Cut tobacco speed and cut tobacco dryer cavity temperature integrated detection method and detection device

Abstract

The invention relates to the technical field of tobacco detection, and discloses a cut tobacco speed and cut tobacco dryer cavity temperature integrated detection method and device, and the method comprises the steps: obtaining a visible light image and an infrared image of cut tobacco; the visible light image and the infrared image are preprocessed; fusing the pre-processed visible light image and the pre-processed infrared image by adopting a spectrum fusion algorithm to generate a fused image; extracting tobacco shred speed information from the fused image by adopting an optical flow method; and acquiring tobacco shred temperature and cavity temperature information from the fused image by adopting a spectral radiation method. Compared with the prior art, the cavity temperature and the tobacco shred speed of the cut-tobacco dryer can be accurately detected in real time at the same time, so that a worker can adjust the drum wall temperature and the drum rotating speed of the cut-tobacco dryer in time, it is ensured that the water content of tobacco meets the processing technology standard, and the quality of finished tobacco products is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tobacco detection, and in particular to an integrated detection method and device for detecting shredded tobacco speed and shredded tobacco drying machine cavity temperature. Background Art

[0002] Drying tobacco is an important process in tobacco production. This process dries and heats tobacco to control the moisture content of tobacco and ensure the quality of tobacco products. During the drying process, the cavity temperature of the tobacco drying machine directly affects the process quality indicators such as moisture and curvature of tobacco. The speed of tobacco in the drying machine is closely related to tobacco stratification, particle agglomeration, uneven drying and dehydration, and particle crushing. Therefore, it is very important to accurately obtain and reasonably control the cavity temperature of the drying machine and the speed of tobacco to avoid the above-mentioned undesirable phenomena and improve the quality of tobacco products. However, during the drying process, the drying machine drum keeps rotating, and its temperature is difficult to measure directly. At the same time, tobacco is a flexible filamentary particle with irregular contours. It rotates, fluctuates, and agglomerates in the drying machine. Its speed detection is difficult, which makes it difficult to control the moisture content of tobacco, affecting the quality of tobacco products.

[0003] The prior art lacks a detection method and a detection device that can simultaneously detect the cavity temperature of a tobacco drying machine and the speed of tobacco cuts inside the machine. Summary of the invention

[0004] In order to address the deficiencies in the prior art, the present invention aims to provide an integrated detection method and device for tobacco shred speed and tobacco drying machine cavity temperature. The detection method and device acquire visible light images and infrared images by setting an image acquisition component and a temperature acquisition component, generate a fused image by using a spectral fusion algorithm, and then extract tobacco shred speed information from the fused image by using an optical flow method and acquire tobacco shred temperature and cavity temperature information from the fused image by using a spectral radiation method. The cavity temperature and tobacco shred speed of the tobacco drying machine can be detected in real time at the same time, so that the staff can adjust the cylinder wall temperature and drum speed of the tobacco drying machine in time to ensure that the moisture content of the tobacco meets the processing technology standards and improve the quality of the tobacco products.

[0005] In order to achieve the above-mentioned object, the present invention provides an integrated detection device and detection system for tobacco shred speed and tobacco shred drying machine cavity temperature, comprising:

[0006] Acquire visible light images and infrared images of tobacco;

[0007] Preprocessing the visible light image and the infrared image;

[0008] The spectral fusion algorithm is used to fuse the preprocessed visible light image and the preprocessed infrared image to generate a fused image;

[0009] extracting tobacco speed information from the fused image using an optical flow method;

[0010] The spectral radiation method is used to obtain the tobacco cut temperature and cavity temperature information from the fused image.

[0011] Optionally, preprocessing the visible light image and the infrared image includes:

[0012] Using a preset image registration method, the visible light image and the infrared image are geometrically aligned to ensure that the visible light image and the infrared image have consistent spatial positions;

[0013] Performing filtering on the visible light image and the infrared image to reduce noise and enhance image contrast;

[0014] The infrared image is subjected to pseudo-color processing to convert the temperature information into a visual image, and the image quality is improved through non-uniformity correction to reduce the error of temperature measurement.

[0015] Optionally, a spectral fusion algorithm is used to fuse the preprocessed visible light image and the preprocessed infrared image to generate a fused image, including:

[0016] Normalizing the preprocessed visible light image and the preprocessed infrared image;

[0017] The preprocessed visible light image and the preprocessed infrared image are fused using a spectral fusion strategy, wherein the spectral fusion strategy includes pixel-level fusion and feature-level fusion, wherein the pixel-level fusion includes weighted average fusion, selective fusion or wavelet transform fusion.

