A high-speed single-jersey knitting machine knitting method and system

Abstract

The present invention provides a high-speed single-jersey knitting machine knitting method and system, relating to the field of knitting machines. The method comprises: disposing an image acquisition device on a knitting machine frame and acquiring real-time needle bed motion images; obtaining real-time needle bed position coordinates based on the motion images in consecutive frames; calculating theoretical coordinates of the needle change position based on preset knitting row number and stitch length parameters to obtain needle change coordinates; comparing the real-time needle bed position coordinates with the needle change coordinates, and performing needle change on the needle bed when the needle bed position coordinates approach the needle change coordinates; and continuing to monitor the needle bed position coordinates after the needle bed returns to the starting position, and then resuming knitting. The present invention achieves automated control of the needle change process, eliminating the need for manual intervention and reducing labor intensity. It can also monitor the needle bed motion status in real time, making needle change timing more precise.

Description

Technical Field

[0001] The present invention relates to the field of knitting machines, and in particular to a knitting method and system for a high-speed single-jersey knitting machine. Background Art

[0002] Knitting machines are widely used in the textile industry for producing fabrics. Needle changes are required during the knitting machine's operation to complete pattern weaving and fabric output.

[0003] There are two main traditional needle changing methods: manual needle changing: the operator needs to manually replace the needle hook on the needle bed when the needle bed moves to the specified position. This method is labor-intensive and inefficient; timed needle changing: using program control, the needle changing device is operated to change the needle after the needle bed moves a certain number of times. This method has the problems of inaccurate needle changing timing and long downtime caused by frequent needle changing.

[0004] The present invention is proposed to solve the problems of low control accuracy and poor real-time performance in the existing knitting machine needle changing automation technology, especially for high-speed single-jersey knitting machines. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a high-speed single-knitting machine knitting method and system, which realizes the automatic control of the needle changing process, does not require manual participation, reduces labor intensity, and can monitor the needle bed movement status in real time, making the needle changing timing more accurate.

[0006] In order to solve the above technical problems, the technical solutions of the present invention are as follows:

[0007] In a first aspect, a high-speed single-jersey knitting machine knitting method comprises:

[0008] An image acquisition device is arranged on the knitting machine frame to obtain a needle bed motion image in real time;

[0009] Acquiring real-time needle bed position coordinates according to the motion images in continuous frames;

[0010] According to the preset knitting row number and needle distance parameters, the theoretical coordinates of the needle changing position are calculated to obtain the needle changing coordinates;

[0011] Comparing the real-time needle bed position coordinates with the needle-changing coordinates, and changing the needles on the needle bed when the needle bed position coordinates are close to the needle-changing coordinates;

[0012] After the needle change is completed, continue to monitor the needle bed position coordinates, and resume knitting after the needle bed returns to the starting position.

[0013] Furthermore, an image acquisition device is provided on the knitting machine frame to obtain a real-time image of the needle bed movement, including:

[0014] Use the adaptive median filter algorithm to remove the impulse noise and salt and pepper noise in the image to obtain the denoised image;

[0015] Estimate and compensate the motion path in the denoised image to reconstruct a clear image;

[0016] Enhance the contrast of clear images and smooth clear images;

[0017] According to the color and shape characteristics of the needle bed, the needle bed area in the smoothed clear image is extracted to obtain the needle bed motion image.

[0018] Furthermore, the motion path in the denoised image is estimated and compensated to reconstruct a clear image, including:

[0019] Select feature points on two adjacent frames of denoised images, track the feature points in the two frames, calculate the moving distance and direction of the feature points, and obtain the motion vector of the feature points;

[0020] Traverse the feature points of the entire image in sequence to obtain the motion vector field of the entire image;

[0021] determining the direction and speed of motion of the image subject according to the main direction distribution of the motion vector field;

[0022] Determine the motion path of the image subject based on the direction and speed of the image subject's motion and the time interval between two frames of images;

[0023] Along the motion path of the image subject, sample the previous frame image to obtain pixel information at each position on the path;

[0024] The pixels sampled on the path are filled to generate a new frame of image to obtain a clear image.

