A dynamic weighing-based vibrating groove shunting control method and device

Abstract

The application discloses a dynamic weighing-based vibration groove shunting control method and device, and the method is applied to a vibration groove. The vibration groove comprises an infrared moisture meter, a binocular camera and a shunting partition plate arranged on a tobacco stem transmission channel. The shunting partition plate is arranged to determine a rotation angle according to shunting requirements, so that the vibration groove can realize material shunting control according to requirements. Secondly, the corresponding tobacco stem flow is calculated according to the collected tobacco stem image, and the rotation angle of the shunting partition plate is dynamically adjusted in combination with the shunting requirements of the tobacco stem, thereby effectively guaranteeing the effectiveness and accuracy of the vibration groove shunting control.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of material distribution, and particularly relates to a vibrating trough distribution control method and device based on dynamic weighing. BACKGROUND

[0002] The tobacco industry belongs to a long-chain economy, and its chain links can include but are not limited to tobacco planting, cigarette production, processing, packaging, transportation and sales. After more than 30 years of development, the tobacco industry has gradually matured and deepened, but as the space for expansion becomes smaller and smaller, improving the level of fine production and management has become the only way to promote the high-quality development of the tobacco industry. At present, the industry has formed a framework based on intelligent equipment layer and digital production control as the upper layer of intelligence. On this basis, the main tobacco production line equipment suppliers in China have realized the intelligentization of some main equipment and the unitization of some process equipment.

[0003] As the main material conveying device in the tobacco cut filler preparation link, the vibrating trough needs to be uniformly fed or flexibly fed according to the production plan. However, the existing vibrating trough mainly controls the distribution amount of tobacco stems according to its width, and the distribution accuracy is poor, which cannot meet the demand for uniform feeding. In addition, the vibrating trough transmits materials in the form of vibration, which not only reduces the working accuracy of mechanical parts directly contacting the vibrating trough, but also affects the transportation accuracy of tobacco stems, thereby failing to guarantee the effectiveness and accuracy of vibrating trough distribution control. SUMMARY

[0004] To solve the technical defects of the existing vibrating trough, that is, the vibrating trough mainly controls the distribution amount of tobacco stems according to its width, the distribution accuracy is poor, and it is difficult to meet the demand for uniform feeding, and in addition, the vibrating trough transmits materials in the form of vibration, which not only reduces the working accuracy of mechanical parts directly contacting the vibrating trough, but also affects the transportation accuracy of tobacco stems, thereby failing to guarantee the effectiveness and accuracy of vibrating trough distribution control, the application provides a vibrating trough distribution control method and device based on dynamic weighing, and the technical scheme is as follows:

[0005] In a first aspect, the application embodiment provides a vibrating trough distribution control method based on dynamic weighing, which is applied to a vibrating trough. The vibrating trough includes an infrared moisture meter, a binocular camera and a distribution partition plate arranged on a tobacco stem transmission channel. The method comprises the following steps:

[0006] According to the distribution parameters of tobacco stems and the preset vibrating trough parameters, a first rotation angle of the distribution partition plate is determined.

[0007] The distribution partition plate is controlled to perform distribution processing on the tobacco stems on the tobacco stem transmission channel according to the first rotation angle, and two binocular cameras acquire initial tobacco stem images after the distribution processing on the tobacco stem transmission channel.

[0008] The initial tobacco stem images are recognized to obtain the volume of the tobacco stems in the tobacco stem transmission channel, and the tobacco stem moisture detected by the infrared moisture meter and the volume of the tobacco stems are used to obtain the tobacco stem flow corresponding to each binocular camera;

[0009] The second rotation angle of the shunt baffle is determined according to the two tobacco stem flows, the shunt parameter of the tobacco stems and the first rotation angle, and the shunt baffle is controlled to perform shunt processing on the tobacco stems in the tobacco stem transmission channel according to the second rotation angle.

[0010] In an optional solution of the first aspect, the initial tobacco stem images are recognized to obtain the volume of the tobacco stems in the tobacco stem transmission channel, including:

[0011] At least two corner points are extracted from each initial tobacco stem image, and the internal and external parameters and the distortion parameters of the corresponding binocular camera are obtained according to the coordinates of all the corner points;

[0012] A distortion correction mapping function is constructed based on the internal and external parameters and the distortion parameters of the binocular camera, and each initial tobacco stem image is subjected to distortion correction processing by the distortion correction mapping function to obtain a first corrected image;

[0013] A projection transformation matrix is constructed based on the internal and external parameters and the distortion parameters of the binocular camera, and each first corrected image is subjected to epipolar rectification processing by the projection transformation matrix to obtain a second corrected image;

[0014] The volume of the tobacco stems in the tobacco stem transmission channel is obtained according to each second corrected image and the corresponding initial tobacco stem image.

[0015] In another optional solution of the first aspect, the volume of the tobacco stems in the tobacco stem transmission channel is obtained according to each second corrected image and the corresponding initial tobacco stem image, including:

[0016] Each second corrected image is converted to obtain a binary image, and a connected block contour image is segmented from each binary image;

[0017] The connected block contour image is preprocessed, and the pixel distance value is obtained by performing adaptive distance transform processing on the preprocessed connected block contour image;

[0018] The binary image is scanned based on the pixel distance value to obtain a distance scan image, and the distance scan image is segmented to obtain a target tobacco stem image;

[0019] The volume of the tobacco stems in the tobacco stem transmission channel is obtained according to each target tobacco stem image and the corresponding initial tobacco stem image.

[0020] In a further optional implementation of the first aspect, the tobacco stem volume in the tobacco stem conveying channel is obtained according to each target tobacco stem image and the corresponding initial tobacco stem image, including:

[0021] The feature points of the tobacco stem are extracted from each target tobacco stem image, and the feature points of the tobacco stem are subjected to stereo matching processing to obtain pixel coordinates of the tobacco stem;

[0022] Based on the pixel coordinates of the tobacco stem and color information of the corresponding pixels in the initial tobacco stem image, a three-dimensional point cloud map of the tobacco stem is constructed;

[0023] The three-dimensional point cloud map of the tobacco stem is subjected to tetrahedral subdivision processing to obtain a tetrahedral mesh;

[0024] The tobacco stem volume in the tobacco stem conveying channel is calculated according to the vertex coordinates of the tetrahedral mesh.

[0025] In a further optional implementation of the first aspect, the tobacco stem flow corresponding to each binocular camera is obtained according to the tobacco stem moisture detected by the infrared moisture meter and the tobacco stem volume, including:

[0026] The actual density of the tobacco stem is calculated according to the tobacco stem moisture and a preset dry tobacco stem density;

[0027] The tobacco stem quality is obtained according to the tobacco stem volume and the actual density of the tobacco stem, and the tobacco stem flow corresponding to each binocular camera is determined based on the tobacco stem quality.

[0028] In a further optional implementation of the first aspect, the tobacco stem flow corresponding to each binocular camera is determined based on the tobacco stem quality, including:

[0029] The camera mapping distance is calculated based on the tobacco stem conveying channel width, the tobacco stem conveying channel length in each initial tobacco stem image, and a preset vibrating trough parameter;

[0030] The tobacco stem flow corresponding to each binocular camera is calculated according to the tobacco stem quality, the camera mapping distance, and a preset running rate.

[0031] In a further optional implementation of the first aspect, the second rotation angle of the shunt partition plate is determined according to the two tobacco stem flows, the shunt parameter of the tobacco stem, and the first rotation angle, including:

[0032] When it is detected that the ratio between the two tobacco stem flows is consistent with the shunt parameter of the tobacco stem, the first rotation angle is taken as the second rotation angle of the shunt partition plate;

[0033] When it is detected that the ratio between the two tobacco stem flows is inconsistent with the shunt parameter of the tobacco stem, the second rotation angle of the shunt partition plate is determined according to the two tobacco stem flows and the shunt parameter of the tobacco stem.

