt subroutine to receive the data on the serial port. When the end flag bit is received, the data transmission is completed, and the microcontroller performs data verification according to the parity bit set during initialization to ensure correct reception.

[0038] Step 3: Use the S7-1500 type PLC to set the processing plan for the wooden boards on the production line, including the positions where the wooden boards need to be processed, and the number and shape of nails to be processed at each position, such as Figure 2 shown; at the same time, transmit the set parameters to the AT32 microcontroller through the RS-485 serial port. After the microcontroller receives the parameters, it assigns them to each variable. If no new parameters are transmitted, the previous parameters are used by default without change;

[0039] Step 4: After the processing of the wooden boards starts, the wooden boards will be sent to the nail gun for processing in sequence under the control of the PLC through the conveyor belt. The processed finished products will be sent to the camera by the conveyor belt. The camera will collect the images of the processed wooden board finished products and transmit the collected image data to the microcontroller for waiting for detection;

[0040] Step 5: After the microcontroller receives the image, it will perform detection through the wooden board nail position detection algorithm. According to the detection result, it will determine whether the wooden board is missing nails or has missed nails, and transmit the detection result to the PLC through the RS-485 serial port for display by the PLC. The staff will judge whether the wooden board is missing nails according to the displayed detection situation. If there are missing nails, they will be replenished.

[0041] The described wooden board nail position detection algorithm is as Figure 3 shown, and the steps are as follows:

[0042] Step S1: Perform grayscale and binarization processing on the wooden board image successively, changing all pixel values in the image to 0 and 255, where 0 is black and 255 is white, for subsequent feature detection and edge extraction. When binarizing, the threshold is set to the global adaptive threshold of the Otsu method. This threshold is automatically calculated according to the histogram of the bimodal image, which can greatly reduce the binarization difference caused by image factors and can obtain a better binarization effect.

[0043] Step S2: Perform image preprocessing according to the specifications and characteristics of the wooden board. The wooden boards are divided into three types: standard, uneven surface, and multi-ribbed. For those with a flat surface and consisting of only one wooden board, they are classified as the standard wooden board type. For those with surfaces that are not all at the same horizontal plane, they are classified as the uneven surface wooden board type. For those composed of multiple wooden ribs spliced together, they are classified as the multi-ribbed wooden board type;

[0044] For the uneven surface wooden board type, set screening limit conditions to remove the boundaries of the uneven surfaces and fill them with the pixel values of the standard wooden board plane. For the multi-ribbed wooden board type, perform void detection and fill the voids between the ribs of the wooden board. By eliminating the characteristics of each type of wooden board and assimilating them into one type, the error of edge extraction and nail position detection can be effectively reduced, and the versatility of the algorithm for nail position detection of various wooden boards can be greatly improved.

[0045] Step S3: Set an algorithm for extracting the edge of the wooden board to find the edge position of the wooden board from the picture;

[0046] The algorithm for extracting the edge of the wooden board is as Figure 4 shown. The jump of the pixel values of the picture from black to white and from white to black is used as the key information to judge the position of the boundary pixels of the wooden board: for a certain pixel, if itself and the n pixels on the left are all black, and the n pixels on the right are all white, it is regarded as a candidate point for the left boundary of the wooden board; for a certain pixel, if itself and the n pixels on the right are all black, and the n pixels on the left are all white, it is regarded as a candidate point for the right boundary of the wooden board; for a certain pixel, if itself and the n pixels above are all black, and the n pixels below are all white, it is regarded as a candidate point for the upper boundary of the wooden board; for a certain pixel, if itself and the n pixels below are all black, and the n pixels above are all white, it is regarded as a candidate point for the lower boundary of the wooden board. At the same time, to prevent errors caused by the unevenness of the wooden board boundary in the image, the following limitations are also set in the algorithm: if among the above-mentioned left and right boundary candidate points, the m pixels above and below them are not black, they are regarded as noise points caused by boundary unevenness and are excluded from the candidate points; similarly, if among the above-mentioned upper and lower boundary candidate points, the m pixels on the left and right of them are not black, they will also be excluded; the above m and n are both set parameters and are determined by the fixed position and relevant parameters of the camera.