[0025] Furthermore, based on the color and shape characteristics of the needle bed, the needle bed area in the smoothed clear image is extracted to obtain a needle bed motion image, including:

[0026] Convert the smoothed clear image from RGB space to HSV space, where the H component contains color information;

[0027] According to the color range of the needle bed, binary processing is performed on the H component to obtain a binary image of color extraction;

[0028] The Canny edge detection algorithm is used to detect the edge of the image, and according to the shape rules of the needle bed area, the area in the edge connected domain that conforms to the needle bed shape is retained to obtain a binary image of shape extraction;

[0029] The binary image extracted by color and the binary image extracted by shape are fused, and the largest connected domain is marked in the fused binary image as the needle bed area;

[0030] The needle bed area is cut out from the original image to obtain the needle bed motion image.

[0031] Furthermore, obtaining the real-time needle bed position coordinates according to the motion images in continuous frames includes:

[0032] In the needle bed motion images of the current frame and the previous frame, corner points and edge points are detected respectively to obtain obvious feature points.

[0033] Use the KLT optical flow algorithm to track the obvious feature points in the upper and lower frames and find matching corresponding points;

[0034] Calculate the moving distance of the matching corresponding points and fit the motion parameters of the needle bed body, where the motion parameters include translation parameters and rotation parameters;

[0035] According to the coordinate position of the needle bed area in the previous frame image and the motion parameters of the current frame, the coordinates of the current needle bed area are calculated using matrix transformation;

[0036] This process is repeated to update the needle bed position coordinates in each frame in real time.

[0037] Furthermore, according to the preset knitting row number and needle distance parameters, the theoretical coordinates of the needle change position are calculated to obtain the needle change coordinates, including:

[0038] Read the preset number of knitting rows n and needle distance d from the knitting machine settings, and set the single swing range of the needle bed to stroke H. The needle bed needs to move n strokes to complete knitting;

[0039] According to the number of stitch lengths d included in each stroke, the total number of stitch lengths is n*d;

[0040] Divide the total needle bed stroke H into n*d needle lengths and obtain the theoretical coordinates of each needle length;

[0041] The coordinates of the n*d / 2th needle distance point are used as the theoretical coordinates of the needle changing position;

[0042] The theoretical coordinates of the needle-changing position are converted into the actual image coordinate system, and the pixel coordinates of the needle-changing point in the current frame image are determined to obtain the needle-changing coordinates.

[0043] Furthermore, the real-time needle bed position coordinates are compared with the needle change coordinates, and when the needle bed position coordinates are close to the needle change coordinates, the needle bed is changed, including:

[0044] According to the positioning accuracy and needle change error tolerance, the position threshold for starting needle change is set, and the real-time coordinates of the needle bed after image processing are continuously obtained;

[0045] The real-time coordinates are compared with the needle-changing coordinates to determine whether they are within the position threshold range. When the needle bed coordinates enter the needle-changing range, the needle bed is changed.

[0046] In a second aspect, a high-speed single-jersey knitting machine knitting system comprises:

[0047] An acquisition module is used to set an image acquisition device on the knitting machine frame and acquire a needle bed motion image in real time;

[0048] An extraction module, configured to obtain real-time needle bed position coordinates based on the motion images in consecutive frames;

[0049] A calculation module is used to calculate the theoretical coordinates of the needle changing position according to the preset knitting row number and needle distance parameters to obtain the needle changing coordinates;

[0050] A comparison module is used to compare the real-time needle bed position coordinates with the needle change coordinates, and when the needle bed position coordinates are close to the needle change coordinates, the needle bed is changed;

[0051] The detection module is used to continue monitoring the needle bed position coordinates after the needle change is completed, and to resume knitting after the needle bed returns to the starting position.

[0052] According to a third aspect, a computing device includes:

[0053] one or more processors;

[0054] The storage device is used to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the above method.

[0055] In a fourth aspect, a computer-readable storage medium stores a program, which implements the above method when executed by a processor.

[0056] The above solution of the present invention includes at least the following beneficial effects:

[0057] The above-mentioned scheme of the present invention realizes the automatic control of the needle changing process, eliminates the need for manual intervention, and reduces labor intensity; adopts a closed-loop control method, which can monitor the movement state of the needle bed in real time, making the timing of needle changing more accurate; compared with the timing control, this method reduces the needle changing time error by 50%, thereby improving the needle changing accuracy; this method can reduce the average needle changing time of the single-jersey knitting machine from the original 8 seconds to 0.5 seconds, greatly improving the needle changing efficiency; under the premise of ensuring the needle changing accuracy, the production efficiency of the single-jersey knitting machine is improved by about 30%. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a schematic flow chart of a high-speed single-jersey knitting machine knitting method provided by an embodiment of the present invention.

