Visual online measuring method and system for weight of rejected sliver

Abstract

The invention discloses a visual on-line measuring method and system for weight of rejected slivers, and the method comprises the steps: collecting an image of the rejected slivers, and obtaining an image of the rejected slivers, the rejected slivers comprising the slivers and / or tobacco shreds; carrying out target detection on the rejected sliver object by adopting a machine vision target detection algorithm to obtain position information of a single material in the rejected sliver object; obtaining the area of the single material according to the position information of the single material; obtaining the weight of the single material according to the area information of the single material by using a pre-constructed area-weight measurement model; according to the weight information of the single material, the weight and proportion of the stem slivers and the cut tobacco in the stem sliver rejected object are calculated. According to the visual online measurement method and system for the weight of the rejected sliver, an online recognition-area calculation-weight online measurement system is constructed, the weight and proportion of the sliver and the cut tobacco are calculated in real time, the sliver rejection rate can be calculated rapidly and accurately, and a process value basis is provided for automatic control over cut stem separation.

Description

Technical Field

[0001] The present invention relates to the technical field of tobacco processing, and more specifically, to a visual online measurement method and system for the weight of rejected stems. Background Art

[0002] The control of stem shreds sorting in the cigarette making machine is an important part of quality and consumption management. The tobacco stems that cannot be completely removed from the tobacco sheets form a small amount of stem sticks after the shredding and drying stages. The hard and sharp stem sticks seriously affect the sensory and smoking quality of the finished cigarettes. The cigarette making machine uses a wind selection device to separate the tobacco shreds and stem sticks before the cigarettes are formed, which is the last step in the removal of stem sticks. The separated stem sticks are generally mixed with a small amount of tobacco shreds. If the stem stick removal rate is too low, the stem stick content of the cigarette will be too high, which may cause the weight deviation of the cigarette to increase, increase the probability of defects such as cigarette puncture, damage the combustion performance and sensory quality of the cigarette, and affect the stability of product quality; if the stem stick removal rate is too high, the tobacco shreds in the removed stem sticks will be too high, the tobacco consumption of the cigarette making machine will increase, and the effective utilization rate of tobacco shreds will be reduced.

[0003] At present, after the air selection process, cigarette factories mainly use manual sampling and random inspection to detect the silk content in stems and the amount of stem sticks removed. The efficiency of manual sampling is low, the management of the amount of stem sticks removed is relatively extensive, the consistency of measurement results from different people is poor, and the measurement accuracy needs to be improved.

[0004] Therefore, there is an urgent need for a visual online measurement method and system for the weight of rejected stems. Summary of the invention

[0005] The purpose of the present invention is to provide a visual online measurement method and system for the weight of rejected stems to solve the above-mentioned problems in the prior art. It can construct an online recognition-area calculation-weight online measurement system and calculate the weight and proportion of stems and tobacco in real time.

[0006] The present invention provides a visual online measurement method for the weight of rejected stems, which comprises the following steps:

[0007] Collecting an image of the stem-stick rejections to obtain a stem-stick rejection image, wherein the stem-stick rejections include stem sticks and / or shredded tobacco;

[0008] The machine vision target detection algorithm is used to detect the stem stick rejection objects and obtain the position information of a single piece of material in the stem stick rejection objects;

[0009] According to the position information of a single piece of material in the rejected stems, the area of ​​the single piece of material is obtained;

[0010] Using the pre-built area-weight measurement model, the weight of a single piece of material is obtained based on its area information;

[0011] Based on the weight information of a single piece of material, the weight and proportion of stems and shredded tobacco in the stem rejects are calculated.

[0012] In the above-mentioned visual online weight measurement method for stem-picked rejects, preferably, the collecting of images of the stem-picked rejects to obtain the stem-picked rejects image specifically includes:

[0013] The image of the stem-stick-removed object is collected by a high-definition camera to obtain the stem-stick-removed object image.

[0014] In the visual online measurement method for the weight of the rejected stems as described above, preferably, the single material comprises a single stem or shredded tobacco,

[0015] The method of using a machine vision target detection algorithm to detect the stem stick rejection target and obtain the position information of a single material in the stem stick rejection specifically includes:

[0016] Based on the PP-YOLOE machine vision target detection algorithm, the stem stick rejection object detection is performed to obtain the position information of a single material in the stem stick rejection object.