[0047] This algorithm uses the jump of the pixel values of the picture from black to white and from white to black as the key information to judge the position of the boundary pixels of the wooden board, and uses the pixel changes of other surrounding points as the basis for eliminating the tilt error. When there are too many noise points in the image data and accurate edge information cannot be extracted, if the wooden board in the image captured by the vision module occupies a large proportion of the whole, and at this time the wooden board edge is close to the image edge, this algorithm approximates the original image edge as the wooden board edge for the algorithm to continue to execute;

[0048] Step S4: Traverse the entire wooden board image through the wooden board edge extraction algorithm to obtain the coordinate sequences of the candidate points on each boundary of the wooden board. Ideally, in the sequences corresponding to the left and right boundaries, the vertical coordinates should all be equal; in the sequences corresponding to the upper and lower boundaries, the horizontal coordinates should be equal. However, considering the shooting angle of the camera, each boundary may be inclined and may not be equal under actual conditions. Take the minimum vertical coordinate of the upper boundary sequence, the minimum horizontal coordinate of the left boundary sequence, the maximum vertical coordinate of the lower boundary sequence, and the maximum horizontal coordinate of the right boundary sequence as the boundary reference values; to ensure that the main body of the wooden board can be completely retained in the image when the image is cropped later.

[0049] Step S5: According to the four boundary reference values obtained in Step S4, form the maximum circumscribed rectangle of the wooden board, crop the image data outside the rectangle, and only retain the pixel information inside the rectangle;

[0050] Step S6: Ideally, the boundary of the cropped image should be equal to the boundary of the wooden board. Considering the influence of the inclination angle during shooting, there may be a gap between the boundary of the wooden board and the boundary of the image after cropping. For the convenience of subsequent processing, fill the gap between the boundary of the wooden board and the boundary of the image with white; at this time, an image with a white background and black nails is obtained;

[0051] Step S7: Eliminate the interference points where the color of the wooden board is similar to that of the nails, and set the pixel characteristics of the nails; regard the nail as a connected domain with a pixel number less than d, where d depends on the fixed position of the camera and the size of the nail itself, and limit the area of this connected domain and the length and width of the circumscribed rectangle of the connected domain: If the area of a connected domain on the wooden board, that is, the number of pixels is less than the area threshold s and the length and width of the circumscribed rectangle are both less than the length and width threshold t, then this connected domain is regarded as a nail; otherwise, if any one of the area or the length and width of the circumscribed rectangle does not meet the requirements, it is regarded as an interference point on the wooden board and is uniformly filled with white. The area threshold s and the length and width threshold t are both determined by the camera position and related parameters.

[0052] Step S8: Considering that the nail position setting schemes for each position on the wooden board are different in the wooden board processing plan, partition the image obtained in Step S7 and perform in-region detection;

[0053] The partition is as follows: The partition width is determined by the number of nail guns in the processing plan, and the partition length is obtained by converting the processing intervals of each area in the PLC processing plan through the scale corresponding to the image size and the actual wooden board size. The number of partitions that the wooden board image should be divided into is equal to the product of the number of nail guns on the horizontal axis and the number of processing positions on the vertical axis, which can avoid detecting other irrelevant positions and can effectively improve the detection speed and detection efficiency.

[0054] The in-region detection is that the coordinate starting points of each sub-region correspond to the wood board processing positions in the PLC set parameters, and zero-point calibration is determined by comparing the starting point of the nailing area in the processing process and the starting point of the wood board boundary on the image.

[0055] Step S9: Perform connected component detection on each sub-region in Step S8 separately to obtain the connected component information in each sub-region, including the area of each connected component, the length and width of the circumscribed rectangle, and the center coordinates. The number of connected components that conform to the nail connected component characteristics is the number of nails detected in this sub-region.

[0056] Step S10: Summarize the detection results of all sub-regions, and judge whether there are missing nails in this sub-region according to the number of nails detected in each sub-region and the number of nails set for processing in each sub-region, and send the final detection result to the PLC through the RS-485 serial port for display. In the present invention, the original wood board image and the processed image are as Figure 5 shown. The algorithm successfully detects the number of nails on the wood board and compares it with Figure 1 the set positions and schemes to obtain the final detection result.