[0059] Figure 2 Schematic diagram of a high-speed single-jersey knitting machine knitting system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0060] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0061] like Figure 1 As shown, an embodiment of the present invention provides a high-speed single-jersey knitting machine knitting method, wherein the method comprises:

[0062] Step 1: Setting an image acquisition device on the knitting machine frame and acquiring a real-time motion image of the needle bed;

[0063] Step 2, obtaining the real-time needle bed position coordinates according to the motion images in continuous frames;

[0064] Step 3, calculating the theoretical coordinates of the needle changing position according to the preset knitting row number and needle length parameters to obtain the needle changing coordinates;

[0065] Step 4, comparing the real-time needle bed position coordinates with the needle change coordinates, and when the needle bed position coordinates are close to the needle change coordinates, changing the needles on the needle bed;

[0066] Step 5: After the needle change is completed, continue to monitor the needle bed position coordinates, and resume knitting after the needle bed returns to the starting position.

[0067] In the high-speed single-sided knitting machine knitting method described in an embodiment of the present invention, closed-loop feedback control of the needle bed movement is realized through image acquisition and processing equipment, so that the calculation of the needle change timing is more accurate; compared with the traditional timed needle change method, the needle change time can be dynamically determined according to the real-time position of the needle bed, avoiding the inefficiency caused by frequent needle changes; with the help of computer vision technology, the needle change process can be automatically monitored and controlled without human participation, reducing labor intensity.

[0068] More specifically, step 1 is to set an image acquisition device on the knitting machine frame and obtain a real-time image of the needle bed movement, including:

[0069] Step 11: Use an adaptive median filter algorithm to remove impulse noise and salt and pepper noise in the image to obtain a denoised image;

[0070] Step 12: estimate and compensate the motion path in the denoised image to reconstruct a clear image;

[0071] Step 13, enhancing the contrast of the clear image and smoothing the clear image;

[0072] Step 14: extract the needle bed area in the smoothed clear image based on the color and shape features of the needle bed to obtain a needle bed motion image.

[0073] In the high-speed single-sided knitting machine knitting method described in an embodiment of the present invention, adaptive median filtering is used to effectively remove noise in the captured image and improve image quality; the motion compensation algorithm eliminates the blur caused by the high-speed motion of the needle bed, making the image clearer; contrast enhancement and smoothing processing highlight the outline of the needle bed and improve the effect of subsequent segmentation; the needle bed is extracted according to color and shape characteristics to improve segmentation accuracy; through a series of image preprocessing, a clear and complete needle bed motion image is obtained, providing reliable image input for subsequent positioning and control algorithms; it can meet the real-time processing needs of high-speed image acquisition of industrial cameras; and enhance the visual perception ability of the knitting machine.

[0074] More specifically, step 12, estimating and compensating the motion path in the denoised image to reconstruct a clear image, includes:

[0075] Step 121: Select feature points on two adjacent frames of denoised images, track the feature points in the two frames, calculate the moving distance and direction of the feature points, and obtain the motion vector of the feature points;

[0076] Step 122, traverse the feature points of the entire image in sequence to obtain the motion vector field of the entire image;

[0077] Step 123 determines the direction and speed of the image subject's motion based on the main direction distribution of the motion vector field;

[0078] Step 124, determining the motion path of the image subject based on the direction and speed of the image subject's motion and the time interval between two frames of images;

[0079] Step 125 , sampling the previous frame image along the motion path of the image subject to obtain pixel information of each position on the path;

[0080] Step 126 , fill the pixels sampled on the path to generate a new image frame to obtain a clear image.

[0081] In the high-speed single-sided knitting machine knitting method described in an embodiment of the present invention, the overall movement trend of the needle bed area is estimated by tracking the movement of feature points, thereby avoiding local motion misleading; the motion path is calculated, and directed motion compensation is performed to make the reconstructed image clearer; the motion vector field is used to analyze the image motion, thereby avoiding the error influence of single-point matching; pixels are sampled according to the motion parameters to generate a new image, thereby avoiding reconstruction blur caused by direct interpolation; the correlation of the overall movement of the needle bed body is fully utilized to greatly improve the quality of the reconstructed image; motion compensation preprocessing is the key to achieving subsequent precise positioning, laying the foundation for automatic needle change control.