[0018] Optionally, extracting tobacco speed information from the fused image using an optical flow method includes:

[0019] Formula (1) to Formula (4) are used to construct the optical flow constraint equation of each pixel point of the fused image:

[0020]

[0021] Among them, A is the brightness gradient matrix, is the flow rate of tobacco, b is a column vector, representing the rate of change of brightness over time;

[0022]

[0023] in, is the gradient of pixel I1 in the x direction, is the gradient of pixel I1 in the y direction, is the gradient of pixel I2 in the x direction, is the gradient of pixel I2 in the y direction, is pixel I N The gradient in the x direction, is pixel I N The gradient in the y direction;

[0024]

[0025] in, is the rate of change of pixel I1 over time, is the rate of change of pixel I2 over time, is pixel I N rate of change over time;

[0026]

[0027] Among them, u is the component of the optical flow velocity vector in the x direction, and v is the component of the optical flow velocity vector in the y direction;

[0028] The tobacco speed is determined using formula (5):

[0029]

[0030] Optionally, using a spectral radiation method to obtain tobacco cut temperature and cavity temperature information from the fused image includes:

[0031] The infrared component is separated from the fused image, and the tobacco temperature and the cavity temperature are calculated according to the radiation intensity of the infrared component and the Planck's law formula (6).

[0032]

[0033] Wherein, I(λ,T) is the radiation intensity at wavelength λ, λ is the wavelength of the infrared sensor, T is the tobacco temperature or the cavity temperature, h is Planck's constant, c is the speed of light, and k is the Boltzmann constant.

[0034] On the other hand, the present invention also provides an integrated detection device for tobacco shred speed and tobacco shred drying machine cavity temperature, the device comprising:

[0035] A lighting assembly, used for providing light source to the tofu drying machine cavity to be tested;

[0036] An image acquisition component, used for acquiring a visible light image of the tofu drying machine cavity;

[0037] A temperature acquisition component, used for acquiring the temperature of the cavity of the tofu drying machine to obtain an infrared image of the cavity of the tofu drying machine;

[0038] The processor is connected to the lighting component, the image acquisition component and the temperature acquisition component, and is used to determine the flow rate and temperature of the tobacco in the drying machine cavity according to any of the above-mentioned integrated detection methods for tobacco speed and drying machine cavity temperature.

[0039] Optionally, the image acquisition component includes a CCD camera and an optical lens, and the optical lens is arranged at the front end of the CCD camera.

[0040] Optionally, the temperature acquisition component includes a temperature detector, and the temperature detector is a dual-spectrum temperature measurement thermal imager.

[0041] Optionally, a power supply component is provided in the detection device, and the power supply component is electrically connected to the image acquisition component and the temperature acquisition component to supply power to the image acquisition component and the temperature acquisition component.

[0042] Optionally, a light source controller is provided in the detection device, and the light source controller is electrically connected to the lighting component to adjust the lighting component according to the light intensity in the tofu drying machine cavity.

[0043] Through the above technical scheme, the embodiment of the present invention provides an integrated detection method and device for tobacco speed and tobacco drying machine cavity temperature. The method and device acquire visible light images and infrared images by setting image acquisition components and temperature acquisition components, generate fused images by using spectral fusion algorithm, and then extract tobacco speed information from the fused image by using optical flow method and acquire tobacco temperature and cavity temperature information from the fused image by using spectral radiation method. The cavity temperature and tobacco speed of the tobacco drying machine can be detected in real time at the same time, so that the staff can adjust the cylinder wall temperature and drum speed of the tobacco drying machine in time, ensure that the moisture content of tobacco meets the processing technology standards, and improve the quality of tobacco products. The method makes up for the lack of a detection device that can simultaneously detect the cavity temperature of the tobacco drying machine and the tobacco speed inside it in the prior art.

[0044] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of an integrated detection method of tobacco speed and tobacco drying machine cavity temperature according to one embodiment of the present invention;

[0046] Figure 2 is a flowchart of visible light image and infrared image preprocessing according to one embodiment of the present invention;

[0047] Figure 3 is a flow chart of fused image generation according to one embodiment of the present invention;

[0048] Figure 4 It is a schematic diagram of the internal structure of a device for integrated detection of tobacco shred speed and tobacco drying machine cavity temperature according to one embodiment of the present invention;

[0049] Figure 5 It is a structural schematic diagram of a device for integrated detection of tobacco shred speed and tobacco shred drying machine cavity temperature according to one embodiment of the present invention;

[0050] Figure 6 It is a structural schematic diagram of an image acquisition component and a temperature acquisition component of an integrated detection device for tobacco speed and tobacco drying machine cavity temperature according to an embodiment of the present invention.