[0017] In the visual online weight measurement method for the rejected stems, preferably, the area of ​​a single stem is obtained according to the position information of the single stem in the rejected stems, which specifically includes:

[0018] Extract the outline of each single material according to the position information of each single material;

[0019] According to the contour information of each single material, the area of ​​each single material in the stem rejection is obtained.

[0020] In the visual online weight measurement method for rejected stems as described above, preferably, the extracting the contour of each single material according to the position information of each single material specifically includes:

[0021] Each single piece of material at the corresponding position is pre-processed to extract the outline of the tobacco stem.

[0022] In the visual online weight measurement method for rejecting stems as described above, preferably, the preprocessing includes at least one of image filtering processing, image grayscale processing, binarization processing and threshold segmentation processing.

[0023] In the visual online weight measurement method for the rejected stems, preferably, the step of obtaining the area of ​​each single material in the rejected stems according to the contour information of each single material comprises:

[0024] The area of ​​each single material is obtained according to the number of pixels and the pixel accuracy in the contour information corresponding to each single material.

[0025] The visual online measurement method for the weight of rejected stems as described above, wherein preferably, the weight of a single piece of material is obtained based on the area information of the single piece of material using a pre-built area-weight measurement model, specifically comprising:

[0026] Pre-established fitting functions for area and weight;

[0027] Substitute the area of ​​a single piece of material into the fitting function of area and weight to obtain the weight of the single piece of material.

[0028] In the visual online measurement method for the weight of the stem rejects as described above, preferably, the weight and proportion of the stems and shredded tobacco in the stem rejects are calculated based on the weight information of a single material, and specifically include:

[0029] The weights of the single pieces of material corresponding to the stem sticks in the stem stick rejection are added together to obtain the weight of the stem sticks in the stem stick rejection;

[0030] The weight of each single piece of tobacco in the stem rejects is added up to obtain the weight of the tobacco in the stem rejects;

[0031] According to the weight of the stems and the weight of the shredded tobacco in the stem rejects, the stem ratio and the shredded tobacco ratio in the stem rejects are obtained.

[0032] The present invention also provides a visual online weight measurement system for stem rejections using the above method, comprising:

[0033] A stem stick rejection object image acquisition module is used to acquire an image of the stem stick rejection object to obtain a stem stick rejection object image, wherein the stem stick rejection object includes stem sticks and / or shredded tobacco;

[0034] The stem stick rejection object detection module is used to detect the stem stick rejection object by using a machine vision object detection algorithm to obtain the position information of a single piece of material in the stem stick rejection object;

[0035] A single material area calculation module is used to obtain the area of ​​a single material according to the position information of the single material in the stem rejection;

[0036] A single material weight calculation module is used to obtain the weight of a single material based on the area information of the single material using a pre-built area-weight measurement model;

[0037] The weight and proportion calculation module is used to calculate the weight and proportion of stems and tobacco in the stem rejection materials based on the weight information of a single material.

[0038] The present invention provides a visual online measurement method and system for the weight of stem stick rejects, which adopts a machine vision target detection algorithm to detect stem stick rejects, obtain the position information of a single material in the stem stick rejects, and obtain the area and weight of the single material on this basis; then calculate the weight and proportion of the stem sticks and shredded tobacco in the stem stick rejects; by constructing an online recognition-area calculation-weight online measurement system, and calculating the weight and proportion of the stem sticks and shredded tobacco in real time, the stem stick rejection rate can be calculated quickly and accurately, and a process value basis is provided for the automatic control of stem and shredded tobacco separation. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described below with reference to the accompanying drawings, in which:

[0040] Figure 1 A flow chart of an embodiment of a visual online measurement method for the weight of rejected stems provided by the present invention;

[0041] Figure 2 The scatter point coordinates and linear fitting diagram of the area and weight of tobacco;

[0042] Figure 3 The scatter point coordinates and linear fitting diagram of the area and weight of tobacco stems;

[0043] Figure 4 is the fitting deviation diagram of tobacco cut;

[0044] Figure 5 is the fitted deviation plot of the stem signature;

[0045] Figure 6 This is a structural block diagram of an embodiment of a visual online measurement system for the weight of rejected stems provided by the present invention. DETAILED DESCRIPTION

[0046] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. The description of the exemplary embodiments is merely illustrative and is in no way intended to limit the present disclosure and its application or use. The present disclosure can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to make the present disclosure thorough and complete and to fully express the scope of the present disclosure to those skilled in the art. It should be noted that unless otherwise specifically stated, the relative arrangement of the components and steps, the composition of the materials, the numerical expressions and the numerical values ​​set forth in these embodiments should be interpreted as being merely exemplary and not as limiting.