[0034] In a second aspect, the embodiments of the present application provide a dynamic weighing-based vibration groove shunt control device, which is applied to a vibration groove.

[0035] The first processing module is configured to determine a first rotation angle of the shunt partition plate according to the shunt parameters of the tobacco stems and preset vibration groove parameters.

[0036] The second processing module is configured to control the shunt partition plate to perform shunt processing on the tobacco stems on the tobacco stem transmission channel according to the first rotation angle, and obtain initial tobacco stem images after the shunt processing on the tobacco stem transmission channel by the two binocular cameras respectively.

[0037] The third processing module is configured to perform identification processing on each initial tobacco stem image to obtain the volume of the tobacco stems on the corresponding tobacco stem transmission channel, and obtain the tobacco stem flow corresponding to each binocular camera according to the moisture of the tobacco stems detected by the infrared moisture meter and the volume of the tobacco stems.

[0038] The fourth processing module is configured to determine a second rotation angle of the shunt partition plate according to the two tobacco stem flows, the shunt parameters of the tobacco stems and the first rotation angle, and control the shunt partition plate to perform shunt processing on the tobacco stems on the tobacco stem transmission channel according to the second rotation angle.

[0039] In a third aspect, the embodiments of the present application further provide a dynamic weighing-based vibration groove shunt control device, which comprises a processor and a memory.

[0040] The processor is connected with the memory.

[0041] The memory is configured to store executable program codes.

[0042] The processor runs a program corresponding to the executable program codes by reading the executable program codes stored in the memory, so as to implement the dynamic weighing-based vibration groove shunt control method provided in the first aspect of the embodiments of the present application or any one of the implementation manners of the first aspect.

[0043] In a fourth aspect, the embodiments of the present application provide a computer storage medium, which stores a computer program, and the computer program comprises program instructions. When the program instructions are executed by a processor, the dynamic weighing-based vibration groove shunt control method provided in the first aspect of the embodiments of the present application or any one of the implementation manners of the first aspect can be implemented.

[0044] In this embodiment, during the sluice gate diversion control, a first rotation angle of the diversion baffle is determined based on the diversion parameters of the tobacco stems and the preset sluice gate parameters. The diversion baffle is controlled to divert the tobacco stems in the tobacco stem transmission channel according to the first rotation angle, and two binocular cameras respectively acquire initial tobacco stem images after diversion processing in the tobacco stem transmission channel. Each initial tobacco stem image is processed to obtain the tobacco stem volume in the corresponding tobacco stem transmission channel, and the tobacco stem flow rate corresponding to each binocular camera is obtained based on the tobacco stem moisture and tobacco stem volume detected by the infrared moisture meter. Based on the two tobacco stem flow rates, the tobacco stem diversion parameters, and the first rotation angle, a second rotation angle of the diversion baffle is determined, and the diversion baffle is controlled to divert the tobacco stems in the tobacco stem transmission channel according to the second rotation angle. By setting a diversion baffle with a rotation angle determined according to diversion requirements, the material diversion control of the vibrating trough can be realized according to the requirements. Secondly, the corresponding tobacco stem flow rate is calculated based on the collected tobacco stem images, and the rotation angle of the diversion baffle is dynamically adjusted in combination with the tobacco stem diversion requirements, thereby effectively ensuring the effectiveness and accuracy of the diversion control of the vibrating trough. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 A flowchart illustrating an overall process for a vibratory trough diversion control method based on dynamic weighing, provided in an embodiment of this application.

[0047] Figure 2 This is a schematic diagram of a vibration groove structure provided in an embodiment of this application;

[0048] Figure 3 This is a schematic diagram of the structure of a flow divider provided in an embodiment of this application;

[0049] Figure 4 A schematic diagram of a vibratory trough diversion control device based on dynamic weighing is provided for an embodiment of this application;

[0050] Figure 5 This is a schematic diagram of another vibration trough diversion control device based on dynamic weighing provided in an embodiment of this application. Detailed Implementation

[0051] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0052] In the following description, the terms "first", "second", etc. are used only for the purpose of description, and should not be interpreted as indicating or implying relative importance. The following description provides a plurality of embodiments of the present application, which can be replaced or combined with each other, so that the present application can also be considered to include all possible combinations of the same and / or different embodiments described. Therefore, if one embodiment includes features A, B, C, and another embodiment includes features B, D, the present application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, even if the embodiment is not explicitly described in the following.

[0053] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes can be made to the functions and arrangements of described elements without departing from the scope of the present application. Various examples can appropriately omit, replace or add various processes or components. For example, the described methods can be performed in a different order from the described order, and various steps can be added, omitted or combined. In addition, features described with respect to some examples can be combined into other examples.

[0054] Since the material advances on the vibrating trough by vibration, the traditional contact type material weighing technology cannot be applied, and the existing several non-contact measurement technologies have certain defects when applied on the vibrating trough, such as but not limited to the capacitive sensing weighing technology capable of performing micro weighing, which realizes weighing by measuring the disturbance of an object passing through an electric field, but the technology application needs to build a static electric field model, which cannot guarantee the measurement accuracy under vibration conditions; such as but not limited to the nuclear weighing technology, which measures the weight data of the passing object by the stable release of gamma rays from a radioactive source, but this technology is mainly applied in the fields of coal, mines, etc., and is not applicable in the tobacco industry; such as but not limited to the ultrasonic weighing technology, which collects object displacement data by using ultrasonic level measurement technology and converts the weight by density, which is mainly applied in the fields of forklifts, cement, etc., but due to the various forms of tobacco stems and tobacco, the water content changes, so this technology is also not applicable in the tobacco industry.

[0055] In summary, the present application will guarantee the accuracy of the weight of the material on the vibrating trough through one or more embodiments shown as follows, and realize dynamic adjustment of the rotation angle of the shunt partition according to the shunting demand of tobacco stems, thereby effectively guaranteeing the effectiveness and accuracy of the vibrating trough shunt control.

[0056] Please refer to Figure 1 , Figure 1 The present application provides a vibrating trough shunt control method based on dynamic weighing.

[0057] As Figure 1 shown, the vibrating trough shunt control method based on dynamic weighing can at least include the following steps:

[0058] In step 102, a first rotation angle of the shunt partition is determined according to the shunt parameters of the tobacco stems and preset vibration chute parameters.

[0059] In the embodiment of the present application, the vibration chute shunt control method based on dynamic weighing can be applied in a control terminal, which can be used to control the material shunt process of the vibration chute. The tobacco stem transmission channel of the vibration chute can be provided with an infrared moisture meter, a binocular camera, and a shunt partition. The infrared moisture meter and the binocular camera can be arranged above the tobacco stem transmission channel through independent fixed supports to avoid the influence of the vibration working condition of the vibration chute on the working accuracy of the material shunt and dynamic weighing. The infrared moisture meter can be used to collect the moisture of the tobacco stems on the tobacco stem transmission channel, and the binocular camera can be used to collect the image of the tobacco stems on the tobacco stem transmission channel. Here, the shunt partition can be in contact with the tobacco stem transmission channel to shunt the tobacco stems on the tobacco stem transmission channel into two parts, that is, the tobacco stem transmission channel can be understood as being shunted into a left channel and a right channel. When there is a need for tobacco stem shunting, the extension piston rod of the lifting cylinder can push the lifting cylinder and the shunt partition to descend to the working position. At this time, the shunt partition is in contact with the tobacco stem transmission channel of the vibration chute. When there is no need for tobacco stem shunting, the retraction piston rod of the lifting cylinder can pull the lifting cylinder and the shunt partition to ascend to the non-working position. It should be noted that the tobacco stem shunting requirement in the embodiment of the present application can be understood as a flexible matching shunt parameter that meets the user's requirements. It can include but is not limited to the material shunt ratio set by the user or the automatically set material shunt ratio.