[0051] Figure 7 (a) is a schematic diagram of a speed measurement verification experimental device according to an embodiment of the present invention;

[0052] Figure 7 (b) is a schematic diagram of a measurement window of a speed measurement verification experimental device according to an embodiment of the present invention;

[0053] Figure 8 (a) (b) are schematic diagrams of the cavity of a speed measurement verification experimental device according to an embodiment of the present invention;

[0054] Fig. 9 is a tobacco flow diagram collected according to one embodiment of the present invention;

[0055] Explanation of the reference numerals: 11, shell; 111, opening; 112, heat dissipation hole; 12, image acquisition component; 121, fixing bracket; 122, CCD camera; 123, optical lens; 124, lighting component; 1241, lighting component; 1242, fixing plate; 1243, adapter; 13, temperature acquisition component; 131, temperature detector; 132, support; 14, power supply component; 15, light source controller. DETAILED DESCRIPTION

[0056] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the embodiment of the present invention.

[0057] like Figure 1 The figure is a flow chart of a method for integrated detection of tobacco shred speed and tobacco drying machine cavity temperature according to one embodiment of the present invention. Figure 1 In the method, the method may include the following steps:

[0058] In step S10, a visible light image and an infrared image of the tobacco are acquired. Considering that in the tobacco production process, it is difficult for traditional monitoring methods to simultaneously achieve accurate monitoring of the tobacco morphology, motion trajectory, and temperature distribution. In the prior art, visible light sensors and infrared sensors often work independently, which makes it difficult to synchronize the collected image data in time and space, affecting the accuracy of subsequent image fusion and data analysis. In addition, the high-speed motion characteristics of tobacco put forward higher requirements on the frame rate of the sensor, and the prior art lacks the ability to dynamically adjust the frame rate, and cannot take into account the needs of high-speed motion detail capture and temperature monitoring. In this embodiment of the present invention, the acquisition of visible light images and infrared images of tobacco can include the following steps:

[0059] In this embodiment, the sensor configuration is as follows: a CCD camera is used as a visible light sensor, and the working band is 400-700nm, which is used to capture the flow form and movement trajectory of tobacco. A temperature detector is used as an infrared sensor, and the working band is 3-5μm (for high temperature environment, such as within 550°C) and 8-14μm (for low temperature environment, such as 20°C to 100°C), which is used to measure the temperature distribution of tobacco and cavity. Synchronous acquisition control: The visible light sensor and the infrared sensor are controlled by a synchronous trigger to collect images at the same time to ensure that the visible light image and the infrared image are captured at the same time. The timestamp technology is used to mark the same timestamp for each pair of visible light and infrared images to ensure the time consistency of the data. Dynamic adjustment of frame rate: The frame rate of the sensor is dynamically adjusted according to the movement speed of the tobacco, and the frame rate of the visible light sensor is set to a higher value (such as 120 frames per second) to meet the needs of capturing details of high-speed moving tobacco. The frame rate of the infrared sensor is set to a lower value (such as 30-60 frames per second) to meet the needs of temperature monitoring. This implementation method ensures that visible light images and infrared images are completely synchronized in time and space through synchronization triggers and timestamp technology, improving the accuracy of image fusion and data analysis. The sensor frame rate is dynamically adjusted according to the movement speed of the tobacco, which not only ensures the capture of the shape and trajectory of high-speed moving tobacco, but also realizes accurate monitoring of temperature distribution. The dual-band design of the infrared sensor can cover a wide temperature range from low to high temperature, and is suitable for tobacco and cavity temperature monitoring in different production environments.

[0060] In step S11, the visible light image and the infrared image are preprocessed. In this embodiment, the specific steps for preprocessing the visible light image and the infrared image can be various forms known to those skilled in the art, including but not limited to image enhancement, noise removal and other preprocessing methods known to those skilled in the art. In one example of the present invention, considering the need to further fuse the visible light image and the infrared image, as shown in FIG. Figure 2 As shown, the preprocessing may include the following steps:

[0061] In step S11.0, a preset image registration method is used to geometrically align the visible light image with the infrared image to ensure that the spatial positions of the visible light image and the infrared image are consistent. Considering the different optical properties of visible light and infrared sensors (such as differences in field of view, resolution and imaging principles), the visible light image and the infrared image may be inconsistent in spatial position, affecting the accuracy of subsequent image fusion and data analysis. Therefore, in this example, a preset image registration method can be used to geometrically align the visible light image with the infrared image to ensure that the two types of data can accurately correspond to the same spatial position. Specifically, a feature point extraction and matching method can be used to select multiple feature points (such as the edge or key nodes of tobacco) in the visible light image and the infrared image, and the images are geometrically aligned through image registration algorithms (such as SIFT, ORB, etc.) to eliminate the field of view and resolution inconsistency problems caused by differences in the optical properties of the sensors.