[0057] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A detection method for automatically judging whether there are missing nails in the processing process according to the wooden board image, characterized in that, The following steps are involved: Step 1: Connect the PLC and AT32 microcontroller through the serial port, and use the camera to connect the camera to the AT32 microcontroller pins through the power line, data line, and control line; Step 2: Initialize the serial port of the microcontroller; configure the pins used for serial communication, enable the clock, set the working mode of the pins and set the baud rate, data format, parity bit and transceiver mode of the serial communication; Step 3: Use PLC to set the wood processing plan on the production line, including the position of the wood to be processed, and the number and shape of nails to be processed at each position; at the same time, transmit the set parameters to the MCU through the serial port. After receiving the parameters, the MCU assigns them to each variable. If no new parameters are passed in, the previous parameters are used by default. Step 4: After the wood board processing starts, the wood board will be sent to the nail gun for processing through the conveyor belt under the control of PLC. The finished product will be sent to the camera by the conveyor belt. The camera will collect the image of the finished wood board and transmit the collected image data to the single-chip computer for detection; Step 5: After receiving the image, the single-chip microcomputer will detect it through the wooden board nail position detection algorithm, and determine whether the wooden board is missing nails or not according to the detection result. The detection result will be transmitted to the PLC through the serial port and displayed by the PLC. The staff will determine whether the wooden board is missing nails according to the displayed detection situation, and if so, add nails; The steps of the wooden board nail position detection algorithm described in step 5 are as follows: Step S1: grayscale and binarize the wooden board image, and change all pixel values ​​in the image to 0 and 255, where 0 is black and 255 is white; Step S2: Preprocess the image according to the specifications and characteristics of the wood board; the wood boards are divided into three types: standard, uneven surface and multi-ribbed wood boards: the wood boards with a flat surface and consisting of only one piece of wood board are classified as standard wood boards; the wood boards with surfaces that are not all on the same horizontal plane are classified as uneven surface wood boards; the wood boards composed of multiple wooden ribbed wood boards are classified as multi-ribbed wood boards; For wooden boards with uneven surfaces, set screening conditions to remove the uneven surface boundaries and fill them with the pixel values ​​of the standard wooden board plane. Check the gaps of multi-ribbed wood boards and fill the gaps between the ribs; Step S3: A board edge extraction algorithm is set to find the edge position of the board from the image; The wooden board edge extraction algorithm is as follows: The jumps of the picture pixels from black to white and from white to black are used as key information to judge the positions of the wooden board boundary pixels. For a certain pixel, if it and the n pixels on its left are all black, and the n pixels on its right are all white, it is regarded as a candidate point for the left boundary of the wooden board. For a certain pixel, if it and the n pixels on its right are all black, and the n pixels on its left are all white, it is regarded as a candidate point for the right boundary of the wooden board. For a certain pixel, if it and the n pixels above it are all black, and the n pixels below it are all white, it is regarded as a candidate point for the upper boundary of the wooden board. For a certain pixel, if it and the n pixels below it are all black, and the n pixels above it are all white, it is regarded as a candidate point for the lower boundary of the wooden board. If among the above left and right boundary candidate points, the m pixels above and below it are not black, it is regarded as noise points caused by uneven boundaries and is excluded from the candidate points. Similarly, if among the above upper and lower boundary candidate points, the m pixels on the left and right are not black, they will also be excluded. The above m and n are both set parameters. Step S4: Traverse the entire wooden board picture through the wooden board edge extraction algorithm to obtain the coordinate sequences of the candidate points for each boundary of the wooden board. Take the minimum ordinate of the upper boundary sequence, the minimum abscissa of the left boundary sequence, the maximum ordinate of the lower boundary sequence, and the maximum abscissa of the right boundary sequence as the boundary reference values. Step S5: According to the four boundary reference values obtained in step S4, form the maximum circumscribed rectangle of the wooden board, and crop the image data outside the rectangle, only retaining the pixel information inside the rectangle. Step S6: Fill the gap between the wooden board boundary and the image boundary with white. Step S7: Eliminate the interference points where the color of the wooden board is similar to that of the nails, and set the pixel characteristics of the nails. Regard the nail as a connected domain with a pixel number less than d. d depends on the fixed position of the camera and the size of the nail itself. Limit the area of this connected domain and the length and width of the circumscribed rectangle of the connected domain. If the area of a certain connected domain on the wooden board, that is, the number of pixels is less than the area threshold s and the length and width of the circumscribed rectangle are both less than the length and width threshold t, then this connected domain is regarded as a nail. Otherwise, if any one of the area or the length and width of the circumscribed rectangle does not meet the requirements, it is regarded as an interference point on the wooden board and is uniformly filled with white. Step S8: Divide the picture obtained in step S7 into regions and perform intra-region detection. Step S9: Perform connected domain detection on each region separately in step S8 to obtain the connected domain information in each region, including the area of each connected domain, the length and width of the circumscribed rectangle, and the center coordinates. The number of connected domains that meet the nail connected domain characteristics is the number of nails detected in this region. Step S10: Summarize the detection results of all regions, judge whether there are missing nails or missed nails in each region according to the number of nails detected in each region and the number of nails set for processing in each region, and send the final detection results to the PLC through the serial port for display.

2. The detection method for automatically judging whether there is a missing nail in the processing process according to the wooden board image as described in claim 1, characterized in that, The partition described in step S8 is such that the partition width is determined by the number of nail guns in the processing plan, and the partition length is obtained by converting the processing intervals of each area in the PLC processing plan according to the scale corresponding to the image size and the actual wooden board size. The number of partitions that the wooden board image should be divided into is equal to the product of the number of nail guns on the horizontal axis and the number of processing positions on the vertical axis; The in-zone detection is as follows: the coordinate starting point of each partition corresponds to the wooden board processing position in the PLC set parameters, and zero-point correction is determined by comparing the starting point of the nailing area during the processing process and the starting point of the wooden board boundary on the image.

Images