[0060] It can be understood that in order to more clearly and accurately obtain the image of the tobacco stems on the tobacco stem transmission channel, two binocular cameras can be provided in the embodiment of the present application to collect the corresponding images of the left channel and the right channel mentioned above, respectively, and the tobacco stem flow of each channel can be determined through recognition processing and other methods. The rotation angle of the shunt partition can be dynamically adjusted in combination with the shunt requirement of the tobacco stems to ensure the effectiveness and accuracy of the vibration chute shunt control.

[0061] Herein Figure 2 A vibration chute structure schematic diagram provided by the embodiment of the present application is shown in FIG. 1. As shown in FIG. 1, the vibration chute structure provided by the embodiment of the present application includes a vibration chute 1, a lifting cylinder 2, a shunt partition 3, an infrared moisture meter 4, and a binocular camera 5. Figure 2As shown, the vibration tank is provided with separately fixed front support and rear support on both sides of the tobacco stem transmission channel, the front support can be used to set the infrared moisture meter for collecting tobacco stem moisture, and the rear support can be used to set two binocular cameras for collecting tobacco stem images of the left channel and the right channel of the tobacco stem transmission channel respectively, and a fill light is also provided beside the two binocular cameras to improve the on-site light condition and improve the quality of the tobacco stem image. Here, the rear support can also be connected with the shunt partition plate through the lifting cylinder and the piston rod, so that the shunt partition plate can be in contact with the tobacco stem transmission channel of the vibration tank under the demand of tobacco stem shunting. When there is a demand for tobacco stem shunting, the piston rod of the lifting cylinder can be extended to push the lifting cylinder and the shunt partition plate to the working position (i.e. in contact with the tobacco stem transmission channel of the vibration tank); and when there is no demand for tobacco stem shunting, the piston rod of the lifting cylinder can be controlled to retract to pull the lifting cylinder and the shunt partition plate to the non-working position.

[0062] It can be understood that, Figure 2 As shown, the vibration tank can generate a control signal according to the production plan demand and send it to the motor, the motor controls the motor shaft and the flange coupling to rotate together, and the lifting cylinder and the shunt partition plate also rotate together under the driving of the flange coupling. The shunt partition plate rotating at different angles can change the tobacco stem flow of the left and right channels of the vibration tank to meet the flexible shunting demand of the actual production plan. Here, the two half shafts of the flange coupling are respectively connected with the motor shaft and the piston rod by keys. When the motor works, the motor shaft drives the flange coupling to rotate, the flange coupling drives the piston rod to rotate, the piston rod drives the lifting cylinder to rotate through the sealing ring, so that the shunt partition plate and the lifting cylinder rotate together, thereby ensuring that the tobacco stems on the vibration tank form a left-right quality proportional material flow through the shunt partition plate, and flow out from the front and rear discharge ports of the vibration tank.

[0063] In addition, after determining the tobacco stem flow of each channel through identification processing and other methods according to the tobacco stem images collected by the binocular cameras, the tobacco stem flow curve graphs of different channels can also be displayed on the display screen of the vibration tank, so that the operator can more intuitively know the tobacco stem shunting situation.

[0064] In order to ensure the vibration reduction effect of the shunt partition plate on the tobacco stem transmission channel and improve the control accuracy of the tobacco stem shunting, the vibration tank can also be provided with a damping device, as shown in Figure 3 As shown, the vibration tank can also be provided with a damping device, as shown in Figure 3As shown, the shunt partition plate can be composed of a spring, a top cover, an upper baffle and a lower baffle, the upper baffle is connected with the top cover through the spring, the both ends of the contact part are provided with slide rails, and the lower baffle is embedded in the upper baffle, wherein the upper baffle is made of rigid material, and the lower baffle is made of rubber flexible material. When the shunt device works, the lower baffle contacts the tobacco stem transmission channel of the vibrating groove, the rubber elasticity plays a buffering and damping role, and the shunt partition plate is always in contact with the surface of the vibrating groove to maintain good shunt function; at the same time, the upper baffle slides up and down along the slide rails, and the spring plays a buffering and damping role to effectively reduce the influence of the vibration of the vibrating groove on the shunt precision of the tobacco stem through two layers of damping.

[0065] Specifically, when the vibrating groove shunt control is performed, the shunt parameter of the corresponding tobacco stem can be determined according to the shunt demand of the user, that is, the shunt ratio between the left channel and the right channel of the tobacco stem transmission channel, and the first rotation angle of the shunt partition plate can be calculated in combination with the preset shunt correction coefficient and the vibrating groove parameter. Here, the vibrating groove parameter can include but is not limited to the width of the tobacco stem transmission channel of the vibrating groove and the length of the shunt partition plate, and in the process of calculating the first rotation angle of the shunt partition plate, the shunt parameter of the tobacco stem, the preset shunt correction coefficient, the width of the tobacco stem transmission channel of the vibrating groove and the length of the shunt partition plate can be substituted into the formula as shown below:

[0066]

[0067] In the above formula, may correspond to the first rotation angle of the shunt partition plate, may correspond to the preset shunt correction coefficient, k may correspond to the shunt parameter of the tobacco stem, L may correspond to the width of the tobacco stem transmission channel of the vibrating groove, and l may correspond to the length of the shunt partition plate.

[0068] It can be understood that the shunt partition plate can be but not limited to arranged on the central axis of the tobacco stem transmission channel, and one end of the shunt partition plate is driven to rotate by the piston rod, so that the shunt processing of the tobacco stem in the tobacco stem transmission channel is realized by the one end of the shunt partition plate, and the included angle between the shunt partition plate and the central axis of the tobacco stem transmission channel is the rotation angle of the shunt partition plate.

[0069] Step 104, control the shunt partition plate to perform shunt processing on the tobacco stem on the tobacco stem transmission channel according to the first rotation angle, and acquire the initial tobacco stem image on the tobacco stem transmission channel after the shunt processing by two binocular cameras respectively.

[0070] Specifically, after obtaining the first rotation angle of the shunt baffle according to the shunt demand of the user, the shunt baffle can be controlled to perform shunt processing on the tobacco stems on the tobacco stem transmission channel according to the first rotation angle, and when the left channel and the right channel of the tobacco stem transmission channel both start to transport the tobacco stems, the binocular camera corresponding to the left channel and the right channel respectively acquires the corresponding initial tobacco stem image, that is, an image containing the tobacco stems. It can be understood that, in order to effectively guarantee the shunt efficiency of the tobacco stems, the channel widths corresponding to the left channel and the right channel respectively in the embodiments of the present application can be kept consistent, and the tobacco stem flow rates corresponding to the left channel and the right channel respectively are affected by the rotation angle of the shunt baffle.

[0071] Here, in order to guarantee the real-time performance of the tobacco stem shunt control, the binocular camera can but not limited to be controlled to acquire the initial tobacco stem image at a preset time interval. The initial tobacco stem image can be understood as one frame of tobacco stem image or multiple frames of tobacco stem images, and the shooting angles corresponding to each frame of tobacco stem image in the multiple frames of tobacco stem images can be different, so as to facilitate the subsequent image recognition processing.