[0062] In step S11.1, the visible light image and the infrared image are filtered to reduce noise and enhance image contrast. Considering that there may be noise in the captured image and the temperature information of the infrared image is difficult to present intuitively, these problems reduce the image quality and the efficiency of subsequent processing. Therefore, in this example, the visible light image and the infrared image are filtered to reduce noise and enhance image contrast. Specifically, Gaussian filtering can be used to remove noise in the image, and the motion contour of the tobacco can be enhanced by edge detection technology (such as Canny operator) to improve the clarity and detail of the image.

[0063] In step S11.2, the infrared image is processed by pseudo color, the temperature information is converted into a visual image, the image quality is improved by non-uniformity correction, and the error of temperature measurement is reduced. By mapping the temperature data into a pseudo color image, the readability and information expression ability of the image are enhanced, which is convenient for intuitive observation and analysis.

[0064] In step S11.0 to step S11.2, the feature point extraction and matching technology solves the problem of spatial position inconsistency between visible light images and infrared images due to differences in sensor optical characteristics, ensuring that the two image data accurately correspond to the same spatial position, providing a reliable basis for subsequent image fusion and data analysis. Through Gaussian filtering and edge detection, image noise is effectively removed and the motion contour of tobacco is enhanced, improving the clarity and detail of the image, which is convenient for subsequent processing and analysis. Through pseudo-color processing and non-uniformity correction, the temperature information in the infrared image is converted into an intuitive visual image, which improves the readability and measurement accuracy of the temperature data and facilitates the rapid acquisition and analysis of temperature distribution information.

[0065] In step S12, a spectral fusion algorithm is used to fuse the preprocessed visible light image and the preprocessed infrared image to generate a fused image. Figure 3 As shown, the steps of generating a fused image using a spectral fusion algorithm may include:

[0066] In step S12.0, the preprocessed visible light image and the preprocessed infrared image are normalized. To facilitate fusion, the visible light and infrared images are first normalized to map the pixel values ​​of the visible light and infrared images to a uniform range of [0, 1].

[0067] In step S12.1, a spectral fusion strategy is used to fuse the preprocessed visible light image and the preprocessed infrared image, wherein the spectral fusion strategy includes pixel-level fusion and feature-level fusion, wherein the pixel-level fusion includes weighted average fusion, selective fusion or wavelet transform fusion.

[0068] In this implementation, the specific steps of the spectral fusion algorithm may be in various forms known to those skilled in the art, including but not limited to fusion methods known to those skilled in the art such as fusion based on spatial domain and fusion based on frequency domain. In one example of the present invention, considering that the spectral fusion algorithm needs to fuse visible light images and infrared images, the spectral fusion algorithm may include pixel-level fusion operations and feature-level fusion operations. Among them, the pixel-level fusion operation may further include weighted average fusion, selective fusion or wavelet transform fusion. Specifically:

[0069] Weighted average fusion generates a fused image by performing a weighted average operation on the pixel values ​​of the visible light image and the infrared image. Weighted average fusion can include the following steps:

[0070] According to formula (7), the pixel values ​​of the visible light image and the infrared image are weighted averaged to generate a fused image:

[0071] I fusion (x′,y′)=α1·I vis-norm (x′,y′)+β1·I ir-norm (x′,y′), (7)

[0072] Among them, I fusion (x′, y′) is the image pixel value after the visible light image and the infrared image are fused at the coordinate (x′, y′), α1 is the weight coefficient of the visible light image, β1 is the weight coefficient of the infrared image, and α1+β1=1 is satisfied; α1 and β1 can be dynamically adjusted according to demand, such as in flow rate monitoring, the proportion of visible light is higher, while in temperature monitoring, the proportion of infrared images is higher.

[0073] Selective fusion selects the image with richer information as the fusion result for each pixel. It can be determined based on gradient or edge strength whether the pixel comes from a visible light image or an infrared image. Selective fusion can include the following steps:

[0074] The pixel value is determined based on the gradient or edge strength according to formula (8):

[0075]

[0076] in, is the visible light image gradient at the coordinate (x′, y′), is the infrared image gradient at the coordinate (x′, y′) of the infrared image; the image gradient can be calculated by the Sobel operator or other edge detection algorithms.