[0047] The words "first", "second" and similar words used in this disclosure do not indicate any order, quantity or importance, but are only used to distinguish different parts. The words "include" or "comprises" and similar words mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of including other elements. "Up", "down" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0048] In the present disclosure, when a specific component is described as being located between a first component and a second component, there may or may not be an intermediate component between the specific component and the first component or the second component. When a specific component is described as being connected to other components, the specific component may be directly connected to the other components without an intermediate component, or may not be directly connected to the other components but have an intermediate component.

[0049] All terms (including technical terms or scientific terms) used in the present disclosure have the same meanings as those understood by ordinary technicians in the field to which the present disclosure belongs, unless otherwise specifically defined. It should also be understood that terms defined in general dictionaries, such as general dictionaries, should be interpreted as having meanings consistent with their meanings in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined herein.

[0050] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0051] like Figure 1 As shown, the visual online measurement method for the weight of rejected stems provided in this embodiment includes the following steps in actual implementation:

[0052] Step S1, collecting images of stem sticks to obtain images of stem sticks, wherein the stem sticks include stem sticks and / or shredded tobacco.

[0053] Specifically, the image of the stem stick rejection is collected by a high-definition camera to obtain the stem stick rejection image. In one embodiment of the present invention, the image of the stem stick rejection can be collected by a high-speed line scan CCD industrial camera. In a specific implementation, the stem stick rejection of the cigarette making machine can be first conveyed through a vibration trough, and then the stem stick rejection image can be collected by a high-speed line scan CCD industrial camera. The high-definition camera can ensure that a high-quality stem stick rejection image is obtained.

[0054] Step S2: using a machine vision target detection algorithm to detect the stem stick rejection objects, and obtaining the position information of a single stem stick rejection object.

[0055] Wherein, the single material includes a single stem or tobacco shreds. Specifically, stem rejection object detection is performed based on the PP-YOLOE machine vision target detection algorithm to obtain the position information of the single material in the stem rejection object. PP-YOLOE is one of the latest improved versions of the YOLO series. It is an improved and optimized version based on YOLOv5. PP-YOLOE uses a more powerful backbone network CSP RepResNet, which has better detection performance than YOLOv5. At the same time, PP-YOLOE introduces an adaptive feature fusion module PAN, which can effectively fuse features at different levels, helping to improve the accuracy and robustness of detection. PP-YOLOE also adds a multi-scale prediction mechanism to the network structure, which can simultaneously detect targets of different scales, thereby improving the accuracy and generalization ability of the model.

[0056] Step S3: obtaining the area of ​​a single piece of material according to the position information of the single piece of material in the rejected stems.

[0057] In one embodiment of the visual online measurement method for the weight of rejected stems of the present invention, the step S3 may specifically include:

[0058] Step S31, extracting the contour of each single material according to the position information of each single material.

[0059] Specifically, each single piece of material at the corresponding position is preprocessed to extract the outline of the tobacco stem, wherein the preprocessing includes at least one of image filtering, image grayscale processing, binarization processing and threshold segmentation processing.

[0060] Step S32: according to the contour information of each single piece of material, the area of ​​each single piece of material in the rejected stems is obtained.

[0061] Specifically, the area of ​​each single material is obtained according to the number of pixels and the pixel accuracy in the contour information corresponding to each single material.

[0062] Step S4: using the pre-built area-weight measurement model to obtain the weight of a single piece of material according to the area information of the single piece of material.

[0063] In one embodiment of the visual online measurement method for the weight of rejected stems of the present invention, the step S4 may specifically include:

[0064] Step S41, pre-establishing a fitting function of area and weight.

[0065] In one embodiment of the present invention, the fitting function of area and weight is a linear function. It should be noted that the present invention does not specifically limit the type of the fitting function of area and weight.

[0066] Step S42: Substitute the area of ​​a single piece of material into the fitting function of area and weight to obtain the weight of the single piece of material.