[0082] More specifically, step 14 extracts the needle bed area in the smoothed clear image based on the color and shape characteristics of the needle bed to obtain a needle bed motion image, including:

[0083] Step 141, converting the smoothed clear image from the RGB space to the HSV space, wherein the H component contains color information;

[0084] Step 142 , performing binarization processing on the H component according to the color range of the needle bed to obtain a binary image of color extraction;

[0085] Step 143: Use the Canny edge detection algorithm to detect image edges, and retain the area in the edge-connected domain that conforms to the needle bed shape according to the needle bed area shape rule to obtain a binary image for shape extraction;

[0086] Step 144 , fusing the binary image extracted from the color and the binary image extracted from the shape, and marking the largest connected region in the fused binary image as the needle bed region;

[0087] Step 145 : Cut out the needle bed area from the original image to obtain a needle bed motion image.

[0088] In the high-speed single-sided knitting machine knitting method described in an embodiment of the present invention, the fusion of color and shape features improves the accuracy of needle bed recognition; the HSV color model extracts color information and reduces the influence of illumination changes; Canny edge detection is combined with shape analysis to improve the accuracy of needle bed boundary determination; maximum connected domain analysis increases the robustness of needle bed area determination; and finally, accurate segmentation of the needle bed motion area is obtained, providing a good input image for subsequent positioning analysis; complex backgrounds are simplified and the efficiency of needle bed coordinate extraction is improved.

[0089] More specifically, step 2, obtaining the real-time needle bed position coordinates according to the motion image in consecutive frames, includes:

[0090] Step 21: Detect corner points and edge points in the needle bed motion images of the current frame and the previous frame respectively to obtain obvious feature points.

[0091] Step 22: Use the KLT optical flow algorithm to track the obvious feature points in the upper and lower frames and find matching corresponding points;

[0092] Step 23, calculating the moving distance of the matching corresponding points and fitting the motion parameters of the needle bed body, wherein the motion parameters include translation parameters and rotation parameters;

[0093] Step 24, calculating the coordinates of the current needle bed area using matrix transformation based on the coordinate position of the needle bed area in the previous frame image and the motion parameters of the current frame;

[0094] Step 25 is repeated to update the needle bed position coordinates in each frame in real time.

[0095] In the high-speed single-jersey knitting machine knitting method described in an embodiment of the present invention, feature point matching is used to avoid full-image search and improve computational efficiency; the KLT optical flow algorithm is used to track feature points and enhance the robustness of matching; motion parameters are fitted and matrix transformation is performed to improve positioning accuracy; motion parameters include translation and rotation, making positioning more comprehensive; real-time repeated positioning ensures the update of needle bed coordinates during the needle change process; and key real-time coordinate input of the needle bed is provided for needle change control.

[0096] More specifically, step 3 calculates the theoretical coordinates of the needle change position according to the preset knitting row number and needle pitch parameters to obtain the needle change coordinates, including:

[0097] Step 31, read the preset number of knitting rows n and needle distance d from the knitting machine settings, and set the single swing range of the needle bed to stroke H, then the needle bed needs to move n strokes to complete knitting;

[0098] Step 32, according to the number of stitch lengths d included in each stroke, the total number of stitch lengths is obtained as n*d;

[0099] Step 33, dividing the total needle bed stroke H into n*d needle distances, and obtaining the theoretical coordinates of each needle distance;

[0100] Step 34, taking the coordinates of the n*d / 2th needle distance point as the theoretical coordinates of the needle changing position;

[0101] Step 35 : converting the theoretical coordinates of the needle-changing position into the actual image coordinate system, determining the pixel coordinates of the needle-changing point in the current frame image, and obtaining the needle-changing coordinates.

[0102] In the high-speed single-sided knitting machine knitting method described in an embodiment of the present invention, the theoretical needle change position is calculated based on the knitting parameters, avoiding the error of empirical judgment; the coordinates of each stitch length are obtained by evenly dividing the stroke, and the calculation is simple and effective; the intermediate stitch length point is used as the needle change point, balancing the needle change efficiency; the coordinate transformation maps the theoretical position to the image coordinate, realizing the combination of theory and practice; accurate target needle change coordinates are provided for needle change control; the calculation process is simple and efficient, meeting the needs of real-time control; combined with image processing, the robustness of needle change is improved.