[0072] Step 106, performing recognition processing on each initial tobacco stem image to obtain the volume of the tobacco stems on the corresponding tobacco stem transmission channel, and obtaining the tobacco stem flow rate corresponding to each binocular camera according to the tobacco stem moisture detected by the infrared moisture meter and the volume of the tobacco stems.

[0073] Specifically, after the initial tobacco stem images are acquired by the binocular camera corresponding to the left channel of the tobacco stem transmission channel and the binocular camera corresponding to the right channel of the tobacco stem transmission channel respectively, recognition processing can be performed on each initial tobacco stem image to calculate the corresponding tobacco stem volume on the basis of obtaining clearer tobacco stem images, and further calculate the tobacco stem flow rate corresponding to each initial tobacco stem image in combination with the tobacco stem moisture value detected by the infrared moisture meter. In the process of performing recognition processing on each initial tobacco stem image, the processing modes can include but are not limited to preprocessing, correction processing, grayscale processing or segmentation processing, so as to segment the corrected and segmented clear tobacco stem image from the initial tobacco stem image.

[0074] It can be understood that the infrared moisture meter can synchronously acquire the tobacco stem moisture value on the tobacco stem transmission channel in the process of acquiring the tobacco stem images of the respective channels by the binocular cameras, and the infrared moisture meter can but not limited to directly acquire the moisture of all the tobacco stems input through the input end of the tobacco stem transmission channel, that is, the tobacco stem moisture value applied in the calculation process of the tobacco stem flow rate corresponding to each initial tobacco stem image is consistent.

[0075] As an option of the embodiments of the present application, the recognition processing on each initial tobacco stem image to obtain the volume of the tobacco stems on the corresponding tobacco stem transmission channel includes:

[0076] At least two corner points are extracted from each initial tobacco stem image, and internal and external parameters of a corresponding binocular camera and distortion parameters are obtained according to coordinates of all the corner points;

[0077] A distortion correction mapping function is constructed based on the internal and external parameters of the binocular camera and the distortion parameters, and each initial tobacco stem image is subjected to distortion correction processing by the distortion correction mapping function to obtain a first corrected image;

[0078] A projection transformation matrix is constructed based on the internal and external parameters of the binocular camera and the distortion parameters, and each first corrected image is subjected to epipolar rectification processing by the projection transformation matrix to obtain a second corrected image;

[0079] According to each second corrected image and a corresponding initial tobacco stem image, a tobacco stem volume on a tobacco stem transmission channel is obtained.

[0080] In order to guarantee the imaging effect of the tobacco stem in the tobacco stem image, the internal and external parameters of the binocular camera can be obtained by camera calibration, and the initial tobacco stem image is subjected to correction processing in combination with the internal and external parameters of the binocular camera.

[0081] Specifically, in the process of identifying each initial tobacco stem image, the corresponding corner points and corner point coordinates can be extracted from each initial tobacco stem image by an image processing algorithm or a corner point detection algorithm, and the internal and external parameters of the binocular camera and the distortion parameters are obtained by processing the corner point coordinates by a camera calibration algorithm. In the process of obtaining the internal parameters of the binocular camera, the world coordinates and image coordinates of the corner points can be normalized (i.e. subtracting the average value of the coordinates and then dividing by the standard deviation of the coordinates), and an augmented matrix and an augmented vector are constructed according to the normalized world coordinates and image coordinates, and the equation set formed by the augmented matrix and the augmented vector is solved by the least square method to obtain the focal length, radial distortion coefficient and tangential distortion coefficient of the camera. Here, the internal parameters of the binocular camera can also include the coordinates of the image principal point, but are not limited thereto.

[0082] In the process of obtaining the external parameters of the binocular camera, the internal parameter matrix of the binocular camera and the normalized image coordinates can be combined to obtain the corresponding camera coordinates by inverse projection transformation processing, and a corresponding relationship equation is constructed according to the camera coordinates and the corresponding world coordinates. Here, the internal parameter matrix of the binocular camera can be composed of the focal length, radial distortion coefficient and tangential distortion coefficient of the camera. Then, an augmented matrix and an augmented vector are constructed according to the world coordinates of all the corner points and the corresponding relationship equation, and the equation set formed by the augmented matrix and the augmented vector is solved by the least square method to obtain the rotation matrix and translation vector of the camera, i.e. the external parameters of the binocular camera.

[0083] Then, a distortion correction mapping function can be constructed based on the intrinsic parameter matrix of the binocular camera and the size parameters of the corresponding initial tobacco stem image, and each initial tobacco stem image can be processed by the distortion correction mapping function, i.e., the pixel coordinates in each initial tobacco stem image are converted into corrected pixel coordinates to obtain a first corrected image. It can be understood that after obtaining the first corrected image, black edges appearing in the first corrected image can be filled by cropping the image or an interpolation method, but not limited thereto.

[0084] Then, a projection transformation matrix can be constructed based on the intrinsic parameter matrix of the binocular camera and the size parameters of the corresponding initial tobacco stem image, and each first corrected image can be processed by the projection transformation matrix, i.e., each first corrected image is processed by projection transformation to obtain a second corrected image. It can be understood that after obtaining the second corrected image, black edges appearing in the second corrected image can be filled by cropping the image or an interpolation method, but not limited thereto.

[0085] Then, after obtaining the corrected images sequentially processed by distortion correction and epipolar rectification, the volume of the tobacco stems in the tobacco stem transmission channel can be obtained based on each corrected image and the corresponding initial tobacco stem image.

[0086] As another alternative of the embodiments of the present application, the volume of the tobacco stems in the tobacco stem transmission channel can be obtained based on each second corrected image and the corresponding initial tobacco stem image, comprising:

[0087] Each second corrected image is processed to obtain a binary image, and a connected block contour image is segmented from each binary image;

[0088] The connected block contour image is preprocessed, and the preprocessed connected block contour image is processed by adaptive distance transformation to obtain a pixel distance value;

[0089] The binary image is scanned based on the pixel distance value to obtain a distance scanning image, and the distance scanning image is segmented to obtain a target tobacco stem image;

[0090] The volume of the tobacco stems in the tobacco stem transmission channel is obtained based on each target tobacco stem image and the corresponding initial tobacco stem image.

[0091] Since the tobacco stems vibrate forward on the tobacco stem transmission channel of the vibrating chute, the tobacco stem images captured by the binocular camera will have a tobacco stem stacking problem. In order to avoid the calculation precision influence caused by the stacked tobacco stem images, a clearer tobacco stem image can be segmented from the initial tobacco stem image by segmentation processing.

[0092] Specifically, in the process of segmenting the second corrected image, a gray scale conversion process can be performed on each second corrected image, but is not limited thereto, to obtain a corresponding gray scale image, and a threshold segmentation process can be performed on the gray scale image based on an OTSU algorithm to obtain a corresponding binary image. Here, the binary image can be, but is not limited to, represented as follows:

[0093]

[0094] In the above formula, The threshold value can be set.

[0095] Of course, the threshold segmentation process can also be, but is not limited to, a global threshold process or an adaptive threshold process, without being limited thereto.

[0096] Next, after obtaining the binary image, a feature extraction algorithm can be used to extract a block contour image corresponding to the tobacco stem from the binary image, and the area and adaptive parameters corresponding to the block contour image can also be calculated, but are not limited thereto. It can be understood that the step of extracting the block contour image corresponding to the tobacco stem can also be performed before the conversion process of the second corrected image, that is, one or more block contour images corresponding to the tobacco stem are first extracted from the second corrected image, and all the block contour images corresponding to the tobacco stem are then converted.

[0097] Next, the binary image corresponding to the block contour image can be preprocessed, such as, but not limited to, removing error regions generated by noise and smoothing the edges of the image by morphological opening and closing operations, so as to better present the target region in the binary image.