[0067] In one embodiment of the present invention, Figure 2 and Figure 3 As shown in the figure, the weight of a certain amount of tobacco is fitted with the area of ​​these fixed tobacco in the image to find the optimal fitting method between the weight of tobacco or tobacco stems and the area of ​​tobacco or tobacco stems. Let the area of ​​tobacco be x and the weight of tobacco be y. Through the fitting method, an optimal fitting model fit(x) is trained. After the fit(x) model is trained, the weight of tobacco and tobacco stems can be predicted by the area of ​​tobacco and tobacco stems. Figure 2 As shown in the figure, the fitting model corresponding to tobacco is y=0.0002x-0.0081, R 2 =0.9889; Figure 3 As shown in the figure, the fitting model corresponding to the stem signature is y=9E-05x-0.0479, R 2 =0.9938, therefore, the stem area and stem weight, as well as the tobacco area and tobacco weight basically conform to the linear fitting relationship. It is feasible to use the image area linear fitting method to measure the weight of tobacco or stems.

[0068] like Figure 4 and Figure 5 As shown in Figure 2, the area weight fitting accuracy of leaf silk and stem sticks was analyzed. Figure 4 As shown in Figure 2, the accuracy of the leaf weight fitted by the visual recognition algorithm is: average error per gram ±0.15g, as shown in Figure 2 Figure 5 As shown in the figure, the accuracy of the stem sticks is: average error per gram ±0.04g. Since the shape of the stem sticks is more stable than that of the tobacco, the relationship between the stem stick area and the stem stick weight is more consistent with the linear fitting relationship, and the fitting effect is better than that between the tobacco stick area and the tobacco stick weight.

[0069] Step S5: Calculate the weight and proportion of the stems and shredded tobacco in the stem rejects based on the weight information of the single tobacco.

[0070] In one embodiment of the visual online weight measurement method for stem rejections of the present invention, step S5 may specifically include:

[0071] Step S51, summing up the weights of the single pieces of material corresponding to the stem sticks in the rejected stem sticks to obtain the weight of the stem sticks in the rejected stem sticks.

[0072] Step S52: sum the weights of the single tobacco strands corresponding to the tobacco shreds in the stem and stick rejects to obtain the weight of the tobacco shreds in the stem and stick rejects.

[0073] Step S53: Obtaining the stem ratio and the tobacco ratio in the stem rejects according to the weight of the stems and the weight of the tobacco shreds in the stem rejects.

[0074] Specifically, the weight of the stems is divided by the sum of the weights of the stems and the shredded tobacco to obtain the proportion of the stems in the stem rejects, and the weight of the shredded tobacco is divided by the sum of the weights of the stems and the shredded tobacco to obtain the proportion of the shredded tobacco in the stem rejects.

[0075] The visual online measurement method for the weight of stem stick rejects provided in the embodiment of the present invention adopts a machine vision target detection algorithm to perform stem stick reject target detection, obtain the position information of a single material in the stem stick rejects, and on this basis obtain the area and weight of the single material; then calculate the weight and ratio of the stem sticks and shredded tobacco in the stem stick rejects; by constructing an online identification-area calculation-weight online measurement system, and calculating the weight and ratio of the stem sticks and shredded tobacco in real time, the stem stick rejection rate can be calculated quickly and accurately, providing a process value basis for the automatic control of stem and shredded tobacco separation.

[0076] Correspondingly, if Figure 6 As shown, the present invention also provides a visual online measurement system for the weight of rejected stems, comprising:

[0077] The stem stick rejection object image acquisition module 101 is used to acquire an image of the stem stick rejection object to obtain a stem stick rejection object image, wherein the stem stick rejection object includes stem sticks and / or shredded tobacco;

[0078] The stem stick rejection object detection module 102 is used to detect the stem stick rejection object by using a machine vision object detection algorithm to obtain the position information of a single piece of material in the stem stick rejection object;

[0079] The single material area calculation 103 is used to obtain the area of ​​the single material according to the position information of the single material in the stem rejection;

[0080] The single material weight calculation module 104 is used to obtain the weight of the single material according to the area information of the single material by using the pre-built area-weight measurement model;

[0081] The weight and ratio calculation module 105 is used to calculate the weight and ratio of stems and shredded tobacco in the stem rejects according to the weight information of a single tobacco stick.

[0082] The visual online metering system for the weight of stem stick rejects provided in the embodiment of the present invention adopts a machine vision target detection algorithm to perform target detection of stem stick rejects, obtains the position information of a single material in the stem stick rejects, and obtains the area and weight of the single material on this basis; then the weight and proportion of the stem sticks and shredded tobacco in the stem stick rejects are calculated; by constructing an online identification-area calculation-weight online measurement system, and calculating the weight and proportion of the stem sticks and shredded tobacco in real time, the stem stick rejection rate can be calculated quickly and accurately, providing a process value basis for the automatic control of stem and shredded tobacco separation.