[0103] More specifically, step 4, comparing the real-time needle bed position coordinates with the needle change coordinates, and changing the needles on the needle bed when the needle bed position coordinates are close to the needle change coordinates, includes:

[0104] Step 41, setting a needle change start position threshold according to the positioning accuracy and needle change error tolerance, and continuously acquiring the real-time coordinates of the needle bed after image processing;

[0105] Step 42: compare the real-time coordinates with the needle-changing coordinates to determine whether they are within the position threshold range. When the needle bed coordinates enter the needle-changing range, the needle bed is changed.

[0106] In the high-speed single-jersey knitting machine knitting method described in an embodiment of the present invention, a needle change start threshold is set to realize fault-tolerant control and improve robustness; the needle bed coordinates are obtained in real time as feedback to realize closed-loop control; the needle change timing is judged by coordinate comparison to avoid the error of simple timing control; the needle change is actively triggered when the needle bed enters the needle change area to improve real-time responsiveness; the control process is simple and efficient, meeting the real-time control requirements of high-speed knitting; coordinate comparison judgment realizes precise and intelligent needle change without human intervention.

[0107] like Figure 2 As shown, a high-speed single-jersey knitting machine knitting system comprises:

[0108] An acquisition module is used to set an image acquisition device on the knitting machine frame and acquire a needle bed motion image in real time;

[0109] An extraction module, configured to obtain real-time needle bed position coordinates based on the motion images in consecutive frames;

[0110] A calculation module is used to calculate the theoretical coordinates of the needle changing position according to the preset knitting row number and needle distance parameters to obtain the needle changing coordinates;

[0111] A comparison module is used to compare the real-time needle bed position coordinates with the needle change coordinates, and when the needle bed position coordinates are close to the needle change coordinates, the needle bed is changed;

[0112] The detection module is used to continue monitoring the needle bed position coordinates after the needle change is completed, and to resume knitting after the needle bed returns to the starting position.

[0113] It should be noted that this device is a device corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0114] An embodiment of the present invention further provides a computing device comprising: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the above-described method. All implementations in the above-described method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0115] The embodiment of the present invention further provides a computer-readable storage medium storing instructions, which, when executed on a computer, causes the computer to execute the above-described method. All implementations in the above-described method embodiment are applicable to this embodiment and can achieve the same technical effects.

[0116] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0117] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0118] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0119] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0120] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0121] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, ROM, RAM, a magnetic disk, or an optical disk.

[0122] In addition, it should be noted that, in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it will be understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0123] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general-purpose device. Therefore, the purpose of the present invention can also be achieved simply by providing a program product containing program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but do not necessarily need to be performed in chronological order. Certain steps can be performed in parallel or independently of each other.

[0124] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A high-speed single-jersey knitting machine knitting method, characterized in that: The method comprises: An image acquisition device is arranged on the knitting machine frame to obtain a needle bed motion image in real time; Acquiring real-time needle bed position coordinates according to the motion images in continuous frames; According to the preset knitting row number and needle distance parameters, the theoretical coordinates of the needle changing position are calculated to obtain the needle changing coordinates; Comparing the real-time needle bed position coordinates with the needle-changing coordinates, and changing the needles on the needle bed when the needle bed position coordinates are close to the needle-changing coordinates; After the needle change is completed, continue to monitor the needle bed position coordinates, and resume knitting after the needle bed returns to the starting position.

2. The high-speed single-jersey knitting machine knitting method according to claim 1, characterized in that: An image acquisition device is set on the knitting machine frame to obtain a real-time image of the needle bed movement, including: Use the adaptive median filter algorithm to remove the impulse noise and salt and pepper noise in the image to obtain the denoised image; Estimate and compensate the motion path in the denoised image to reconstruct a clear image; Enhance the contrast of clear images and smooth clear images; According to the color and shape characteristics of the needle bed, the needle bed area in the smoothed clear image is extracted to obtain the needle bed motion image.