[0098] Next, the preprocessed block contour image can be inverted, that is, the brightness value (pixel value) in the image is transformed in the opposite way, and the inverted image is then subjected to an adaptive distance transformation process, that is, a pixel-based distance transformation or a region-based distance transformation, to calculate the distance value of each pixel in the image from the nearest target or boundary. It can be understood that the pixel distance value obtained by the adaptive distance transformation process can also be understood as a distance transformation image, and the distance transformation image can be normalized to map each pixel distance value within a suitable range.

[0099] Then, the corresponding binary image of the adhesion block contour image can be processed by two times of scanning based on the pixel distance value. The process of the forward scanning can be understood as starting from the top-left pixel of the binary image, scanning the image from left to right row by row, and judging based on the corresponding pixel distance value for each pixel and the surrounding pixels to finally obtain a distance map. The process of the backward scanning can be understood as starting from the bottom-right pixel of the binary image, scanning the image from right to left row by row, and updating and optimizing the obtained distance map to obtain a final distance scanning image.

[0100] Then, the distance scanning image can be segmented by a watershed algorithm, that is, the image is regarded as a terrain, the distance value in the distance map is regarded as the terrain height, and the low-lying area (the area with smaller distance) is taken as the boundary of segmentation by using the algorithm to obtain the target tobacco stem region. It can be understood that, in order to obtain a clearer tobacco stem image, the segmented image can also be inverted and threshold segmented, and the method is not limited thereto.

[0101] Then, after obtaining the clear target tobacco stem image, the volume of the tobacco stem in the transmission channel can be obtained according to each target tobacco stem image and the corresponding initial tobacco stem image.

[0102] As another optional embodiment of the present application, the volume of the tobacco stem in the transmission channel is obtained according to each target tobacco stem image and the corresponding initial tobacco stem image, comprising:

[0103] The feature points of the tobacco stem are extracted from each target tobacco stem image, and the feature points of the tobacco stem are stereoscopically matched to obtain the pixel coordinates of the tobacco stem.

[0104] Based on the pixel coordinates of the tobacco stem and the color information of the corresponding pixels in the initial tobacco stem image, a three-dimensional point cloud map of the tobacco stem is constructed.

[0105] The three-dimensional point cloud map of the tobacco stem is tetrahedronally divided to obtain a tetrahedral mesh.

[0106] The volume of the tobacco stem in the transmission channel is calculated according to the vertex coordinates of the tetrahedral mesh.

[0107] Specifically, after obtaining the target tobacco stem image, the tobacco stem feature points can be extracted from the target tobacco stem image by a feature extraction algorithm, and the tobacco stem feature points can be subjected to stereo matching processing to obtain pixel coordinates of the tobacco stem, which can specifically include depth coordinates, horizontal axis coordinates and vertical axis coordinates (Zc, Xc and Yc). It can be understood that in the stereo matching processing of the tobacco stem feature points, other tobacco stem images corresponding to the target tobacco stem image can be obtained at other shooting angles, tobacco stem feature points can be extracted in the same way, and the two tobacco stem feature points can be subjected to matching processing to calculate the corresponding parallax value; then, the parallax value can be processed by a stereo matching algorithm to obtain the depth coordinates of each pixel. Here, the stereo matching algorithm can be but not limited to a window matching based method (such as block matching algorithm), and is not limited thereto.

[0108] It can also be understood that in the embodiments of the present application, the horizontal axis coordinates and the vertical axis coordinates of the pixels can be obtained by converting the parallax map corresponding to the parallax value mentioned above (based on the principle of pinhole imaging).

[0109] Then, after obtaining the pixel coordinates of the tobacco stem, an empty point cloud data object can be created in combination with the existing point cloud library, and each pixel coordinate and the color information (RGB information) of the corresponding pixel in the initial tobacco stem image can be traversed to construct a three-dimensional point cloud map of the tobacco stem in combination with the point cloud filtering, point cloud registration, point cloud segmentation and three-dimensional reconstruction modules in the point cloud library.

[0110] Then, after obtaining the three-dimensional point cloud map of the tobacco stem, a tetrahedral subdivision method based on the Delaunay algorithm can be used to subdivide the three-dimensional convex hull of the scattered point cloud on the surface of the tobacco stem, that is, to perform tetrahedral subdivision processing (which can also be understood as triangular subdivision processing) on the three-dimensional point cloud map of the tobacco stem to obtain an initial tetrahedron, and the remaining points in the three-dimensional point cloud map of the tobacco stem can be used to generate a tetrahedral mesh according to the initial tetrahedron. After generating the tetrahedral mesh, the sum of the volumes of all tetrahedrons, i.e. the volume of the tobacco stem, can be obtained by determining the vertex coordinates of all tetrahedrons in the tetrahedral mesh and combining a preset volume calculation formula.

[0111] As another alternative of the embodiments of the present application, the tobacco stem flow corresponding to each binocular camera can be obtained according to the tobacco stem moisture detected by the infrared moisture meter and the volume of the tobacco stem, including:

[0112] The actual density of the tobacco stem is calculated according to the tobacco stem moisture and a preset dry tobacco stem density;

[0113] The quality of the tobacco stem is obtained according to the volume of the tobacco stem and the actual density of the tobacco stem, and the tobacco stem flow corresponding to each binocular camera is determined based on the quality of the tobacco stem.

[0114] Specifically, in the process of obtaining the tobacco stem flow corresponding to each binocular camera, after obtaining the tobacco stem volume corresponding to each binocular camera, the dry mass of the tobacco stem can be obtained according to the product of the tobacco stem volume and the preset dry tobacco stem density; then, the wet mass of the tobacco stem can be obtained by combining the dry mass and the tobacco stem moisture detected by the infrared moisture meter through the following expression:

[0115] Wet mass = Dry mass / (1 - Tobacco stem moisture)

[0116] Then, the actual density of the tobacco stem can be obtained by calculating the ratio between the wet mass of the tobacco stem and the tobacco stem volume, and the mass of the tobacco stem can be obtained by calculating the product between the actual density of the tobacco stem and the tobacco stem volume.

[0117] As another alternative of the embodiments of the present application, the tobacco stem flow corresponding to each binocular camera is determined based on the mass of the tobacco stem, which includes:

[0118] The camera mapping distance is calculated based on the tobacco stem transmission channel width, the tobacco stem transmission channel length in each initial tobacco stem image, and the preset shaking groove parameters;

[0119] The tobacco stem flow corresponding to each binocular camera is calculated according to the mass of the tobacco stem, the camera mapping distance, and the preset running speed.

[0120] Specifically, in the process of determining the tobacco stem flow corresponding to each binocular camera, the product of the tobacco stem transmission channel length in each initial tobacco stem image and the tobacco stem transmission channel width in the preset shaking groove parameters can be calculated, and the ratio between the product and the tobacco stem transmission channel width in each initial tobacco stem image can be taken as the actual distance of the camera shooting range mapped on the shaking groove, i.e., the camera mapping distance. Here, the tobacco stem transmission channel in each initial tobacco stem image can correspond to the left channel or the right channel mentioned above.

[0121] Then, the mass of the tobacco stem, the camera mapping distance, and the preset running speed can be substituted into the formula shown below to calculate the tobacco stem flow corresponding to each binocular camera:

[0122]

[0123] In the above formula, Q can correspond to the tobacco stem flow, M can correspond to the mass of the tobacco stem, V can correspond to the preset running speed (i.e., the average speed of the tobacco stem advancing on the shaking groove), and D can correspond to the camera mapping distance.