[0077] Wavelet transform fusion uses wavelet transform to decompose the image into multiple scales, then fuses the decomposed images of each scale, and then obtains the fused image through inverse wavelet transform. Wavelet transform fusion can include the following steps:

[0078] According to formulas (9) and (10), the second visible light image and the second infrared image are decomposed by wavelet to obtain low-frequency components and high-frequency components:

[0079] I vis-low ,I vis-high =WaveletDecompose(I vis-norm ), (9)

[0080] I ir-low ,I ir-high =WaveletDecompose(I ir-norm ), (10)

[0081] Among them, I vis-low is the low-frequency component of the visible light image, I vis-high is the high-frequency component of the visible light image, I ir-low is the low frequency component of the infrared image, I ir-high is the high-frequency component of the visible light image.

[0082] According to formula (11), the low-frequency components are weighted average fused, and according to formula (12), the high-frequency components are fused with the maximum coefficient selection:

[0083] I low-fusion (x′,y′)=α2·I vis-low (x′,y′)+β2·I ir-low (x′,y′), (11)

[0084] I high-fusion (x′,y′)=max (I vis-high (x′,y′),I ir-high (x′,y′)), (12)

[0085] Among them, I low-fusion (x′, y′) is the fused low-frequency component of the visible light image and the infrared image at the coordinate (x′, y′), α2 is I vis-low The weight coefficient of (x′,y′), β2 is I ir-low The weight coefficient of (x′, y′) satisfies α2+β2=1; I high-fusion (x′, y′) is the fused high-frequency component of the visible light image and the infrared image at the coordinate (x′, y′).

[0086] According to formula (13), the fused image is obtained by inverse wavelet transform:

[0087] I fusion (x′,y′)=WaveletReconstruct(I low-fusion ,I high-fusion ), (13).

[0088] Feature-level fusion is performed after extracting high-level features of the image (such as edges, textures, or temperature gradients). Pre-trained convolutional neural networks can be used to extract deep features of visible light images and infrared images respectively, and then fuse them in high-level feature space. Feature-level fusion can include the following steps:

[0089] The visible light image and infrared image are input into the pre-trained CNN model respectively, and the high-dimensional feature vectors of the visible light image and infrared image are extracted according to formulas (14) and (15).

[0090] F vis =CNN(I vis-norm ), (14)

[0091] F ir =CNN(I ir-norm ), (15)

[0092] Among them, F vis is the high-dimensional feature vector of the visible light image, F ir is the high-dimensional feature vector of the infrared image.

[0093] According to formula (16), the high-dimensional feature vector of the visible light image and the high-dimensional feature vector of the infrared image are weighted fused to obtain the fused feature vector:

[0094] F fusion =α3·F vis +β3·F ir , (16)

[0095] Among them, F fusionis the fused feature vector, α3 is the weight coefficient of the high-dimensional feature vector of the visible light image, β3 is the weight coefficient of the high-dimensional feature vector of the infrared image, and α3+β3=1 is satisfied.

[0096] According to formula (17), the fused feature vector is back-propagated to generate a fused image.

[0097] I fusion =CNN -1 (F fusion ), (17).

[0098] In step S12.0 to step S12.1, the visible light image and infrared image data are effectively fused through a spectral fusion algorithm to generate an image containing multi-dimensional information such as tobacco flow rate, temperature and density.

[0099] In step S13, the speed information of the tobacco shreds is extracted from the fused image using an optical flow method. In this example, the steps of extracting the speed information of the tobacco shreds may include:

[0100] Formulas (1) to (4) are used to construct the optical flow constraint equation for each pixel of the fused image:

[0101]

[0102] Among them, A is the brightness gradient matrix, is the flow rate of tobacco, b is a column vector, representing the rate of change of brightness over time;

[0103]

[0104] in, is the gradient of pixel I1 in the x direction, is the gradient of pixel I1 in the y direction, is the gradient of pixel I2 in the x direction, is the gradient of pixel I2 in the y direction, is pixel I N The gradient in the x direction, is pixel I N The gradient in the y direction;

[0105]

[0106] in, is the rate of change of pixel I1 over time, is the rate of change of pixel I2 over time, is pixel I N rate of change over time;

[0107]

[0108] Among them, u is the component of the optical flow velocity vector in the x direction, and v is the component of the optical flow velocity vector in the y direction;

[0109] The tobacco speed is determined using formula (5):

[0110]

[0111] In step S14, the spectral radiation method is used to obtain the tobacco temperature and cavity temperature information from the fused image. In this example, the spectral radiation law is used to measure the tobacco temperature. According to Planck's radiation law, the intensity of infrared radiation energy is directly related to the object temperature. Combined with the band of the infrared sensor, the tobacco temperature can be calculated. The following steps can be included to obtain the tobacco temperature and cavity temperature information:

[0112] The infrared component is separated from the fused image, and the tobacco temperature and cavity temperature are calculated based on the radiation intensity of the infrared component and combined with Planck's law formula (6).