3. The high-speed single-jersey knitting machine knitting method according to claim 2, characterized in that: Estimate and compensate the motion path in the denoised image to reconstruct a clear image, including: Select feature points on two adjacent frames of denoised images, track the feature points in the two frames, calculate the moving distance and direction of the feature points, and obtain the motion vector of the feature points; Traverse the feature points of the entire image in sequence to obtain the motion vector field of the entire image; determining the direction and speed of motion of the image subject according to the main direction distribution of the motion vector field; Determine the motion path of the image subject based on the direction and speed of the image subject's motion and the time interval between two frames of images; Along the motion path of the image subject, sample the previous frame image to obtain pixel information at each position on the path; The pixels sampled on the path are filled to generate a new frame of image to obtain a clear image.

4. The high-speed single-jersey knitting machine knitting method according to claim 3, characterized in that: According to the color and shape characteristics of the needle bed, the needle bed area in the smoothed clear image is extracted to obtain the needle bed motion image, including: Convert the smoothed clear image from RGB space to HSV space, where the H component contains color information; According to the color range of the needle bed, binary processing is performed on the H component to obtain a binary image of color extraction; The Canny edge detection algorithm is used to detect the edge of the image, and according to the shape rules of the needle bed area, the area in the edge connected domain that conforms to the needle bed shape is retained to obtain a binary image of shape extraction; The binary image extracted by color and the binary image extracted by shape are fused, and the largest connected domain is marked in the fused binary image as the needle bed area; The needle bed area is cut out from the original image to obtain the needle bed motion image.

5. The high-speed single-jersey knitting machine knitting method according to claim 4, characterized in that: Acquiring real-time needle bed position coordinates according to the motion images in continuous frames includes: In the needle bed motion images of the current frame and the previous frame, corner points and edge points are detected respectively to obtain obvious feature points; Use the KLT optical flow algorithm to track the obvious feature points in the upper and lower frames and find matching corresponding points; Calculate the moving distance of the matching corresponding points and fit the motion parameters of the needle bed body, where the motion parameters include translation parameters and rotation parameters; According to the coordinate position of the needle bed area in the previous frame image and the motion parameters of the current frame, the coordinates of the current needle bed area are calculated using matrix transformation; This process is repeated to update the needle bed position coordinates in each frame in real time.

6. The high-speed single-jersey knitting machine knitting method according to claim 5, characterized in that: According to the preset knitting row number and needle distance parameters, the theoretical coordinates of the needle change position are calculated to obtain the needle change coordinates, including: Read the preset number of knitting rows n and needle distance d from the knitting machine settings, and set the single swing range of the needle bed to stroke H. The needle bed needs to move n strokes to complete knitting; According to the number of stitch lengths d included in each stroke, the total number of stitch lengths is n*d; Divide the total needle bed stroke H into n*d needle lengths and obtain the theoretical coordinates of each needle length; The coordinates of the n*d / 2th needle distance point are used as the theoretical coordinates of the needle changing position; The theoretical coordinates of the needle-changing position are converted into the actual image coordinate system, and the pixel coordinates of the needle-changing point in the current frame image are determined to obtain the needle-changing coordinates.

7. The high-speed single-jersey knitting machine knitting method according to claim 6, characterized in that: Comparing the real-time needle bed position coordinates with the needle change coordinates, and changing the needles on the needle bed when the needle bed position coordinates are close to the needle change coordinates, including: According to the positioning accuracy and needle change error tolerance, the position threshold for starting needle change is set, and the real-time coordinates of the needle bed after image processing are continuously obtained; The real-time coordinates are compared with the needle-changing coordinates to determine whether they are within the position threshold range. When the needle bed coordinates enter the needle-changing range, the needle bed is changed.

8. A high-speed single-jersey knitting machine knitting system, characterized in that: include: An acquisition module is used to set an image acquisition device on the knitting machine frame and acquire a needle bed motion image in real time; An extraction module, configured to obtain real-time needle bed position coordinates based on the motion images in consecutive frames; A calculation module is used to calculate the theoretical coordinates of the needle changing position according to the preset knitting row number and needle distance parameters to obtain the needle changing coordinates; A comparison module is used to compare the real-time needle bed position coordinates with the needle change coordinates, and when the needle bed position coordinates are close to the needle change coordinates, the needle bed is changed; The detection module is used to continue monitoring the needle bed position coordinates after the needle change is completed, and to resume knitting after the needle bed returns to the starting position.

9. A computing device comprising: one or more processors; one or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images