[0124] Step 108, according to two tobacco stem flow, tobacco stem shunt parameters and the first rotation angle, determine the second rotation angle of the shunt baffle, and control the shunt baffle to shunt the tobacco stem on the tobacco stem transmission channel according to the second rotation angle.

[0125] Specifically, after obtaining the tobacco stem flow corresponding to each binocular camera, the ratio between the two tobacco stem flows can be calculated, but not limited to, and when it is detected that the ratio is consistent with the tobacco stem shunt parameter (or the inverse of the ratio is consistent with the tobacco stem shunt parameter), it indicates that the tobacco stem shunt process of the shunt baffle has no error, and the rotation angle of the shunt baffle can be maintained to shunt the tobacco stem on the tobacco stem transmission channel.

[0126] Possibly, when it is detected that the ratio is not consistent with the tobacco stem shunt parameter, it indicates that the tobacco stem shunt process of the shunt baffle has certain error, in order to eliminate the error, the difference between the target flow ratio corresponding to the tobacco stem transmission channel of each tobacco stem flow can be determined according to the tobacco stem shunt parameter, then the difference between the actual flow ratio corresponding to the tobacco stem transmission channel of each tobacco stem flow can be determined according to the two tobacco stem flows, and half of the difference between the target flow ratio and the actual flow ratio can be calculated, at this time, the rotation angle corresponding to the calculation result is the second rotation angle, which can also be understood as the correction angle. For example, the tobacco stem shunt parameter is 0.5, and the ratio between the two tobacco stem flows is 3 / 7. The difference between the target flow ratio can be 0 (the difference between 0.5 and 0.5), the difference between the actual flow ratio can be 0.4 (the difference between 0.7 and 0.3), and the calculation result can be 0.2 (0.5* (0.4-0)).

[0127] Here, the calculation result and the corresponding rotation angle can be obtained by querying a preset corresponding list, and the preset corresponding list can be obtained by sorting the results of multiple rotation angles and corresponding channel flows.

[0128] Further, after determining the second rotation angle, the shunt baffle can be controlled to shunt the tobacco stem on the tobacco stem transmission channel according to the second rotation angle on the basis of the first rotation angle, so that the tobacco stem shunt effect is consistent with the user-set shunt parameter.

[0129] Please refer to Figure 4 , Figure 4 A structure schematic diagram of a dynamic weighing based vibrating trough shunt control device provided by the embodiment of the application is shown.

[0130] The vibration groove shunt control device based on dynamic weighing is applied to the vibration groove, and the vibration groove includes an infrared moisture meter, a binocular camera, and a shunt partition plate arranged on a tobacco stem transmission channel.

[0131] The first processing module 401 is configured to determine a first rotation angle of the shunt partition plate according to the shunt parameter of the tobacco stem and a preset vibration groove parameter.

[0132] The second processing module 402 is configured to control the shunt partition plate to perform shunt processing on the tobacco stems on the tobacco stem transmission channel according to the first rotation angle, and obtain initial tobacco stem images after the shunt processing on the tobacco stem transmission channel by the two binocular cameras.

[0133] The third processing module 403 is configured to perform identification processing on each initial tobacco stem image to obtain the volume of the tobacco stems on the corresponding tobacco stem transmission channel, and obtain the tobacco stem flow corresponding to each binocular camera according to the tobacco stem moisture detected by the infrared moisture meter and the volume of the tobacco stems.

[0134] The fourth processing module 404 is configured to determine a second rotation angle of the shunt partition plate according to the two tobacco stem flows, the shunt parameter of the tobacco stem, and the first rotation angle, and control the shunt partition plate to perform shunt processing on the tobacco stems on the tobacco stem transmission channel according to the second rotation angle.

[0135] In some possible embodiments, the identification processing on each initial tobacco stem image to obtain the volume of the tobacco stems on the corresponding tobacco stem transmission channel includes:

[0136] At least two corner points are extracted from each initial tobacco stem image, and the internal and external parameters and the distortion parameters of the corresponding binocular camera are obtained according to the coordinates of all the corner points;

[0137] A distortion correction mapping function is constructed based on the internal and external parameters and the distortion parameters of the binocular camera, and each initial tobacco stem image is subjected to distortion correction processing by the distortion correction mapping function to obtain a first corrected image;

[0138] A projection transformation matrix is constructed based on the internal and external parameters and the distortion parameters of the binocular camera, and each first corrected image is subjected to epipolar rectification processing by the projection transformation matrix to obtain a second corrected image;

[0139] The volume of the tobacco stems on the tobacco stem transmission channel is obtained according to each second corrected image and the corresponding initial tobacco stem image.

[0140] In some possible embodiments, the volume of the tobacco stems on the tobacco stem transmission channel is obtained according to each second corrected image and the corresponding initial tobacco stem image, including:

[0141] The conversion processing is performed on each second correction image to obtain a binary image, and a connected block contour image is segmented from each binary image;

[0142] The connected block contour image is preprocessed, and an adaptive distance transform processing is performed on the preprocessed connected block contour image to obtain a pixel distance value;

[0143] The binary image is scanned based on the pixel distance value to obtain a distance scanning image, and a target tobacco stem image is segmented from the distance scanning image;

[0144] The tobacco stem volume in the tobacco stem transmission channel is obtained according to each target tobacco stem image and the corresponding initial tobacco stem image.

[0145] In some possible embodiments, the tobacco stem volume in the tobacco stem transmission channel is obtained according to each target tobacco stem image and the corresponding initial tobacco stem image, including:

[0146] The tobacco stem feature points are extracted from each target tobacco stem image, and a stereo matching processing is performed on the tobacco stem feature points to obtain pixel coordinates of the tobacco stem;

[0147] Based on the pixel coordinates of the tobacco stem and color information of corresponding pixels in the initial tobacco stem image, a three-dimensional point cloud map of the tobacco stem is constructed;

[0148] A tetrahedral mesh is obtained by performing a tetrahedral subdivision processing on the three-dimensional point cloud map of the tobacco stem;

[0149] The tobacco stem volume in the tobacco stem transmission channel is calculated according to the vertex coordinates of the tetrahedral mesh.

[0150] In some possible embodiments, the tobacco stem flow corresponding to each binocular camera is obtained according to the tobacco stem moisture detected by the infrared moisture meter and the tobacco stem volume, including:

[0151] The actual density of the tobacco stem is calculated according to the tobacco stem moisture and a preset dry tobacco stem density;

[0152] The tobacco stem quality is obtained according to the tobacco stem volume and the actual density of the tobacco stem, and the tobacco stem flow corresponding to each binocular camera is determined based on the tobacco stem quality.

[0153] In some possible embodiments, the tobacco stem flow corresponding to each binocular camera is determined based on the tobacco stem quality, including:

[0154] The camera mapping distance is calculated based on the tobacco stem transmission channel width, the tobacco stem transmission channel length in each initial tobacco stem image, and a preset vibrating trough parameter;

[0155] According to the tobacco stem quality, the camera mapping distance and the preset running rate, the tobacco stem flow corresponding to each binocular camera is calculated.

[0156] In some possible embodiments, according to the two tobacco stem flows, the shunt parameter of the tobacco stem and the first rotation angle, the second rotation angle of the shunt partition is determined, including:

[0157] When it is detected that the ratio between the two tobacco stem flows is consistent with the shunt parameter of the tobacco stem, the first rotation angle is taken as the second rotation angle of the shunt partition;

[0158] When it is detected that the ratio between the two tobacco stem flows is inconsistent with the shunt parameter of the tobacco stem, the second rotation angle of the shunt partition is determined according to the two tobacco stem flows and the shunt parameter of the tobacco stem.