[0113]

[0114] Where I(λ,T) is the radiation intensity at wavelength λ, λ is the wavelength of the infrared sensor, T is the tobacco temperature or cavity temperature, h is Planck's constant, c is the speed of light, and k is the Boltzmann constant.

[0115] In steps S10 to S14, the obtained visible light image and infrared image of the tobacco are preprocessed, and then the preprocessed visible light image and the preprocessed infrared image are fused using a spectral fusion algorithm to generate a fused image, and the tobacco speed information, tobacco temperature and cavity temperature information are obtained from the fused image using an optical flow method and a spectral radiation method.

[0116] On the other hand, the present invention also provides an integrated detection device for tobacco shred speed and tobacco drying machine cavity temperature, which includes an illumination component 124, an image acquisition component 12, a temperature acquisition component 13 and a processor. Among them, the illumination component 124 can be used to provide a light source to the tobacco drying machine cavity to be tested. The image acquisition component 12 can be used to acquire a visible light image of the tobacco drying machine cavity. The temperature acquisition component 13 can be used to acquire the temperature of the tobacco drying machine cavity to obtain an infrared image of the tobacco drying machine cavity. The processor can be connected to the illumination component, the image acquisition component and the temperature acquisition component to determine the tobacco shred flow rate and temperature in the tobacco drying machine cavity according to any of the above methods.

[0117] Considering that during the tobacco production process, the tobacco shape and temperature distribution inside the tobacco drying machine need to be monitored in real time to ensure production quality and process stability. In addition, in order to cope with the complex internal environment of the tobacco drying machine (such as high temperature, insufficient light, etc.), it is difficult to ensure that the monitoring equipment works stably. Therefore, in this example, Figure 4-6 As shown, the housing 11 is hollow, and an opening 111 is provided on the front end surface for observing the inside of the tofu drying machine. Heat dissipation holes 112 are provided on the left and right end surfaces of the housing 11 for dissipating heat from the internal components.

[0118] The image acquisition component 12 includes a fixed bracket 121, a CCD camera 122, an optical lens 123 and a lighting component 124. The fixed bracket 121 is arranged in the housing 11 along the vertical direction, close to the opening 111; the CCD camera 122 is arranged on the top of the fixed bracket 121, and an optical lens 123 is arranged at the front end, which is used to stably collect the image of the tobacco inside the tobacco drying machine. The CCD camera 122 shoots at a frame rate of not less than 300 frames per second, so as to clearly capture the high-speed movement details of the tobacco. The lighting component 124 is arranged on the left and right sides of the optical lens 123, including a lighting component 1241, a fixed plate 1242 and an adapter 1243, which is used to adjust the light intensity in the tobacco drying machine cavity to ensure that the CCD camera 122 can clearly shoot under different lighting conditions.

[0119] The temperature acquisition component 13 includes a temperature detector 131 and a support 132. The temperature detector 131 is disposed in the support 132, and the support 132 is connected to the fixing bracket 121 to fix the temperature detector 131 and ensure its stable operation. The temperature detector 131 can use a dual-spectrum temperature measurement thermal imager to ensure that the temperature detector 131 can still work stably in a high temperature environment, ensuring the accuracy and reliability of the temperature data.

[0120] The housing 11 is provided with a power supply component 14 to supply power to the image acquisition component 12 and the temperature acquisition component 13. The housing 11 is also provided with a light source controller 15, which is electrically connected to the lighting component 124 and is used to control the lighting component 124 according to the light intensity in the drying machine cavity.

[0121] The working process of the device includes: first, the light intensity of the lighting component 124 is adjusted to an appropriate level by the light source controller 15. Then, the CCD camera 122 is used to continuously shoot the tobacco drying machine cavity at a frame rate of not less than 300 frames per second, and the video data is retained. At the same time, a dual-spectrum temperature measurement thermal imager is used as a temperature detector 131 to collect temperature data of tobacco and the cavity in real time to ensure good temperature measurement stability in a high temperature environment. Then, the processor processes the collected visible light image (video data) and infrared image (temperature data), and uses a spectral fusion algorithm to generate a fused image. Finally, the optical flow method is used to extract tobacco velocity information from the fused image, and the spectral radiation method is used to obtain tobacco temperature and cavity temperature information from the fused image.

[0122] The above detection device can synchronously detect the tobacco speed and cavity temperature in the tobacco drying machine, thereby improving the detection efficiency and facilitating the adjustment of the temperature and rolling speed of the tobacco drying machine drum, thereby improving the quality of the finished tobacco. At the same time, the detection device has a simple and compact structure and is easy to take and put, which is convenient for multi-point detection of the tobacco drying machine, further improving the accuracy of the detection.