[0083] So far, various embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0084] Although some specific embodiments of the present disclosure have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified or some technical features may be replaced by equivalents without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A visual online measurement method for the weight of rejected stems, characterized in that: include: Collecting an image of the stem-stick rejections to obtain a stem-stick rejection image, wherein the stem-stick rejections include stem sticks and / or shredded tobacco; The machine vision target detection algorithm is used to detect the stem stick rejection objects and obtain the position information of a single piece of material in the stem stick rejection objects; According to the position information of a single piece of material in the rejected stems, the area of ​​the single piece of material is obtained; Using the pre-built area-weight measurement model, the weight of a single piece of material is obtained based on its area information; Based on the weight information of a single piece of material, the weight and proportion of stems and shredded tobacco in the stem rejects are calculated.

2. The visual online measurement method for the weight of rejected stems according to claim 1 is characterized in that: The collecting of the image of the stem-stick-removed object to obtain the stem-stick-removed object image specifically includes: The image of the stem-stick-removed object is collected by a high-definition camera to obtain the stem-stick-removed object image.

3. The visual online measurement method for the weight of rejected stems according to claim 1 is characterized in that: The single material includes a single stem or a single tobacco shred. The method of using a machine vision target detection algorithm to detect the stem stick rejection target and obtain the position information of a single material in the stem stick rejection specifically includes: Based on the PP-YOLOE machine vision target detection algorithm, the stem stick rejection object detection is performed to obtain the position information of a single material in the stem stick rejection object.

4. The visual online measurement method for the weight of rejected stems according to claim 3 is characterized in that: The step of obtaining the area of ​​a single piece of material according to the position information of the single piece of material in the rejected stems specifically includes: Extract the outline of each single material according to the position information of each single material; According to the contour information of each single material, the area of ​​each single material in the stem rejection is obtained.

5. The visual online measurement method for the weight of rejected stems according to claim 4 is characterized in that: The step of extracting the contour of each single material according to the position information of each single material specifically includes: Each single piece of material at the corresponding position is pre-processed to extract the outline of the tobacco stem.

6. The visual online measurement method for the weight of rejected stems according to claim 5 is characterized in that: The preprocessing includes at least one of image filtering processing, image grayscale processing, binarization processing and threshold segmentation processing.

7. The visual online measurement method for the weight of rejected stems according to claim 4, characterized in that: The area of ​​each single material in the rejected stems is obtained according to the contour information of each single material, specifically including: The area of ​​each single material is obtained according to the number of pixels and the pixel accuracy in the contour information corresponding to each single material.

8. The visual online measurement method for the weight of rejected stems according to claim 1, characterized in that: The method of using the pre-built area-weight measurement model to obtain the weight of a single piece of material according to the area information of the single piece of material specifically includes: Pre-establish the fitting functions of area and weight; Substitute the area of ​​a single piece of material into the fitting function of area and weight to obtain the weight of the single piece of material.

9. The visual online measurement method for the weight of rejected stems according to claim 1, characterized in that: The step of calculating the weight and ratio of stems and shredded tobacco in the stem rejects according to the weight information of a single material specifically includes: The weights of the single pieces of material corresponding to the stem sticks in the stem stick rejection are added together to obtain the weight of the stem sticks in the stem stick rejection; The weight of each single piece of tobacco in the stem rejects is added up to obtain the weight of the tobacco in the stem rejects; According to the weight of the stems and the weight of the shredded tobacco in the stem rejects, the stem ratio and the shredded tobacco ratio in the stem rejects are obtained.

10. A visual online weight measurement system for stem rejections using the method described in any one of claims 1 to 9, characterized in that: include: A stem stick rejection object image acquisition module is used to acquire an image of the stem stick rejection object to obtain a stem stick rejection object image, wherein the stem stick rejection object includes stem sticks and / or shredded tobacco; The stem stick rejection object detection module is used to detect the stem stick rejection object by using a machine vision object detection algorithm to obtain the position information of a single piece of material in the stem stick rejection object; A single material area calculation module is used to obtain the area of ​​a single material according to the position information of the single material in the stem rejection; A single material weight calculation module is used to obtain the weight of a single material based on the area information of the single material using a pre-built area-weight measurement model; The weight and proportion calculation module is used to calculate the weight and proportion of stems and tobacco in the stem rejection materials based on the weight information of a single material.

Images