[0159] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be realized by means of software and / or hardware. The "unit" and "module" in the specification refer to software and / or hardware that can independently complete or cooperate with other components to complete a specific function, and the hardware may, for example, be a field programmable gate array (FPGA), an integrated circuit (IC) and the like.

[0160] Please refer to Figure 5 , Figure 5 Another structure schematic diagram of the dynamic weighing based vibrating groove shunt control device provided by the embodiments of the present application is shown.

[0161] As Figure 5 shown, the dynamic weighing based vibrating groove shunt control device 500 can include at least one processor 501, at least one network interface 504, a user interface 503, a memory 505 and at least one communication bus 502.

[0162] The communication bus 502 can be used to realize the connection and communication of the above-mentioned components.

[0163] The user interface 503 can include a key, and the optional user interface can further include a standard wired interface, a wireless interface.

[0164] The network interface 504 can include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module and the like.

[0165] The processor 501 may include one or more processing cores. The processor 501 connects to various parts within the dynamic weighing-based sluice gate current distribution control device 500 using various interfaces and lines. It executes or runs instructions, programs, code sets, or instruction sets stored in memory 505, and calls data stored in memory 505 to perform various functions and process data of the dynamic weighing-based sluice gate current distribution control device 500. Optionally, the processor 501 may be implemented using at least one hardware form of DSP, FPGA, or PLA. The processor 501 may integrate one or more of the following: CPU, GPU, and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 501 and may be implemented as a separate chip.

[0166] The memory 505 may include RAM or ROM. Optionally, the memory 505 may include a non-transitory computer-readable medium. The memory 505 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 505 may also be at least one storage device located remotely from the aforementioned processor 501. Figure 5 As shown, the memory 505, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a dynamic weighing-based trough diversion control application.

[0167] Specifically, the processor 501 can be used to call the dynamic weighing-based trough diversion control application stored in the memory 505, and specifically perform the following operations:

[0168] The first rotation angle of the diversion baffle is determined based on the diversion parameters of the tobacco stem and the preset vibration groove parameters.

[0169] The control diversion baffle divides the tobacco stems in the tobacco stem transport channel according to the first rotation angle, and two binocular cameras respectively acquire the initial tobacco stem images after the diversion process in the tobacco stem transport channel;

[0170] The initial tobacco stem images are identified to obtain the volume of the tobacco stems in the tobacco stem transmission channel, and the tobacco stem moisture detected by the infrared moisture meter and the volume of the tobacco stems are used to obtain the tobacco stem flow corresponding to each binocular camera;

[0171] The second rotation angle of the shunt baffle is determined according to the two tobacco stem flows, the shunt parameter of the tobacco stems and the first rotation angle, and the shunt baffle is controlled to perform shunt processing on the tobacco stems in the tobacco stem transmission channel according to the second rotation angle.

[0172] In some possible embodiments, the initial tobacco stem images are identified to obtain the volume of the tobacco stems in the tobacco stem transmission channel, including:

[0173] At least two corner points are extracted from each initial tobacco stem image, and the internal and external parameters and the distortion parameters of the corresponding binocular camera are obtained according to the coordinates of all the corner points;

[0174] A distortion correction mapping function is constructed based on the internal and external parameters and the distortion parameters of the binocular camera, and each initial tobacco stem image is subjected to distortion correction processing by the distortion correction mapping function to obtain a first corrected image;

[0175] A projection transformation matrix is constructed based on the internal and external parameters and the distortion parameters of the binocular camera, and each first corrected image is subjected to epipolar rectification processing by the projection transformation matrix to obtain a second corrected image;

[0176] The volume of the tobacco stems in the tobacco stem transmission channel is obtained according to each second corrected image and the corresponding initial tobacco stem image.

[0177] In some possible embodiments, the volume of the tobacco stems in the tobacco stem transmission channel is obtained according to each second corrected image and the corresponding initial tobacco stem image, including:

[0178] Each second corrected image is converted to obtain a binary image, and a connected block contour image is segmented from each binary image;

[0179] The connected block contour image is preprocessed, and the connected block contour image after the preprocessing is subjected to adaptive distance transformation processing to obtain a pixel distance value;

[0180] The binary image is subjected to scanning processing based on the pixel distance value to obtain a distance scanning image, and the distance scanning image is subjected to segmentation processing to obtain a target tobacco stem image;

[0181] The volume of the tobacco stems in the tobacco stem transmission channel is obtained according to each target tobacco stem image and the corresponding initial tobacco stem image.

[0182] In some possible embodiments, the tobacco stem volume on the tobacco stem conveying channel is obtained according to each target tobacco stem image and the corresponding initial tobacco stem image, and the method comprises the following steps:

[0183] The tobacco stem feature points are extracted from each target tobacco stem image, and the tobacco stem feature points are subjected to stereo matching processing to obtain pixel coordinates of the tobacco stem;

[0184] Based on the pixel coordinates of the tobacco stem and color information of the corresponding pixels in the initial tobacco stem image, a three-dimensional point cloud map of the tobacco stem is constructed;

[0185] The three-dimensional point cloud map of the tobacco stem is subjected to tetrahedral subdivision processing to obtain a tetrahedral mesh;

[0186] The tobacco stem volume on the tobacco stem conveying channel is calculated according to the vertex coordinates of the tetrahedral mesh.

[0187] In some possible embodiments, the tobacco stem flow corresponding to each binocular camera is obtained according to the tobacco stem moisture detected by the infrared moisture meter and the tobacco stem volume, and the method comprises the following steps:

[0188] The actual density of the tobacco stem is calculated according to the tobacco stem moisture and a preset dry tobacco stem density;

[0189] The tobacco stem quality is obtained according to the tobacco stem volume and the actual density of the tobacco stem, and the tobacco stem flow corresponding to each binocular camera is determined based on the tobacco stem quality.

[0190] In some possible embodiments, the tobacco stem flow corresponding to each binocular camera is determined based on the tobacco stem quality, and the method comprises the following steps:

[0191] The camera mapping distance is calculated based on the tobacco stem conveying channel width, the tobacco stem conveying channel length in each initial tobacco stem image, and a preset vibrating trough parameter;

[0192] The tobacco stem flow corresponding to each binocular camera is calculated according to the tobacco stem quality, the camera mapping distance, and a preset running rate.

[0193] In some possible embodiments, the second rotation angle of the shunt partition plate is determined according to the two tobacco stem flows, the shunt parameter of the tobacco stem, and the first rotation angle, and the method comprises the following steps:

[0194] When it is detected that the ratio between the two tobacco stem flows is consistent with the shunt parameter of the tobacco stem, the first rotation angle is taken as the second rotation angle of the shunt partition plate;

[0195] When it is detected that the ratio between the two tobacco stem flows is inconsistent with the shunt parameter of the tobacco stem, the second rotation angle of the shunt partition plate is determined according to the two tobacco stem flows and the shunt parameter of the tobacco stem.

[0196] The application further provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps of the method. The computer readable storage medium can include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0197] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0198] In the above embodiments, the description of each embodiment is focused on, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0199] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented by other means. For example, the device embodiments described above are only illustrative, and the division of units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some service interface, device or unit, which can be electrical or other forms.