[0123] In order to simulate the flow of tobacco in the drying chamber, a simple experimental platform was built. Figure 7 The experimental setup is shown in Figure 7 As shown in (a), it is mainly composed of a square column with a length of 0.2 meters, a width of 0.15 meters, and a height of 1.5 meters. Three different sizes of measurement windows are set on one side of the square column to observe and measure the flow of tobacco. A transfer hole is designed at the bottom of the square column, which is connected to the blower through a hose to provide a driving airflow. Through this device, the flow behavior of tobacco in the drying machine cavity can be studied and analyzed in detail.

[0124] The tobacco is in high-speed motion in the cavity. To accurately measure its motion speed, a CCD camera 122 with a frame rate of up to 300 frames per second is used to take photos. Figure 8 (a) and Figure 8 (b) shows the experimental speed measurement status. The experimental steps are as follows: First, start the blower to send air into the cavity of the experimental device to make the tobacco flow. Then, place the detection device 5 cm outside the measurement window to film the movement of the tobacco in the cavity. Finally, shoot continuously for a period of time and save the video, and measure the movement speed of the tobacco by analyzing the video frame by frame. This method can accurately capture the details of high-speed motion and provide sufficient data support to ensure the accuracy and reliability of the measurement results. High frame rate shooting technology can capture the subtle movement of tobacco in a very short time, providing important data support for subsequent research and applications.

[0125] Single tobacco flow velocity analysis: Use the image acquisition component 12 to collect a one-minute video as the original measurement data. By recording the coordinates of the feature points in each frame, the movement rate of each feature point is calculated. The specific steps are as follows: First, mark the feature points in each frame and record their coordinate positions. Then, compare the displacement of the feature points in consecutive frames and calculate their movement speed between each frame. Finally, average the speed at all times to obtain the average flow speed of the tobacco.

[0126] Multi-cut tobacco flow velocity analysis: In order to further simulate the actual measurement situation, a large amount of cut tobacco was added into the cavity and a velocity measurement experiment was carried out. Fig. 9 The flow images of multiple tobacco shreds are shown. The speed measurement of multiple tobacco shreds is more complicated than that of single tobacco shreds because it is impossible to measure the speed of all tobacco shreds comprehensively. To this end, tobacco shreds with more obvious feature points are selected, the coordinates of the feature points of each tobacco shred are recorded, their motion trajectories are analyzed, and the motion speed is calculated. Finally, these speeds are averaged to obtain the overall flow speed of the tobacco shreds. This method can not only reflect the overall movement trend of the tobacco shreds, but also improve the accuracy and efficiency of the measurement.

[0127] In order to verify the performance of the temperature measuring component 13, a dual-spectrum temperature measuring thermal imager was used for experiments. The verification process is as follows: adjust the electric soldering iron to 300 degrees Celsius and heat it for a period of time to ensure that the temperature is stable. Use the temperature measuring component 13 to photograph the electric soldering iron tip and record its temperature distribution. The experimental results show that the temperature measuring component 13 can accurately measure the temperature of high-temperature objects and provide detailed temperature distribution images, providing reliable data support for subsequent analysis. In order to verify the temperature measurement stability of the temperature measuring component 13 in a high temperature environment, a continuous measurement experiment was carried out on the temperature of the electric soldering iron tip. The experiment selected a fixed point of the electric soldering iron tip and recorded the temperature data every ten seconds, for a total of 30 times. The experimental results show that the temperature data is relatively stable, proving that the infrared camera has good temperature measurement stability in a high temperature environment.

[0128] Through the above technical scheme, the embodiment of the present invention provides an integrated detection method and detection device for tobacco shred speed and tobacco shred drying machine cavity temperature. The method and device acquire visible light images and infrared images by setting image acquisition components and temperature acquisition components, generate fused images by using spectral fusion algorithm, and then extract tobacco shred speed information from the fused image by using optical flow method and acquire tobacco shred temperature and cavity temperature information from the fused image by using spectral radiation method. The cavity temperature and tobacco shred speed of the tobacco shred drying machine can be detected in real time at the same time, so that the staff can adjust the cylinder wall temperature and drum speed of the tobacco shred drying machine in time, ensure that the moisture content of tobacco meets the processing technology standards, and improve the quality of tobacco products. The method makes up for the lack of a detection device that can simultaneously detect the cavity temperature of the tobacco shred drying machine and the tobacco shred speed inside the tobacco shred drying machine in the prior art.