[0200] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0201] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0202] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable memory. Based on such understanding, the technical solutions of the present application essentially or the part of the prior art that contributes or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned memory includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

Claims

1. A dynamic weighing-based swing bin flow control method, characterized in that, The method is applied to a vibrating chute, the vibrating chute comprising an infrared moisture meter, binocular cameras and a shunt partition plate arranged on a tobacco stem transmission channel, and the method comprises: According to the shunt parameters of the tobacco stems and preset vibrating chute parameters, a first rotation angle of the shunt partition plate is determined; The shunt partition plate is controlled to perform shunt processing on the tobacco stems on the tobacco stem transmission channel according to the first rotation angle, and two binocular cameras are used to respectively acquire initial tobacco stem images of the tobacco stems on the tobacco stem transmission channel after the shunt processing; Each initial tobacco stem image is subjected to identification processing to obtain a tobacco stem volume on the corresponding tobacco stem transmission channel, and according to the tobacco stem moisture detected by the infrared moisture meter and the tobacco stem volume, a tobacco stem flow corresponding to each binocular camera is obtained; According to two tobacco stem flows, the shunt parameters of the tobacco stems and the first rotation angle, a second rotation angle of the shunt partition plate is determined, and the shunt partition plate is controlled to perform shunt processing on the tobacco stems on the tobacco stem transmission channel according to the second rotation angle; According to the tobacco stem moisture detected by the infrared moisture meter and the tobacco stem volume, a tobacco stem flow corresponding to each binocular camera is obtained, which comprises: According to the tobacco stem moisture and a preset dry tobacco stem density, a tobacco stem actual density is calculated; According to the tobacco stem volume and the tobacco stem actual density, a tobacco stem quality is obtained, and based on the tobacco stem quality, a tobacco stem flow corresponding to each binocular camera is determined; Wherein, a dry tobacco stem quality is obtained according to the product of the tobacco stem volume and the preset dry tobacco stem density, and then based on the dry tobacco stem quality and the tobacco stem moisture detected by the infrared moisture meter, a wet tobacco stem quality is obtained through the following expression: Wet quality = dry quality / (1-tobacco stem moisture) The tobacco stem actual density is obtained by calculating the ratio between the wet tobacco stem quality and the tobacco stem volume, and the tobacco stem quality is obtained by calculating the product between the tobacco stem actual density and the tobacco stem volume; Based on the tobacco stem quality, a tobacco stem flow corresponding to each binocular camera is determined, which comprises: Based on the tobacco stem transmission channel width, the tobacco stem transmission channel length in each initial tobacco stem image and the preset vibrating chute parameters, a camera mapping distance is calculated; According to the tobacco stem quality, the camera mapping distance and a preset running rate, a tobacco stem flow corresponding to each binocular camera is calculated; Wherein, the camera mapping distance is obtained by calculating the product of the tobacco stem transmission channel length in each initial tobacco stem image and the tobacco stem transmission channel width in the preset vibrating chute parameters, and taking the ratio between the product and the tobacco stem transmission channel width in each initial tobacco stem image as the camera mapping distance; Then, the tobacco stem quality, the camera mapping distance and the preset running rate are substituted into the formula shown below to calculate a tobacco stem flow corresponding to each binocular camera: In the above formula, Q corresponds to the tobacco stem flow corresponding to each of the binocular cameras, M corresponds to the tobacco stem mass, corresponds to the preset running speed, and ΔL corresponds to the camera mapping distance.

2. The method of claim 1, wherein, Each initial tobacco stem image is subjected to identification processing to obtain a tobacco stem volume on the corresponding tobacco stem transmission channel, which comprises: extract at least two corner points from each of the initial tobacco stem images, and obtain internal and external parameters and distortion parameters of the corresponding binocular camera according to coordinates of all the corner points; construct a distortion correction mapping function based on the internal and external parameters and distortion parameters of the binocular camera, and perform distortion correction processing on each of the initial tobacco stem images by using the distortion correction mapping function to obtain first corrected images; construct a projection transformation matrix based on the internal and external parameters and distortion parameters of the binocular camera, and perform epipolar rectification processing on each of the first corrected images by using the projection transformation matrix to obtain second corrected images; obtain the volume of the tobacco stems in the tobacco stem transmission channel according to each of the second corrected images and the corresponding initial tobacco stem images.

3. The method of claim 2, wherein, The method for obtaining the volume of the tobacco stems in the tobacco stem transmission channel according to each of the second corrected images and the corresponding initial tobacco stem images comprises: perform conversion processing on each of the second corrected images to obtain a binary image, and segment a conglutination block contour image from each of the binary images; perform preprocessing on the conglutination block contour image, and perform adaptive distance transform processing on the preprocessed conglutination block contour image to obtain a pixel distance value; perform scanning processing on the binary image based on the pixel distance value to obtain a distance scanning image, and perform segmentation processing on the distance scanning image to obtain a target tobacco stem image; obtain the volume of the tobacco stems in the tobacco stem transmission channel according to each of the target tobacco stem images and the corresponding initial tobacco stem images.

4. The method of claim 3, wherein, The method for obtaining the volume of the tobacco stems in the tobacco stem transmission channel according to each of the target tobacco stem images and the corresponding initial tobacco stem images comprises: extract a tobacco stem feature point from each of the target tobacco stem images, and perform stereo matching processing on the tobacco stem feature point to obtain a pixel coordinate of the tobacco stem; construct a three-dimensional point cloud map of the tobacco stem based on the pixel coordinate of the tobacco stem and color information of a corresponding pixel in the initial tobacco stem image; perform tetrahedron subdivision processing on the three-dimensional point cloud map of the tobacco stem to obtain a tetrahedron mesh; calculate the volume of the tobacco stems in the tobacco stem transmission channel according to vertex coordinates of the tetrahedron mesh.

5. The method of claim 1, wherein, The method for determining the second rotation angle of the shunt partition plate according to the two tobacco stem flows, the shunt parameter of the tobacco stems, and the first rotation angle comprises: when it is detected that a ratio between the two tobacco stem flows is consistent with the shunt parameter of the tobacco stems, taking the first rotation angle as the second rotation angle of the shunt partition plate; when it is detected that a ratio between the two tobacco stem flows is inconsistent with the shunt parameter of the tobacco stems, determining the second rotation angle of the shunt partition plate according to the two tobacco stem flows and the shunt parameter of the tobacco stems.

6. A dynamic weighing based surge control device, characterized in that, The device is applied to the dynamic weighing-based shaker shunt control method according to any one of claims 1-5, and the device is applied to a shaker. The shaker comprises an infrared moisture meter, a binocular camera, and a shunt partition plate arranged on a tobacco stem transmission channel. The device comprises: The first processing module is configured to determine a first rotation angle of the shunt baffle according to the shunt parameter of the tobacco stem and a preset shaking groove parameter; The second processing module is configured to control the shunt baffle to perform shunt processing on the tobacco stems on the tobacco stem transmission channel according to the first rotation angle, and obtain initial tobacco stem images of the tobacco stems after the shunt processing on the tobacco stem transmission channel by the two binocular cameras respectively; The third processing module is configured to perform identification processing on each of the initial tobacco stem images to obtain a volume of the tobacco stems on the corresponding tobacco stem transmission channel, and obtain tobacco stem flows corresponding to the two binocular cameras according to the tobacco stem moisture detected by the infrared moisture meter and the volume of the tobacco stems; The fourth processing module is configured to determine a second rotation angle of the shunt baffle according to the two tobacco stem flows, the shunt parameter of the tobacco stem and the first rotation angle, and control the shunt baffle to perform shunt processing on the tobacco stems on the tobacco stem transmission channel according to the second rotation angle.

7. A dynamic weighing based surge control device, characterized in that, The processor and the memory are connected; The memory is configured to store executable program codes; The processor runs a program corresponding to the executable program codes by reading the executable program codes stored in the memory, so as to execute the steps of the method according to any one of claims 1-5. The computer readable storage medium stores instructions, and when the instructions run on the computer or the processor, the computer or the processor executes the steps of the method according to any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, ​

Images