[0129] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0130] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0131] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0132] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0133] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0134] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0135] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0136] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0137] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for integrated detection of tobacco shred speed and tobacco shred drying machine cavity temperature, characterized in that: include: Acquire visible light images and infrared images of tobacco; Preprocessing the visible light image and the infrared image; The spectral fusion algorithm is used to fuse the preprocessed visible light image and the preprocessed infrared image to generate a fused image; extracting tobacco speed information from the fused image using an optical flow method; The spectral radiation method is used to obtain the tobacco cut temperature and cavity temperature information from the fused image.

2. The integrated detection method for tobacco shred speed and tobacco shred drying machine cavity temperature according to claim 1, characterized in that: Preprocessing the visible light image and the infrared image includes: Using a preset image registration method, the visible light image and the infrared image are geometrically aligned to ensure that the visible light image and the infrared image have consistent spatial positions; Performing filtering on the visible light image and the infrared image to reduce noise and enhance image contrast; The infrared image is subjected to pseudo-color processing to convert the temperature information into a visual image, and the image quality is improved through non-uniformity correction to reduce the error of temperature measurement.

3. The integrated detection method for tobacco shred speed and tobacco shred drying machine cavity temperature according to claim 1, characterized in that: The spectral fusion algorithm is used to fuse the preprocessed visible light image and the preprocessed infrared image to generate a fused image, including: Normalizing the preprocessed visible light image and the preprocessed infrared image; The preprocessed visible light image and the preprocessed infrared image are fused using a spectral fusion strategy, wherein the spectral fusion strategy includes pixel-level fusion and feature-level fusion, wherein the pixel-level fusion includes weighted average fusion, selective fusion or wavelet transform fusion.

4. The integrated detection method for tobacco shred speed and tobacco shred drying machine cavity temperature according to claim 1, characterized in that: The optical flow method is used to extract tobacco speed information from the fused image, including: Formula (1) to Formula (4) are used to construct the optical flow constraint equation of each pixel point of the fused image: Among them, A is the brightness gradient matrix, is the flow rate of tobacco, b is a column vector, representing the rate of change of brightness over time; in, is the gradient of pixel I1 in the x direction, is the gradient of pixel I1 in the y direction, is the gradient of pixel I2 in the x direction, is the gradient of pixel I2 in the y direction, is pixel I N The gradient in the x direction, is pixel I N The gradient in the y direction; in, is the rate of change of pixel I1 over time, is the rate of change of pixel I2 over time, is pixel I N rate of change over time; Among them, u is the component of the optical flow velocity vector in the x direction, and v is the component of the optical flow velocity vector in the y direction; The tobacco speed is determined using formula (5):

5. The integrated detection method for tobacco shred speed and tobacco shred drying machine cavity temperature according to claim 1, characterized in that: The spectral radiation method is used to obtain the tobacco temperature and cavity temperature information from the fused image, including: The infrared component is separated from the fused image, and the tobacco temperature and the cavity temperature are calculated according to the radiation intensity of the infrared component and the Planck's law formula (6). Where I(λ,T) is the radiation intensity at wavelength λ, λ is the wavelength of the infrared sensor, T is the tobacco temperature or cavity temperature, h is Planck's constant, c is the speed of light, and k is the Boltzmann constant.

6. An integrated detection device for tobacco shred speed and tobacco shred drying machine cavity temperature, characterized in that: include: A lighting assembly, used for providing light source to the tofu drying machine cavity to be tested; An image acquisition component, used for acquiring a visible light image of the tofu drying machine cavity; A temperature acquisition component, used for acquiring the temperature of the cavity of the tofu drying machine to obtain an infrared image of the cavity of the tofu drying machine; A processor is connected to the lighting component, the image acquisition component and the temperature acquisition component, and is used to determine the flow rate and temperature of the tobacco in the drying machine cavity according to any method of claims 1 to 5.

7. The integrated detection device for tobacco shred speed and tobacco shred drying machine cavity temperature according to claim 6, characterized in that: The image acquisition component includes a CCD camera and an optical lens, and the optical lens is arranged at the front end of the CCD camera.

8. The integrated detection device for tobacco shred speed and tobacco shred drying machine cavity temperature according to claim 6, characterized in that: The temperature acquisition component includes a temperature detector, and the temperature detector is a dual-spectrum temperature measurement thermal imager.

9. The integrated detection device for tobacco shred speed and tobacco shred drying machine cavity temperature according to claim 6, characterized in that: A power supply component is arranged in the detection device, and the power supply component is electrically connected to the image acquisition component and the temperature acquisition component to supply power to the image acquisition component and the temperature acquisition component.

10. The integrated detection device for tobacco shred speed and tobacco shred drying machine cavity temperature according to claim 6, characterized in that: A light source controller is arranged in the detection device, and the light source controller is electrically connected to the lighting component so as to adjust the lighting component according to the light intensity in the tofu drying machine cavity.

Images